PPaperPicks

Meng Cao

18 papers at tracked venues · 13 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. Putting Captions to the Test: Evaluating Video Caption Quality through Multiple-Choice Question Answering
  2. AnyTalk: Multi-modal Driven Multi-domain Talking Head Generation
  3. Checklists Are Better Than Reward Models For Aligning Language Models
  4. Contrastive Localized Language-Image Pre-Training
  5. ETVA: Evaluation of Text-to-Video Alignment via Fine-Grained Question Generation and Answering
  6. MMAU: A Holistic Benchmark of Agent Capabilities Across Diverse Domains
  7. MR. Judge: Multimodal Reasoner as a Judge
  8. Revisit Large-Scale Image-Caption Data in Pre-training Multimodal Foundation Models
  9. StreamBridge: Turning Your Offline Video Large Language Model into a Proactive Streaming Assistant
  10. TIS-DPO: Token-level Importance Sampling for Direct Preference Optimization With Estimated Weights
  11. The Reasoning-Memorization Interplay in Language Models Is Mediated by a Single Direction
  12. BIM: Improving Graph Neural Networks with Balanced Influence Maximization
  13. Direct Large Language Model Alignment Through Self-Rewarding Contrastive Prompt Distillation
  14. Efficient ConvBN Blocks for Transfer Learning and Beyond
  15. Enhancing Reinforcement Learning with Dense Rewards from Language Model Critic
    EMNLP 2024 · Meng Cao
  16. Real-Time Exposure Correction via Collaborative Transformations and Adaptive Sampling
  17. Uncertainty-Aware Sign Language Video Retrieval with Probability Distribution Modeling
  18. VeCLIP: Improving CLIP Training via Visual-Enriched Captions