Search

Due to the continuous emergence of new data, version updates have become an indispensable requirement for Large Language Models (LLMs). The training paradigms for version updates of LLMs include pre-training from scratch (PTFS) and continual pre-training (CPT). Preliminary experiments demonstrate that PTFS achieves better pre-training performance, while CPT has lower training cost. Moreover, their performance and training cost gaps widen progressively with version updates. To investigate the underlying reasons for this phenomenon, we analyze the effect of learning rate adjustments during the two stages of CPT: preparing an initialization checkpoint and continual pre-training based on this checkpoint. We find that a large learning rate in the first stage and a complete learning rate decay process in the second stage are crucial for version updates of LLMs. Hence, we propose a learning rate path switching training paradigm. Our paradigm comprises one main path, where we pre-train a LLM with the maximal learning rate, and multiple branching paths, each of which corresponds to an update of the LLM with newly-added training data. Extensive experiments demonstrate the effectiveness and generalization of our paradigm. Particularly, when training four versions of LLMs, our paradigm reduces the total training cost to 58% compared to PTFS, while maintaining comparable pre-training performance., Comment: EMNLP 2024 (main,long paper)

Autoregressive (AR) models have reformulated image generation as next-token prediction, demonstrating remarkable potential and emerging as strong competitors to diffusion models. However, control-to-image generation, akin to ControlNet, remains largely unexplored within AR models. Although a natural approach, inspired by advancements in Large Language Models, is to tokenize control images into tokens and prefill them into the autoregressive model before decoding image tokens, it still falls short in generation quality compared to ControlNet and suffers from inefficiency. To this end, we introduce ControlAR, an efficient and effective framework for integrating spatial controls into autoregressive image generation models. Firstly, we explore control encoding for AR models and propose a lightweight control encoder to transform spatial inputs (e.g., canny edges or depth maps) into control tokens. Then ControlAR exploits the conditional decoding method to generate the next image token conditioned on the per-token fusion between control and image tokens, similar to positional encodings. Compared to prefilling tokens, using conditional decoding significantly strengthens the control capability of AR models but also maintains the model's efficiency. Furthermore, the proposed ControlAR surprisingly empowers AR models with arbitrary-resolution image generation via conditional decoding and specific controls. Extensive experiments can demonstrate the controllability of the proposed ControlAR for the autoregressive control-to-image generation across diverse inputs, including edges, depths, and segmentation masks. Furthermore, both quantitative and qualitative results indicate that ControlAR surpasses previous state-of-the-art controllable diffusion models, e.g., ControlNet++. Code, models, and demo will soon be available at https://github.com/hustvl/ControlAR., Comment: Preprint. Work in progress

Vision-language models have showcased impressive zero-shot classification capabilities when equipped with suitable text prompts. Previous studies have shown the effectiveness of test-time prompt tuning; however, these methods typically require per-image prompt adaptation during inference, which incurs high computational budgets and limits scalability and practical deployment. To overcome this issue, we introduce Self-TPT, a novel framework leveraging Self-supervised learning for efficient Test-time Prompt Tuning. The key aspect of Self-TPT is that it turns to efficient predefined class adaptation via self-supervised learning, thus avoiding computation-heavy per-image adaptation at inference. Self-TPT begins by co-training the self-supervised and the classification task using source data, then applies the self-supervised task exclusively for test-time new class adaptation. Specifically, we propose Contrastive Prompt Learning (CPT) as the key task for self-supervision. CPT is designed to minimize the intra-class distances while enhancing inter-class distinguishability via contrastive learning. Furthermore, empirical evidence suggests that CPT could closely mimic back-propagated gradients of the classification task, offering a plausible explanation for its effectiveness. Motivated by this finding, we further introduce a gradient matching loss to explicitly enhance the gradient similarity. We evaluated Self-TPT across three challenging zero-shot benchmarks. The results consistently demonstrate that Self-TPT not only significantly reduces inference costs but also achieves state-of-the-art performance, effectively balancing the efficiency-efficacy trade-off.

Segment Anything Model (SAM) has attracted widespread attention for its superior interactive segmentation capabilities with visual prompts while lacking further exploration of text prompts. In this paper, we empirically investigate what text prompt encoders (e.g., CLIP or LLM) are good for adapting SAM for referring expression segmentation and introduce the Early Vision-language Fusion-based SAM (EVF-SAM). EVF-SAM is a simple yet effective referring segmentation method which exploits multimodal prompts (i.e., image and text) and comprises a pre-trained vision-language model to generate referring prompts and a SAM model for segmentation. Surprisingly, we observe that: (1) multimodal prompts and (2) vision-language models with early fusion (e.g., BEIT-3) are beneficial for prompting SAM for accurate referring segmentation. Our experiments show that the proposed EVF-SAM based on BEIT-3 can obtain state-of-the-art performance on RefCOCO/+/g for referring expression segmentation and demonstrate the superiority of prompting SAM with early vision-language fusion. In addition, the proposed EVF-SAM with 1.32B parameters achieves remarkably higher performance while reducing nearly 82% of parameters compared to previous SAM methods based on large multimodal models., Comment: Preprint. Update: (1) better performance and (2) versatile segmentation. Code and models are available at: https://github.com/hustvl/EVF-SAM

