-
Less is More: Recursive Reasoning with Tiny Networks
Paper • 2510.04871 • Published • 514 -
Cache-to-Cache: Direct Semantic Communication Between Large Language Models
Paper • 2510.03215 • Published • 99 -
When Thoughts Meet Facts: Reusable Reasoning for Long-Context LMs
Paper • 2510.07499 • Published • 49 -
StreamingVLM: Real-Time Understanding for Infinite Video Streams
Paper • 2510.09608 • Published • 53
Jiwon Song
jiwonsong
AI & ML interests
Efficient AI | Ph.D Student @ SNU-VLSI
Recent Activity
authored a paper 3 days ago
CompactAttention: Accelerating Chunked Prefill with Block-Union KV Selection upvoted a paper 4 days ago
CompactAttention: Accelerating Chunked Prefill with Block-Union KV Selection submitted a paper 4 days ago
CompactAttention: Accelerating Chunked Prefill with Block-Union KV SelectionOrganizations
-
Less is More: Recursive Reasoning with Tiny Networks
Paper • 2510.04871 • Published • 514 -
Cache-to-Cache: Direct Semantic Communication Between Large Language Models
Paper • 2510.03215 • Published • 99 -
When Thoughts Meet Facts: Reusable Reasoning for Long-Context LMs
Paper • 2510.07499 • Published • 49 -
StreamingVLM: Real-Time Understanding for Infinite Video Streams
Paper • 2510.09608 • Published • 53
datasets 0
None public yet