97 accepted papers
We present 360Explorer, a novel approach for generating 4D controllable panoramic videos conditioned on user-provided 3D instructions for exploring and manipulating dynamic worlds. Compared to existing perspective-based methods struggle to address spatial consistency during camera rotation in place,
Fine-tuning large language models (LLMs) improves performance but introduces critical safety vulnerabilities: even minimal harmful data can severely compromise safety measures. We observe that perturbations orthogonal to the alignment direction—defined by weight differences between aligned (safe) an
AI-assisted coding has rapidly reshaped software practice and research workflows, yet today's models still struggle to produce correct code for complex 3D geometric vision. If models could reliably write such code, the research of our community would change substantially. To measure progress toward
The realization of autonomous scientific experimentation is currently limited by LLMs' struggle to grasp the strict procedural logic and accuracy required by biological protocols. To address this fundamental challenge, we present **BioProBench**, a comprehensive resource for procedural reasoning in …
Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a central paradigm for scaling LLM reasoning, yet its optimization often suffers from training instability and suboptimal convergence. Through a systematic dissection of the GRPO-based objective, we reveal that the rigid clipping d…
Following the success of Group Relative Policy Optimization (GRPO) in foundation LLMs, an increasing number of works have sought to adapt GRPO to Visual Large Language Models (VLLMs) for visual perception tasks (e.g., detection and segmentation). However, much of this line of research rests on a lon
We introduce **EA3D**, an Event-Augmented 3D Diffusion framework for generalizable novel view synthesis from event streams and sparse RGB inputs. Existing approaches either rely solely on RGB frames for generalizable synthesis, which limits their robustness under rapid camera motion, or require per…
Spiking Neural Networks (SNNs), with their event-driven and biologically inspired mechanisms, are well-suited for energy-efficient neuromorphic hardware. Neural coding, which is critical to SNNs, determines how information is represented via spikes. While Time-to-First-Spike (TTFS) coding uses a sin…
Multimodal Knowledge Editing (MKE) extends traditional knowledge editing to settings involving both textual and visual modalities. However, existing MKE benchmarks primarily assess final answer correctness, neglecting the quality of intermediate reasoning and robustness to visually rephrased inputs.
Current chemical large language models (LLMs) predominantly rely on explicit Chain-of-Thought (CoT) to solve complex reasoning problems. However, forcing nonverbal tacit chemical logic into discrete natural language imposes a fundamental ``modality mismatch,'' creating an artificial bottleneck for r…
Multimodal Large Language Models (MLLMs) have achieved remarkable progress in multimodal reasoning. However, they often excessively rely on textual information during the later stages of inference, neglecting the crucial integration of visual input. Current methods typically address this by explicit
3D Gaussian Splatting (3DGS) achieves impressive quality and rendering speed, but with millions of 3D Gaussians and significant storage and transmission costs. In this paper, we aim to develop a simple yet effective method called NeuralGS that compresses the original 3DGS into a compact representati
Autoregressive models, built based on the Next Token Prediction (NTP) paradigm, show great potential in developing a unified framework that integrates both language and vision tasks. Pioneering works introduce NTP to autoregressive visual generation tasks. In this work, we rethink the NTP for autore
Reinforcement Learning with Verifiable Rewards (RLVR) has become a promising paradigm for scaling reasoning capabilities of Large Language Models (LLMs). However, the sparsity of binary verifier rewards often leads to low efficiency and optimization instability. To stabilize training, existing metho…
Mixture-of-Experts (MoE) architectures employ sparse activation to deliver faster training and inference with higher accuracy than dense LLMs. However, in production serving, MoE models require batch inference to optimize hardware efficiency, which may cause excessive expert activation and thus slow…
Recent progress in text-to-image generation has greatly advanced visual fidelity and creativity, but it has also imposed higher demands on prompt complexity--particularly in encoding intricate spatial relationships. In such cases, achieving satisfactory results often requires multiple sampling attem
