AI.info

Hao Peng

Explore Hao Peng on AI.info.

• ReBeCA: Unveiling Interpretable Behavior Hierarchy behind the Iterative Self-Reflection of Language Models with Causal Analysis
• Faithful Bi-Directional Model Steering via Distribution Matching and Distributed Interchange Interventions
• MuVaC: A Variational Causal Framework for Multimodal Sarcasm Understanding in Dialogues
• Watching, Reasoning, and Searching: A Video Deep Research Benchmark on Open Web for Agentic Video Reasoning
• Hyperbolic Continuous Structural Entropy for Hierarchical Clustering
• SeSE: Black-Box Uncertainty Quantification for Large Language Models Based on Structural Information Theory
• RAGFort: Dual-Path Defense Against Proprietary Knowledge Base Extraction in Retrieval-Augmented Generation
• RLVE: Scaling Up Reinforcement Learning for Language Models with Adaptive Verifiable Environments