Search

Recent advancements in Distributional Reinforcement Learning (DRL) for modeling loss distributions have shown promise in developing hedging strategies in derivatives markets. A common approach in DRL involves learning the quantiles of loss distributions at specified levels using Quantile Regression (QR). This method is particularly effective in option hedging due to its direct quantile-based risk assessment, such as Value at Risk (VaR) and Conditional Value at Risk (CVaR). However, these risk measures depend on the accurate estimation of extreme quantiles in the loss distribution's tail, which can be imprecise in QR-based DRL due to the rarity and extremity of tail data, as highlighted in the literature. To address this issue, we propose EXtreme DRL (EX-DRL), which enhances extreme quantile prediction by modeling the tail of the loss distribution with a Generalized Pareto Distribution (GPD). This method introduces supplementary data to mitigate the scarcity of extreme quantile observations, thereby improving estimation accuracy through QR. Comprehensive experiments on gamma hedging options demonstrate that EX-DRL improves existing QR-based models by providing more precise estimates of extreme quantiles, thereby improving the computation and reliability of risk metrics for complex financial risk management., Comment: 14 pages

The integration of generative AI in visual art has revolutionized not only how visual content is created but also how AI interacts with and reflects the underlying domain knowledge. This survey explores the emerging realm of diffusion-based visual art creation, examining its development from both artistic and technical perspectives. We structure the survey into three phases, data feature and framework identification, detailed analyses using a structured coding process, and open-ended prospective outlooks. Our findings reveal how artistic requirements are transformed into technical challenges and highlight the design and application of diffusion-based methods within visual art creation. We also provide insights into future directions from technical and synergistic perspectives, suggesting that the confluence of generative AI and art has shifted the creative paradigm and opened up new possibilities. By summarizing the development and trends of this emerging interdisciplinary area, we aim to shed light on the mechanisms through which AI systems emulate and possibly, enhance human capacities in artistic perception and creativity., Comment: 35 pages, 9 figures

Although neural rendering has made significant advancements in creating lifelike, animatable full-body and head avatars, incorporating detailed expressions into full-body avatars remains largely unexplored. We present DEGAS, the first 3D Gaussian Splatting (3DGS)-based modeling method for full-body avatars with rich facial expressions. Trained on multiview videos of a given subject, our method learns a conditional variational autoencoder that takes both the body motion and facial expression as driving signals to generate Gaussian maps in the UV layout. To drive the facial expressions, instead of the commonly used 3D Morphable Models (3DMMs) in 3D head avatars, we propose to adopt the expression latent space trained solely on 2D portrait images, bridging the gap between 2D talking faces and 3D avatars. Leveraging the rendering capability of 3DGS and the rich expressiveness of the expression latent space, the learned avatars can be reenacted to reproduce photorealistic rendering images with subtle and accurate facial expressions. Experiments on an existing dataset and our newly proposed dataset of full-body talking avatars demonstrate the efficacy of our method. We also propose an audio-driven extension of our method with the help of 2D talking faces, opening new possibilities to interactive AI agents.

Recent advancements in generative AI, particularly Latent Diffusion Models (LDMs), have revolutionized image synthesis and manipulation. However, these generative techniques raises concerns about data misappropriation and intellectual property infringement. Adversarial attacks on machine learning models have been extensively studied, and a well-established body of research has extended these techniques as a benign metric to prevent the underlying misuse of generative AI. Current approaches to safeguarding images from manipulation by LDMs are limited by their reliance on model-specific knowledge and their inability to significantly degrade semantic quality of generated images. In response to these shortcomings, we propose the Posterior Collapse Attack (PCA) based on the observation that VAEs suffer from posterior collapse during training. Our method minimizes dependence on the white-box information of target models to get rid of the implicit reliance on model-specific knowledge. By accessing merely a small amount of LDM parameters, in specific merely the VAE encoder of LDMs, our method causes a substantial semantic collapse in generation quality, particularly in perceptual consistency, and demonstrates strong transferability across various model architectures. Experimental results show that PCA achieves superior perturbation effects on image generation of LDMs with lower runtime and VRAM. Our method outperforms existing techniques, offering a more robust and generalizable solution that is helpful in alleviating the socio-technical challenges posed by the rapidly evolving landscape of generative AI., Comment: 21 pages, 7 figures, 10 tables

Urban mobility and transportation systems have been profoundly transformed by the advancement of autonomous vehicle technologies. Baidu Apollo Go, a pioneer robotaxi service from the Chinese tech giant Baidu, has recently been widely deployed in major cities like Beijing and Wuhan, sparking increased conversation and offering a glimpse into the future of urban mobility. This study investigates public attitudes towards Apollo Go across China using Sentiment Analysis with a hybrid BERT model on 36,096 Weibo posts from January to July 2024. The analysis shows that 89.56\% of posts related to Apollo Go are clustered in July. From January to July, public sentiment was mostly positive, but negative comments began to rise after it became a hot topic on July 21. Spatial analysis indicates a strong correlation between provinces with high discussion intensity and those where Apollo Go operates. Initially, Hubei and Guangdong dominated online posting volume, but by July, Guangdong, Beijing, and international regions had overtaken Hubei. Attitudes varied significantly among provinces, with Xinjiang and Qinghai showing optimism and Tibet and Gansu expressing concerns about the impact on traditional taxi services. Sentiment analysis revealed that positive comments focused on technology applications and personal experiences, while negative comments centered on job displacement and safety concerns. In summary, this study highlights the divergence in public perceptions of autonomous ride-hailing services, providing valuable insights for planners, policymakers, and service providers. The model is published on Hugging Face at https://huggingface.co/wsqstar/bert-finetuned-weibo-luobokuaipao and the repository on GitHub at https://github.com/GIStudio/trb2024.