Does \emph{Comprehending the main idea of a 2-hour movie} and \emph{Counting the birds appearing in a 15-second clip} really warrant the same video processing pipeline? We present Task-Aware Mechanism (TAM), a hybrid-gated Mixture-of-Experts (MoE) vision tower that adapts frame count and resolution …
Image-to-text (I2T) understanding and text-to-image (T2I) generation are two fundamental, important yet traditionally isolated multimodal tasks. Despite their intrinsic connection, existing approaches typically optimize them independently, missing the opportunity for mutual enhancement. In this pape
Text-to-Image (T2I) models are capable of generating high-quality artistic creations and visual content. However, existing research and evaluation standards predominantly focus on image realism and shallow text-image alignment, lacking a comprehensive assessment of complex semantic understanding and…
Compared to frame-based methods, computational neuromorphic imaging using event cameras offers significant advantages, such as minimal motion blur, enhanced temporal resolution, and high dynamic range. The multi-view consistency of Neural Radiance Fields combined with the unique benefits of event ca…
While large language models (LLMs) with Chain-of-Thought (CoT) reasoning excel in mathematics and coding, their potential for systematic reasoning in chemistry, a domain demanding rigorous structural analysis for real-world tasks like drug design and reaction engineering, remains untapped. Current b…
Current text-to-image (T2I) generation models struggle to align spatial composition with the input text, especially in complex scenes. Even layout-based approaches yield suboptimal spatial control, as their generation process is decoupled from layout planning, making it difficult to refine the layo…
Multimodal Information Extraction (MIE) has gained attention for extracting structured information from multimedia sources. Traditional methods tackle MIE tasks separately, missing opportunities to share knowledge across tasks. Recent approaches unify these tasks into a generation problem using inst
Recent 3D large reconstruction models typically employ a two-stage process, including first generate multi-view images by a multi-view diffusion model, and then utilize a feed-forward model to reconstruct images to 3D content. However, multi-view diffusion models often produce low-quality and incons…
In this work, we present DreamDance, a novel method for animating human images using only skeleton pose sequences as conditional inputs. Existing approaches struggle with generating coherent, high-quality content in an efficient and user-friendly manner. Concretely, baseline methods relying on only…
Diffusion models have demonstrated exceptional visual quality in video generation, making them promising for autonomous driving world modeling. However, existing video diffusion-based world models struggle with flexible-length, long-horizon predictions and integrating trajectory planning. This is be…
3D Gaussian Splatting (3D-GS) has demonstrated exceptional capabilities in synthesizing novel views of 3D scenes. However, its training is heavily reliant on high-quality images and precise camera poses. Meeting these criteria can be challenging in non-ideal real-world conditions, where motion-blurr…
We introduce GS2E (Gaussian Splatting to Event Generation), a large-scale synthetic event dataset designed for high-fidelity event vision tasks, captured from real-world sparse multi-view RGB images. Existing event datasets are often synthesized from dense RGB videos, which typically suffer from lim…
Three key challenges hinder the development of current deepfake video detection: (1) Temporal features can be complex and diverse: how can we identify general temporal artifacts to enhance model generalization? (2) Spatiotemporal models often lean heavily on one type of artifact and ignore the other…
Identity-preserving text-to-video (IPT2V) generation aims to create high-fidelity videos with consistent human identity. It is an important task in video generation but remains an open problem for generative models. This paper pushes the technical frontier of IPT2V in two directions that have not b…
Recent advancements in generative models have enabled high-fidelity text-to-image generation. However, open-source image-editing models still lag behind their proprietary counterparts, primarily due to limited high-quality data and insufficient benchmarks. To overcome these limitations, we introduce…
Large Language Models (LLMs) often suffer from catastrophic forgetting when learning multiple tasks sequentially, making continual learning (CL) essential for their dynamic deployment. Existing state-of-the-art (SOTA) methods, such as O-LoRA, typically focus on constructing orthogonality tasks to de…
