👋 Hi there! I'm Jang-Hyun, a Machine Learning researcher. You can find my work on my homepage.
-
Seoul Nat'l University
- Seoul, Korea
- in/jang-hyun-kim-346160173
Pinned Loading
-
snu-mllab/KVzip
snu-mllab/KVzip Public[NeurIPS'25 Oral] Query-agnostic KV cache eviction: 3–4× reduction in memory and 2× decrease in latency (Qwen3/2.5, Gemma3, LLaMA3)
-
snu-mllab/Context-Memory
snu-mllab/Context-Memory PublicPytorch implementation for "Compressed Context Memory For Online Language Model Interaction" (ICLR'24)
-
snu-mllab/PuzzleMix
snu-mllab/PuzzleMix PublicOfficial PyTorch implementation of "Puzzle Mix: Exploiting Saliency and Local Statistics for Optimal Mixup" (ICML'20)
-
snu-mllab/Co-Mixup
snu-mllab/Co-Mixup PublicOfficial PyTorch implementation of "Co-Mixup: Saliency Guided Joint Mixup with Supermodular Diversity" (ICLR'21 Oral)
-
snu-mllab/Efficient-Dataset-Condensation
snu-mllab/Efficient-Dataset-Condensation PublicOfficial PyTorch implementation of "Dataset Condensation via Efficient Synthetic-Data Parameterization" (ICML'22)
-
Speaker_Verification
Speaker_Verification PublicTensorflow implementation of "Generalized End-to-End Loss for Speaker Verification"
If the problem persists, check the GitHub status page or contact support.