Search

4D driving simulation is essential for developing realistic autonomous driving simulators. Despite advancements in existing methods for generating driving scenes, significant challenges remain in view transformation and spatial-temporal dynamic modeling. To address these limitations, we propose a Spatial-Temporal simulAtion for drivinG (Stag-1) model to reconstruct real-world scenes and design a controllable generative network to achieve 4D simulation. Stag-1 constructs continuous 4D point cloud scenes using surround-view data from autonomous vehicles. It decouples spatial-temporal relationships and produces coherent keyframe videos. Additionally, Stag-1 leverages video generation models to obtain photo-realistic and controllable 4D driving simulation videos from any perspective. To expand the range of view generation, we train vehicle motion videos based on decomposed camera poses, enhancing modeling capabilities for distant scenes. Furthermore, we reconstruct vehicle camera trajectories to integrate 3D points across consecutive views, enabling comprehensive scene understanding along the temporal dimension. Following extensive multi-level scene training, Stag-1 can simulate from any desired viewpoint and achieve a deep understanding of scene evolution under static spatial-temporal conditions. Compared to existing methods, our approach shows promising performance in multi-view scene consistency, background coherence, and accuracy, and contributes to the ongoing advancements in realistic autonomous driving simulation. Code: https://github.com/wzzheng/Stag., Comment: Code is available at: https://github.com/wzzheng/Stag

Large vision-language models (VLMs) often rely on a substantial number of visual tokens when interacting with large language models (LLMs), which has proven to be inefficient. Recent efforts have aimed to accelerate VLM inference by pruning visual tokens. Most existing methods assess the importance of visual tokens based on the text-visual cross-attentions in LLMs. In this study, we find that the cross-attentions between text and visual tokens in LLMs are inaccurate. Pruning tokens based on these inaccurate attentions leads to significant performance degradation, especially at high reduction ratios. To this end, we introduce FasterVLM, a simple yet effective training-free visual token pruning method that evaluates the importance of visual tokens more accurately by utilizing attentions between the [CLS] token and image tokens from the visual encoder. Since FasterVLM eliminates redundant visual tokens immediately after the visual encoder, ensuring they do not interact with LLMs and resulting in faster VLM inference. It is worth noting that, benefiting from the accuracy of [CLS] cross-attentions, FasterVLM can prune 95\% of visual tokens while maintaining 90\% of the performance of LLaVA-1.5-7B. We apply FasterVLM to various VLMs, including LLaVA-1.5, LLaVA-NeXT, and Video-LLaVA, to demonstrate its effectiveness. Experimental results show that our FasterVLM maintains strong performance across various VLM architectures and reduction ratios, significantly outperforming existing text-visual attention-based methods. Our code is available at https://github.com/Theia-4869/FasterVLM., Comment: 23 pages, 11 figures, code: https://github.com/Theia-4869/FasterVLM, project page: https://theia-4869.github.io/FasterVLM

3D geometric information is essential for manipulation tasks, as robots need to perceive the 3D environment, reason about spatial relationships, and interact with intricate spatial configurations. Recent research has increasingly focused on the explicit extraction of 3D features, while still facing challenges such as the lack of large-scale robotic 3D data and the potential loss of spatial geometry. To address these limitations, we propose the Lift3D framework, which progressively enhances 2D foundation models with implicit and explicit 3D robotic representations to construct a robust 3D manipulation policy. Specifically, we first design a task-aware masked autoencoder that masks task-relevant affordance patches and reconstructs depth information, enhancing the 2D foundation model's implicit 3D robotic representation. After self-supervised fine-tuning, we introduce a 2D model-lifting strategy that establishes a positional mapping between the input 3D points and the positional embeddings of the 2D model. Based on the mapping, Lift3D utilizes the 2D foundation model to directly encode point cloud data, leveraging large-scale pretrained knowledge to construct explicit 3D robotic representations while minimizing spatial information loss. In experiments, Lift3D consistently outperforms previous state-of-the-art methods across several simulation benchmarks and real-world scenarios.

Advancing towards generalist agents necessitates the concurrent processing of multiple tasks using a unified model, thereby underscoring the growing significance of simultaneous model training on multiple downstream tasks. A common issue in multi-task learning is the occurrence of gradient conflict, which leads to potential competition among different tasks during joint training. This competition often results in improvements in one task at the expense of deterioration in another. Although several optimization methods have been developed to address this issue by manipulating task gradients for better task balancing, they cannot decrease the incidence of gradient conflict. In this paper, we systematically investigate the occurrence of gradient conflict across different methods and propose a strategy to reduce such conflicts through sparse training (ST), wherein only a portion of the model's parameters are updated during training while keeping the rest unchanged. Our extensive experiments demonstrate that ST effectively mitigates conflicting gradients and leads to superior performance. Furthermore, ST can be easily integrated with gradient manipulation techniques, thus enhancing their effectiveness.

Photorealistic reconstruction of street scenes is essential for developing real-world simulators in autonomous driving. While recent methods based on 3D/4D Gaussian Splatting (GS) have demonstrated promising results, they still encounter challenges in complex street scenes due to the unpredictable motion of dynamic objects. Current methods typically decompose street scenes into static and dynamic objects, learning the Gaussians in either a supervised manner (e.g., w/ 3D bounding-box) or a self-supervised manner (e.g., w/o 3D bounding-box). However, these approaches do not effectively model the motions of dynamic objects (e.g., the motion speed of pedestrians is clearly different from that of vehicles), resulting in suboptimal scene decomposition. To address this, we propose Explicit Motion Decomposition (EMD), which models the motions of dynamic objects by introducing learnable motion embeddings to the Gaussians, enhancing the decomposition in street scenes. The proposed EMD is a plug-and-play approach applicable to various baseline methods. We also propose tailored training strategies to apply EMD to both supervised and self-supervised baselines. Through comprehensive experimentation, we illustrate the effectiveness of our approach with various established baselines. The code will be released at: https://qingpowuwu.github.io/emdgaussian.github.io/.

Current vision-language models (VLMs) show exceptional abilities across diverse tasks including visual question answering. To enhance user experience in practical applications, recent studies investigate VLM personalization to understand user-provided concepts. However, existing studies mainly focus on single-concept personalization, neglecting the existence and interplay of multiple concepts, which limits the real-world applicability of personalized VLMs. In this paper, we propose the first multi-concept personalization method named MC-LLaVA along with a high-quality multi-concept personalization dataset. Specifically, MC-LLaVA uses a joint training strategy incorporating multiple concepts in a single training step, allowing VLMs to perform accurately in multi-concept personalization. To reduce the cost of joint training, MC-LLaVA leverages visual token information for concept token initialization, yielding improved concept representation and accelerating joint training. To advance multi-concept personalization research, we further contribute a high-quality dataset. We carefully collect images from various movies that contain multiple characters and manually generate the multi-concept question-answer samples. Our dataset features diverse movie types and question-answer types. We conduct comprehensive qualitative and quantitative experiments to demonstrate that MC-LLaVA can achieve impressive multi-concept personalized responses, paving the way for VLMs to become better user-specific assistants. The code and dataset will be publicly available at https://github.com/arctanxarc/MC-LLaVA.

