← authors · overview

• VRPRM: Process Reward Modeling via Visual Reasoning
  2025 · 5 citations
• A Mousetrap: Fooling Large Reasoning Models for Jailbreak with Chain of Iterative Chaos
  2025 · 1 citations
• Feature Correlation-guided Knowledge Transfer for Federated Self-supervised Learning
  2022 · 1 citations
• Fake Alignment: Are LLMs Really Aligned Well?
  2023 · 1 citations
• Mechanistic Origin Of Moral Indifference In Language Models
  2026
• Beyond Correctness: Confidence-Aware Reward Modeling for Enhancing Large Language Model Reasoning
  2025
• StolenLoRA: Exploring LoRA Extraction Attacks via Synthetic Data
  2025
• VRPRM: Process Reward Modeling via Visual Reasoning
  2025
• LinguaSafe: A Comprehensive Multilingual Safety Benchmark for Large Language Models
  2025
• Evolve the Method, Not the Prompts: Evolutionary Synthesis of Jailbreak Attacks on LLMs
  2025
• HoneypotNet: Backdoor Attacks Against Model Extraction
  2025
• Data Quality-aware Mixed-precision Quantization via Hybrid Reinforcement Learning
  2023
• Towards Fairer and More Efficient Federated Learning via Multidimensional Personalized Edge Models
  2023
• From GPT-4 to Gemini and Beyond: Assessing the Landscape of MLLMs on Generalizability, Trustworthiness and Causality through Four Modalities
  2024
• Reflection-Bench: probing AI intelligence with reflection
  2024