Large language models have demonstrated substantial advancements in reasoning capabilities. However, current Vision-Language Models (VLMs) often struggle to perform systematic and structured reasoning, especially when handling complex visual question-answering tasks. In this work, we introduce LLaVA…
Recent years have witnessed remarkable advances in Large Vision-Language Models (LVLMs), which have achieved human-level performance across various complex vision-language tasks. Following LLaVA's paradigm, mainstream LVLMs typically employ a shallow MLP for visual-language alignment through a two-s…
In this work, we aim to simultaneously enhance the effectiveness and efficiency of Mixture-of-Experts (MoE) methods. To achieve this, we propose MoE++, a general and heterogeneous MoE framework that integrates both Feed-Forward Network (FFN) and zero-computation experts. Specifically, we introduce t…
In this work, we upgrade the multi-head attention mechanism, the core of the Transformer model, to reduce computational costs while maintaining or surpassing the previous accuracy level. We show that multi-head attention can be expressed in the summation form. Drawing on the insight that not all att…
Subject-to-Video (S2V) generation aims to create videos that faithfully incorporate reference content, providing enhanced flexibility in the production of videos. To establish the infrastructure for S2V generation, we propose **OpenS2V-Nexus**, consisting of (i) **OpenS2V‑Eval**, a fine‑grained benc…
Detecting AI-generated images (AIGIs), such as natural images or face images, has become increasingly important yet challenging. In this paper, we start from a new perspective to excavate the reason behind the failure generalization in AIGI detection, named the asymmetry phenomenon, where a naively…
Existing large language models (LLMs) evaluation methods typically focus on testing the performance on some closed-environment and domain-specific benchmarks with human annotations. In this paper, we explore a novel unsupervised evaluation direction, utilizing peer-review mechanisms to measure LLMs…
In recent years, protein-text models have gained significant attention for their potential in protein generation and understanding. Current approaches focus on integrating protein-related knowledge into large language models through continued pretraining and multi-modal alignment, enabling simultane
Indoor scene texture synthesis has garnered significant interest due to its important potential applications in virtual reality, digital media and creative arts. Existing diffusion-model-based researches either rely on per-view inpainting techniques, which are plagued by severe cross-view inconsiste…
Knowledge editing emerges as a promising approach for updating target knowledge in Large Language Models (LLMs) in a timely manner, thereby preventing undesirable behaviors stemming from outdated, inaccurate, or incomplete knowledge. However, existing methods mainly focus on instance-level editing,…
Spiking Neural Networks are celebrated for energy efficiency and biological plausibility. Building on Spiking Self-Attention (SSA), Spiking Transformers are extensively studied due to their exceptional performance. However, SSA focuses solely on spatial dimension at each time step, overlooking the c…
Multimodal Large Language Models (MLLMs) have emerged to tackle the challenges of Visual Question Answering (VQA), sparking a new research focus on conducting objective evaluations of these models. Existing evaluation mechanisms face limitations due to the significant human workload required to desi…
Video Variational Autoencoder (VAE) encodes videos into a low-dimensional latent space, becoming a key component of most Latent Video Diffusion Models (LVDMs) to reduce model training costs. However, as the resolution and duration of generated videos increase, the encoding cost of Video VAEs becomes…
Generating coherent and credible explanations remains a significant challenge in the field of AI. In recent years, researchers have delved into the utilization of entailment trees to depict explanations, which exhibit a reasoning process of how a hypothesis is deduced from the supporting facts. Howe…
Large language models have demonstrated impressive universal capabilities across a wide range of open-ended tasks and have extended their utility to encompass multimodal conversations. However existing methods encounter challenges in effectively handling both image and video understanding particular…
We propose a novel text-to-video (T2V) generation benchmark, *ChronoMagic-Bench*, to evaluate the temporal and metamorphic knowledge skills in time-lapse video generation of the T2V models (e.g. Sora and Lumiere). Compared to existing benchmarks that focus on visual quality and text relevance of gen…
We propose a new comprehensive benchmark to revolutionize the current deepfake detection field to the next generation. Predominantly, existing works identify top-notch detection algorithms and models by adhering to the common practice: training detectors on one specific dataset (*e.g.,* FF++) and te…