Semi-supervised domain adaptation (SSDA) has been widely studied due to its ability to utilize a few labeled target data to improve the generalization ability of the model. However, existing methods only consider designing certain strategies for target samples to adapt, ignoring the exploration of customized learning for different target samples. When the model encounters complex target distribution, existing methods will perform limited due to the inability to clearly and comprehensively learn the knowledge of multiple types of target samples. To fill this gap, this paper focuses on designing a framework to use different strategies for comprehensively mining different target samples. We propose a novel source-free framework (SOUF) to achieve semi-supervised fine-tuning of the source pre-trained model on the target domain. Different from existing SSDA methods, SOUF decouples SSDA from the perspectives of different target samples, specifically designing robust learning techniques for unlabeled, reliably labeled, and noisy pseudo-labeled target samples. For unlabeled target samples, probability-based weighted contrastive learning (PWC) helps the model learn more discriminative feature representations. To mine the latent knowledge of labeled target samples, reliability-based mixup contrastive learning (RMC) learns complex knowledge from the constructed reliable sample set. Finally, predictive regularization learning (PR) further mitigates the misleading effect of noisy pseudo-labeled samples on the model. Extensive experiments on benchmark datasets demonstrate the superiority of our framework over state-of-the-art methods.

Diffusion models have demonstrated excellent capabilities in text-to-image generation. Their semantic understanding (i.e., prompt following) ability has also been greatly improved with large language models (e.g., T5, Llama). However, existing models cannot perfectly handle long and complex text prompts, especially when the text prompts contain various objects with numerous attributes and interrelated spatial relationships. While many regional prompting methods have been proposed for UNet-based models (SD1.5, SDXL), but there are still no implementations based on the recent Diffusion Transformer (DiT) architecture, such as SD3 and FLUX.1.In this report, we propose and implement regional prompting for FLUX.1 based on attention manipulation, which enables DiT with fined-grained compositional text-to-image generation capability in a training-free manner. Code is available at https://github.com/antonioo-c/Regional-Prompting-FLUX., Comment: Code is available at https://github.com/antonioo-c/Regional-Prompting-FLUX

Autoregression in large language models (LLMs) has shown impressive scalability by unifying all language tasks into the next token prediction paradigm. Recently, there is a growing interest in extending this success to vision foundation models. In this survey, we review the recent advances and discuss future directions for autoregressive vision foundation models. First, we present the trend for next generation of vision foundation models, i.e., unifying both understanding and generation in vision tasks. We then analyze the limitations of existing vision foundation models, and present a formal definition of autoregression with its advantages. Later, we categorize autoregressive vision foundation models from their vision tokenizers and autoregression backbones. Finally, we discuss several promising research challenges and directions. To the best of our knowledge, this is the first survey to comprehensively summarize autoregressive vision foundation models under the trend of unifying understanding and generation. A collection of related resources is available at https://github.com/EmmaSRH/ARVFM., Comment: 17 pages, 1 table, 2 figures

World models integrate raw data from various modalities, such as images and language to simulate comprehensive interactions in the world, thereby displaying crucial roles in fields like mixed reality and robotics. Yet, applying the world model for accurate video prediction is quite challenging due to the complex and dynamic intentions of the various scenes in practice. In this paper, inspired by the human rethinking process, we decompose the complex video prediction into four meta-tasks that enable the world model to handle this issue in a more fine-grained manner. Alongside these tasks, we introduce a new benchmark named Embodied Video Anticipation Benchmark (EVA-Bench) to provide a well-rounded evaluation. EVA-Bench focused on evaluating the video prediction ability of human and robot actions, presenting significant challenges for both the language model and the generation model. Targeting embodied video prediction, we propose the Embodied Video Anticipator (EVA), a unified framework aiming at video understanding and generation. EVA integrates a video generation model with a visual language model, effectively combining reasoning capabilities with high-quality generation. Moreover, to enhance the generalization of our framework, we tailor-designed a multi-stage pretraining paradigm that adaptatively ensembles LoRA to produce high-fidelity results. Extensive experiments on EVA-Bench highlight the potential of EVA to significantly improve performance in embodied scenes, paving the way for large-scale pre-trained models in real-world prediction tasks.

In vision-language models (VLMs), visual tokens usually consume a significant amount of computational overhead, despite their sparser information density compared to text tokens. To address this, most existing methods learn a network to prune redundant visual tokens and require additional training data. Differently, we propose an efficient training-free token optimization mechanism dubbed SparseVLM without extra parameters or fine-tuning costs. Concretely, given that visual tokens complement text tokens in VLMs for linguistic reasoning, we select visual-relevant text tokens to rate the significance of vision tokens within the self-attention matrix extracted from the VLMs. Then we progressively prune irrelevant tokens. To maximize sparsity while retaining essential information, we introduce a rank-based strategy to adaptively determine the sparsification ratio for each layer, alongside a token recycling method that compresses pruned tokens into more compact representations. Experimental results show that our SparseVLM improves the efficiency of various VLMs across a range of image and video understanding tasks. In particular, LLaVA equipped with SparseVLM reduces 61% to 67% FLOPs with a compression ratio of 78% while maintaining 93% of the accuracy. Our code is available at https://github.com/Gumpest/SparseVLMs., Comment: 17 pages

Radiology is a vital and complex component of modern clinical workflow and covers many tasks. Recently, vision-language (VL) foundation models in medicine have shown potential in processing multimodal information, offering a unified solution for various radiology tasks. However, existing studies either pre-trained VL models on natural data or did not fully integrate vision-language architecture and pretraining, often neglecting the unique multimodal complexity in radiology images and their textual contexts. Additionally, their practical applicability in real-world scenarios remains underexplored. Here, we present RadFound, a large and open-source vision-language foundation model tailored for radiology, that is trained on the most extensive dataset of over 8.1 million images and 250,000 image-text pairs, covering 19 major organ systems and 10 imaging modalities. To establish expert-level multimodal perception and generation capabilities, RadFound introduces an enhanced vision encoder to capture intra-image local features and inter-image contextual information, and a unified cross-modal learning design tailored to radiology. To fully assess the models' capability, we construct a benchmark, RadVLBench, including radiology interpretation tasks like medical vision-language question-answering, as well as text generation tasks ranging from captioning to report generation. We also propose a human evaluation framework. When evaluated on the real-world benchmark involving three representative modalities, 2D images (chest X-rays), multi-view images (mammograms), and 3D images (thyroid CT scans), RadFound significantly outperforms other VL foundation models on both quantitative metrics and human evaluation. In summary, the development of RadFound represents an advancement in radiology generalists, demonstrating broad applicability potential for integration into clinical workflows.

Massive multi-modality datasets play a significant role in facilitating the success of large video-language models. However, current video-language datasets primarily provide text descriptions for visual frames, considering audio to be weakly related information. They usually overlook exploring the potential of inherent audio-visual correlation, leading to monotonous annotation within each modality instead of comprehensive and precise descriptions. Such ignorance results in the difficulty of multiple cross-modality studies. To fulfill this gap, we present MMTrail, a large-scale multi-modality video-language dataset incorporating more than 20M trailer clips with visual captions, and 2M high-quality clips with multimodal captions. Trailers preview full-length video works and integrate context, visual frames, and background music. In particular, the trailer has two main advantages: (1) the topics are diverse, and the content characters are of various types, e.g., film, news, and gaming. (2) the corresponding background music is custom-designed, making it more coherent with the visual context. Upon these insights, we propose a systemic captioning framework, achieving various modality annotations with more than 27.1k hours of trailer videos. Here, to ensure the caption retains music perspective while preserving the authority of visual context, we leverage the advanced LLM to merge all annotations adaptively. In this fashion, our MMtrail dataset potentially paves the path for fine-grained large multimodal-language model training. In experiments, we provide evaluation metrics and benchmark results on our dataset, demonstrating the high quality of our annotation and its effectiveness for model training., Comment: 15 Pages. Dataset report

