← authors · overview

• EDGE-LLM: Enabling Efficient Large Language Model Adaptation On Edge Devices Via Layerwise Unified Compression And Adaptive Layer Tuning And Voting
  2024 · 55 citations
• Large Language Models Meet Harry Potter: A Bilingual Dataset for Aligning Dialogue Agents with Characters
  2022 · 4 citations
• Reinforcement Learning with Continuous Actions Under Unmeasured Confounding
  2025 · 3 citations
• LoopRPT: Reinforcement Pre-Training for Looped Language Models
  2026
• OmniTrack: General Motion Tracking via Physics-Consistent Reference
  2026
• OmniXtreme: Breaking the Generality Barrier in High-Dynamic Humanoid Control
  2026
• UniAct: Unified Motion Generation and Action Streaming for Humanoid Robots
  2025
• Seed3D 1.0: From Images to High-Fidelity Simulation-Ready 3D Assets
  2025
• GraphRAG-R1: Graph Retrieval-Augmented Generation with Process-Constrained Reinforcement Learning
  2025
• Towards Fast, Memory-based and Data-Efficient Vision-Language Policy
  2025
• StyleLoco: Generative Adversarial Distillation for Natural Humanoid Robot Locomotion
  2025