相关论文: Bootstrapping Physics-Grounded Video Generation th…
Text-to-video generation has shown promising results. However, by taking only natural languages as input, users often face difficulties in providing detailed information to precisely control the model's output. In this work, we propose…
Video quality assessment (VQA) aims to objectively quantify perceptual quality degradation in alignment with human visual perception. Despite recent advances, existing VQA models still suffer from two critical limitations: \textit{poor…
Recent advances in large language models have significantly improved textual reasoning through the effective use of Chain-of-Thought (CoT) and reinforcement learning. However, extending these successes to vision-language tasks remains…
Recent advancements in Chain of Thought (COT) generation have significantly improved the reasoning capabilities of Large Language Models (LLMs), with reinforcement learning (RL) emerging as an effective post-training approach. Multimodal…
Customized video generation aims to generate high-quality videos guided by text prompts and subject's reference images. However, since it is only trained on static images, the fine-tuning process of subject learning disrupts abilities of…
Recent large vision-language models (LVLMs) have demonstrated impressive reasoning ability by generating long chain-of-thought (CoT) responses. However, CoT reasoning in multimodal contexts is highly vulnerable to visual hallucination…
Recent studies have demonstrated the effectiveness of Large Language Models (LLMs) as reasoning modules that can deconstruct complex tasks into more manageable sub-tasks, particularly when applied to visual reasoning tasks for images. In…
Applying Reinforcement Learning (RL) to Video Large Language Models (Video-LLMs) shows significant promise for complex video reasoning. However, popular Reinforcement Fine-Tuning (RFT) methods, such as outcome-based Group Relative Policy…
Video reasoning requires models to locate and track question-relevant evidence across frames. While reinforcement learning (RL) with verifiable rewards improves accuracy, it still struggles to achieve reliable spatio-temporal grounding…
Evaluating whether Multimodal Large Language Models (MLLMs) genuinely reason about physical dynamics remains challenging. Most existing benchmarks rely on recognition-style protocols such as Visual Question Answering (VQA) and Violation of…
End-to-end generative methods are considered a more promising solution for image restoration in physics-based vision compared with the traditional deconstructive methods based on handcrafted composition models. However, existing generative…
Understanding real-world videos with complex semantics and long temporal dependencies remains a fundamental challenge in computer vision. Recent progress in multimodal large language models (MLLMs) has demonstrated strong capabilities in…
Music enhances video narratives and emotions, driving demand for automatic video-to-music (V2M) generation. However, existing V2M methods relying solely on visual features or supplementary textual inputs generate music in a black-box…
While vision-language models (VLMs) have exhibited multi-turn visual reasoning capabilities, their reasoning trajectories remain relatively shallow and are dominated by a text-centric paradigm, limiting their applicability to complex visual…
Video generation has been used to generate visual plans for controlling robotic systems. Given an image observation and a language instruction, previous work has generated video plans which are then converted to robot controls to be…
Text-to-image (T2I) models have achieved remarkable progress, yet they continue to struggle with complex prompts that require simultaneously handling multiple objects, relations, and attributes. Existing inference-time strategies, such as…
Video Large Language Models (Video-LLMs) have recently shown strong performance in basic video understanding tasks, such as captioning and coarse-grained question answering, but struggle with compositional reasoning that requires multi-step…
Current video generation models produce physically inconsistent motion that violates real-world dynamics. We propose TrajVLM-Gen, a two-stage framework for physics-aware image-to-video generation. First, we employ a Vision Language Model to…
Large Vision-Language Models (LVLMs) have achieved significant success in multimodal tasks, with multimodal chain-of-thought (MCoT) further enhancing performance and interpretability. Recent MCoT methods fall into two categories: (i)…
Convolutional video models have an order of magnitude larger computational complexity than their counterpart image-level models. Constrained by computational resources, there is no model or training method that can train long video…