6 papers
4DPChat: Towards Dynamic Point Cloud Understanding with Failure-Aware Bootstrapping
Xindan Zhang, Weilong Yan, Yufei Shi +5
Point clouds provide a compact and expressive representation of 3D objects, and have recently been integrated into multimodal large language models (MLLMs). However, existing metho…
Mind Your Margin and Boundary: Are Your Distilled Datasets Truly Robust?
Muquan Li, Yingyi Ma, Yihong Huang +5
Dataset distillation (DD) compresses a large training set into a small synthetic set for efficient training, but most DD methods optimize only clean accuracy and leave robustness u…
One Sentence, One Drama: Personalized Short-Form Drama Generation via Multi-Agent Systems
Yufei Shi, Weilong Yan, Naixuan Huang +5
Existing approaches for digital short-drama production typically rely on one-shot LLM generated scripts and loosely coupled pipelines, which fail to satisfy three key requirements…
Risk Awareness Injection: Calibrating Vision-Language Models for Safety without Compromising Utility
Mengxuan Wang, Yuxin Chen, Gang Xu +3
Vision language models (VLMs) extend the reasoning capabilities of large language models (LLMs) to cross-modal settings, yet remain highly vulnerable to multimodal jailbreak attack…
When Agents See Humans as the Outgroup: Belief-Dependent Bias in LLM-Powered Agents
Zongwei Wang, Bincheng Gu, Hongyu Yu +5
This paper reveals that LLM-powered agents exhibit not only demographic bias (e.g., gender, religion) but also intergroup bias under minimal "us" versus "them" cues. When such grou…
SciEducator: Scientific Video Understanding and Educating via Deming-Cycle Multi-Agent System
Zhiyu Xu, Weilong Yan, Yufei Shi +5
Recent advancements in multimodal large language models (MLLMs) and video agent systems have significantly improved general video understanding. However, when applied to scientific…