Janghwan Lee PRO

superdocker's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a paper 2 days ago

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

Paper • 2606.06302 • Published 3 days ago • 9

upvoted 2 papers 12 months ago

InfiniPot: Infinite Context Processing on Memory-Constrained LLMs

Paper • 2410.01518 • Published Oct 2, 2024 • 3

InfiniPot-V: Memory-Constrained KV Cache Compression for Streaming Video Understanding

Paper • 2506.15745 • Published Jun 18, 2025 • 14

upvoted a paper over 1 year ago

Addition is All You Need for Energy-efficient Language Models

Paper • 2410.00907 • Published Oct 1, 2024 • 151