Point cloud registration is essential in computer vision and robotics. Recently, transformer-based methods have achieved advanced point cloud registration performance. However, the standard attention mechanism utilized in these methods considers many low-relevance points, and it has difficulty focus…
Interactive Segmentation (IS) segments specific objects or parts in the image according to user input. Current IS pipelines fall into two categories: single-granularity output and multi-granularity output. The latter aims to alleviate the spatial ambiguity present in the former. However the multi-gr…
Much of commonsense knowledge in real world is the form of procudures or sequences of steps to achieve particular goals. In recent years, knowledge extraction on procedural documents has attracted considerable attention. However, they often focus on procedural text but ignore a common multimodal sce…
"Recent advances in diffusion models have enabled 3D generation from a single image. However, current methods often produce suboptimal results for novel views, with blurred textures and deviations from the reference image, limiting their practical applications. In this paper, we introduce HiFi-123,…
Long-context Multimodal Large Language Models (MLLMs) demand substantial computational resources for inference as the growth of their multimodal Key-Value (KV) cache, in response to increasing input lengths, challenges memory and time efficiency. Unlike single-modality LLMs that manage only textual…
The video-language (VL) pretraining has achieved remarkable improvement in multiple downstream tasks. However, the current VL pretraining framework is hard to extend to multiple modalities (N modalities, N ≥ 3) beyond vision and language. We thus propose LanguageBind, taking the language as the bind…
"Text-driven 3D texturing requires the generation of high-fidelity texture that conforms to given geometry and description. Recently, the high-quality text-to-image generation ability of 2D diffusion model has significantly promoted this task, by converting it into a texture optimization process gui…
Recent advancements in general-purpose or domain-specific multimodal large language models (LLMs) have witnessed remarkable progress for medical decision-making. However, they are designated for specific classification or generative tasks, and require model training or finetuning on large-scale data…
Spiking Neural Networks (SNNs) have emerged as a promising third generation of neural networks, offering unique characteristics such as binary outputs, high sparsity, and biological plausibility. However, the lack of effective learning algorithms remains a challenge for SNNs. For instance, while con…
Unified visual grounding (UVG) capitalizes on a wealth of task-related knowledge across various grounding tasks via one-shot training, which curtails retraining costs and task-specific architecture design efforts. Vertex generation-based UVG methods achieve this versatility by unified modeling objec…
Recent text-to-3D generation methods achieve impressive 3D content creation capacity thanks to the advances in image diffusion models and optimizing strategies. However, current methods struggle to generate correct 3D content for a complex prompt in semantics, i.e., a prompt describing multiple inte…
Spiking Transformers, which integrate Spiking Neural Networks (SNNs) with Transformer architectures, have attracted significant attention due to their potential for low energy consumption and high performance. However, there remains a substantial gap in performance between SNNs and Artificial Neural…
Text-Video Retrieval (TVR) aims to align relevant video content with natural language queries. To date, most of the state-of-the-art TVR methods learn image-to-video transfer learning based on the large-scale pre-trained vision-language models (e.g., CLIP). However, fully fine-tuning these pre-train…
Crowd counting has achieved significant progress by training regressors to predict instance positions. In heavily crowded scenarios however regressors are challenged by uncontrollable annotation variance which causes density map bias and context information inaccuracy. In this study we propose mutua…
We present the ShareGPT4Video series, aiming to facilitate the video understanding of large video-language models (LVLMs) and the video generation of text-to-video models (T2VMs) via dense and precise captions. The series comprises: 1) ShareGPT4Video, 40K GPT4V annotated dense captions of videos wit…
Spiking Neural Networks (SNNs) provide a sparse spike-driven mechanism which is believed to be critical for energy-efficient deep learning. Mixture-of-Experts (MoE), on the other side, aligns with the brain mechanism of distributed and sparse processing, resulting in an efficient way of enhancing m…
