← authors · overview

• Improved Few-shot Jailbreaking Can Circumvent Aligned Language Models And Their Defenses
  2024 · 79 citations
• Defeating the Training-Inference Mismatch via FP16
  2025 · 34 citations
• BAFFLE: A Baseline of Backpropagation-Free Federated Learning
  2023 · 6 citations
• Efficient Diffusion Policies for Offline Reinforcement Learning
  2023 · 5 citations
• Black-box Detection of Backdoor Attacks with Limited Information and Data
  2021 · 3 citations
• On Calibrating Diffusion Probabilistic Models
  2023 · 2 citations
• Denial-of-Service Poisoning Attacks against Large Language Models
  2024 · 1 citations
• Flow-DPPO: Divergence Proximal Policy Optimization for Flow Matching Models
  2026
• Active Beyond-Diagonal RIS Empowered Heterogeneous Edge Computing: A Distributional Reinforcement Learning Approach
  2026
• Rethinking the Divergence Regularization in LLM RL