5 papers
TARAC: Mitigating Hallucination in LVLMs via Temporal Attention Real-time Accumulative Connection
Lei Jiang, Chunzhao Xie, Tongxuan Liu +6
Large Vision-Language Models have demonstrated remarkable capabilities, yet they suffer from hallucinations that limit practical deployment. While various mitigation strategies exi…
Mitigating Cultural Bias in LLMs via Multi-Agent Cultural Debate
Qian Tan, Lei Jiang, Yuting Zeng +2
Large language models (LLMs) exhibit systematic Western-centric bias, yet whether prompting in non-Western languages (e.g., Chinese) can mitigate this remains understudied. Answeri…
Chem3DLLM: 3D Multimodal Large Language Models for Chemistry
Lei Jiang, Shuzhou Sun, Biqing Qi +5
In the real world, a molecule is a 3D geometric structure. Compared to 1D SMILES sequences and 2D molecular graphs, 3D molecules represent the most informative molecular modality.…
Cross-Modal Obfuscation for Jailbreak Attacks on Large Vision-Language Models
Lei Jiang, Zixun Zhang, Zizhou Wang +4
Large Vision-Language Models (LVLMs) demonstrate exceptional performance across multimodal tasks, yet remain vulnerable to jailbreak attacks that bypass built-in safety mechanisms…
S-MAD: Breaking the Token Barrier to Enhance Multi-Agent Debate Efficiency
Yuting Zeng, Weizhe Huang, Lei Jiang +5
Large language models (LLMs) have demonstrated remarkable capabilities across various natural language processing (NLP) scenarios, but they still face challenges when handling comp…