AI.info

Sharon Li

Explore Sharon Li on AI.info.

• ExecCritic: Learn to Test, Test to Improve for Coding Agents
• Uncertainty Quantification in LLM Agents: Foundations, Emerging Challenges, and Opportunities
• How Do Transformers Learn to Associate Tokens: Gradient Leading Terms Bring Mechanistic Interpretability
• Beyond In-Domain Detection: SpikeScore for Cross-Domain Hallucination Detection
• ModeX: Evaluator-Free Best-of-N Selection for Open-Ended Generation
• UniGame: Turning a Unified Multimodal Model Into Its Own Adversary