PPaperPicks

Yu Lu

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

Venues

Frequent coauthors

Papers

  1. Parameter Importance is Not Static: Evolving Parameter Isolation for Supervised Fine-Tuning
  2. Reason Only When Needed: Efficient Generative Reward Modeling via Model-Internal Uncertainty
  3. Why Supervised Fine-Tuning Fails to Learn: A Systematic Study of Incomplete Learning in Large Language Models
  4. Do Large Language Models Truly Grasp Addition? A Rule-Focused Diagnostic Using Two-Integer Arithmetic
  5. Domain Generalized Medical Landmark Detection via Robust Boundary-Aware Pre-Training
  6. EnAnchored-X2X: English-Anchored Optimization for Many-to-Many Translation
  7. HarmonySet: A Comprehensive Dataset for Understanding Video-Music Semantic Alignment and Temporal Synchronization
  8. NOVA: An Iterative Planning Framework for Enhancing Scientific Innovation with Large Language Models
  9. ActiveDC: Distribution Calibration for Active Finetuning
  10. Automated Multi-level Preference for MLLMs
  11. G-DIG: Towards Gradient-based DIverse and hiGh-quality Instruction Data Selection for Machine Translation
  12. Model AI Assignments 2024
  13. Retaining Key Information under High Compression Ratios: Query-Guided Compressor for LLMs
  14. Understanding the Therapeutic Relationship between Counselors and Clients in Online Text-based Counseling using LLMs