Lune

Profiles2019-2026

Qingming Huang

University of Chinese Academy of Sciences

107Papers
84Last author
135Unique co-authors
0First author
0Solo

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

Recent papers107

  1. BlackMirror: Black-Box Backdoor Detection for Text-to-Image Models via Instruction-Response DeviationAuthor 7 of 7CVPR 2026 · 2 citations
  2. From Static to Dynamic: Exploring Self-supervised Image-to-Video Representation Transfer LearningAuthor 6 of 6CVPR 2026 · 2 citations
  3. Guiding Diffusion-based Reconstruction with Contrastive Signals for Balanced Visual RepresentationAuthor 7 of 7CVPR 2026 · 2 citations
  4. Locate-then-Sparsify: Attribution Guided Sparse Strategy for Visual Hallucination MitigationAuthor 5 of 6CVPR 2026 · 2 citations
  5. Making Training-Free Diffusion Segmentors Scale with the Generative PowerAuthor 6 of 6CVPR 2026 · 2 citations
  6. Mind the Way You Select Negative Texts: Pursuing the Distance Consistency in OOD Detection with VLMsAuthor 7 of 7CVPR 2026 · 1 citation
  7. Quantifying the Potential to Escape Filter Bubbles: A Behavior-Aware Measure via Contrastive SimulationAuthor 6 of 6AAAI 2026 · 1 citation
  8. Adaptive Nonlinear Compression for Large Foundation ModelsAuthor 3 of 6ICLR 2026
  9. DMGINE: Day-Memory Guided Nighttime Image Enhancement for Dynamic Traffic ScenesAuthor 5 of 5AAAI 2026
  10. GoodDiffusion: Proactive Copyright Protection for Diffusion Generative Models via Learnable Sample-specific SignaturesAuthor 6 of 6ICML 2026
  11. Hidden Dangers of Compositional Generation: Diagnosing Semantic Safety Failures in Text-to-Image ModelsAuthor 7 of 7CVPR 2026
  12. HiGFA: Hierarchical Guidance for Fine-grained Data Augmentation with Diffusion ModelsAuthor 4 of 4AAAI 2026
  13. Localize and Neutralize: Gradient-Guided Token Suppression Against Visual Prompt Injection AttackAuthor 7 of 7ICML 2026
  14. PTNET: A Proposal-Centric Transformer Net-Work for 3D Object DetectionAuthor 7 of 7ICLR 2026
  15. Safe Codebook: Token-Level Moderation for Safer Visual Autoregressive GenerationAuthor 6 of 6CVPR Findings 2026
  16. The Bridge-Garden Dilemma in LLM Distillation: Why Mixing Hard and Soft Labels WorksAuthor 8 of 8ICML 2026
  17. The Devil is in the Condition Numbers: Why is GLU Better than non-GLU Structure?Author 5 of 5ICML 2026
  18. TuckA: Hierarchical Compact Tensor Experts for Efficient Fine-TuningAuthor 6 of 6AAAI 2026
  19. LightFair: Towards an Efficient Alternative for Fair T2I Diffusion via Debiasing Pre-trained Text EncodersAuthor 6 of 6NeurIPS 2025 · 17 citations
  20. VL-SAE: Interpreting and Enhancing Vision-Language Alignment with a Unified Concept SetAuthor 3 of 4NeurIPS 2025 · 13 citations
  21. Exploring Structural Degradation in Dense Representations for Self-supervised LearningAuthor 5 of 5NeurIPS 2025 · 5 citations
  22. Generalizing Single-Frame Supervision to Event-Level Understanding for Video Anomaly DetectionAuthor 6 of 6NeurIPS 2025 · 4 citations
  23. Relieving the Over-Aggregating Effect in Graph TransformersAuthor 4 of 5NeurIPS 2025 · 3 citations
  24. FlowDubber: Movie Dubbing with LLM-based Semantic-aware Learning and Flow Matching based Voice EnhancingAuthor 8 of 8ACM MM 2025 · 2 citations
  25. SSE-SAM: Balancing Head and Tail Classes Gradually Through Stage-Wise SAMAuthor 5 of 5AAAI 2025 · 2 citations
  26. Bidirectional Logits Tree: Pursuing Granularity Reconcilement in Fine-Grained ClassificationAuthor 5 of 5AAAI 2025 · 1 citation
  27. Query-centric Audio-Visual Cognition Network for Moment Retrieval, Segmentation and Step-CaptioningAuthor 4 of 4AAAI 2025 · 1 citation
  28. Cannot See the Forest for the Trees: Invoking Heuristics and Biases to Elicit Irrational Choices of LLMsAuthor 6 of 6ICML 2025
  29. Diffusion-based Adversarial Purification from the Perspective of the Frequency DomainAuthor 5 of 5ICML 2025
  30. Dis²Booth: Learning Image Distribution with Disentangled Features for Text-to-Image Diffusion ModelsAuthor 7 of 7AAAI 2025

Showing the 30 most recent indexed papers.

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