Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets
  • Docs
  • Enterprise
  • Pricing
    • Website
      • Tasks
      • HuggingChat
      • