Jiwon Song

jiwonsong's activity

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

upvoted 2 papers 13 days ago

Thinkless: LLM Learns When to Think

Paper • 2505.13379 • Published 15 days ago • 50

Think Only When You Need with Large Hybrid-Reasoning Models

Paper • 2505.14631 • Published 14 days ago • 19

upvoted a paper 14 days ago

Reasoning Path Compression: Compressing Generation Trajectories for Efficient LLM Reasoning

Paper • 2505.13866 • Published 15 days ago • 16

upvoted 3 papers 3 months ago

LServe: Efficient Long-sequence LLM Serving with Unified Sparse Attention

Paper • 2502.14866 • Published Feb 20 • 13

Revisiting the Test-Time Scaling of o1-like Models: Do they Truly Possess Test-Time Scaling Capabilities?

Paper • 2502.12215 • Published Feb 17 • 16

Skrr: Skip and Re-use Text Encoder Layers for Memory Efficient Text-to-Image Generation

Paper • 2502.08690 • Published Feb 12 • 44

upvoted 4 papers 4 months ago

Large Language Diffusion Models

Paper • 2502.09992 • Published Feb 14 • 118

Can LLMs Maintain Fundamental Abilities under KV Cache Compression?

Paper • 2502.01941 • Published Feb 4 • 15

FastKV: KV Cache Compression for Fast Long-Context Processing with Token-Selective Propagation

Paper • 2502.01068 • Published Feb 3 • 17

SLEB: Streamlining LLMs through Redundancy Verification and Elimination of Transformer Blocks

Paper • 2402.09025 • Published Feb 14, 2024 • 8

upvoted a paper 7 months ago

Selective Attention Improves Transformer

Paper • 2410.02703 • Published Oct 3, 2024 • 24

upvoted a paper 12 months ago

Mixture-of-Agents Enhances Large Language Model Capabilities

Paper • 2406.04692 • Published Jun 7, 2024 • 60