← authors · overview

• Active Boundary Loss for Semantic Segmentation
  2021 · 6 citations
• Investigating effective LLM-based in-context tool use: what matters and how to improve
  2026
• Entropy Polarity in Reinforcement Fine-Tuning: Direction, Asymmetry, and Control
  2026
• DFPO: Scaling Value Modeling via Distributional Flow towards Robust and Generalizable LLM Post-Training
  2026
• MagicAgent: Towards Generalized Agent Planning
  2026
• Know What You Know: Metacognitive Entropy Calibration for Verifiable RL Reasoning
  2026
• DVPO: Distributional Value Modeling-based Policy Optimization for LLM Post-Training
  2025
• From Scores to Preferences: Redefining MOS Benchmarking for Speech Quality Reward Modeling
  2025
• VRPO: Rethinking Value Modeling for Robust RL Training under Noisy Supervision
  2025
• MagicGUI: A Foundational Mobile GUI Agent with Scalable Data Pipeline and Reinforcement Fine-tuning
  2025
• What Makes a Good Speech Tokenizer for LLM-Centric Speech Generation? A Systematic Study
  2025
• Towards Large Reasoning Models: A Survey of Reinforced Reasoning with Large Language Models
  2025
• Attention-guided Temporally Coherent Video Object Matting
  2021