Jiwon Song

jiwonsong's activity

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

upvoted a paper 4 days ago

Can LLMs Maintain Fundamental Abilities under KV Cache Compression?

Paper • 2502.01941 • Published 6 days ago • 10

upvoted a paper 6 days ago

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

Paper • 2502.01068 • Published 7 days ago • 14

authored a paper 6 days ago

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

Paper • 2502.01068 • Published 7 days ago • 14

upvoted a paper 6 days ago

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

Paper • 2402.09025 • Published Feb 14, 2024 • 7

upvoted a paper 3 months ago

Selective Attention Improves Transformer

Paper • 2410.02703 • Published Oct 3, 2024 • 24

liked a model 4 months ago

hugging-quants/Meta-Llama-3.1-8B-Instruct-GPTQ-INT4

Text Generation • Updated Aug 7, 2024 • 12.9k • 21

liked a model 7 months ago

codellama/CodeLlama-13b-hf

Text Generation • Updated Apr 12, 2024 • 10.1k • • 103

authored a paper 8 months ago

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

Paper • 2402.09025 • Published Feb 14, 2024 • 7

upvoted a paper 8 months ago

Mixture-of-Agents Enhances Large Language Model Capabilities

Paper • 2406.04692 • Published Jun 7, 2024 • 56

liked a model 9 months ago

DiscoResearch/Llama3-DiscoLeo-Instruct-8B-32k-v0.1

Text Generation • Updated Sep 10, 2024 • 333 • 13