← authors · overview

• Fake Alignment: Are LLMs Really Aligned Well?
  2023 · 1 citations
• Disentangling Semantic Attention from Structural Bias in the Attention Manifold
  2026
• A Safety Report on GPT-5.2, Gemini 3 Pro, Qwen3-VL, Doubao 1.8, Grok 4.1 Fast, Nano Banana Pro, and Seedream 4.5
  2026
• CL-bench: A Benchmark for Context Learning
  2026
• SciAgentGym: Benchmarking Multi-Step Scientific Tool-use in LLM Agents
  2026
• ROSE: Retrieval-Oriented Segmentation Enhancement
  2026
• RedTopic: Toward Topic-Diverse Red Teaming of Large Language Models
  2025
• A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment
  2025
• WorldPM: Scaling Human Preference Modeling
  2025
• MLLMs are Deeply Affected by Modality Bias
  2025
• AgentGym-RL: Training LLM Agents for Long-Horizon Decision Making through Multi-Turn Reinforcement Learning
  2025
• To See is to Believe: Prompting GPT-4V for Better Visual Instruction Tuning
  2023
• Secrets of RLHF in Large Language Models Part II: Reward Modeling
  2024
• AgentGym: Evolving Large Language Model-based Agents across Diverse Environments
  2024
• Inst-IT: Boosting Multimodal Instance Understanding via Explicit Visual Prompt Instruction Tuning
  2024