-
Less is More: Recursive Reasoning with Tiny Networks
Paper • 2510.04871 • Published • 506 -
Cache-to-Cache: Direct Semantic Communication Between Large Language Models
Paper • 2510.03215 • Published • 98 -
When Thoughts Meet Facts: Reusable Reasoning for Long-Context LMs
Paper • 2510.07499 • Published • 48 -
StreamingVLM: Real-Time Understanding for Infinite Video Streams
Paper • 2510.09608 • Published • 51
Jiwon Song
jiwonsong
AI & ML interests
Efficient AI | Ph.D Student @ SNU-VLSI
Recent Activity
authored
a paper
about 9 hours ago
Token Sparse Attention: Efficient Long-Context Inference with Interleaved Token Selection
upvoted
a
paper
about 15 hours ago
L4Q: Parameter Efficient Quantization-Aware Training on Large Language
Models via LoRA-wise LSQ
published
a Space
about 15 hours ago
SNU-VLSI/README