The mathematical capabilities of Multi-modal Large Language Models (MLLMs) remain under-explored with three areas to be improved: visual encoding of math diagrams, diagram-language alignment, and chain-of-thought (CoT) reasoning. This draws forth an urgent demand for an effective training paradigm and a large-scale, comprehensive dataset with detailed CoT rationales, which is challenging to collect and costly to annotate manually. To tackle this issue, we propose MAVIS, a MAthematical VISual instruction tuning pipeline for MLLMs, featuring an automatic data engine to efficiently create mathematical visual datasets. We design the data generation process to be entirely independent of human intervention or GPT API usage, while ensuring the diagram-caption correspondence, question-answer correctness, and CoT reasoning quality. With this approach, we curate two datasets, MAVIS-Caption (558K diagram-caption pairs) and MAVIS-Instruct (834K visual math problems with CoT rationales), and propose four progressive stages for training MLLMs from scratch. First, we utilize MAVIS-Caption to fine-tune a math-specific vision encoder (CLIP-Math) through contrastive learning, tailored for improved diagram visual encoding. Second, we also leverage MAVIS-Caption to align the CLIP-Math with a large language model (LLM) by a projection layer, enhancing vision-language alignment in mathematical domains. Third, we adopt MAVIS-Instruct to perform the instruction tuning for robust problem-solving skills, and term the resulting model as MAVIS-7B. Fourth, we apply Direct Preference Optimization (DPO) to enhance the CoT capabilities of our model, further refining its step-wise reasoning performance. Code and data will be released at https://github.com/ZrrSkywalker/MAVIS, Comment: WData and Models will be released at https://github.com/ZrrSkywalker/MAVIS

The impact of quantization on the overall performance of deep learning models is a well-studied problem. However, understanding and mitigating its effects on a more fine-grained level is still lacking, especially for harder tasks such as object detection with both classification and regression objectives. This work defines the performance for a subset of task-critical categories, i.e. the critical-category performance, as a crucial yet largely overlooked fine-grained objective for detection tasks. We analyze the impact of quantization at the category-level granularity, and propose methods to improve performance for the critical categories. Specifically, we find that certain critical categories have a higher sensitivity to quantization, and are prone to overfitting after quantization-aware training (QAT). To explain this, we provide theoretical and empirical links between their performance gaps and the corresponding loss landscapes with the Fisher information framework. Using this evidence, we apply a Fisher-aware mixed-precision quantization scheme, and a Fisher-trace regularization for the QAT on the critical-category loss landscape. The proposed methods improve critical-category metrics of the quantized transformer-based DETR detectors. They are even more significant in case of larger models and higher number of classes where the overfitting becomes more severe. For example, our methods lead to 10.4% and 14.5% mAP gains for, correspondingly, 4-bit DETR-R50 and Deformable DETR on the most impacted critical classes in the COCO Panoptic dataset., Comment: Poster presentation at the 2nd Workshop on Advancing Neural Network Training: Computational Efficiency, Scalability, and Resource Optimization (WANT@ICML 2024)

In recent years, multimodal large language models (MLLMs) have shown remarkable capabilities in tasks like visual question answering and common sense reasoning, while visual perception models have made significant strides in perception tasks, such as detection and segmentation. However, MLLMs mainly focus on high-level image-text interpretations and struggle with fine-grained visual understanding, and vision perception models usually suffer from open-world distribution shifts due to their limited model capacity. To overcome these challenges, we propose the Mutually Reinforced Multimodal Large Language Model (MR-MLLM), a novel framework that synergistically enhances visual perception and multimodal comprehension. First, a shared query fusion mechanism is proposed to harmonize detailed visual inputs from vision models with the linguistic depth of language models, enhancing multimodal comprehension and vision perception synergistically. Second, we propose the perception-enhanced cross-modal integration method, incorporating novel modalities from vision perception outputs, like object detection bounding boxes, to capture subtle visual elements, thus enriching the understanding of both visual and textual data. In addition, an innovative perception-embedded prompt generation mechanism is proposed to embed perceptual information into the language model's prompts, aligning the responses contextually and perceptually for a more accurate multimodal interpretation. Extensive experiments demonstrate MR-MLLM's superior performance in various multimodal comprehension and vision perception tasks, particularly those requiring corner case vision perception and fine-grained language comprehension., Comment: 14 pages, 8 figures

A fundamental objective in robot manipulation is to enable models to comprehend visual scenes and execute actions. Although existing robot Multimodal Large Language Models (MLLMs) can handle a range of basic tasks, they still face challenges in two areas: 1) inadequate reasoning ability to tackle complex tasks, and 2) high computational costs for MLLM fine-tuning and inference. The recently proposed state space model (SSM) known as Mamba demonstrates promising capabilities in non-trivial sequence modeling with linear inference complexity. Inspired by this, we introduce RoboMamba, an end-to-end robotic MLLM that leverages the Mamba model to deliver both robotic reasoning and action capabilities, while maintaining efficient fine-tuning and inference. Specifically, we first integrate the vision encoder with Mamba, aligning visual data with language embedding through co-training, empowering our model with visual common sense and robot-related reasoning. To further equip RoboMamba with action pose prediction abilities, we explore an efficient fine-tuning strategy with a simple policy head. We find that once RoboMamba possesses sufficient reasoning capability, it can acquire manipulation skills with minimal fine-tuning parameters (0.1\% of the model) and time (20 minutes). In experiments, RoboMamba demonstrates outstanding reasoning capabilities on general and robotic evaluation benchmarks. Meanwhile, our model showcases impressive pose prediction results in both simulation and real-world experiments, achieving inference speeds 7 times faster than existing robot MLLMs. Our project web page: https://sites.google.com/view/robomamba-web

Photorealistic 3D reconstruction of street scenes is a critical technique for developing real-world simulators for autonomous driving. Despite the efficacy of Neural Radiance Fields (NeRF) for driving scenes, 3D Gaussian Splatting (3DGS) emerges as a promising direction due to its faster speed and more explicit representation. However, most existing street 3DGS methods require tracked 3D vehicle bounding boxes to decompose the static and dynamic elements for effective reconstruction, limiting their applications for in-the-wild scenarios. To facilitate efficient 3D scene reconstruction without costly annotations, we propose a self-supervised street Gaussian ($\textit{S}^3$Gaussian) method to decompose dynamic and static elements from 4D consistency. We represent each scene with 3D Gaussians to preserve the explicitness and further accompany them with a spatial-temporal field network to compactly model the 4D dynamics. We conduct extensive experiments on the challenging Waymo-Open dataset to evaluate the effectiveness of our method. Our $\textit{S}^3$Gaussian demonstrates the ability to decompose static and dynamic scenes and achieves the best performance without using 3D annotations. Code is available at: https://github.com/nnanhuang/S3Gaussian/., Comment: Code is available at: https://github.com/nnanhuang/S3Gaussian/

Robot manipulation policies have shown unsatisfactory action performance when confronted with novel task or object instances. Hence, the capability to automatically detect and self-correct failure action is essential for a practical robotic system. Recently, Multimodal Large Language Models (MLLMs) have shown promise in visual instruction following and demonstrated strong reasoning abilities in various tasks. To unleash general MLLMs as an end-to-end robotic agent, we introduce a Self-Corrected (SC)-MLLM, equipping our model not only to predict end-effector poses but also to autonomously recognize and correct failure actions. Specifically, we first conduct parameter-efficient fine-tuning to empower MLLM with pose prediction ability, which is reframed as a language modeling problem. When facing execution failures, our model learns to identify low-level action error causes (i.e., position and rotation errors) and adaptively seeks prompt feedback from experts. Based on the feedback, SC-MLLM rethinks the current failure scene and generates the corrected actions. Furthermore, we design a continuous policy learning method for successfully corrected samples, enhancing the model's adaptability to the current scene configuration and reducing the frequency of expert intervention. To evaluate our SC-MLLM, we conduct extensive experiments in both simulation and real-world settings. SC-MLLM agent significantly improve manipulation accuracy compared to previous state-of-the-art robotic MLLM (ManipLLM), increasing from 57\% to 79\% on seen object categories and from 47\% to 69\% on unseen novel categories.

