Lune

Profiles2019-2026

Leonid Sigal

University of British Columbia

28Papers
16Last author
51Unique co-authors
0First author
0Solo

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

Recent papers28

  1. InvAD: Inversion-based Reconstruction-Free Anomaly Detection with Diffusion ModelsAuthor 4 of 5CVPR 2026 · 3 citations
  2. Learning What Matters: Prioritized Concept Learning via Relative Error-driven Sample SelectionAuthor 5 of 6CVPR 2026 · 3 citations
  3. SPIKE-RL: Video-LLMs meet Bayesian SurpriseAuthor 4 of 5ICLR 2026
  4. MM-R³: On (In-)Consistency of Vision-Language Models (VLMs)Author 4 of 6ACL Findings 2025 · 3 citations
  5. ChartGaze: Enhancing Chart Understanding in LVLMs with Eye-Tracking Guided Attention RefinementAuthor 6 of 7EMNLP 2025 · 1 citation
  6. Black Swan: Abductive and Defeasible Video Reasoning in Unpredictable EventsAuthor 6 of 6CVPR 2025
  7. Locality Sensitive Avatars From VideoAuthor 5 of 6ICLR 2025
  8. Mitigate One, Skew Another? Tackling Intersectional Biases in Text-to-Image ModelsAuthor 7 of 8EMNLP Findings 2025
  9. Prompt2Perturb (P2P): Text-Guided Diffusion-Based Adversarial Attack on Breast Ultrasound ImagesAuthor 4 of 5CVPR 2025
  10. Response Wide Shut? Surprising Observations in Basic Vision Language Model CapabilitiesAuthor 5 of 5ACL 2025
  11. Prompting Hard or Hardly Prompting: Prompt Inversion for Text-to-Image Diffusion ModelsAuthor 4 of 4CVPR 2024 · 12 citations
  12. Emergent Open-Vocabulary Semantic Segmentation from Off-the-Shelf Vision-Language ModelsAuthor 3 of 4CVPR 2024 · 10 citations
  13. Extending Video Masked Autoencoders to 128 framesAuthor 11 of 11NeurIPS 2024 · 6 citations
  14. Light Field Neural RenderingAuthor 3 of 4CVPR 2022 · 108 citations
  15. Iterative Scene Graph GenerationAuthor 2 of 2NeurIPS 2022 · 47 citations
  16. Referring Transformer: A One-step Approach to Multi-task Visual GroundingAuthor 2 of 2NeurIPS 2021 · 270 citations
  17. Segmentation-grounded Scene Graph GenerationAuthor 3 of 3ICCV 2021 · 32 citations
  18. TriBERT: Human-centric Audio-visual Representation LearningAuthor 3 of 3NeurIPS 2021 · 15 citations
  19. Energy-Based Learning for Scene Graph GenerationAuthor 7 of 7CVPR 2021
  20. Saliency-Guided Image TranslationAuthor 4 of 4CVPR 2021
  21. UniT: Unified Knowledge Transfer for Any-Shot Object Detection and SegmentationAuthor 3 of 3CVPR 2021
  22. Front2Back: Single View 3D Shape Reconstruction via Front to Back PredictionAuthor 5 of 6CVPR 2020
  23. Improved Few-Shot Visual ClassificationAuthor 5 of 5CVPR 2020
  24. LayoutVAE: Stochastic Scene Layout Generation From a Label SetAuthor 4 of 5ICCV 2019 · 194 citations
  25. Watch, Listen and Tell: Multi-Modal Weakly Supervised Dense Event CaptioningAuthor 3 of 3ICCV 2019 · 89 citations
  26. G3raphGround: Graph-Based Language GroundingAuthor 3 of 3ICCV 2019 · 67 citations
  27. Mixture-Kernel Graph Attention Network for Situation RecognitionAuthor 2 of 2ICCV 2019 · 32 citations
  28. AttentionRNN: A Structured Spatial Attention MechanismAuthor 2 of 2ICCV 2019 · 4 citations
Dusk over the sea between two cliffs drawn in fine vertical lines