4 papers
SafeThinker: Reasoning about Risk to Deepen Safety Beyond Shallow Alignment
Xianya Fang, Xianying Luo, Yadong Wang +8
Despite the intrinsic risk-awareness of Large Language Models (LLMs), current defenses often result in shallow safety alignment, rendering models vulnerable to disguised attacks (e…
SEARA: An Automated Approach for Obtaining Optimal Retrievers
Zou Yuheng, Wang Yiran, Tian Yuzhu +2
Retrieval-Augmented Generation (RAG) is a core approach for enhancing Large Language Models (LLMs), where the effectiveness of the retriever largely determines the overall response…
Orientation Matters: Making 3D Generative Models Orientation-Aligned
Yichong Lu, Yuzhuo Tian, Zijin Jiang +7
Humans intuitively perceive object shape and orientation from a single image, guided by strong priors about canonical poses. However, existing 3D generative models often produce mi…
SegAgent: Exploring Pixel Understanding Capabilities in MLLMs by Imitating Human Annotator Trajectories
Muzhi Zhu, Yuzhuo Tian, Hao Chen +5
While MLLMs have demonstrated adequate image understanding capabilities, they still struggle with pixel-level comprehension, limiting their practical applications. Current evaluati…