Lune

Profiles2020-2026

Yansong Tang

Tsinghua University

23Papers
15Last author
33Unique co-authors
1First author
0Solo

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

Recent papers23

  1. AgentMath: Empowering Mathematical Reasoning for Large Language Models via Tool-Augmented AgentAuthor 9 of 9ICLR 2026 · 22 citations
  2. Meta-CoT: Enhancing Granularity and Generalization in Image EditingAuthor 11 of 11CVPR 2026 · 3 citations
  3. IteRPrimE: Zero-shot Referring Image Segmentation with Iterative Grad-CAM Refinement and Primary Word EmphasisAuthor 5 of 5AAAI 2025 · 23 citations
  4. DreamLight: Towards Harmonious and Consistent Image RelightingAuthor 8 of 8NeurIPS 2025 · 9 citations
  5. Momentum-Gs: Momentum Gaussian Self-Distillation for High-Quality Large Scene ReconstructionAuthor 5 of 5ICCV 2025 · 9 citations
  6. FlexiAct: Towards Flexible Action Control in Heterogeneous ScenariosAuthor 3 of 5SIGGRAPH 2025 · 8 citations
  7. KV-Edit: Training-Free Image Editing for Precise Background PreservationAuthor 4 of 4ICCV 2025 · 8 citations
  8. Stepping Out of Similar Semantic Space for Open-Vocabulary SegmentationAuthor 6 of 6ICCV 2025 · 6 citations
  9. Ponder & Press: Advancing Visual GUI Agent towards General Computer ControlAuthor 4 of 4ACL Findings 2025 · 4 citations
  10. SAM2-LOVE: Segment Anything Model 2 in Language-aided Audio-Visual ScenesAuthor 5 of 5CVPR 2025
  11. WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-InstructAuthor 10 of 11ICLR 2025
  12. Q-VLM: Post-training Quantization for Large Vision-Language ModelsAuthor 4 of 6NeurIPS 2024 · 57 citations
  13. GeoLRM: Geometry-Aware Large Reconstruction Model for High-Quality 3D Gaussian GenerationAuthor 6 of 6NeurIPS 2024 · 40 citations
  14. Universal Segmentation at Arbitrary Granularity with Language InstructionAuthor 6 of 6CVPR 2024 · 15 citations
  15. PTM-VQA: Efficient Video Quality Assessment Leveraging Diverse PreTrained Models from the WildAuthor 9 of 9CVPR 2024 · 8 citations
  16. WizardArena: Post-training Large Language Models via Simulated Offline Chatbot ArenaAuthor 8 of 9NeurIPS 2024 · 7 citations
  17. Learning Multi-Scale Video-Text Correspondence for Weakly Supervised Temporal Article GrondingAuthor 6 of 6AAAI 2024 · 3 citations
  18. Open-Vocabulary Segmentation with Semantic-Assisted CalibrationAuthor 5 of 5CVPR 2024
  19. FineDance: A Fine-grained Choreography Dataset for 3D Full Body Dance GenerationAuthor 7 of 8ICCV 2023 · 110 citations
  20. LOGO: A Long-Form Video Dataset for Group Action Quality AssessmentAuthor 7 of 7CVPR 2023
  21. OrdinalCLIP: Learning Rank Prompts for Language-Guided Ordinal RegressionAuthor 4 of 7NeurIPS 2022 · 65 citations
  22. Semantic-Aware Auto-Encoders for Self-supervised Representation LearningAuthor 2 of 4CVPR 2022 · 8 citations
  23. Uncertainty-Aware Score Distribution Learning for Action Quality AssessmentAuthor 1 of 8CVPR 2020
Dusk over the sea between two cliffs drawn in fine vertical lines