We present GS-ID, a novel framework for illumination decomposition on Gaussian Splatting, achieving photorealistic novel view synthesis and intuitive light editing. Illumination decomposition is an ill-posed problem facing three main challenges: 1) priors for geometry and material are often lacking; 2) complex illumination conditions involve multiple unknown light sources; and 3) calculating surface shading with numerous light sources is computationally expensive. To address these challenges, we first introduce intrinsic diffusion priors to estimate the attributes for physically based rendering. Then we divide the illumination into environmental and direct components for joint optimization. Last, we employ deferred rendering to reduce the computational load. Our framework uses a learnable environment map and Spherical Gaussians (SGs) to represent light sources parametrically, therefore enabling controllable and photorealistic relighting on Gaussian Splatting. Extensive experiments and applications demonstrate that GS-ID produces state-of-the-art illumination decomposition results while achieving better geometry reconstruction and rendering performance., Comment: 15 pages, 13 figures

Humans continuously perceive and process visual signals. However, current video models typically either sample key frames sparsely or divide videos into chunks and densely sample within each chunk. This approach stems from the fact that most existing video benchmarks can be addressed by analyzing key frames or aggregating information from separate chunks. We anticipate that the next generation of vision models will emulate human perception by processing visual input continuously and holistically. To facilitate the development of such models, we propose the Continuous Perception Benchmark, a video question answering task that cannot be solved by focusing solely on a few frames or by captioning small chunks and then summarizing using language models. Extensive experiments demonstrate that existing models, whether commercial or open-source, struggle with these tasks, indicating the need for new technical advancements in this direction.

The rapid development of the mobile Internet and the Internet of Things is leading to a diversification of user devices and the emergence of new mobile applications on a regular basis. Such applications include those that are computationally intensive, such as pattern recognition, interactive gaming, virtual reality, and augmented reality. However, the computing and energy resources available on the user's equipment are limited, which presents a challenge in effectively supporting such demanding applications. In this work, we propose a heterogeneous computing resource allocation model based on a data-driven approach. The model first collects and analyzes historical workload data at scale, extracts key features, and builds a detailed data set. Then, a data-driven deep neural network is used to predict future resource requirements. Based on the prediction results, the model adopts a dynamic adjustment and optimization resource allocation strategy. This strategy not only fully considers the characteristics of different computing resources, but also accurately matches the requirements of various tasks, and realizes dynamic and flexible resource allocation, thereby greatly improving the overall performance and resource utilization of the system. Experimental results show that the proposed method is significantly better than the traditional resource allocation method in a variety of scenarios, demonstrating its excellent accuracy and adaptability.

Diffusion models have made significant strides in language-driven and layout-driven image generation. However, most diffusion models are limited to visible RGB image generation. In fact, human perception of the world is enriched by diverse viewpoints, such as chromatic contrast, thermal illumination, and depth information. In this paper, we introduce a novel diffusion model for general layout-guided cross-modal generation, called DiffX. Notably, DiffX presents a simple yet effective cross-modal generative modeling pipeline, which conducts diffusion and denoising processes in the modality-shared latent space. Moreover, we introduce the Joint-Modality Embedder (JME) to enhance interaction between layout and text conditions by incorporating a gated attention mechanism. Meanwhile, the advanced Long-CLIP is employed for long caption embedding for user instruction. To facilitate the user-instructed generative training, we construct the cross-modal image datasets with detailed text captions assisted by the Large-Multimodal Model (LMM). Through extensive experiments, DiffX demonstrates robustness in cross-modal generation across three ``RGB+X'' datasets: FLIR, MFNet, and COME15K, guided by various layout conditions. It also shows the potential for the adaptive generation of ``RGB+X+Y+Z'' images or more diverse modalities on COME15K and MCXFace datasets. Our code and constructed cross-modal image datasets are available at https://github.com/zeyuwang-zju/DiffX.

Vision Transformer and its variants have been adopted in many visual tasks due to their powerful capabilities, which also bring significant challenges in computation and storage. Consequently, researchers have introduced various compression methods in recent years, among which the pruning techniques are widely used to remove a significant fraction of the network. Therefore, these methods can reduce significant percent of the FLOPs, but often lead to a decrease in model performance. To investigate the underlying causes, we focus on the pruning methods specifically belonging to the pruning-during-training category, then drew inspiration from neuroscience and propose a new concept for artificial neural network models named Neural Burden. We investigate its impact in the model pruning process, and subsequently explore a simple yet effective approach to mitigate the decline in model performance, which can be applied to any pruning-during-training technique. Extensive experiments indicate that the neural burden phenomenon indeed exists, and show the potential of our method. We hope that our findings can provide valuable insights for future research. Code will be made publicly available after this paper is published.

This study introduces a novel Remote Sensing (RS) Urban Prediction (UP) task focused on future urban planning, which aims to forecast urban layouts by utilizing information from existing urban layouts and planned change maps. To address the proposed RS UP task, we propose UP-Diff, which leverages a Latent Diffusion Model (LDM) to capture positionaware embeddings of pre-change urban layouts and planned change maps. In specific, the trainable cross-attention layers within UP-Diff's iterative diffusion modules enable the model to dynamically highlight crucial regions for targeted modifications. By utilizing our UP-Diff, designers can effectively refine and adjust future urban city plans by making modifications to the change maps in a dynamic and adaptive manner. Compared with conventional RS Change Detection (CD) methods, the proposed UP-Diff for the RS UP task avoids the requirement of paired prechange and post-change images, which enhances the practical usage in city development. Experimental results on LEVIRCD and SYSU-CD datasets show UP-Diff's ability to accurately predict future urban layouts with high fidelity, demonstrating its potential for urban planning. Code and model weights are available at https://github.com/zeyuwang-zju/UP-Diff., Comment: 5 pages, 4 figures

