相关论文: Towards Sparse Video Understanding and Reasoning

Audio-Visual Question Answering (AVQA) requires not only question-based multimodal reasoning but also precise temporal grounding to capture subtle dynamics for accurate prediction. However, existing methods mainly use question information…

Visual attention mechanisms are widely used in multimodal tasks, as visual question answering (VQA). One drawback of softmax-based attention mechanisms is that they assign some probability mass to all image regions, regardless of their…

End-to-end Vision-language Models (VLMs) often answer visual questions by exploiting spurious correlations instead of causal visual evidence, and can become more shortcut-prone when fine-tuned. We introduce VISTA (Visual-Information…

Multimodal Large Language Models (MLLMs) achieve strong multimodal reasoning performance, yet we identify a recurring failure mode in long-form generation: as outputs grow longer, models progressively drift away from image evidence and fall…

Current evaluations of spatial intelligence can be systematically invalid under modern vision-language model (VLM) settings. First, many benchmarks derive question-answer (QA) pairs from point-cloud-based 3D annotations originally curated…

Given the explosive growth of online videos, it is becoming increasingly important to relieve the tedious work of browsing and managing the video content of interest. Video summarization aims at providing such a technique by transforming…

Visual reasoning refers to the task of solving questions about visual information. Current visual reasoning methods typically employ pre-trained vision-language model (VLM) strategies or deep neural network approaches. However, existing…

Visual Question Answering (VQA) has attracted attention from both computer vision and natural language processing communities. Most existing approaches adopt the pipeline of representing an image via pre-trained CNNs, and then using the…

Recent advances in text-only "slow-thinking" reasoning have prompted efforts to transfer this capability to vision-language models (VLMs), for training visual reasoning models (\textbf{VRMs}). owever, such transfer faces critical…

Reinforcement learning has advanced video reasoning in large multi-modal models, yet dominant pipelines either rely on on-policy self-exploration, which plateaus at the model's knowledge boundary, or hybrid replay that mixes policies and…

Video Question Answering is a challenging task, which requires the model to reason over multiple frames and understand the interaction between different objects to answer questions based on the context provided within the video, especially…

Prior works on improving speech quality with visual input typically study each type of auditory distortion separately (e.g., separation, inpainting, video-to-speech) and present tailored algorithms. This paper proposes to unify these…

Large language models (LLMs) have recently shown strong progress on scientific reasoning, yet two major bottlenecks remain. First, explicit retrieval fragments reasoning, imposing a hidden "tool tax" of extra tokens and steps. Second,…

Video reasoning segmentation (VRS) endeavors to delineate referred objects in videos guided by implicit instructions that encapsulate human intent and temporal logic. Previous approaches leverage large vision language models (LVLMs) to…

Short-video recommender systems typically optimize ranking models using dense user behavioral signals, such as clicks and watch time. However, these signals are only indirect proxies of user satisfaction and often suffer from noise and…

Multi-view visual reasoning is essential for intelligent systems that must understand complex environments from sparse and discrete viewpoints, yet existing research has largely focused on single-image or temporally dense video settings. In…

Enabling robots to execute long-horizon manipulation tasks from free-form language instructions remains a fundamental challenge in embodied AI. While vision-language models (VLMs) have shown promise as high-level planners, their deployment…

Streaming video understanding often involves time-sensitive scenarios where models need to answer exactly when the supporting visual evidence appears: answering before the evidence reflects speculation, answering after it has passed reduces…

Evaluating the alignment between textual prompts and generated images is critical for ensuring the reliability and usability of text-to-image (T2I) models. However, most existing evaluation methods rely on coarse-grained metrics or static…

Manual annotation of high-quality visual question answering with grounding (VQA-G) datasets, which pair visual questions with evidential grounding, is crucial for advancing vision-language models (VLMs), but remains unscalable. Existing…