Few-shot class-incremental learning (FSCIL) is proposed to continually learn from novel classes with only a few samples after the (pre-)training on base classes with sufficient data. However, this remains a challenge. In contrast, humans can easily recognize novel classes with a few samples. Cognitive science demonstrates that an important component of such human capability is compositional learning. This involves identifying visual primitives from learned knowledge and then composing new concepts using these transferred primitives, making incremental learning both effective and interpretable. To imitate human compositional learning, we propose a cognitive-inspired method for the FSCIL task. We define and build a compositional model based on set similarities, and then equip it with a primitive composition module and a primitive reuse module. In the primitive composition module, we propose to utilize the Centered Kernel Alignment (CKA) similarity to approximate the similarity between primitive sets, allowing the training and evaluation based on primitive compositions. In the primitive reuse module, we enhance primitive reusability by classifying inputs based on primitives replaced with the closest primitives from other classes. Experiments on three datasets validate our method, showing it outperforms current state-of-the-art methods with improved interpretability. Our code is available at https://github.com/Zoilsen/Comp-FSCIL.

Deriving co-speech 3D gestures has seen tremendous progress in virtual avatar animation. Yet, the existing methods often produce stiff and unreasonable gestures with unseen human speech inputs due to the limited 3D speech-gesture data. In this paper, we propose CoCoGesture, a novel framework enabling vivid and diverse gesture synthesis from unseen human speech prompts. Our key insight is built upon the custom-designed pretrain-fintune training paradigm. At the pretraining stage, we aim to formulate a large generalizable gesture diffusion model by learning the abundant postures manifold. Therefore, to alleviate the scarcity of 3D data, we first construct a large-scale co-speech 3D gesture dataset containing more than 40M meshed posture instances across 4.3K speakers, dubbed GES-X. Then, we scale up the large unconditional diffusion model to 1B parameters and pre-train it to be our gesture experts. At the finetune stage, we present the audio ControlNet that incorporates the human voice as condition prompts to guide the gesture generation. Here, we construct the audio ControlNet through a trainable copy of our pre-trained diffusion model. Moreover, we design a novel Mixture-of-Gesture-Experts (MoGE) block to adaptively fuse the audio embedding from the human speech and the gesture features from the pre-trained gesture experts with a routing mechanism. Such an effective manner ensures audio embedding is temporal coordinated with motion features while preserving the vivid and diverse gesture generation. Extensive experiments demonstrate that our proposed CoCoGesture outperforms the state-of-the-art methods on the zero-shot speech-to-gesture generation. The dataset will be publicly available at: https://mattie-e.github.io/GES-X/, Comment: The dataset will be released as soon as possible

Continual Test-Time Adaptation (CTTA), which aims to adapt the pre-trained model to ever-evolving target domains, emerges as an important task for vision models. As current vision models appear to be heavily biased towards texture, continuously adapting the model from one domain distribution to another can result in serious catastrophic forgetting. Drawing inspiration from the human visual system's adeptness at processing both shape and texture according to the famous Trichromatic Theory, we explore the integration of a Mixture-of-Activation-Sparsity-Experts (MoASE) as an adapter for the CTTA task. Given the distinct reaction of neurons with low/high activation to domain-specific/agnostic features, MoASE decomposes the neural activation into high-activation and low-activation components with a non-differentiable Spatial Differentiate Dropout (SDD). Based on the decomposition, we devise a multi-gate structure comprising a Domain-Aware Gate (DAG) that utilizes domain information to adaptive combine experts that process the post-SDD sparse activations of different strengths, and the Activation Sparsity Gate (ASG) that adaptively assigned feature selection threshold of the SDD for different experts for more precise feature decomposition. Finally, we introduce a Homeostatic-Proximal (HP) loss to bypass the error accumulation problem when continuously adapting the model. Extensive experiments on four prominent benchmarks substantiate that our methodology achieves state-of-the-art performance in both classification and segmentation CTTA tasks. Our code is now available at https://github.com/RoyZry98/MoASE-Pytorch.

Large vision-language models (LVLMs) have recently achieved rapid progress, exhibiting great perception and reasoning abilities concerning visual information. However, when faced with prompts in different sizes of solution spaces, LVLMs fail to always give consistent answers regarding the same knowledge point. This inconsistency of answers between different solution spaces is prevalent in LVLMs and erodes trust. To this end, we provide a multi-modal benchmark ConBench, to intuitively analyze how LVLMs perform when the solution space of a prompt revolves around a knowledge point. Based on the ConBench tool, we are the first to reveal the tapestry and get the following findings: (1) In the discriminate realm, the larger the solution space of the prompt, the lower the accuracy of the answers. (2) Establish the relationship between the discriminative and generative realms: the accuracy of the discriminative question type exhibits a strong positive correlation with its Consistency with the caption. (3) Compared to open-source models, closed-source models exhibit a pronounced bias advantage in terms of Consistency. Eventually, we ameliorate the consistency of LVLMs by trigger-based diagnostic refinement, indirectly improving the performance of their caption. We hope this paper will accelerate the research community in better evaluating their models and encourage future advancements in the consistency domain. The project is available at https://github.com/foundation-multimodal-models/ConBench., Comment: Accepted by NeurIPS 2024

In this paper, we introduce Era3D, a novel multiview diffusion method that generates high-resolution multiview images from a single-view image. Despite significant advancements in multiview generation, existing methods still suffer from camera prior mismatch, inefficacy, and low resolution, resulting in poor-quality multiview images. Specifically, these methods assume that the input images should comply with a predefined camera type, e.g. a perspective camera with a fixed focal length, leading to distorted shapes when the assumption fails. Moreover, the full-image or dense multiview attention they employ leads to an exponential explosion of computational complexity as image resolution increases, resulting in prohibitively expensive training costs. To bridge the gap between assumption and reality, Era3D first proposes a diffusion-based camera prediction module to estimate the focal length and elevation of the input image, which allows our method to generate images without shape distortions. Furthermore, a simple but efficient attention layer, named row-wise attention, is used to enforce epipolar priors in the multiview diffusion, facilitating efficient cross-view information fusion. Consequently, compared with state-of-the-art methods, Era3D generates high-quality multiview images with up to a 512*512 resolution while reducing computation complexity by 12x times. Comprehensive experiments demonstrate that Era3D can reconstruct high-quality and detailed 3D meshes from diverse single-view input images, significantly outperforming baseline multiview diffusion methods. Project page: https://penghtyx.github.io/Era3D/., Comment: NeurIPS2024

The distribution of subpopulations is an important property hidden within a dataset. Uncovering and analyzing the subpopulation distribution within datasets provides a comprehensive understanding of the datasets, standing as a powerful tool beneficial to various downstream tasks, including Dataset Subpopulation Organization, Subpopulation Shift, and Slice Discovery. Despite its importance, there has been no work that systematically explores the subpopulation distribution of datasets to our knowledge. To address the limitation and solve all the mentioned tasks in a unified way, we introduce a novel concept of subpopulation structures to represent, analyze, and utilize subpopulation distributions within datasets. To characterize the structures in an interpretable manner, we propose the Subpopulation Structure Discovery with Large Language Models (SSD-LLM) framework, which employs world knowledge and instruction-following capabilities of Large Language Models (LLMs) to linguistically analyze informative image captions and summarize the structures. Furthermore, we propose complete workflows to address downstream tasks, named Task-specific Tuning, showcasing the application of the discovered structure to a spectrum of subpopulation-related tasks, including dataset subpopulation organization, subpopulation shift, and slice discovery. Furthermore, we propose complete workflows to address downstream tasks, named Task-specific Tuning, showcasing the application of the discovered structure to a spectrum of subpopulation-related tasks, including dataset subpopulation organization, subpopulation shift, and slice discovery., Comment: ECCV24 Camera Ready