Event cameras harness advantages such as low latency, high temporal resolution, and high dynamic range (HDR), compared to standard cameras. Due to the distinct imaging paradigm shift, a dominant line of research focuses on event-to-video (E2V) reconstruction to bridge event-based and standard computer vision. However, this task remains challenging due to its inherently ill-posed nature: event cameras only detect the edge and motion information locally. Consequently, the reconstructed videos are often plagued by artifacts and regional blur, primarily caused by the ambiguous semantics of event data. In this paper, we find language naturally conveys abundant semantic information, rendering it stunningly superior in ensuring semantic consistency for E2V reconstruction. Accordingly, we propose a novel framework, called LaSe-E2V, that can achieve semantic-aware high-quality E2V reconstruction from a language-guided perspective, buttressed by the text-conditional diffusion models. However, due to diffusion models' inherent diversity and randomness, it is hardly possible to directly apply them to achieve spatial and temporal consistency for E2V reconstruction. Thus, we first propose an Event-guided Spatiotemporal Attention (ESA) module to condition the event data to the denoising pipeline effectively. We then introduce an event-aware mask loss to ensure temporal coherence and a noise initialization strategy to enhance spatial consistency. Given the absence of event-text-video paired data, we aggregate existing E2V datasets and generate textual descriptions using the tagging models for training and evaluation. Extensive experiments on three datasets covering diverse challenging scenarios (e.g., fast motion, low light) demonstrate the superiority of our method., Comment: Project Page: https://vlislab22.github.io/LaSe-E2V/

Detecting objects in real-world scenes is a complex task due to various challenges, including the vast range of object categories, and potential encounters with previously unknown or unseen objects. The challenges necessitate the development of public benchmarks and challenges to advance the field of object detection. Inspired by the success of previous COCO and LVIS Challenges, we organize the V3Det Challenge 2024 in conjunction with the 4th Open World Vision Workshop: Visual Perception via Learning in an Open World (VPLOW) at CVPR 2024, Seattle, US. This challenge aims to push the boundaries of object detection research and encourage innovation in this field. The V3Det Challenge 2024 consists of two tracks: 1) Vast Vocabulary Object Detection: This track focuses on detecting objects from a large set of 13204 categories, testing the detection algorithm's ability to recognize and locate diverse objects. 2) Open Vocabulary Object Detection: This track goes a step further, requiring algorithms to detect objects from an open set of categories, including unknown objects. In the following sections, we will provide a comprehensive summary and analysis of the solutions submitted by participants. By analyzing the methods and solutions presented, we aim to inspire future research directions in vast vocabulary and open-vocabulary object detection, driving progress in this field. Challenge homepage: https://v3det.openxlab.org.cn/challenge

Wavefront shaping can tailor multipath interference to control multiple scattering of waves in complex optical systems. However, full-wave simulations that capture multiple scattering are computationally demanding given the large system size and the large number of input channels. Recently, an "augmented partial factorization" (APF) method was proposed to significantly speed-up such full-wave simulations. In this tutorial, we illustrate how to perform wavefront shaping simulations with the APF method using the open-source frequency-domain electromagnetic scattering solver MESTI. We present the foundational concepts and then walk through four examples: computing the scattering matrix of a slab with random permittivities, open high-transmission channels through disorder, focusing inside disorder with phase conjugation, and reflection matrix computation in a spatial focused-beam basis. The goal is to lower the barrier for researchers to use simulations to explore the rich phenomena enabled by wavefront shaping.

In this technical report, we present our findings from the research conducted on the Vast Vocabulary Visual Detection (V3Det) dataset for Supervised Vast Vocabulary Visual Detection task. How to deal with complex categories and detection boxes has become a difficulty in this track. The original supervised detector is not suitable for this task. We have designed a series of improvements, including adjustments to the network structure, changes to the loss function, and design of training strategies. Our model has shown improvement over the baseline and achieved excellent rankings on the Leaderboard for both the Vast Vocabulary Object Detection (Supervised) track and the Open Vocabulary Object Detection (OVD) track of the V3Det Challenge 2024.

Web-crawled image-text pairs are inherently noisy. Prior studies demonstrate that semantically aligning and enriching textual descriptions of these pairs can significantly enhance model training across various vision-language tasks, particularly text-to-image generation. However, large-scale investigations in this area remain predominantly closed-source. Our paper aims to bridge this community effort, leveraging the powerful and \textit{open-sourced} LLaMA-3, a GPT-4 level LLM. Our recaptioning pipeline is simple: first, we fine-tune a LLaMA-3-8B powered LLaVA-1.5 and then employ it to recaption 1.3 billion images from the DataComp-1B dataset. Our empirical results confirm that this enhanced dataset, Recap-DataComp-1B, offers substantial benefits in training advanced vision-language models. For discriminative models like CLIP, we observe enhanced zero-shot performance in cross-modal retrieval tasks. For generative models like text-to-image Diffusion Transformers, the generated images exhibit a significant improvement in alignment with users' text instructions, especially in following complex queries. Our project page is https://www.haqtu.me/Recap-Datacomp-1B/, Comment: First five authors contributed equally

