共计 381 篇文章
2026
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
S0 Tuning： Zero-Overhead Adaptation of Hybrid Recurrent-Attention Models
Where Does Reasoning Break? Step-Level Hallucination Detection via Hidden-State Transport Geometry
AutoRISE： Agent-Driven Strategy Evolution for Red-Teaming Large Language Models
Detecting Contextual Hallucinations in LLMs with Frequency-Aware Attention
SwiftSage： A Generative Agent with Fast and Slow Thinking for Complex Interactive Tasks