Lune

Profiles2019-2026ORCID 0000-0002-8525-9163

Lu Sheng

Beihang University

22Papers
9Last author
44Unique co-authors
1First author
0Solo

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

Recent papers22

  1. Geometrically-Constrained Agent for Spatial ReasoningAuthor 9 of 9CVPR 2026 · 29 citations
  2. PGS: Effective LLM Code Refinement via Property-Oriented and Structurally Minimal FeedbackAuthor 5 of 5ICML 2026 · 4 citations
  3. Personalize Anything for Free with Diffusion TransformerAuthor 4 of 4AAAI 2026 · 1 citation
  4. RoboRefer: Towards Spatial Referring with Reasoning in Vision-Language Models for RoboticsAuthor 10 of 11NeurIPS 2025 · 159 citations
  5. Mv-Adapter: Multi-View Consistent Image Generation Made EasyAuthor 7 of 7ICCV 2025 · 14 citations
  6. Systematic Reward Gap Optimization for Mitigating VLM HallucinationsAuthor 6 of 6NeurIPS 2025 · 7 citations
  7. Multi-Agent Amodal Completion: Direct Synthesis with Fine-Grained Semantic GuidanceAuthor 6 of 6ACM MM 2025 · 3 citations
  8. Code-as-Monitor: Constraint-aware Visual Programming for Reactive and Proactive Robotic Failure DetectionAuthor 7 of 8CVPR 2025
  9. Octavius: Mitigating Task Interference in MLLMs via LoRA-MoEAuthor 7 of 10ICLR 2024 · 24 citations
  10. Data-Free Generalized Zero-Shot LearningAuthor 5 of 6AAAI 2024 · 18 citations
  11. MP5: A Multi-modal Open-ended Embodied System in Minecraft via Active PerceptionAuthor 5 of 8CVPR 2024 · 11 citations
  12. Multi-Modality Affinity Inference for Weakly Supervised 3D Semantic SegmentationAuthor 6 of 7AAAI 2024 · 7 citations
  13. Distortion-aware Transformer in 360° Salient Object DetectionAuthor 4 of 6ACM MM 2023 · 14 citations
  14. Siamese DETRAuthor 8 of 8CVPR 2023
  15. DanceFormer: Music Conditioned 3D Dance Generation with Parametric Motion TransformerAuthor 4 of 4AAAI 2022 · 182 citations
  16. 3DJCG: A Unified Framework for Joint Dense Captioning and Visual Grounding on 3D Point CloudsAuthor 4 of 5CVPR 2022 · 80 citations
  17. 3DVG-Transformer: Relation Modeling for Visual Grounding on Point CloudsAuthor 3 of 4ICCV 2021 · 234 citations
  18. VoteHMR: Occlusion-Aware Voting Network for Robust 3D Human Mesh Recovery from Partial Point CloudsAuthor 3 of 3ACM MM 2021 · 27 citations
  19. Morphing and Sampling Network for Dense Point Cloud CompletionAuthor 2 of 5AAAI 2020 · 363 citations
  20. CAMP: Cross-Modal Adaptive Message Passing for Text-Image RetrievalAuthor 4 of 7ICCV 2019 · 349 citations
  21. Improving Pedestrian Attribute Recognition With Weakly-Supervised Multi-Scale Attribute-Specific LocalizationAuthor 2 of 4ICCV 2019 · 153 citations
  22. Unsupervised Collaborative Learning of Keyframe Detection and Visual Odometry Towards Monocular Deep SLAMAuthor 1 of 4ICCV 2019 · 42 citations
Dusk over the sea between two cliffs drawn in fine vertical lines