AI.info

Shumin Deng

Explore Shumin Deng on AI.info.

• Learning to Evaluate Before Improving: Automatic Rubric Induction for Automatic Research Agents
• Mechanist: AI as a Scientific Instrument for Discovering the Mechanisms of Intelligence
• How Controllable Are Large Language Models? A Unified Evaluation across Behavioral Granularities
• Why Steering Works: Toward a Unified View of Language Model Parameter Dynamics
• Illusions of Confidence? Diagnosing LLM Truthfulness via Neighborhood Consistency
• Retrieval-augmented Prompt Learning for Pre-trained Foundation Models
• InnoGym: Benchmarking the Innovation Potential of AI Agents
• LightMem: Lightweight and Efficient Memory-Augmented Generation