Propelled by the rapid advancement of deep learning technologies, the YOLO series has set a new benchmark for real-time object detectors. Researchers have continuously explored innovative applications of reparameterization, efficient layer aggregation networks, and anchor-free techniques on the foundation of YOLO. To further enhance detection performance, Transformer-based structures have been introduced, significantly expanding the model's receptive field and achieving notable performance gains. However, such improvements come at a cost, as the quadratic complexity of the self-attention mechanism increases the computational burden of the model. Fortunately, the emergence of State Space Models (SSM) as an innovative technology has effectively mitigated the issues caused by quadratic complexity. In light of these advancements, we introduce Mamba-YOLO a novel object detection model based on SSM. Mamba-YOLO not only optimizes the SSM foundation but also adapts specifically for object detection tasks. Given the potential limitations of SSM in sequence modeling, such as insufficient receptive field and weak image locality, we have designed the LSBlock and RGBlock. These modules enable more precise capture of local image dependencies and significantly enhance the robustness of the model. Extensive experimental results on the publicly available benchmark datasets COCO and VOC demonstrate that Mamba-YOLO surpasses the existing YOLO series models in both performance and competitiveness, showcasing its substantial potential and competitive edge.The PyTorch code is available at:\url{https://github.com/HZAI-ZJNU/Mamba-YOLO}

This study presents Medical Vision Generalist (MVG), the first foundation model capable of handling various medical imaging tasks -- such as cross-modal synthesis, image segmentation, denoising, and inpainting -- within a unified image-to-image generation framework. Specifically, MVG employs an in-context generation strategy that standardizes the handling of inputs and outputs as images. By treating these tasks as an image generation process conditioned on prompt image-label pairs and input images, this approach enables a flexible unification of various tasks, even those spanning different modalities and datasets. To capitalize on both local and global context, we design a hybrid method combining masked image modeling with autoregressive training for conditional image generation. This hybrid approach yields the most robust performance across all involved medical imaging tasks. To rigorously evaluate MVG's capabilities, we curated the first comprehensive generalist medical vision benchmark, comprising 13 datasets and spanning four imaging modalities (CT, MRI, X-ray, and micro-ultrasound). Our results consistently establish MVG's superior performance, outperforming existing vision generalists, such as Painter and LVM. Furthermore, MVG exhibits strong scalability, with its performance demonstrably improving when trained on a more diverse set of tasks, and can be effectively adapted to unseen datasets with only minimal task-specific samples. The code is available at \url{https://github.com/OliverRensu/MVG}.

Recently, few-shot molecular property prediction (FSMPP) has garnered increasing attention. Despite impressive breakthroughs achieved by existing methods, they often overlook the inherent many-to-many relationships between molecules and properties, which limits their performance. For instance, similar substructures of molecules can inspire the exploration of new compounds. Additionally, the relationships between properties can be quantified, with high-related properties providing more information in exploring the target property than those low-related. To this end, this paper proposes a novel meta-learning FSMPP framework (KRGTS), which comprises the Knowledge-enhanced Relation Graph module and the Task Sampling module. The knowledge-enhanced relation graph module constructs the molecule-property multi-relation graph (MPMRG) to capture the many-to-many relationships between molecules and properties. The task sampling module includes a meta-training task sampler and an auxiliary task sampler, responsible for scheduling the meta-training process and sampling high-related auxiliary tasks, respectively, thereby achieving efficient meta-knowledge learning and reducing noise introduction. Empirically, extensive experiments on five datasets demonstrate the superiority of KRGTS over a variety of state-of-the-art methods. The code is available in https://github.com/Vencent-Won/KRGTS-public.

Modern information querying systems are progressively incorporating multimodal inputs like vision and audio. However, the integration of gaze -- a modality deeply linked to user intent and increasingly accessible via gaze-tracking wearables -- remains underexplored. This paper introduces a novel gaze-facilitated information querying paradigm, named G-VOILA, which synergizes users' gaze, visual field, and voice-based natural language queries to facilitate a more intuitive querying process. In a user-enactment study involving 21 participants in 3 daily scenarios (p = 21, scene = 3), we revealed the ambiguity in users' query language and a gaze-voice coordination pattern in users' natural query behaviors with G-VOILA. Based on the quantitative and qualitative findings, we developed a design framework for the G-VOILA paradigm, which effectively integrates the gaze data with the in-situ querying context. Then we implemented a G-VOILA proof-of-concept using cutting-edge deep learning techniques. A follow-up user study (p = 16, scene = 2) demonstrates its effectiveness by achieving both higher objective score and subjective score, compared to a baseline without gaze data. We further conducted interviews and provided insights for future gaze-facilitated information querying systems., Comment: 25 pages, 12 figures

Remote photoplethysmography (rPPG) emerges as a promising method for non-invasive, convenient measurement of vital signs, utilizing the widespread presence of cameras. Despite advancements, existing datasets fall short in terms of size and diversity, limiting comprehensive evaluation under diverse conditions. This paper presents an in-depth analysis of the VitalVideo dataset, the largest real-world rPPG dataset to date, encompassing 893 subjects and 6 Fitzpatrick skin tones. Our experimentation with six unsupervised methods and three supervised models demonstrates that datasets comprising a few hundred subjects(i.e., 300 for UBFC-rPPG, 500 for PURE, and 700 for MMPD-Simple) are sufficient for effective rPPG model training. Our findings highlight the importance of diversity and consistency in skin tones for precise performance evaluation across different datasets., Comment: 11 pages, 5 figures, CHI24 Workshop PhysioCHI

Approximate nearest neighbor search (ANNS) on high-dimensional vectors has become a fundamental and essential component in various machine learning tasks. Prior research has shown that the distance comparison operation is the bottleneck of ANNS, which determines the query and indexing performance. To overcome this challenge, some novel methods have been proposed recently. The basic idea is to estimate the actual distance with fewer calculations, at the cost of accuracy loss. Inspired by this, we also propose that some classical techniques and deep learning models can also be adapted to this purpose. In this paper, we systematically categorize the techniques that have been or can be used to accelerate distance approximation. And to help the users understand the pros and cons of different techniques, we design a fair and comprehensive benchmark, Fudist implements these techniques with the same base index and evaluates them on 16 real datasets with several evaluation metrics. Designed as an independent and portable library, Fudist is orthogonal to the specific index structure and thus can be easily utilized in the current ANNS library to achieve significant improvements.

