6 papers · 1 filter
V-DEAL: Diagnosing Video Safety De-Calibration as an Understanding-Refusal Coupling Failure
Zhetong Zhang, Honghao Fu, Miao Xu +2
As Video Large Language Models are increasingly deployed in real-world applications, ensuring their safety alignment has become critical. Counterintuitively, we find that harmful v…
ContextNav: Towards Agentic Multimodal In-Context Learning
Honghao Fu, Yuan Ouyang, Kai-Wei Chang +3
Recent advances demonstrate that multimodal large language models (MLLMs) exhibit strong multimodal in-context learning (ICL) capabilities, enabling them to adapt to novel vision-l…
RefineShot: Rethinking Cinematography Understanding with Foundational Skill Evaluation
Hang Wu, Yujun Cai, Haonan Ge +3
Cinematography understanding refers to the ability to recognize not only the visual content of a scene but also the cinematic techniques that shape narrative meaning. This capabili…
DiMo-GUI: Advancing Test-time Scaling in GUI Grounding via Modality-Aware Visual Reasoning
Hang Wu, Hongkai Chen, Yujun Cai +4
Grounding natural language queries in graphical user interfaces (GUIs) poses unique challenges due to the diversity of visual elements, spatial clutter, and the ambiguity of langua…
BRIGHT+: Upgrading the BRIGHT Benchmark with MARCUS, a Multi-Agent RAG Clean-Up Suite
Liyang Chen, Yujun Cai, Jieqiong Dong +1
Retrieval-Augmented Generation (RAG) systems require corpora that are both structurally clean and semantically coherent. BRIGHT is a recent and influential benchmark designed to ev…
Process or Result? Manipulated Ending Tokens Can Mislead Reasoning LLMs to Ignore the Correct Reasoning Steps
Yu Cui, Bryan Hooi, Yujun Cai +1
Recent reasoning large language models (LLMs) have demonstrated remarkable improvements in mathematical reasoning capabilities through long Chain-of-Thought. The reasoning tokens o…