← authors · overview

• Human-In-the-Loop Software Development Agents
  2024 · 2 citations
• Metis-SPECS: Decoupling Multimodal Learning via Self-distilled Preference-based Cold Start
  2025 · 1 citations
• Tool-Use Failure Analysis and Recovery Framework for LLM Agents
  2026
• Not All Tokens See Equally: Perception-Grounded Policy Optimization for Large Vision-Language Models
  2026
• Decentralized Heterogeneous Multi-Robot Collaborative Exploration for Indoor and Outdoor 3D Environments
  2026
• Try, Check and Retry: A Divide-and-Conquer Framework for Boosting Long-context Tool-Calling Performance of LLMs
  2026
• APEX-Searcher: Augmenting LLMs' Search Capabilities through Agentic Planning and Execution
  2026
• Apex-searcher: Augmenting Llms' Search Capabilities Through Agentic Planning And Execution
  2026
• LLaDA2.1: Speeding Up Text Diffusion via Token Editing
  2026
• Flexible Entropy Control in RLVR with a Gradient-Preserving Perspective
  2026
• Metis-SPECS: Decoupling Multimodal Learning via Self-distilled Preference-based Cold Start
  2025
• How LLMs Learn to Reason: A Complex Network Perspective
  2025
• Collaboration Equilibrium in Federated Learning
  2021