共计 117 篇文章
2026
Structural Graph Probing of Vision-Language Models
When Do Hallucinations Arise？ A Graph Perspective on the Evolution of Path Reuse and Path Compression
Graph of Thoughts： Solving Elaborate Problems with Large Language Models
LLMs Encode Harmfulness and Refusal Separately
Q-MLLM： Vector Quantization for Robust Multimodal Large Language Model Security
Trap： Mitigating Poisoning-Based Backdoor Attacks by Treating Poison With Poison
Hallucination as Exploit： Evidence-Carrying Multimodal Agents
Finding the Correct Visual Evidence Without Forgetting： Mitigating Hallucination in LVLMs via Inter-Layer Visual Attention Discrepancy
IN-CONTEXT SHARPNESS AS ALERTS： AN INNER REPRESENTATION PERSPECTIVE FOR HALLUCINATION MITIGATION
CYBER-ZERO： Training Cybersecurity Agents without Runtime