Sihwa Lee

macto

3

AI & ML interests

None yet

Recent Activity

upvoted a paper 5 days ago

BeaconKV: Key-Value Cache Compression Guided by Beacon Queries for Efficient Large Reasoning Model Inference

upvoted a paper 3 months ago

ReSET: Accurate Latency-Critical NVFP4 Reasoning via Step-Aware Temperature Scaling

upvoted a paper 3 months ago

Tangram: Unlocking Non-Uniform KV Cache Compression for Efficient Multi-turn LLM Serving

View all activity

Organizations

None yet

upvoted a paper 5 days ago

BeaconKV: Key-Value Cache Compression Guided by Beacon Queries for Efficient Large Reasoning Model Inference

Paper • 2609.04971 • Published 10 days ago • 39

upvoted 2 papers 3 months ago

ReSET: Accurate Latency-Critical NVFP4 Reasoning via Step-Aware Temperature Scaling

Paper • 2606.13233 • Published Jun 11 • 2

Tangram: Unlocking Non-Uniform KV Cache Compression for Efficient Multi-turn LLM Serving

Paper • 2606.06302 • Published Jun 15 • 10