Large foundation models have recently emerged as a prominent focus of interest, attaining superior performance in widespread scenarios. Due to the scarcity of 3D data, many efforts have been made to adapt pre-trained transformers from vision to 3D domains. However, such 2D-to-3D approaches are still limited, due to the potential loss of spatial geometries and high computation cost. More importantly, their frameworks are mainly designed for 2D models, lacking a general any-to-3D paradigm. In this paper, we introduce Any2Point, a parameter-efficient method to empower any-modality large models (vision, language, audio) for 3D understanding. Given a frozen transformer from any source modality, we propose a 3D-to-any (1D or 2D) virtual projection strategy that correlates the input 3D points to the original 1D or 2D positions within the source modality. This mechanism enables us to assign each 3D token with a positional encoding paired with the pre-trained model, which avoids 3D geometry loss caused by the true projection and better motivates the transformer for 3D learning with 1D/2D positional priors. Then, within each transformer block, we insert an any-to-3D guided adapter module for parameter-efficient fine-tuning. The adapter incorporates prior spatial knowledge from the source modality to guide the local feature aggregation of 3D tokens, compelling the semantic adaption of any-modality transformers. We conduct extensive experiments to showcase the effectiveness and efficiency of our method. Code and models are released at https://github.com/Ivan-Tang-3D/Any2Point., Comment: Code and models are released at https://github.com/Ivan-Tang-3D/Any2Point

One of the most critical factors in achieving sharp Novel View Synthesis (NVS) using neural field methods like Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS) is the quality of the training images. However, Conventional RGB cameras are susceptible to motion blur. In contrast, neuromorphic cameras like event and spike cameras inherently capture more comprehensive temporal information, which can provide a sharp representation of the scene as additional training data. Recent methods have explored the integration of event cameras to improve the quality of NVS. The event-RGB approaches have some limitations, such as high training costs and the inability to work effectively in the background. Instead, our study introduces a new method that uses the spike camera to overcome these limitations. By considering texture reconstruction from spike streams as ground truth, we design the Texture from Spike (TfS) loss. Since the spike camera relies on temporal integration instead of temporal differentiation used by event cameras, our proposed TfS loss maintains manageable training costs. It handles foreground objects with backgrounds simultaneously. We also provide a real-world dataset captured with our spike-RGB camera system to facilitate future research endeavors. We conduct extensive experiments using synthetic and real-world datasets to demonstrate that our design can enhance novel view synthesis across NeRF and 3DGS. The code and dataset will be made available for public access.

The interaction between humans and artificial intelligence (AI) is a crucial factor that reflects the effectiveness of multimodal large language models (MLLMs). However, current MLLMs primarily focus on image-level comprehension and limit interaction to textual instructions, thereby constraining their flexibility in usage and depth of response. In this paper, we introduce the Draw-and-Understand project: a new model, a multi-domain dataset, and a challenging benchmark for visual prompting. Specifically, we propose SPHINX-V, a new end-to-end trained Multimodal Large Language Model (MLLM) that connects a vision encoder, a visual prompt encoder and an LLM for various visual prompts (points, bounding boxes, and free-form shape) and language understanding. To advance visual prompting research for MLLMs, we introduce MDVP-Data and MDVP-Bench. MDVP-Data features a multi-domain dataset containing 1.6M unique image-visual prompt-text instruction-following samples, including natural images, document images, OCR images, mobile screenshots, web screenshots, and multi-panel images. Furthermore, we present MDVP-Bench, a comprehensive and challenging benchmark to assess a model's capability in understanding visual prompting instructions. Our experiments demonstrate SPHINX-V's impressive multimodal interaction capabilities through visual prompting, revealing significant improvements in detailed pixel-level description and question-answering abilities., Comment: 16 pages, 7 figures

Training high-accuracy 3D detectors necessitates massive labeled 3D annotations with 7 degree-of-freedom, which is laborious and time-consuming. Therefore, the form of point annotations is proposed to offer significant prospects for practical applications in 3D detection, which is not only more accessible and less expensive but also provides strong spatial information for object localization. In this paper, we empirically discover that it is non-trivial to merely adapt Point-DETR to its 3D form, encountering two main bottlenecks: 1) it fails to encode strong 3D prior into the model, and 2) it generates low-quality pseudo labels in distant regions due to the extreme sparsity of LiDAR points. To overcome these challenges, we introduce Point-DETR3D, a teacher-student framework for weakly semi-supervised 3D detection, designed to fully capitalize on point-wise supervision within a constrained instance-wise annotation budget.Different from Point-DETR which encodes 3D positional information solely through a point encoder, we propose an explicit positional query initialization strategy to enhance the positional prior. Considering the low quality of pseudo labels at distant regions produced by the teacher model, we enhance the detector's perception by incorporating dense imagery data through a novel Cross-Modal Deformable RoI Fusion (D-RoI).Moreover, an innovative point-guided self-supervised learning technique is proposed to allow for fully exploiting point priors, even in student models.Extensive experiments on representative nuScenes dataset demonstrate our Point-DETR3D obtains significant improvements compared to previous works. Notably, with only 5% of labeled data, Point-DETR3D achieves over 90% performance of its fully supervised counterpart., Comment: Accepted by AAAI2024

Recently, how to achieve precise image editing has attracted increasing attention, especially given the remarkable success of text-to-image generation models. To unify various spatial-aware image editing abilities into one framework, we adopt the concept of layers from the design domain to manipulate objects flexibly with various operations. The key insight is to transform the spatial-aware image editing task into a combination of two sub-tasks: multi-layered latent decomposition and multi-layered latent fusion. First, we segment the latent representations of the source images into multiple layers, which include several object layers and one incomplete background layer that necessitates reliable inpainting. To avoid extra tuning, we further explore the inner inpainting ability within the self-attention mechanism. We introduce a key-masking self-attention scheme that can propagate the surrounding context information into the masked region while mitigating its impact on the regions outside the mask. Second, we propose an instruction-guided latent fusion that pastes the multi-layered latent representations onto a canvas latent. We also introduce an artifact suppression scheme in the latent space to enhance the inpainting quality. Due to the inherent modular advantages of such multi-layered representations, we can achieve accurate image editing, and we demonstrate that our approach consistently surpasses the latest spatial editing methods, including Self-Guidance and DiffEditor. Last, we show that our approach is a unified framework that supports various accurate image editing tasks on more than six different editing tasks., Comment: technical report, 15 pages, webpage: https://design-edit.github.io/

Zero-Shot Object Navigation (ZSON) requires agents to autonomously locate and approach unseen objects in unfamiliar environments and has emerged as a particularly challenging task within the domain of Embodied AI. Existing datasets for developing ZSON algorithms lack consideration of dynamic obstacles, object attribute diversity, and scene texts, thus exhibiting noticeable discrepancies from real-world situations. To address these issues, we propose a Dataset for Open-Vocabulary Zero-Shot Object Navigation in Dynamic Environments (DOZE) that comprises ten high-fidelity 3D scenes with over 18k tasks, aiming to mimic complex, dynamic real-world scenarios. Specifically, DOZE scenes feature multiple moving humanoid obstacles, a wide array of open-vocabulary objects, diverse distinct-attribute objects, and valuable textual hints. Besides, different from existing datasets that only provide collision checking between the agent and static obstacles, we enhance DOZE by integrating capabilities for detecting collisions between the agent and moving obstacles. This novel functionality enables the evaluation of the agents' collision avoidance abilities in dynamic environments. We test four representative ZSON methods on DOZE, revealing substantial room for improvement in existing approaches concerning navigation efficiency, safety, and object recognition accuracy. Our dataset can be found at https://DOZE-Dataset.github.io/., Comment: This version of the paper has been accepted for publication in IEEE Robotics and Automation Letters (RA-L)