We present HeadEvolver, a novel framework to generate stylized head avatars from text guidance. HeadEvolver uses locally learnable mesh deformation from a template head mesh, producing high-quality digital assets for detail-preserving editing and animation. To tackle the challenges of lacking fine-grained and semantic-aware local shape control in global deformation through Jacobians, we introduce a trainable parameter as a weighting factor for the Jacobian at each triangle to adaptively change local shapes while maintaining global correspondences and facial features. Moreover, to ensure the coherence of the resulting shape and appearance from different viewpoints, we use pretrained image diffusion models for differentiable rendering with regularization terms to refine the deformation under text guidance. Extensive experiments demonstrate that our method can generate diverse head avatars with an articulated mesh that can be edited seamlessly in 3D graphics software, facilitating downstream applications such as more efficient animation with inherited blend shapes and semantic consistency., Comment: 12 pages, 17 figures

We present SplattingAvatar, a hybrid 3D representation of photorealistic human avatars with Gaussian Splatting embedded on a triangle mesh, which renders over 300 FPS on a modern GPU and 30 FPS on a mobile device. We disentangle the motion and appearance of a virtual human with explicit mesh geometry and implicit appearance modeling with Gaussian Splatting. The Gaussians are defined by barycentric coordinates and displacement on a triangle mesh as Phong surfaces. We extend lifted optimization to simultaneously optimize the parameters of the Gaussians while walking on the triangle mesh. SplattingAvatar is a hybrid representation of virtual humans where the mesh represents low-frequency motion and surface deformation, while the Gaussians take over the high-frequency geometry and detailed appearance. Unlike existing deformation methods that rely on an MLP-based linear blend skinning (LBS) field for motion, we control the rotation and translation of the Gaussians directly by mesh, which empowers its compatibility with various animation techniques, e.g., skeletal animation, blend shapes, and mesh editing. Trainable from monocular videos for both full-body and head avatars, SplattingAvatar shows state-of-the-art rendering quality across multiple datasets., Comment: [CVPR 2024] Code and data are available at https://github.com/initialneil/SplattingAvatar

We have performed electrochemical treatment of the van der Waals antiferromagnetic materials FePS$_3$ and NiPS$_3$ with the ionic liquid EMIM-BF$_4$, achieving significant molecular intercalation. Mass analysis of the intercalated compounds, EMIM$_x$-FePS$_3$ and EMIM$_x$-NiPS$_3$, indicated respective intercalation levels, $x$, of approximately 27\% and 37\%, and X-ray diffraction measurements demonstrated a massive (over 50\%) enhancement of the $c$-axis lattice parameters. To investigate the consequences of these changes for the magnetic properties, we performed magnetic susceptibility and $^{31}$P nuclear magnetic resonance (NMR) studies of both systems. For EMIM$_x$-FePS$_3$, intercalation reduces the magnetic ordering temperature from $T_N = 120$~K to 78~K, and we find a spin gap in the antiferromagnetic phase that drops from 45~K to 30~K. For EMIM$_x$-NiPS$_3$, the ordering temperature is almost unaffected (changing from 148~K to 145~K), but a change towards nearly isotropic spin fluctuations suggests an alteration of the magnetic Hamiltonian. Such relatively modest changes, given that the huge extension of the $c$ axes is expected to cause a very strong suppression any interlayer interactions, point unequivocally to the conclusion that the magnetic properties of both parent compounds are determined solely by two-dimensional (2D), intralayer physics. The changes in transition temperatures and low-temperature spin dynamics in both compounds therefore indicate that intercalation also results in a significant modulation of the intralayer magnetic interactions, which we propose is due to charge doping and localization on the P sites. Our study offers chemical intercalation with ionic liquids as an effective method to control not only the interlayer but also the intralayer interactions in quasi-2D magnetic materials.

Image-goal navigation is a challenging task that requires an agent to navigate to a goal indicated by an image in unfamiliar environments. Existing methods utilizing diverse scene memories suffer from inefficient exploration since they use all historical observations for decision-making without considering the goal-relevant fraction. To address this limitation, we present MemoNav, a novel memory model for image-goal navigation, which utilizes a working memory-inspired pipeline to improve navigation performance. Specifically, we employ three types of navigation memory. The node features on a map are stored in the short-term memory (STM), as these features are dynamically updated. A forgetting module then retains the informative STM fraction to increase efficiency. We also introduce long-term memory (LTM) to learn global scene representations by progressively aggregating STM features. Subsequently, a graph attention module encodes the retained STM and the LTM to generate working memory (WM) which contains the scene features essential for efficient navigation. The synergy among these three memory types boosts navigation performance by enabling the agent to learn and leverage goal-relevant scene features within a topological map. Our evaluation on multi-goal tasks demonstrates that MemoNav significantly outperforms previous methods across all difficulty levels in both Gibson and Matterport3D scenes. Qualitative results further illustrate that MemoNav plans more efficient routes., Comment: Accepted to CVPR 2024. Code: https://github.com/ZJULiHongxin/MemoNav

Digital twinning in structural engineering is a rapidly evolving technology that aims to eliminate the gap between physical systems and their digital models through real-time sensing, visualization, and control techniques. Although digital twins can offer dynamic insights into physical systems, their accuracy is inevitably compromised by uncertainties in sensing, modeling, simulation, and controlling. This paper proposes a specialized digital twin formulation, named Risk Twin, designed for real-time risk visualization and risk-informed control of structural systems. Integrating structural reliability and Bayesian inference methods with digital twining techniques, Risk Twin can analyze and visualize the reliability indices for structural components in real-time. To facilitate real-time inference and reliability updating, a "simulation-free" scheme is proposed, leveraging precomputed quantities prepared during an offline phase for rapid inference in the online phase. Proof-of-concept numerical and real-world Risk Twins are constructed to showcase the proposed concepts.

