Lune

Profiles2020-2026

Zongqing Lu

Peking University

54Papers
50Last author
29Unique co-authors
0First author
0Solo

First and last author come from byline position, which some venues assign alphabetically.

Recent papers54

  1. Guided Policy Optimization under Partial ObservabilityAuthor 3 of 3ICLR 2026 · 4 citations
  2. Multi-Agent Guided Policy OptimizationAuthor 3 of 3ICLR 2026 · 4 citations
  3. GTR-Turbo: Merged Checkpoint is Secretly a Free Teacher for Agentic VLM TrainingAuthor 6 of 8CVPR 2026 · 2 citations
  4. OpenT2M: No-frill Motion Generation with Open-source, Large-scale, High-quality DataAuthor 6 of 6CVPR 2026 · 1 citation
  5. Actionable Human Motion Generation via Latent Imitation and Fine-Grained Text CompletionAuthor 3 of 3CVPR Findings 2026
  6. End-to-End Language-Action Model for Humanoid Whole Body ControlAuthor 5 of 5CVPR 2026
  7. Learning Diverse Bimanual Dexterous Manipulation Skills from Human DemonstrationsAuthor 4 of 4AAAI 2026
  8. MEgoHand: Multimodal Egocentric Hand-Object Interaction Motion GenerationAuthor 4 of 4NeurIPS 2025 · 14 citations
  9. OpenMMEgo: Enhancing Egocentric Understanding for LMMs with Open Weights and DataAuthor 7 of 7NeurIPS 2025 · 10 citations
  10. Taking Notes Brings Focus? Towards Multi-Turn Multimodal Dialogue LearningAuthor 4 of 4EMNLP 2025 · 2 citations
  11. GTR: Guided Thought Reinforcement Prevents Thought Collapse in RL-Based VLM Agent TrainingAuthor 5 of 6ICCV 2025 · 1 citation
  12. MotionCtrl: A Real-Time Controllable Vision-Language-Motion ModelAuthor 8 of 8ICCV 2025 · 1 citation
  13. Cradle: Empowering Foundation Agents towards General Computer ControlAuthor 28 of 28ICML 2025
  14. Cross-Embodiment Dexterous Grasping with Reinforcement LearningAuthor 4 of 4ICLR 2025
  15. Discrete Latent Plans via Semantic Skill AbstractionsAuthor 3 of 3ICLR 2025
  16. Efficient Residual Learning with Mixture-of-Experts for Universal Dexterous GraspingAuthor 4 of 4ICLR 2025
  17. From Pixels to Tokens: Byte-Pair Encoding on Quantized Visual ModalitiesAuthor 7 of 7ICLR 2025
  18. Learning Video-Conditioned Policy on Unlabelled Data with Joint Embedding Predictive TransformerAuthor 2 of 2ICLR 2025
  19. MLLM as Retriever: Interactively Learning Multimodal Retrieval for Embodied AgentsAuthor 4 of 4ICLR 2025
  20. Planning with Quantized Opponent ModelsAuthor 3 of 3NeurIPS 2025
  21. Revisiting Cooperative Off-Policy Multi-Agent Reinforcement LearningAuthor 3 of 3ICML 2025
  22. Scaling Large Motion Models with Million-Level Human MotionsAuthor 7 of 7ICML 2025
  23. VideoOrion: Tokenizing Object Dynamics in VideosAuthor 7 of 7ICCV 2025
  24. Watch Less, Do More: Implicit Skill Discovery for Video-Conditioned PolicyAuthor 2 of 2ICLR 2025
  25. Steve-Eye: Equipping LLM-based Embodied Agents with Visual Perception in Open WorldsAuthor 4 of 4ICLR 2024 · 57 citations
  26. Pre-Training Goal-based Models for Sample-Efficient Reinforcement LearningAuthor 4 of 4ICLR 2024 · 26 citations
  27. SEABO: A Simple Search-Based Method for Offline Imitation LearningAuthor 6 of 6ICLR 2024 · 17 citations
  28. Settling Decentralized Multi-Agent Coordinated Exploration by Novelty SharingAuthor 3 of 3AAAI 2024 · 12 citations
  29. Opponent Modeling based on Subgoal InferenceAuthor 3 of 3NeurIPS 2024 · 7 citations
  30. Pre-Trained Multi-Goal Transformers with Prompt Optimization for Efficient Online AdaptationAuthor 4 of 4NeurIPS 2024 · 5 citations

Showing the 30 most recent indexed papers.

Dusk over the sea between two cliffs drawn in fine vertical lines