← authors · overview

• Alphazero-like Tree-search Can Guide Large Language Model Decoding And Training
  2023 · 322 citations
• Adaptive Joint Optimization for 3D Reconstruction with Differentiable Rendering
  2022 · 14 citations
• DB-VIO: Dual-Branch Visual Inertial Odometry with Enhanced Visual-Inertial Representation
  2026
• Lens: Rethinking Training Efficiency for Foundational Text-to-Image Models
  2026
• MAGIC: A Co-Evolving Attacker-Defender Adversarial Game for Robust LLM Safety
  2026
• MorphoSim: An Interactive, Controllable, and Editable Language-guided 4D World Simulator
  2025
• RubricRL: Simple Generalizable Rewards for Text-to-Image Generation
  2025
• PARL-MT: Learning to Call Functions in Multi-Turn Conversation with Progress Awareness
  2025
• VLM4D: Towards Spatiotemporal Awareness in Vision Language Models
  2025
• ThinkBench: Dynamic Out-of-Distribution Evaluation for Robust LLM Reasoning
  2025