Conventional approaches to human mesh recovery predominantly employ a region-based strategy. This involves initially cropping out a human-centered region as a preprocessing step, with subsequent modeling focused on this zoomed-in image. While effective for single figures, this pipeline poses challenges when dealing with images featuring multiple individuals, as different people are processed separately, often leading to inaccuracies in relative positioning. Despite the advantages of adopting a whole-image-based approach to address this limitation, early efforts in this direction have fallen short in performance compared to recent region-based methods. In this work, we advocate for this under-explored area of modeling all people at once, emphasizing its potential for improved accuracy in multi-person scenarios through considering all individuals simultaneously and leveraging the overall context and interactions. We introduce a new model with a streamlined transformer-based design, featuring three critical design choices: multi-scale feature incorporation, focused attention mechanisms, and relative joint supervision. Our proposed model demonstrates a significant performance improvement, surpassing state-of-the-art region-based and whole-image-based methods on various benchmarks involving multiple individuals.

Space-time (ST) beams, ultrafast optical wavepackets with customized spatial and temporal characteristics, present a significant contrast to conventional spatial-structured light and hold the potential to revolutionize our understanding and manipulation of light. However, the progress in ST beam research has been constrained by the absence of a universal framework for their analysis and generation. Here, we introduce the concept of "two-dimensional ST duality", establishing a foundational duality between spatial-structured light and ST beams. We show that breaking the exact balance between paraxial diffraction and narrow-band dispersion is crucial for guiding the dynamics of ST wavepackets. Leveraging this insight, we pioneer a versatile complex-amplitude modulation strategy, enabling the precise crafting of ST beams with an exceptional fidelity exceeding 97%. Furthermore, we uncover a new range of ST wavepackets by harnessing the exact one-to-one relationship between scalar spatial-structured light and ST beams. Our findings suggest a paradigm shift opportunity in ST beam research and may apply to a broader range of wave physics systems.

Hierarchical text classification (HTC) is a complex subtask under multi-label text classification, characterized by a hierarchical label taxonomy and data imbalance. The best-performing models aim to learn a static representation by combining document and hierarchical label information. However, the relevance of document sections can vary based on the hierarchy level, necessitating a dynamic document representation. To address this, we propose HiGen, a text-generation-based framework utilizing language models to encode dynamic text representations. We introduce a level-guided loss function to capture the relationship between text and label name semantics. Our approach incorporates a task-specific pretraining strategy, adapting the language model to in-domain knowledge and significantly enhancing performance for classes with limited examples. Furthermore, we present a new and valuable dataset called ENZYME, designed for HTC, which comprises articles from PubMed with the goal of predicting Enzyme Commission (EC) numbers. Through extensive experiments on the ENZYME dataset and the widely recognized WOS and NYT datasets, our methodology demonstrates superior performance, surpassing existing approaches while efficiently handling data and mitigating class imbalance. The data and code will be released publicly.

Learning effective joint representations has been a central task in multi-modal sentiment analysis. Previous works addressing this task focus on exploring sophisticated fusion techniques to enhance performance. However, the inherent heterogeneity of distinct modalities remains a core problem that brings challenges in fusing and coordinating the multi-modal signals at both the representational level and the informational level, impeding the full exploitation of multi-modal information. To address this problem, we propose the Multi-modal Information Disentanglement (MInD) method, which decomposes the multi-modal inputs into modality-invariant and modality-specific components through a shared encoder and multiple private encoders. Furthermore, by explicitly training generated noise in an adversarial manner, MInD is able to isolate uninformativeness, thus improves the learned representations. Therefore, the proposed disentangled decomposition allows for a fusion process that is simpler than alternative methods and results in improved performance. Experimental evaluations conducted on representative benchmark datasets demonstrate MInD's effectiveness in both multi-modal emotion recognition and multi-modal humor detection tasks. Code will be released upon acceptance of the paper.

The machine learning community has witnessed a drastic change in the training pipeline, pivoted by those ''foundation models'' with unprecedented scales. However, the field of adversarial training is lagging behind, predominantly centered around small model sizes like ResNet-50, and tiny and low-resolution datasets like CIFAR-10. To bridge this transformation gap, this paper provides a modern re-examination with adversarial training, investigating its potential benefits when applied at scale. Additionally, we introduce an efficient and effective training strategy to enable adversarial training with giant models and web-scale data at an affordable computing cost. We denote this newly introduced framework as AdvXL. Empirical results demonstrate that AdvXL establishes new state-of-the-art robust accuracy records under AutoAttack on ImageNet-1K. For example, by training on DataComp-1B dataset, our AdvXL empowers a vanilla ViT-g model to substantially surpass the previous records of $l_{\infty}$-, $l_{2}$-, and $l_{1}$-robust accuracy by margins of 11.4%, 14.2% and 12.9%, respectively. This achievement posits AdvXL as a pioneering approach, charting a new trajectory for the efficient training of robust visual representations at significantly larger scales. Our code is available at https://github.com/UCSC-VLAA/AdvXL., Comment: Accepted by CVPR 2024

