8 papers
VideoThinker: Building Agentic VideoLLMs with LLM-Guided Tool Reasoning
Chenglin Li, Qianglong Chen, Feng Han +6
Long-form video understanding remains a fundamental challenge for current Video Large Language Models. Most existing models rely on static reasoning over uniformly sampled frames,…
VideoPro: Adaptive Program Reasoning for Long Video Understanding
Chenglin Li, Feng Han, Yikun Wang +9
Large language models (LLMs) have shown promise in generating program workflows for visual tasks. However, previous approaches often rely on closed-source models, lack systematic r…
2K-Characters-10K-Stories: A Quality-Gated Stylized Narrative Dataset with Disentangled Control and Sequence Consistency
Xingxi Yin, Yicheng Li, Gong Yan +5
Sequential identity consistency under precise transient attribute control remains a long-standing challenge in controllable visual storytelling. Existing datasets lack sufficient f…
VideoCogQA: A Controllable Benchmark for Evaluating Cognitive Abilities in Video-Language Models
Chenglin Li, Qianglong Chen, Zhi Li +2
Recent advancements in Large Video-Language Models (LVLMs) have led to promising results in multimodal video understanding. However, it remains unclear whether these models possess…
Iterative Zoom-In: Temporal Interval Exploration for Long Video Understanding
Chenglin Li, Qianglong Chen, fengtao +1
Multimodal Large Language Models (MLLMs) have shown strong performance in video understanding tasks. However, they continue to struggle with long-form videos because of an ineffici…
RelationAdapter: Learning and Transferring Visual Relation with Diffusion Transformers
Yan Gong, Yiren Song, Yicheng Li +2
Inspired by the in-context learning mechanism of large language models (LLMs), a new paradigm of generalizable visual prompt-based image editing is emerging. Existing single-refere…