PPaperPicks

Tao Lin

12 papers at tracked venues · 11 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. Rethinking Expert Trajectory Utilization in LLM Post-training for Mathematical Reasoning
  2. CollabEdit: Towards Non-destructive Collaborative Knowledge Editing
  3. DeFT: Decoding with Flash Tree-attention for Efficient Tree-structured LLM Inference
  4. ELICIT: LLM Augmentation Via External In-context Capability
  5. GIFT: Unlocking Full Potential of Labels in Distilled Dataset at Near-zero Cost
  6. Learn How to Query from Unlabeled Data Streams in Federated Learning
  7. STI-Bench: Are MLLMs Ready for Precise Spatial-Temporal World Understanding?
  8. Cooperative Hardware-Prompt Learning for Snapshot Compressive Imaging
  9. Efficiency for Free: Ideal Data Are Transportable Representations
  10. Increasing Model Capacity for Free: A Simple Strategy for Parameter Efficient Fine-tuning
  11. Out-of-Bounding-Box Triggers: A Stealthy Approach to Cheat Object Detectors
    ECCV 2024 · Tao Lin
  12. Towards Robust Multi-Modal Reasoning via Model Selection