PPaperPicks

Boyang Li

Nanyang Technological University, School of Computer Science and Engineering, Singapore

16 papers at tracked venues · 9 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. Learning to Animate Images from A Few Videos to Portray Delicate Human Actions
  2. Black Swan: Abductive and Defeasible Video Reasoning in Unpredictable Events
  3. CAT Merging: A Training-Free Approach for Resolving Conflicts in Model Merging
  4. Conversational Explanations: Discussing Explainable AI with Non-AI Experts
  5. Enhancing Vision-Language Compositional Understanding with Multimodal Synthetic Data
  6. Local Masked Reconstruction for Efficient Self-Supervised Learning on High-Resolution Images
  7. SPHERE: Unveiling Spatial Blind Spots in Vision-Language Models Through Hierarchical Evaluation
  8. Task Arithmetic in Trust Region: A Training-Free Model Merging Approach to Navigate Knowledge Conflicts
  9. Towards Minimizing Feature Drift in Model Merging: Layer-wise Task Vector Fusion for Adaptive Knowledge Integration
  10. Two Causally Related Needles in a Video Haystack
  11. Concept-skill Transferability-based Data Selection for Large Vision-Language Models
  12. Distilling Autoregressive Models to Obtain High-Performance Non-autoregressive Solvers for Vehicle Routing Problems with Faster Inference Speed
  13. Emergent Open-Vocabulary Semantic Segmentation from Off-the-Shelf Vision-Language Models
  14. Event Causality Is Key to Computational Story Understanding
  15. Multilingual Synopses of Movie Narratives: A Dataset for Vision-Language Story Understanding
  16. What Are We Measuring When We Evaluate Large Vision-Language Models? An Analysis of Latent Factors and Biases