In this report, we present our solution to the multi-task robustness track of the 1st Visual Continual Learning (VCL) Challenge at ICCV 2023 Workshop. We propose a vanilla framework named UniNet that seamlessly combines various visual perception algorithms into a multi-task model. Specifically, we choose DETR3D, Mask2Former, and BinsFormer for 3D object detection, instance segmentation, and depth estimation tasks, respectively. The final submission is a single model with InternImage-L backbone, and achieves a 49.6 overall score (29.5 Det mAP, 80.3 mTPS, 46.4 Seg mAP, and 7.93 silog) on SHIFT validation set. Besides, we provide some interesting observations in our experiments which may facilitate the development of multi-task learning in dense visual prediction., Comment: Technical Report

Multi-modal large language models (MLLMs) have demonstrated remarkable vision-language capabilities, primarily due to the exceptional in-context understanding and multi-task learning strengths of large language models (LLMs). The advent of visual instruction tuning has further enhanced MLLMs' performance in vision-language understanding. However, while existing MLLMs adeptly recognize \textit{what} objects are in an image, they still face challenges in effectively discerning \textit{where} these objects are, particularly along the distance (scene depth) axis. To overcome this limitation in MLLMs, we introduce Proximity Question Answering (Proximity QA), a novel framework designed to enable MLLMs to infer the proximity relationship between objects in images. The framework operates in two phases: the first phase focuses on guiding the models to understand the relative depth of objects, and the second phase further encourages the models to infer the proximity relationships between objects based on their depth perceptions. We also propose a VQA dataset called Proximity-110K, containing additional instructions that incorporate depth information and the proximity relationships of objects. We have conducted extensive experiments to validate Proximity QA's superior ability in depth perception and proximity analysis, outperforming other state-of-the-art MLLMs. Code and dataset will be released at \textcolor{magenta}{https://github.com/NorthSummer/ProximityQA.git}., Comment: 15 pages,version 1

Finetuning a pretrained vision model (PVM) is a common technique for learning downstream vision tasks. However, the conventional finetuning process with randomly sampled data points results in diminished training efficiency. To address this drawback, we propose a novel approach, Vision-language Collaborative Active Finetuning (VeCAF). With the emerging availability of labels and natural language annotations of images through web-scale crawling or controlled generation, VeCAF makes use of these information to perform parametric data selection for PVM finetuning. VeCAF incorporates the finetuning objective to select significant data points that effectively guide the PVM towards faster convergence to meet the performance goal. This process is assisted by the inherent semantic richness of the text embedding space which we use to augment image features. Furthermore, the flexibility of text-domain augmentation allows VeCAF to handle out-of-distribution scenarios without external data. Extensive experiments show the leading performance and high computational efficiency of VeCAF that is superior to baselines in both in-distribution and out-of-distribution image classification tasks. On ImageNet, VeCAF uses up to 3.3x less training batches to reach the target performance compared to full finetuning, and achieves an accuracy improvement of 2.7% over the state-of-the-art active finetuning method with the same number of batches., Comment: 13 pages

Recent work on Neural Radiance Fields (NeRF) exploits multi-view 3D consistency, achieving impressive results in 3D scene modeling and high-fidelity novel-view synthesis. However, there are limitations. First, existing methods assume enough high-quality images are available for training the NeRF model, ignoring real-world image degradation. Second, previous methods struggle with ambiguity in the training set due to unmodeled inconsistencies among different views. In this work, we present RustNeRF for real-world high-quality NeRF. To improve NeRF's robustness under real-world inputs, we train a 3D-aware preprocessing network that incorporates real-world degradation modeling. We propose a novel implicit multi-view guidance to address information loss during image degradation and restoration. Extensive experiments demonstrate RustNeRF's advantages over existing approaches under real-world degradation. The code will be released.

In the realm of household robotics, the Zero-Shot Object Navigation (ZSON) task empowers agents to adeptly traverse unfamiliar environments and locate objects from novel categories without prior explicit training. This paper introduces VoroNav, a novel semantic exploration framework that proposes the Reduced Voronoi Graph to extract exploratory paths and planning nodes from a semantic map constructed in real time. By harnessing topological and semantic information, VoroNav designs text-based descriptions of paths and images that are readily interpretable by a large language model (LLM). In particular, our approach presents a synergy of path and farsight descriptions to represent the environmental context, enabling LLM to apply commonsense reasoning to ascertain waypoints for navigation. Extensive evaluation on HM3D and HSSD validates VoroNav surpasses existing benchmarks in both success rate and exploration efficiency (absolute improvement: +2.8% Success and +3.7% SPL on HM3D, +2.6% Success and +3.8% SPL on HSSD). Additionally introduced metrics that evaluate obstacle avoidance proficiency and perceptual efficiency further corroborate the enhancements achieved by our method in ZSON planning. Project page: https://voro-nav.github.io, Comment: 18 pages, 13 figures

Copyright law confers upon creators the exclusive rights to reproduce, distribute, and monetize their creative works. However, recent progress in text-to-image generation has introduced formidable challenges to copyright enforcement. These technologies enable the unauthorized learning and replication of copyrighted content, artistic creations, and likenesses, leading to the proliferation of unregulated content. Notably, models like stable diffusion, which excel in text-to-image synthesis, heighten the risk of copyright infringement and unauthorized distribution.Machine unlearning, which seeks to eradicate the influence of specific data or concepts from machine learning models, emerges as a promising solution by eliminating the \enquote{copyright memories} ingrained in diffusion models. Yet, the absence of comprehensive large-scale datasets and standardized benchmarks for evaluating the efficacy of unlearning techniques in the copyright protection scenarios impedes the development of more effective unlearning methods. To address this gap, we introduce a novel pipeline that harmonizes CLIP, ChatGPT, and diffusion models to curate a dataset. This dataset encompasses anchor images, associated prompts, and images synthesized by text-to-image models. Additionally, we have developed a mixed metric based on semantic and style information, validated through both human and artist assessments, to gauge the effectiveness of unlearning approaches. Our dataset, benchmark library, and evaluation metrics will be made publicly available to foster future research and practical applications (https://rmpku.github.io/CPDM-page/, website / http://149.104.22.83/unlearning.tar.gz, dataset)., Comment: 20 pages, 7 figures, 3 table

The Mixture-of-Experts (MoE) approach has demonstrated outstanding scalability in multi-task learning including low-level upstream tasks such as concurrent removal of multiple adverse weather effects. However, the conventional MoE architecture with parallel Feed Forward Network (FFN) experts leads to significant parameter and computational overheads that hinder its efficient deployment. In addition, the naive MoE linear router is suboptimal in assigning task-specific features to multiple experts which limits its further scalability. In this work, we propose an efficient MoE architecture with weight sharing across the experts. Inspired by the idea of linear feature modulation (FM), our architecture implicitly instantiates multiple experts via learnable activation modulations on a single shared expert block. The proposed Feature Modulated Expert (FME) serves as a building block for the novel Mixture-of-Feature-Modulation-Experts (MoFME) architecture, which can scale up the number of experts with low overhead. We further propose an Uncertainty-aware Router (UaR) to assign task-specific features to different FM modules with well-calibrated weights. This enables MoFME to effectively learn diverse expert functions for multiple tasks. The conducted experiments on the multi-deweather task show that our MoFME outperforms the baselines in the image restoration quality by 0.1-0.2 dB and achieves SOTA-compatible performance while saving more than 72% of parameters and 39% inference time over the conventional MoE counterpart. Experiments on the downstream segmentation and classification tasks further demonstrate the generalizability of MoFME to real open-world applications., Comment: aaai2024

