相关论文: Thinking with Video: Video Generation as a Promisi…
Video reasoning, which requires multi-step deduction across frames, remains a major challenge for multimodal large language models (MLLMs). While reinforcement learning (RL)-based methods enhance reasoning capabilities, they often rely on…
What does it take to design a machine that learns to answer natural questions about a video? A Video QA system must simultaneously understand language, represent visual content over space-time, and iteratively transform these…
Despite rapid advances in vision-language models (VLMs), current benchmarks for multimodal reasoning fall short in three key dimensions. First, they overwhelmingly rely on static images, failing to capture the temporal complexity of…
Text-to-video (T2V) generation has recently garnered significant attention thanks to the large multi-modality model Sora. However, T2V generation still faces two important challenges: 1) Lacking a precise open sourced high-quality dataset.…
Multimodal Large Language Models (MLLMs) have made rapid progress in perception, understanding, and reasoning, yet existing benchmarks fall short in evaluating these abilities under continuous and dynamic real-world video streams. Such…
Language models have recently advanced into the realm of reasoning, yet it is through multimodal reasoning that we can fully unlock the potential to achieve more comprehensive, human-like cognitive capabilities. This survey provides a…
Recent text-to-image systems face limitations in handling multimodal inputs and complex reasoning tasks. We introduce MindOmni, a unified multimodal large language model that addresses these challenges by incorporating reasoning generation…
Multimodal Large Language Models (MLLMs) excel in solving text-based mathematical problems, but they struggle with mathematical diagrams since they are primarily trained on natural scene images. For humans, visual aids generally enhance…
Recent advances in Vision-Language Models (VLMs) have benefited from Reinforcement Learning (RL) for enhanced reasoning. However, existing methods still face critical limitations, including the lack of low-level visual information and…
While recent advances in reinforcement learning have significantly enhanced reasoning capabilities in large language models (LLMs), these techniques remain underexplored in multi-modal LLMs for video captioning. This paper presents the…
Vision-Language Models (VLMs) have achieved substantial progress across a wide range of understanding and reasoning tasks, driven by large-scale image-text training aimed at multimodal fusion. Ideally, replacing a textual question with its…
While humans perceive the world through diverse modalities that operate synergistically to support a holistic understanding of their surroundings, existing omnivideo models still face substantial challenges on audio-visual understanding…
Traditional video reasoning segmentation methods rely on supervised fine-tuning, which limits generalization to out-of-distribution scenarios and lacks explicit reasoning. To address this, we propose \textbf{VideoSeg-R1}, the first…
Understanding the contents of multimodal documents is essential to accurately extract relevant evidence and use it for reasoning. Existing document understanding models tend to generate answers with a single word or phrase directly,…
Spatial reasoning from monocular images is essential for autonomous driving, yet current Vision-Language Models (VLMs) still struggle with fine-grained geometric perception, particularly under large scale variation and ambiguous object…
Camera-controllable video generation aims to synthesize videos with flexible and physically plausible camera movements. However, existing methods either provide imprecise camera control from text prompts or rely on labor-intensive manual…
Multimodal Large Language Models (MLLMs) have achieved notable gains in various tasks by incorporating Chain-of-Thought (CoT) reasoning in language spaces. Recent work extends this direction by leveraging external tools for visual editing,…
Recent Video Large Language Models (Video-LLMs) have shown strong multimodal reasoning capabilities, yet remain challenged by video understanding tasks that require consistent temporal ordering and causal coherence. Many parameter-efficient…
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…
Current large vision-language models (LVLMs) typically rely on text-only reasoning based on a single-pass visual encoding, which often leads to loss of fine-grained visual information. Recently the proposal of ''thinking with images''…