共计 117 篇文章
2026
Attention MoA
Locate-then-Sparsify： Attribution Guided Sparse Strategy for Visual Hallucination Mitigation
Fighting Hallucinations with Counterfactuals： Diffusion-Guided Perturbations for LVLM Hallucination Suppression
Efficient Refusal Ablation in LLM through Optimal Transport
The Assistant Axis： Situating and Stabilizing the Default Persona of Language Model
Why LVLMs Are More Prone to Hallucinations in Longer Responses： The Role of Context
HALP： Detecting Hallucinations in Vision-Language Models without Generating a Single Token
Lyapunov Probes for Hallucination Detection in Large Foundation Models
从零开始构建一个极简的 AI agent
Learning to Reason in 13 Parameters