Predicting human pose sequences via existing pose estimators often encounters various estimation errors. Motion refinement methods aim to optimize the predicted human pose sequences from pose estimators while ensuring minimal computational overhead and latency. Prior investigations have primarily co…
Visual imitation learning (VIL) provides an efficient and intuitive strategy for robotic systems to acquire novel skills. Recent advancements in Vision Language Models (VLMs) have demonstrated remarkable performance in vision and language reasoning capabilities for VIL tasks. Despite the progress, c…
Large Vision-Language Model (LVLM) has enhanced the performance of various downstream tasks in visual-language understanding. Most existing approaches encode images and videos into separate feature spaces, which are then fed as inputs to large language models. However, due to the lack of unified tok…
Recently, self-supervised large-scale visual pre-training models have shown great promise in representing pixel-level semantic relationships, significantly promoting the development of unsupervised dense prediction tasks, e.g., unsupervised semantic segmentation (USS). The extracted relationship amo…
Most text-driven human motion generation methods employ sequential modeling approaches, e.g., transformer, to extract sentence-level text representations automatically and implicitly for human motion synthesis. However, these compact text representations may overemphasize the action names at the exp…
Point cloud registration is a crucial technology in the fields of robotics and computer vision. Despite the significant advances in point cloud registration enabled by Transformer-based methods, limitations persist due to indistinct feature extraction, noise sensitivity, and outlier handling. These…
Existing text-video retrieval solutions are, in essence, discriminant models focused on maximizing the conditional likelihood, i.e., p(candidates|query). While straightforward, this de facto paradigm overlooks the underlying data distribution p(query), which makes it challenging to identify out-of-d…
Co-occurrent visual patterns suggest that pixel relation modeling facilitates dense prediction tasks, which inspires the development of numerous context modeling paradigms, \emph{e.g.}, multi-scale-driven and similarity-driven context schemes. Despite the impressive results, these existing paradigms…
Multimodal named entity recognition (MNER) and multimodal relation extraction (MRE) are two fundamental subtasks in the multimodal knowledge graph construction task. However, the existing methods usually handle two tasks independently, which ignores the bidirectional interaction between them. This p…
Few-shot class-incremental learning (FSCIL) aims at learning to classify new classes continually from limited samples without forgetting the old classes. The mainstream framework tackling FSCIL is first to adopt the cross-entropy (CE) loss for training at the base session, then freeze the feature ex…
Interactive segmentation enables users to segment as needed by providing cues of objects, which introduces human-computer interaction for many fields, such as image editing and medical image analysis. Typically, massive and expansive pixel-level annotations are spent to train deep models by object-o…
Weakly supervised semantic segmentation is typically inspired by class activation maps, which serve as pseudo masks with class-discriminative regions highlighted. Although tremendous efforts have been made to recall precise and complete locations for each class, existing methods still commonly suffe…
Large language models (LLMs) based on the generative pre-training transformer (GPT) have demonstrated remarkable effectiveness across a diverse range of downstream tasks. Inspired by the advancements of the GPT, we present PointGPT, a novel approach that extends the concept of GPT to point clouds, a…
Robot grasping is subject to an inherent tradeoff: Grippers with a large span typically take a longer time to close, and fast grippers usually cover a small span. However, many practical applications of grippers require the ability to close a large distance rapidly. For example, grasping cloth typic…
Point cloud registration is essential in computer vision and robotics. In this paper, a critical observation is made that the invisible parts of each point cloud can be directly utilized as inherent masks, and the aligned point cloud pair can be regarded as the reconstruction target. Motivated by th…
Spiking Neural Networks (SNNs) provide an energy-efficient deep learning option due to their unique spike-based event-driven (i.e., spike-driven) paradigm. In this paper, we incorporate the spike-driven paradigm into Transformer by the proposed Spike-driven Transformer with four unique properties: (…
