Lune

Profiles2022-2026

Junliang Xing

Tsinghua University

33Papers
5Last author
67Unique co-authors
0First author
0Solo

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

Recent papers33

  1. GTR-Turbo: Merged Checkpoint is Secretly a Free Teacher for Agentic VLM TrainingAuthor 4 of 8CVPR 2026 · 2 citations
  2. K²-Agent: Co-Evolving Know-What and Know-How for Hierarchical Mobile Device ControlAuthor 4 of 10ICLR 2026 · 1 citation
  3. Bridging the Temporal Gap in Multimodal LLMs: Deeply Stacking Temporal Tokens for Audio-Visual Speech RecognitionAuthor 2 of 6ACL Findings 2026
  4. Deep (Predictive) Discounted Counterfactual Regret MinimizationAuthor 5 of 7AAAI 2026
  5. Multivariate Diffusion Transformer with Decoupled Attention for High-Fidelity Mask-Text Collaborative Facial GenerationAuthor 8 of 8AAAI 2026
  6. Multi-View 3D Human Pose Estimation with Weakly Synchronized ImagesAuthor 4 of 6AAAI 2025 · 3 citations
  7. An Open-Ended Learning Framework for Opponent ModelingAuthor 6 of 7AAAI 2025 · 1 citation
  8. Dual-Flow: Transferable Multi-Target, Instance-Agnostic Attacks via In-the-wild Cascading Flow OptimizationAuthor 6 of 6NeurIPS 2025 · 1 citation
  9. GTR: Guided Thought Reinforcement Prevents Thought Collapse in RL-Based VLM Agent TrainingAuthor 3 of 6ICCV 2025 · 1 citation
  10. Position-Aware Guided Point Cloud Completion with CLIP ModelAuthor 6 of 6AAAI 2025 · 1 citation
  11. BodyGen: Advancing Towards Efficient Embodiment Co-DesignAuthor 3 of 7ICLR 2025
  12. Diverse Policies Recovering via Pointwise Mutual Information Weighted Imitation LearningAuthor 11 of 16ICLR 2025
  13. Goal-Oriented Skill Abstraction for Offline Multi-Task Reinforcement LearningAuthor 6 of 7ICML 2025
  14. Habitizing Diffusion Planning for Efficient and Effective Decision MakingAuthor 4 of 5ICML 2025
  15. Minimal Impact ControlNet: Advancing Multi-ControlNet IntegrationAuthor 8 of 10ICLR 2025
  16. Offline Opponent Modeling with Truncated Q-driven Instant Policy RefinementAuthor 7 of 8ICML 2025
  17. StickMotion: Generating 3D Human Motions by Drawing a StickmanAuthor 7 of 9CVPR 2025
  18. Efficient Multi-task Reinforcement Learning with Cross-Task Policy GuidanceAuthor 6 of 7NeurIPS 2024 · 11 citations
  19. Not All Tasks Are Equally Difficult: Multi-Task Deep Reinforcement Learning with Dynamic Depth RoutingAuthor 6 of 7AAAI 2024 · 11 citations
  20. Opponent Modeling with In-context SearchAuthor 7 of 8NeurIPS 2024 · 8 citations
  21. Advancing Video Synchronization with Fractional Frame Analysis: Introducing a Novel Dataset and ModelAuthor 3 of 5AAAI 2024 · 7 citations
  22. Dynamic Discounted Counterfactual Regret MinimizationAuthor 5 of 6ICLR 2024 · 7 citations
  23. Towards Offline Opponent Modeling with In-context LearningAuthor 7 of 8ICLR 2024 · 7 citations
  24. Dual Critic Reinforcement Learning under Partial ObservabilityAuthor 4 of 5NeurIPS 2024 · 3 citations
  25. Inner Classifier-Free Guidance and Its Taylor Expansion for Diffusion ModelsAuthor 5 of 7ICLR 2024 · 2 citations
  26. PAE: Reinforcement Learning from External Knowledge for Efficient ExplorationAuthor 3 of 7ICLR 2024 · 1 citation
  27. SynSP: Synergy of Smoothness and Precision in Pose Sequences RefinementAuthor 10 of 11CVPR 2024
  28. Automatic Grouping for Efficient Cooperative Multi-Agent Reinforcement LearningAuthor 6 of 7NeurIPS 2023 · 37 citations
  29. MMTSA: Multi-Modal Temporal Segment Attention Network for Efficient Human Activity RecognitionAuthor 4 of 7UbiComp 2023 · 22 citations
  30. Single-Stage Multi-human Parsing via Point Sets and Center-based OffsetsAuthor 3 of 4ACM MM 2023 · 14 citations

Showing the 30 most recent indexed papers.

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