Park, Junyoung
13 publications
NeurIPS
2025
KeyDiff: Key Similarity-Based KV Cache Eviction for Long-Context LLM Inference in Resource-Constrained Environments
ECCV
2024
Enhancing Source-Free Domain Adaptive Object Detection with Low-Confidence Pseudo Label Distillation
ICLRW
2024
Recursive Speculative Decoding: Accelerating LLM Inference via Sampling Without Replacement