We consider two biologically plausible structures, the Spiking Neural Network (SNN) and the self-attention mechanism. The former offers an energy-efficient and event-driven paradigm for deep learning, while the latter has the ability to capture feature dependencies, enabling Transformer to achieve g…
Text-video retrieval is a challenging cross-modal task, which aims to align visual entities with natural language descriptions. Current methods either fail to leverage the local details or are computationally expensive. What's worse, they fail to leverage the heterogeneous concepts in data. In this…
Contrastive learning-based video-language representation learning approaches, e.g., CLIP, have achieved outstanding performance, which pursue semantic interaction upon pre-defined video-text pairs. To clarify this coarse-grained global interaction and move a step further, we have to encounter challe…
Recently, MLP-like vision models have achieved promising performances on mainstream visual recognition tasks. In contrast with vision transformers and CNNs, the success of MLP-like models shows that simple information fusion operations among tokens and channels can yield a good representation power…
"The transformer models have shown promising effectiveness in dealing with various vision tasks. However, compared with training Convolutional Neural Network (CNN) models, training Vision Transformer (ViT) models is more difficult and relies on the large-scale training set. To explain this observati…
"While the Vision Transformer (VT) architecture is becoming trendy in computer vision, pure VT models perform poorly on tiny datasets. To address this issue, this paper proposes the locality guidance for improving the performance of VTs on tiny datasets. We first analyze that the local information,…
"As a promising scheme of self-supervised learning, masked autoencoding has significantly advanced natural language processing and computer vision. Inspired by this, we propose a neat scheme of masked autoencoders for point cloud self-supervised learning, addressing the challenges posed by point clo…
In this paper, we present token labeling---a new training objective for training high-performance vision transformers (ViTs). Different from the standard training objective of ViTs that computes the classification loss on an additional trainable class token, our proposed one takes advantage of all t…
Continual learning tackles the setting of learning different tasks sequentially. Despite the lots of previous solutions, most of them still suffer significant forgetting or expensive memory cost. In this work, targeted at these problems, we first study the continual learning process through the lens…
Recently, DETR pioneered the solution of vision tasks with transformers, it directly translates the image feature map into the object detection result. Though effective, translating the full feature map can be costly due to redundant computation on some area like the background. In this work, we enc…
It is well-known that stochastic gradient noise (SGN) acts as implicit regularization for deep learning and is essentially important for both optimization and generalization of deep networks. Some works attempted to artificially simulate SGN by injecting random noise to improve deep learning. Howeve…
Transformers, which are popular for language modeling, have been explored for solving vision tasks recently, e.g., the Vision Transformer (ViT) for image classification. The ViT model splits each image into a sequence of tokens with fixed length and then applies multiple Transformer layers to model…
Existing data-dependent hashing methods usually learn hash functions from pairwise or triplet data relationships, which only capture the data similarity locally, and often suffer from low learning efficiency and low collision rate. In this work, we propose a new global similarity metric, termed as c…
Knowledge Distillation (KD) aims to distill the knowledge of a cumbersome teacher model into a lightweight student model. Its success is generally attributed to the privileged information on similarities among categories provided by the teacher model, and in this sense, only strong teacher models ar…
State-of-the-art CNN based recognition models are often computationally prohibitive to deploy on low-end devices. A promising high level approach tackling this limitation is knowledge distillation, which let small student model mimic cumbersome teacher model's output to get improved generalization.…
To mitigate the detection performance drop caused by domain shift, we aim to develop a novel few-shot adaptation approach that requires only a few target domain images with limited bounding box annotations. To this end, we first observe several significant challenges. First, the target domain data i…