Lune

Profiles2019-2026

Qi Tian

Huawei Inc

108Papers
68Last author
243Unique co-authors
0First author
0Solo

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

Recent papers108

  1. Dereflection Any Image with Diffusion Priors and Diversified DataAuthor 5 of 6AAAI 2026 · 7 citations
  2. LongVideo-R1: Smart Navigation for Low-cost Long Video UnderstandingAuthor 4 of 5CVPR 2026 · 7 citations
  3. Model Merging in the Essential SubspaceAuthor 3 of 4CVPR 2026 · 6 citations
  4. Energy-Structured Low-Rank Adaptation for Continual LearningAuthor 3 of 4ICML 2026 · 1 citation
  5. Few-step Flow for 3D Generation via Marginal-Data Transport DistillationAuthor 8 of 8AAAI 2026 · 1 citation
  6. ParaUni: Enhance Generation in Unified Multimodal Model with Reinforcement-driven Hierarchical Parallel Information InteractionAuthor 5 of 6CVPR 2026 · 1 citation
  7. Reasoning LLM Improves Speaker Recognition in Long-form TV DramasAuthor 9 of 9ICML 2026
  8. SFedHIFI: Fire Rate-Based Heterogeneous Information Fusion for Spiking Federated LearningAuthor 5 of 6AAAI 2026
  9. TextOVSR: Text-Guided Real-World Opera Video Super-ResolutionAuthor 7 of 7CVPR 2026
  10. UniLat3D: Geometry-Appearance Unified Latents for Single-Stage 3D GenerationAuthor 14 of 14CVPR Findings 2026
  11. Segment Any 3D GaussiansAuthor 7 of 7AAAI 2025 · 175 citations
  12. MagCache: Fast Video Generation with Magnitude-Aware CacheAuthor 5 of 5NeurIPS 2025 · 41 citations
  13. CLIP-Adapted Region-to-Text Learning for Generative Open-Vocabulary Semantic SegmentationAuthor 7 of 8ICCV 2025 · 3 citations
  14. Boosting Segment Anything Model Towards Open-Vocabulary LearningAuthor 9 of 9AAAI 2025 · 2 citations
  15. Diffusion-Driven Progressive Target Manipulation for Source-Free Domain AdaptationAuthor 8 of 8NeurIPS 2025 · 2 citations
  16. METEOR: Multi-Encoder Collaborative Token Pruning for Efficient Vision Language ModelsAuthor 8 of 8ICCV 2025 · 2 citations
  17. Enhancing Pre-trained Representation Classifiability can Boost its InterpretabilityAuthor 5 of 6ICLR 2025
  18. IM-Zero: Instance-level Motion Controllable Video Generation in a Zero-shot MannerAuthor 8 of 8CVPR 2025
  19. 4D Gaussian Splatting for Real-Time Dynamic Scene RenderingAuthor 8 of 9CVPR 2024 · 513 citations
  20. QA-LoRA: Quantization-Aware Low-Rank Adaptation of Large Language ModelsAuthor 8 of 8ICLR 2024 · 179 citations
  21. GaussianEditor: Editing 3D Gaussians Delicately with Text InstructionsAuthor 5 of 5CVPR 2024 · 65 citations
  22. LION: Implicit Vision Prompt TuningAuthor 7 of 7AAAI 2024 · 38 citations
  23. HalluciDoctor: Mitigating Hallucinatory Toxicity in Visual Instruction DataAuthor 8 of 9CVPR 2024 · 29 citations
  24. BarLeRIa: An Efficient Tuning Framework for Referring Image SegmentationAuthor 8 of 8ICLR 2024 · 11 citations
  25. Parameter Efficient Fine-Tuning via Cross Block Orchestration for Segment Anything ModelAuthor 5 of 6CVPR 2024 · 11 citations
  26. Hybrid Distillation: Connecting Masked Autoencoders with Contrastive LearnersAuthor 8 of 8ICLR 2024 · 10 citations
  27. OVMR: Open-Vocabulary Recognition with Multi-Modal ReferencesAuthor 4 of 4CVPR 2024 · 6 citations
  28. Inner Classifier-Free Guidance and Its Taylor Expansion for Diffusion ModelsAuthor 7 of 7ICLR 2024 · 2 citations
  29. The KFIoU Loss for Rotated Object DetectionAuthor 8 of 8ICLR 2023 · 89 citations
  30. SAILER: Structure-aware Pre-trained Language Model for Legal Case RetrievalAuthor 8 of 8SIGIR 2023 · 68 citations

Showing the 30 most recent indexed papers.

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