相关论文: Let's Think Frame by Frame with VIP: A Video Infil…

Rapid progress in video models has largely focused on visual quality, leaving their reasoning capabilities underexplored. Video reasoning grounds intelligence in spatiotemporally consistent visual environments that go beyond what text can…

Despite recent advances in Vision-Language Models (VLMs), long-video understanding remains a challenging problem. Although state-of-the-art long-context VLMs can process around 1000 input frames, they still struggle to effectively leverage…

Recent video generation models can produce smooth and visually appealing clips, but they often struggle to synthesize complex dynamics with a coherent chain of consequences. Accurately modeling visual outcomes and state transitions over…

Recent advancements in Video Large Language Models (VideoLLMs) have enabled strong performance across diverse multimodal video tasks. To reduce the high computational cost of processing dense video frames, efficiency-oriented methods such…

Vision-Language Models have excelled at textual reasoning, but they often struggle with fine-grained spatial understanding and continuous action planning, failing to simulate the dynamics required for complex visual reasoning. In this work,…

Video understanding requires not only visual recognition but also complex reasoning. While Vision-Language Models (VLMs) demonstrate impressive capabilities, they typically process videos largely in a single-pass manner with limited support…

Large Language Models (LLMs) have demonstrated effectiveness not only in language tasks but also in video reasoning. This paper introduces a novel dataset, Tropes in Movies (TiM), designed as a testbed for exploring two critical yet…

Long-video understanding~(LVU) is a challenging problem in computer vision. Existing methods either downsample frames for single-pass reasoning, sacrificing fine-grained details, or depend on textual reasoning over task-agnostic…

Video Models have achieved remarkable success in high-fidelity video generation with coherent motion dynamics. Analogous to the development from text generation to text-based reasoning in language modeling, the development of video models…

The rapid evolution of video generative models has shifted their focus from producing visually plausible outputs to tackling tasks requiring physical plausibility and logical consistency. However, despite recent breakthroughs such as Veo…

Existing video benchmarks often resemble image-based benchmarks, with question types like "What actions does the person perform throughout the video?" or "What color is the woman's dress in the video?" For these, models can often answer by…

Large vision-language models (VLMs) have advanced multimodal tasks such as video question answering (QA). However, VLMs face the challenge of selecting frames effectively and efficiently, as standard uniform sampling is expensive and…

While Large Language Models (LLMs) excel at reasoning on text and Vision-Language Models (VLMs) are highly effective for visual perception, applying those models for visual instruction-based planning remains a widely open problem. In this…

Current video understanding models excel at recognizing "what" is happening but fall short in high-level cognitive tasks like causal reasoning and future prediction, a limitation rooted in their lack of commonsense world knowledge. To…

While Large Vision-Language Models (LVLMs) have achieved substantial progress in video understanding, their application to long video reasoning is hindered by uniform frame sampling and static textual reasoning, which are inefficient and…

Physical computing infrastructure, data gathering, and algorithms have recently had significant advances to extract information from images and videos. The growth has been especially outstanding in image captioning and video captioning.…

Recent breakthroughs in video generation have demonstrated an emerging capability termed Chain-of-Frames (CoF) reasoning, where models resolve complex tasks through the generation of continuous frames. While these models show promise for…

Reward and representation learning are two long-standing challenges for learning an expanding set of robot manipulation skills from sensory observations. Given the inherent cost and scarcity of in-domain, task-specific robot data, learning…

Large pre-trained vision and language models have demonstrated remarkable capacities for various tasks. However, solving the knowledge-based visual reasoning tasks remains challenging, which requires a model to comprehensively understand…

Recent progress in generative video models, such as Veo-3, has shown surprising zero-shot reasoning abilities, creating a growing need for systematic and reliable evaluation. We introduce V-ReasonBench, a benchmark designed to assess video…