High-fidelity reconstruction of 3D human avatars has a wild application in visual reality. In this paper, we introduce FAGhead, a method that enables fully controllable human portraits from monocular videos. We explicit the traditional 3D morphable meshes (3DMM) and optimize the neutral 3D Gaussians to reconstruct with complex expressions. Furthermore, we employ a novel Point-based Learnable Representation Field (PLRF) with learnable Gaussian point positions to enhance reconstruction performance. Meanwhile, to effectively manage the edges of avatars, we introduced the alpha rendering to supervise the alpha value of each pixel. Extensive experimental results on the open-source datasets and our capturing datasets demonstrate that our approach is able to generate high-fidelity 3D head avatars and fully control the expression and pose of the virtual avatars, which is outperforming than existing works.

Micro-expressions (MEs) are involuntary movements revealing people's hidden feelings, which has attracted numerous interests for its objectivity in emotion detection. However, despite its wide applications in various scenarios, micro-expression recognition (MER) remains a challenging problem in real life due to three reasons, including (i) data-level: lack of data and imbalanced classes, (ii) feature-level: subtle, rapid changing, and complex features of MEs, and (iii) decision-making-level: impact of individual differences. To address these issues, we propose a dual-branch meta-auxiliary learning method, called LightmanNet, for fast and robust micro-expression recognition. Specifically, LightmanNet learns general MER knowledge from limited data through a dual-branch bi-level optimization process: (i) In the first level, it obtains task-specific MER knowledge by learning in two branches, where the first branch is for learning MER features via primary MER tasks, while the other branch is for guiding the model obtain discriminative features via auxiliary tasks, i.e., image alignment between micro-expressions and macro-expressions since their resemblance in both spatial and temporal behavioral patterns. The two branches of learning jointly constrain the model of learning meaningful task-specific MER knowledge while avoiding learning noise or superficial connections between MEs and emotions that may damage its generalization ability. (ii) In the second level, LightmanNet further refines the learned task-specific knowledge, improving model generalization and efficiency. Extensive experiments on various benchmark datasets demonstrate the superior robustness and efficiency of LightmanNet., Comment: 10 pages, 7 figures, 3 tables

Recent advances in text-to-video generation have harnessed the power of diffusion models to create visually compelling content conditioned on text prompts. However, they usually encounter high computational costs and often struggle to produce videos with coherent physical motions. To tackle these issues, we propose GPT4Motion, a training-free framework that leverages the planning capability of large language models such as GPT, the physical simulation strength of Blender, and the excellent image generation ability of text-to-image diffusion models to enhance the quality of video synthesis. Specifically, GPT4Motion employs GPT-4 to generate a Blender script based on a user textual prompt, which commands Blender's built-in physics engine to craft fundamental scene components that encapsulate coherent physical motions across frames. Then these components are inputted into Stable Diffusion to generate a video aligned with the textual prompt. Experimental results on three basic physical motion scenarios, including rigid object drop and collision, cloth draping and swinging, and liquid flow, demonstrate that GPT4Motion can generate high-quality videos efficiently in maintaining motion coherency and entity consistency. GPT4Motion offers new insights in text-to-video research, enhancing its quality and broadening its horizon for further explorations.

We present ImageBind-LLM, a multi-modality instruction tuning method of large language models (LLMs) via ImageBind. Existing works mainly focus on language and image instruction tuning, different from which, our ImageBind-LLM can respond to multi-modality conditions, including audio, 3D point clouds, video, and their embedding-space arithmetic by only image-text alignment training. During training, we adopt a learnable bind network to align the embedding space between LLaMA and ImageBind's image encoder. Then, the image features transformed by the bind network are added to word tokens of all layers in LLaMA, which progressively injects visual instructions via an attention-free and zero-initialized gating mechanism. Aided by the joint embedding of ImageBind, the simple image-text training enables our model to exhibit superior multi-modality instruction-following capabilities. During inference, the multi-modality inputs are fed into the corresponding ImageBind encoders, and processed by a proposed visual cache model for further cross-modal embedding enhancement. The training-free cache model retrieves from three million image features extracted by ImageBind, which effectively mitigates the training-inference modality discrepancy. Notably, with our approach, ImageBind-LLM can respond to instructions of diverse modalities and demonstrate significant language generation quality. Code is released at https://github.com/OpenGVLab/LLaMA-Adapter., Comment: Code is available at https://github.com/OpenGVLab/LLaMA-Adapter