The burgeoning field of Multimodal Large Language Models (MLLMs) has exhibited remarkable performance in diverse tasks such as captioning, commonsense reasoning, and visual scene understanding. However, the deployment of these large-scale MLLMs on client devices is hindered by their extensive model parameters, leading to a notable decline in generalization capabilities when these models are compressed for device deployment. Addressing this challenge, we introduce a Cloud-Device Collaborative Continual Adaptation framework, designed to enhance the performance of compressed, device-deployed MLLMs by leveraging the robust capabilities of cloud-based, larger-scale MLLMs. Our framework is structured into three key components: a device-to-cloud uplink for efficient data transmission, cloud-based knowledge adaptation, and an optimized cloud-to-device downlink for model deployment. In the uplink phase, we employ an Uncertainty-guided Token Sampling (UTS) strategy to effectively filter out-of-distribution tokens, thereby reducing transmission costs and improving training efficiency. On the cloud side, we propose Adapter-based Knowledge Distillation (AKD) method to transfer refined knowledge from large-scale to compressed, pocket-size MLLMs. Furthermore, we propose a Dynamic Weight update Compression (DWC) strategy for the downlink, which adaptively selects and quantizes updated weight parameters, enhancing transmission efficiency and reducing the representational disparity between cloud and device models. Extensive experiments on several multimodal benchmarks demonstrate the superiority of our proposed framework over prior Knowledge Distillation and device-cloud collaboration methods. Notably, we also validate the feasibility of our approach to real-world experiments.

Diffusion models have shown impressive performance in many domains. However, the model's capability to follow natural language instructions (e.g., spatial relationships between objects, generating complex scenes) is still unsatisfactory. In this work, we propose Iterative Prompt Relabeling (IPR), a novel algorithm that aligns images to text through iterative image sampling and prompt relabeling with feedback. IPR first samples a batch of images conditioned on the text, then relabels the text prompts of unmatched text-image pairs with classifier feedback. We conduct thorough experiments on SDv2 and SDXL, testing their capability to follow instructions on spatial relations. With IPR, we improved up to 15.22% (absolute improvement) on the challenging spatial relation VISOR benchmark, demonstrating superior performance compared to previous RL methods. Our code is publicly available at https://github.com/cxy000000/IPR-RLDF.

The superior performances of pre-trained foundation models in various visual tasks underscore their potential to enhance the 2D models' open-vocabulary ability. Existing methods explore analogous applications in the 3D space. However, most of them only center around knowledge extraction from singular foundation models, which limits the open-vocabulary ability of 3D models. We hypothesize that leveraging complementary pre-trained knowledge from various foundation models can improve knowledge transfer from 2D pre-trained visual language models to the 3D space. In this work, we propose FM-OV3D, a method of Foundation Model-based Cross-modal Knowledge Blending for Open-Vocabulary 3D Detection, which improves the open-vocabulary localization and recognition abilities of 3D model by blending knowledge from multiple pre-trained foundation models, achieving true open-vocabulary without facing constraints from original 3D datasets. Specifically, to learn the open-vocabulary 3D localization ability, we adopt the open-vocabulary localization knowledge of the Grounded-Segment-Anything model. For open-vocabulary 3D recognition ability, We leverage the knowledge of generative foundation models, including GPT-3 and Stable Diffusion models, and cross-modal discriminative models like CLIP. The experimental results on two popular benchmarks for open-vocabulary 3D object detection show that our model efficiently learns knowledge from multiple foundation models to enhance the open-vocabulary ability of the 3D model and successfully achieves state-of-the-art performance in open-vocabulary 3D object detection tasks. Code is released at https://github.com/dmzhang0425/FM-OV3D.git., Comment: Accepted by AAAI 2024. Code will be released at https://github.com/dmzhang0425/FM-OV3D.git

Recently, Large Language Models (LLMs) and Multimodal Large Language Models (MLLMs) have shown promise in instruction following and 2D image understanding. While these models are powerful, they have not yet been developed to comprehend the more challenging 3D physical scenes, especially when it comes to the sparse outdoor LiDAR data. In this paper, we introduce LiDAR-LLM, which takes raw LiDAR data as input and harnesses the remarkable reasoning capabilities of LLMs to gain a comprehensive understanding of outdoor 3D scenes. The central insight of our LiDAR-LLM is the reformulation of 3D outdoor scene cognition as a language modeling problem, encompassing tasks such as 3D captioning, 3D grounding, 3D question answering, etc. Specifically, due to the scarcity of 3D LiDAR-text pairing data, we introduce a three-stage training strategy and generate relevant datasets, progressively aligning the 3D modality with the language embedding space of LLM. Furthermore, we design a View-Aware Transformer (VAT) to connect the 3D encoder with the LLM, which effectively bridges the modality gap and enhances the LLM's spatial orientation comprehension of visual features. Our experiments show that LiDAR-LLM possesses favorable capabilities to comprehend various instructions regarding 3D scenes and engage in complex spatial reasoning. LiDAR-LLM attains a 40.9 BLEU-1 on the 3D captioning task and achieves a 63.1\% classification accuracy and a 14.3\% BEV mIoU on the 3D grounding task. Web page: https://sites.google.com/view/lidar-llm

Continual Test-Time Adaptation (CTTA) is proposed to migrate a source pre-trained model to continually changing target distributions, addressing real-world dynamism. Existing CTTA methods mainly rely on entropy minimization or teacher-student pseudo-labeling schemes for knowledge extraction in unlabeled target domains. However, dynamic data distributions cause miscalibrated predictions and noisy pseudo-labels in existing self-supervised learning methods, hindering the effective mitigation of error accumulation and catastrophic forgetting problems during the continual adaptation process. To tackle these issues, we propose a continual self-supervised method, Adaptive Distribution Masked Autoencoders (ADMA), which enhances the extraction of target domain knowledge while mitigating the accumulation of distribution shifts. Specifically, we propose a Distribution-aware Masking (DaM) mechanism to adaptively sample masked positions, followed by establishing consistency constraints between the masked target samples and the original target samples. Additionally, for masked tokens, we utilize an efficient decoder to reconstruct a hand-crafted feature descriptor (e.g., Histograms of Oriented Gradients), leveraging its invariant properties to boost task-relevant representations. Through conducting extensive experiments on four widely recognized benchmarks, our proposed method attains state-of-the-art performance in both classification and segmentation CTTA tasks. Our project page: https://sites.google.com/view/continual-mae/home., Comment: Accepted by CVPR2024

With the growing size of pre-trained models, full fine-tuning and storing all the parameters for various downstream tasks is costly and infeasible. In this paper, we propose a new parameter-efficient fine-tuning method, Gradient-based Parameter Selection (GPS), demonstrating that only tuning a few selected parameters from the pre-trained model while keeping the remainder of the model frozen can generate similar or better performance compared with the full model fine-tuning method. Different from the existing popular and state-of-the-art parameter-efficient fine-tuning approaches, our method does not introduce any additional parameters and computational costs during both the training and inference stages. Another advantage is the model-agnostic and non-destructive property, which eliminates the need for any other design specific to a particular model. Compared with the full fine-tuning, GPS achieves 3.33% (91.78% vs. 88.45%, FGVC) and 9.61% (73.1% vs. 65.57%, VTAB) improvement of the accuracy with tuning only 0.36% parameters of the pre-trained model on average over 24 image classification tasks; it also demonstrates a significant improvement of 17% and 16.8% in mDice and mIoU, respectively, on medical image segmentation task. Moreover, GPS achieves state-of-the-art performance compared with existing PEFT methods.

