相关论文: Factorized Learning for Temporally Grounded Video-…

Multimodal Large Language Models (MLLMs) excel in generating responses based on visual inputs. However, they often suffer from a bias towards generating responses similar to their pretraining corpus, overshadowing the importance of visual…

Reasoning over dynamic visual content remains a central challenge for multimodal large language models. Recent thinking models generate explicit reasoning traces for interpretability; however, their reasoning often appears convincing while…

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…

Cause-and-effect reasoning in video is a significant challenge for Vision-Language Models (VLMs), as it requires going beyond surface-level perception to a deeper understanding of causal mechanisms. However, existing benchmarks rarely…

Large Language Models (LLMs) have shown remarkable performances on a wide range of natural language understanding and generation tasks. We observe that the LLMs provide effective priors in exploiting $\textit{linguistic shortcuts}$ for…

Understanding videos requires more than answering open ended questions, it demands the ability to pinpoint when events occur and how entities interact across time. While recent Video LLMs have achieved remarkable progress in holistic…

Video large language models have achieved remarkable performance in tasks such as video question answering, however, their temporal understanding remains suboptimal. To address this limitation, we curate a dedicated instruction fine-tuning…

Multimodal large language models (MLLMs) often struggle to ground reasoning in perceptual evidence. We present a systematic study of perception strategies-explicit, implicit, visual, and textual-across four multimodal benchmarks and two…

While Video Large Language Models (Video-LLMs) have demonstrated remarkable performance across general video understanding benchmarks-particularly in video captioning and descriptive tasks-they consistently underperform on tasks that…

Videos, with their unique temporal dimension, demand precise grounded understanding, where answers are directly linked to visual, interpretable evidence. Despite significant breakthroughs in text-based reasoning with large language models,…

While existing video benchmarks largely consider specialized downstream tasks like retrieval or question-answering (QA), contemporary multimodal AI systems must be capable of well-rounded common-sense reasoning akin to human visual…

Although reinforcement learning (RL) has significantly advanced reasoning capabilities in large multimodal language models (MLLMs), its efficacy remains limited for lightweight models essential for edge deployments. To address this issue,…

Recently, preference optimization methods such as DPO have significantly enhanced large language models (LLMs) in wide tasks including dialogue and question-answering. However, current methods fail to account for the varying difficulty…

Preference modeling techniques, such as direct preference optimization (DPO), has shown effective in enhancing the generalization abilities of large language model (LLM). However, in tasks involving video instruction-following, providing…

Hallucination remains a fundamental challenge in vision-language models (VLMs), where autoregressive generation may produce linguistically plausible yet physically inconsistent or visually ungrounded responses due to likelihood maximization…

Temporal grounding aims to locate a target video moment that semantically corresponds to the given sentence query in an untrimmed video. However, recent works find that existing methods suffer a severe temporal bias problem. These methods…

Recent breakthroughs in reasoning language models have significantly advanced text-based reasoning. On the other hand, Multi-modal Large Language Models (MLLMs) still lag behind, hindered by their outdated internal LLMs. Upgrading these…

Temporal grounding of activities, the identification of specific time intervals of actions within a larger event context, is a critical task in video understanding. Recent advancements in multimodal large language models (LLMs) offer new…

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…

While Reinforcement Learning from Verifiable Rewards (RLVR) has advanced reasoning in Large Vision-Language Models (LVLMs), prevailing frameworks suffer from a foundational methodological flaw: by distributing identical advantages across…