← authors · overview

• Defeating the Training-Inference Mismatch via FP16
  2025 · 34 citations
• VerlTool: Towards Holistic Agentic Reinforcement Learning with Tool Use
  2025
• Defeating the Training-Inference Mismatch via FP16
  2025
• Why LLM Safety Guardrails Collapse After Fine-tuning: A Similarity Analysis Between Alignment and Fine-tuning Datasets
  2025
• Sailor2: Sailing in South-East Asia with Inclusive Multilingual LLMs
  2025
• Optimizing Anytime Reasoning via Budget Relative Policy Optimization
  2025
• BanditSpec: Adaptive Speculative Decoding via Bandit Algorithms
  2025
• LIFT the Veil for the Truth: Principal Weights Emerge after Rank Reduction for Reasoning-Focused Supervised Fine-Tuning
  2025
• Muon Outperforms Adam in Tail-End Associative Memory Learning
  2025
• Accumulative Poisoning Attacks On Real-time Data
  2021
• Weak-to-Strong Jailbreaking on Large Language Models
  2024
• RegMix: Data Mixture as Regression for Language Model Pre-training
  2024
• Cheating Automatic LLM Benchmarks: Null Models Achieve High Win Rates
  2024