In this paper, we present a novel two-stage approach that fully utilizes the information provided by the reference image to establish a customized knowledge prior for image-to-3D generation. While previous approaches primarily rely on a general diffusion prior, which struggles to yield consistent results with the reference image, we propose a subject-specific and multi-modal diffusion model. This model not only aids NeRF optimization by considering the shading mode for improved geometry but also enhances texture from the coarse results to achieve superior refinement. Both aspects contribute to faithfully aligning the 3D content with the subject. Extensive experiments showcase the superiority of our method, Customize-It-3D, outperforming previous works by a substantial margin. It produces faithful 360-degree reconstructions with impressive visual quality, making it well-suited for various applications, including text-to-3D creation., Comment: Project Page: https://nnanhuang.github.io/projects/customize-it-3d/

Uncertainty estimation is crucial for machine learning models to detect out-of-distribution (OOD) inputs. However, the conventional discriminative deep learning classifiers produce uncalibrated closed-set predictions for OOD data. A more robust classifiers with the uncertainty estimation typically require a potentially unavailable OOD dataset for outlier exposure training, or a considerable amount of additional memory and compute to build ensemble models. In this work, we improve on uncertainty estimation without extra OOD data or additional inference costs using an alternative Split-Ensemble method. Specifically, we propose a novel subtask-splitting ensemble training objective, where a common multiclass classification task is split into several complementary subtasks. Then, each subtask's training data can be considered as OOD to the other subtasks. Diverse submodels can therefore be trained on each subtask with OOD-aware objectives. The subtask-splitting objective enables us to share low-level features across submodels to avoid parameter and computational overheads. In particular, we build a tree-like Split-Ensemble architecture by performing iterative splitting and pruning from a shared backbone model, where each branch serves as a submodel corresponding to a subtask. This leads to improved accuracy and uncertainty estimation across submodels under a fixed ensemble computation budget. Empirical study with ResNet-18 backbone shows Split-Ensemble, without additional computation cost, improves accuracy over a single model by 0.8%, 1.8%, and 25.5% on CIFAR-10, CIFAR-100, and Tiny-ImageNet, respectively. OOD detection for the same backbone and in-distribution datasets surpasses a single model baseline by, correspondingly, 2.2%, 8.1%, and 29.6% mean AUROC., Comment: ICML2024. Project website is available at https://antonioo-c.github.io/projects/split-ensemble

With the rapid growth in the scale of pre-trained foundation models, parameter-efficient fine-tuning techniques have gained significant attention, among which Adapter Tuning is the most widely used. Despite achieving efficiency, it still underperforms full fine-tuning, and the performance improves at the cost of an increase in parameters. Recent efforts have either focused on training multiple adapter experts to increase model capacity or on pruning adapters to achieve parameter efficiency. However, both approaches introduce more parameters compared to the original adapter, hence are not computationally efficient. Motivated by this, we propose Mixture of Sparse Adapters, or MoSA, as a novel Adapter Tuning method to fully unleash the potential of each parameter in the adapter. We first split the standard adapter into multiple non-overlapping modules, then stochastically activate them for sparse training, and finally merge them to form a complete adapter after tuning. In this way, MoSA can achieve significantly better performance than standard adapters without any additional computational or storage overhead. Furthermore, we propose a hierarchical sparse strategy to better leverage limited training data. Extensive experiments on a series of 27 visual tasks demonstrate that MoSA consistently outperforms other Adapter Tuning methods as well as other baselines by a large margin. Furthermore, MoSA brings consistent improvements across various model scales, architectures, and different PEFT methods. Code will be released., Comment: 16 pages, 7 figures. Official code: https://github.com/Theia-4869/MoSA

Emerging Implicit Neural Representation (INR) is a promising data compression technique, which represents the data using the parameters of a Deep Neural Network (DNN). Existing methods manually partition a complex scene into local regions and overfit the INRs into those regions. However, manually designing the partition scheme for a complex scene is very challenging and fails to jointly learn the partition and INRs. To solve the problem, we propose MoEC, a novel implicit neural compression method based on the theory of mixture of experts. Specifically, we use a gating network to automatically assign a specific INR to a 3D point in the scene. The gating network is trained jointly with the INRs of different local regions. Compared with block-wise and tree-structured partitions, our learnable partition can adaptively find the optimal partition in an end-to-end manner. We conduct detailed experiments on massive and diverse biomedical data to demonstrate the advantages of MoEC against existing approaches. In most of experiment settings, we have achieved state-of-the-art results. Especially in cases of extreme compression ratios, such as 6000x, we are able to uphold the PSNR of 48.16.

While current LLM chatbots like GPT-4V bridge the gap between human instructions and visual representations to enable text-image generations, they still lack efficient alignment methods for high-fidelity performance on multiple downstream tasks. In this paper, we propose \textbf{$M^{2}Chat$}, a novel unified multimodal LLM framework for generating interleaved text-image conversation across various scenarios. Specifically, we propose an $M^{3}Adapter$ that efficiently integrates granular low-level visual information and high-level semantic features from multi-modality prompts. Upon the well-aligned fused feature, $M^{3}Adapter$ tailors a learnable gating strategy to balance the model creativity and consistency across various tasks adaptively. Moreover, to further enhance the effectiveness of $M^{3}Adapter$ while preserving the coherence of semantic context comprehension, we introduce a two-stage $M^{3}FT$ fine-tuning strategy. This strategy optimizes disjoint groups of parameters for image-text alignment and visual-instruction respectively. Extensive experiments demonstrate our $M^{2}Chat$ surpasses state-of-the-art counterparts across diverse benchmarks, showcasing its prowess in interleaving generation, storytelling, and multimodal dialogue systems. The demo and code are available at \red{https://mattie-e.github.io/M2Chat.github.io}.

Generating vivid and emotional 3D co-speech gestures is crucial for virtual avatar animation in human-machine interaction applications. While the existing methods enable generating the gestures to follow a single emotion label, they overlook that long gesture sequence modeling with emotion transition is more practical in real scenes. In addition, the lack of large-scale available datasets with emotional transition speech and corresponding 3D human gestures also limits the addressing of this task. To fulfill this goal, we first incorporate the ChatGPT-4 and an audio inpainting approach to construct the high-fidelity emotion transition human speeches. Considering obtaining the realistic 3D pose annotations corresponding to the dynamically inpainted emotion transition audio is extremely difficult, we propose a novel weakly supervised training strategy to encourage authority gesture transitions. Specifically, to enhance the coordination of transition gestures w.r.t different emotional ones, we model the temporal association representation between two different emotional gesture sequences as style guidance and infuse it into the transition generation. We further devise an emotion mixture mechanism that provides weak supervision based on a learnable mixed emotion label for transition gestures. Last, we present a keyframe sampler to supply effective initial posture cues in long sequences, enabling us to generate diverse gestures. Extensive experiments demonstrate that our method outperforms the state-of-the-art models constructed by adapting single emotion-conditioned counterparts on our newly defined emotion transition task and datasets. Our code and dataset will be released on the project page: https://xingqunqi-lab.github.io/Emo-Transition-Gesture/., Comment: Accepted by CVPR 2024