PPaperPicks

Seung-Hoon Na

9 papers at tracked venues · 6 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. EAIR: Entity-aware Inference-Time Knowledge Routing for Multi-Hop Knowledge Editing
  2. PRIME: Ultra-Low-Rank Principal-Residual Model Merging
  3. PURE: Post-hoc Unlocking and REfinement for Discrete Diffusion Decoding
  4. GenPoE: Generative Passage-level Mixture of Experts for Knowledge Enhancement of LLMs
  5. SeqMMR: Sequential Model Merging and LLM Routing for Enhanced Batched Sequential Knowledge Editing
  6. Wasserstein Distance Constraint and Parameter Sparsification for Batched and Iterative Knowledge Editing
  7. COMEM: In-Context Retrieval-Augmented Mass-Editing Memory in Large Language Models
  8. DistillMIKE: Editing Distillation of Massive In-Context Knowledge Editing in Large Language Models
  9. SARCAT: Generative Span-Act Guided Response Generation using Copy-enhanced Target Augmentation