共计 242 篇文章

---

2026

06-15

Graph of Thoughts： Solving Elaborate Problems with Large Language Models

06-12

LLMs Encode Harmfulness and Refusal Separately

06-11

Q-MLLM： Vector Quantization for Robust Multimodal Large Language Model Security

06-10

Trap： Mitigating Poisoning-Based Backdoor Attacks by Treating Poison With Poison

06-01

Hallucination as Exploit： Evidence-Carrying Multimodal Agents

05-29

Finding the Correct Visual Evidence Without Forgetting： Mitigating Hallucination in LVLMs via Inter-Layer Visual Attention Discrepancy

05-28

IN-CONTEXT SHARPNESS AS ALERTS： AN INNER REPRESENTATION PERSPECTIVE FOR HALLUCINATION MITIGATION

05-27

CYBER-ZERO： Training Cybersecurity Agents without Runtime

05-21

S0 Tuning： Zero-Overhead Adaptation of Hybrid Recurrent-Attention Models

05-20

Where Does Reasoning Break? Step-Level Hallucination Detection via Hidden-State Transport Geometry