Molecular property prediction refers to the task of labeling molecules with some biochemical properties, playing a pivotal role in the drug discovery and design process. Recently, with the advancement of machine learning, deep learning-based molecular property prediction has emerged as a solution to the resource-intensive nature of traditional methods, garnering significant attention. Among them, molecular representation learning is the key factor for molecular property prediction performance. And there are lots of sequence-based, graph-based, and geometry-based methods that have been proposed. However, the majority of existing studies focus solely on one modality for learning molecular representations, failing to comprehensively capture molecular characteristics and information. In this paper, a novel multi-modal representation learning model, which integrates the sequence, graph, and geometry characteristics, is proposed for molecular property prediction, called SGGRL. Specifically, we design a fusion layer to fusion the representation of different modalities. Furthermore, to ensure consistency across modalities, SGGRL is trained to maximize the similarity of representations for the same molecule while minimizing similarity for different molecules. To verify the effectiveness of SGGRL, seven molecular datasets, and several baselines are used for evaluation and comparison. The experimental results demonstrate that SGGRL consistently outperforms the baselines in most cases. This further underscores the capability of SGGRL to comprehensively capture molecular information. Overall, the proposed SGGRL model showcases its potential to revolutionize molecular property prediction by leveraging multi-modal representation learning to extract diverse and comprehensive molecular insights. Our code is released at https://github.com/Vencent-Won/SGGRL., Comment: 8 pages, 3 figures

Distributional Reinforcement Learning (RL) estimates return distribution mainly by learning quantile values via minimizing the quantile Huber loss function, entailing a threshold parameter often selected heuristically or via hyperparameter search, which may not generalize well and can be suboptimal. This paper introduces a generalized quantile Huber loss function derived from Wasserstein distance (WD) calculation between Gaussian distributions, capturing noise in predicted (current) and target (Bellman-updated) quantile values. Compared to the classical quantile Huber loss, this innovative loss function enhances robustness against outliers. Notably, the classical Huber loss function can be seen as an approximation of our proposed loss, enabling parameter adjustment by approximating the amount of noise in the data during the learning process. Empirical tests on Atari games, a common application in distributional RL, and a recent hedging strategy using distributional RL, validate the effectiveness of our proposed loss function and its potential for parameter adjustments in distributional RL. The implementation of the proposed loss function is available here., Comment: 6 pages, 1 figure, to be published in ICASSP 2024

Visual storytelling often uses nontypical aspect-ratio images like scroll paintings, comic strips, and panoramas to create an expressive and compelling narrative. While generative AI has achieved great success and shown the potential to reshape the creative industry, it remains a challenge to generate coherent and engaging content with arbitrary size and controllable style, concept, and layout, all of which are essential for visual storytelling. To overcome the shortcomings of previous methods including repetitive content, style inconsistency, and lack of controllability, we propose MagicScroll, a multi-layered, progressive diffusion-based image generation framework with a novel semantic-aware denoising process. The model enables fine-grained control over the generated image on object, scene, and background levels with text, image, and layout conditions. We also establish the first benchmark for nontypical aspect-ratio image generation for visual storytelling including mediums like paintings, comics, and cinematic panoramas, with customized metrics for systematic evaluation. Through comparative and ablation studies, MagicScroll showcases promising results in aligning with the narrative text, improving visual coherence, and engaging the audience. We plan to release the code and benchmark in the hope of a better collaboration between AI researchers and creative practitioners involving visual storytelling., Comment: Project page: https://magicscroll.github.io/

Conventional approaches to dietary assessment are primarily grounded in self-reporting methods or structured interviews conducted under the supervision of dietitians. These methods, however, are often subjective, potentially inaccurate, and time-intensive. Although artificial intelligence (AI)-based solutions have been devised to automate the dietary assessment process, these prior AI methodologies encounter challenges in their ability to generalize across a diverse range of food types, dietary behaviors, and cultural contexts. This results in AI applications in the dietary field that possess a narrow specialization and limited accuracy. Recently, the emergence of multimodal foundation models such as GPT-4V powering the latest ChatGPT has exhibited transformative potential across a wide range of tasks (e.g., Scene understanding and image captioning) in numerous research domains. These models have demonstrated remarkable generalist intelligence and accuracy, capable of processing various data modalities. In this study, we explore the application of multimodal ChatGPT within the realm of dietary assessment. Our findings reveal that GPT-4V excels in food detection under challenging conditions with accuracy up to 87.5% without any fine-tuning or adaptation using food-specific datasets. By guiding the model with specific language prompts (e.g., African cuisine), it shifts from recognizing common staples like rice and bread to accurately identifying regional dishes like banku and ugali. Another GPT-4V's standout feature is its contextual awareness. GPT-4V can leverage surrounding objects as scale references to deduce the portion sizes of food items, further enhancing its accuracy in translating food weight into nutritional content. This alignment with the USDA National Nutrient Database underscores GPT-4V's potential to advance nutritional science and dietary assessment techniques., Comment: 10 pages

This paper enhances image-GPT (iGPT), one of the pioneering works that introduce autoregressive pretraining to predict the next pixels for visual representation learning. Two simple yet essential changes are made. First, we shift the prediction target from raw pixels to semantic tokens, enabling a higher-level understanding of visual content. Second, we supplement the autoregressive modeling by instructing the model to predict not only the next tokens but also the visible tokens. This pipeline is particularly effective when semantic tokens are encoded by discriminatively trained models, such as CLIP. We introduce this novel approach as D-iGPT. Extensive experiments showcase that D-iGPT excels as a strong learner of visual representations: A notable achievement is its compelling performance on the ImageNet-1K dataset -- by training on publicly available datasets, D-iGPT unprecedentedly achieves \textbf{90.0\%} top-1 accuracy with a vanilla ViT-H. Additionally, D-iGPT shows strong generalization on the downstream task. Code is available at https://github.com/OliverRensu/D-iGPT., Comment: This paper is accepted by ICML2024

Automated creation of synthetic traffic scenarios is a key part of validating the safety of autonomous vehicles (AVs). In this paper, we propose Scenario Diffusion, a novel diffusion-based architecture for generating traffic scenarios that enables controllable scenario generation. We combine latent diffusion, object detection and trajectory regression to generate distributions of synthetic agent poses, orientations and trajectories simultaneously. To provide additional control over the generated scenario, this distribution is conditioned on a map and sets of tokens describing the desired scenario. We show that our approach has sufficient expressive capacity to model diverse traffic patterns and generalizes to different geographical regions., Comment: NeurIPS 2023

