6 papers
Beyond Superficial Unlearning: Sharpness-Aware Robust Erasure of Hallucinations in Multimodal LLMs
Xianya Fang, Feiyang Ren, Xiang Chen +4
Multimodal LLMs are powerful but prone to object hallucinations, which describe non-existent entities and harm reliability. While recent unlearning methods attempt to mitigate this…
Beyond Dense States: Elevating Sparse Transcoders to Active Operators for Latent Reasoning
Yadong Wang, Haodong Chen, Yu Tian +3
Latent reasoning compresses the chain-of-thought (CoT) into continuous hidden states, yet existing methods rely on dense latent transitions that remain difficult to interpret and c…
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…
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…
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…
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…