Prompt learning has emerged as an efficient and effective approach for transferring foundational Vision-Language Models (e.g., CLIP) to downstream tasks. However, current methods tend to overfit to seen categories, thereby limiting their generalization ability for unseen classes. In this paper, we propose a new method, Decoupled Prompt Learning (DPL), which reformulates the attention in prompt learning to alleviate this problem. Specifically, we theoretically investigate the collaborative process between prompts and instances (i.e., image patches/text tokens) by reformulating the original self-attention into four separate sub-processes. Through detailed analysis, we observe that certain sub-processes can be strengthened to bolster robustness and generalizability by some approximation techniques. Furthermore, we introduce language-conditioned textual prompting based on decoupled attention to naturally preserve the generalization of text input. Our approach is flexible for both visual and textual modalities, making it easily extendable to multi-modal prompt learning. By combining the proposed techniques, our approach achieves state-of-the-art performance on three representative benchmarks encompassing 15 image recognition datasets, while maintaining parameter-efficient. Moreover, our DPL does not rely on any auxiliary regularization task or extra training data, further demonstrating its remarkable generalization ability., Comment: 11 pages, 5 figures, 8 tables

Prompt learning has been designed as an alternative to fine-tuning for adapting Vision-language (V-L) models to the downstream tasks. Previous works mainly focus on text prompt while visual prompt works are limited for V-L models. The existing visual prompt methods endure either mediocre performance or unstable training process, indicating the difficulty of visual prompt learning. In this paper, we propose a new Progressive Visual Prompt (ProVP) structure to strengthen the interactions among prompts of different layers. More importantly, our ProVP could effectively propagate the image embeddings to deep layers and behave partially similar to an instance adaptive prompt method. To alleviate generalization deterioration, we further propose a new contrastive feature re-formation, which prevents the serious deviation of the prompted visual feature from the fixed CLIP visual feature distribution. Combining both, our method (ProVP-Ref) is evaluated on 11 image benchmark datasets and achieves 7/11 state-of-theart results on both few-shot and base-to-novel settings. To the best of our knowledge, we are the first to demonstrate the superior performance of visual prompts in V-L models to previous prompt-based methods in downstream tasks. Meanwhile, it implies that our ProVP-Ref shows the best capability to adapt and to generalize., Comment: IJCV 2024 Accepted

Moire patterns appear frequently when taking photos of digital screens, drastically degrading the image quality. Despite the advance of CNNs in image demoireing, existing networks are with heavy design, causing redundant computation burden for mobile devices. In this paper, we launch the first study on accelerating demoireing networks and propose a dynamic demoireing acceleration method (DDA) towards a real-time deployment on mobile devices. Our stimulus stems from a simple-yet-universal fact that moire patterns often unbalancedly distribute across an image. Consequently, excessive computation is wasted upon non-moire areas. Therefore, we reallocate computation costs in proportion to the complexity of image patches. In order to achieve this aim, we measure the complexity of an image patch by designing a novel moire prior that considers both colorfulness and frequency information of moire patterns. Then, we restore image patches with higher-complexity using larger networks and the ones with lower-complexity are assigned with smaller networks to relieve the computation burden. At last, we train all networks in a parameter-shared supernet paradigm to avoid additional parameter burden. Extensive experiments on several benchmarks demonstrate the efficacy of our proposed DDA. In addition, the acceleration evaluated on the VIVO X80 Pro smartphone equipped with a chip of Snapdragon 8 Gen 1 shows that our method can drastically reduce the inference time, leading to a real-time image demoireing on mobile devices. Source codes and models are released at https://github.com/zyxxmu/DDA, Comment: To appear in the eleventh International Conference on Learning Representations (ICLR 2023)

Humans have a strong class-agnostic object segmentation ability and can outline boundaries of unknown objects precisely, which motivates us to propose a box-supervised class-agnostic object segmentation (BoxCaseg) based solution for weakly-supervised instance segmentation. The BoxCaseg model is jointly trained using box-supervised images and salient images in a multi-task learning manner. The fine-annotated salient images provide class-agnostic and precise object localization guidance for box-supervised images. The object masks predicted by a pretrained BoxCaseg model are refined via a novel merged and dropped strategy as proxy ground truth to train a Mask R-CNN for weakly-supervised instance segmentation. Only using $7991$ salient images, the weakly-supervised Mask R-CNN is on par with fully-supervised Mask R-CNN on PASCAL VOC and significantly outperforms previous state-of-the-art box-supervised instance segmentation methods on COCO. The source code, pretrained models and datasets are available at \url{https://github.com/hustvl/BoxCaseg}.

We report on the observation of a Tc ~0.9 K superconductivity at the interface between LaAlO3 film and the 5d transition-metal oxide KTaO3(110) single crystal. The interface shows a large anisotropy of the upper critical field, and its superconducting transition is consistent with a Berezinskii-Kosterlitz-Thouless transition. Both facts suggest that the superconductivity is two-dimensional (2D) in nature. The carrier density measured at 5 K is ~7 time 10^13 cm-2. The superconducting layer thickness and coherence length are estimated to be ~8 and ~30 nm, respectively. Our result provides a new platform for the study of 2D superconductivity at oxide interfaces., Comment: 10 pages, 4 figures for main text; plus 6 pages, 8 figures for supplemental materials