Contrastive learning has emerged as a promising paradigm for 3D open-world understanding, i.e., aligning point cloud representation to image and text embedding space individually. In this paper, we introduce MixCon3D, a simple yet effective method aiming to sculpt holistic 3D representation in contrastive language-image-3D pre-training. In contrast to point cloud only, we develop the 3D object-level representation from complementary perspectives, e.g., multi-view rendered images with the point cloud. Then, MixCon3D performs language-3D contrastive learning, comprehensively depicting real-world 3D objects and bolstering text alignment. Additionally, we pioneer the first thorough investigation of various training recipes for the 3D contrastive learning paradigm, building a solid baseline with improved performance. Extensive experiments conducted on three representative benchmarks reveal that our method significantly improves over the baseline, surpassing the previous state-of-the-art performance on the challenging 1,156-category Objaverse-LVIS dataset by 5.7%. The versatility of MixCon3D is showcased in applications such as text-to-3D retrieval and point cloud captioning, further evidencing its efficacy in diverse scenarios. The code is available at https://github.com/UCSC-VLAA/MixCon3D., Comment: Accepted by CVPR 2024

Federated learning (FL) is an emerging paradigm in machine learning, where a shared model is collaboratively learned using data from multiple devices to mitigate the risk of data leakage. While recent studies posit that Vision Transformer (ViT) outperforms Convolutional Neural Networks (CNNs) in addressing data heterogeneity in FL, the specific architectural components that underpin this advantage have yet to be elucidated. In this paper, we systematically investigate the impact of different architectural elements, such as activation functions and normalization layers, on the performance within heterogeneous FL. Through rigorous empirical analyses, we are able to offer the first-of-its-kind general guidance on micro-architecture design principles for heterogeneous FL. Intriguingly, our findings indicate that with strategic architectural modifications, pure CNNs can achieve a level of robustness that either matches or even exceeds that of ViTs when handling heterogeneous data clients in FL. Additionally, our approach is compatible with existing FL techniques and delivers state-of-the-art solutions across a broad spectrum of FL benchmarks. The code is publicly available at https://github.com/UCSC-VLAA/FedConv, Comment: 9 pages, 6 figures. Equal contribution by P. Xu and Z. Wang

Multi-label aspect category detection is intended to detect multiple aspect categories occurring in a given sentence. Since aspect category detection often suffers from limited datasets and data sparsity, the prototypical network with attention mechanisms has been applied for few-shot aspect category detection. Nevertheless, most of the prototypical networks used so far calculate the prototypes by taking the mean value of all the instances in the support set. This seems to ignore the variations between instances in multi-label aspect category detection. Also, several related works utilize label text information to enhance the attention mechanism. However, the label text information is often short and limited, and not specific enough to discern categories. In this paper, we first introduce support set attention along with the augmented label information to mitigate the noise at word-level for each support set instance. Moreover, we use a sentence-level attention mechanism that gives different weights to each instance in the support set in order to compute prototypes by weighted averaging. Finally, the calculated prototypes are further used in conjunction with query instances to compute query attention and thereby eliminate noises from the query set. Experimental results on the Yelp dataset show that our proposed method is useful and outperforms all baselines in four different scenarios., Comment: DEXA23

3D perception based on the representations learned from multi-camera bird's-eye-view (BEV) is trending as cameras are cost-effective for mass production in autonomous driving industry. However, there exists a distinct performance gap between multi-camera BEV and LiDAR based 3D object detection. One key reason is that LiDAR captures accurate depth and other geometry measurements, while it is notoriously challenging to infer such 3D information from merely image input. In this work, we propose to boost the representation learning of a multi-camera BEV based student detector by training it to imitate the features of a well-trained LiDAR based teacher detector. We propose effective balancing strategy to enforce the student to focus on learning the crucial features from the teacher, and generalize knowledge transfer to multi-scale layers with temporal fusion. We conduct extensive evaluations on multiple representative models of multi-camera BEV. Experiments reveal that our approach renders significant improvement over the student models, leading to the state-of-the-art performance on the popular benchmark nuScenes., Comment: ICCV 2023

Sorting is fundamental and ubiquitous in modern computing systems. Hardware sorting systems are built based on comparison operations with Von Neumann architecture, but their performance are limited by the bandwidth between memory and comparison units and the performance of complementary metal-oxide-semiconductor (CMOS) based circuitry. Sort-in-memory (SIM) based on emerging memristors is desired but not yet available due to comparison operations that are challenging to be implemented within memristive memory. Here we report fast and reconfigurable SIM system enabled by digit read (DR) on 1-transistor-1-resistor (1T1R) memristor arrays. We develop DR tree node skipping (TNS) that support variable data quantity and data types, and extend TNS with multi-bank, bit-slice and multi-level strategies to enable cross-array TNS (CA-TNS) for practical adoptions. Experimented on benchmark sorting datasets, our memristor-enabled SIM system presents up to 3.32x~7.70x speedup, 6.23x~183.5x energy efficiency improvement and 2.23x~7.43x area reduction compared with state-of-the-art sorting systems. We apply such SIM system for shortest path search with Dijkstra's algorithm and neural network inference with in-situ pruning, demonstrating the capability in solving practical sorting tasks and the compatibility in integrating with other compute-in-memory (CIM) schemes. The comparison-free TNS/CA-TNS SIM enabled by memristors pushes sorting into a new paradigm of sort-in-memory for next-generation sorting systems., Comment: Submitted to Nature Electronics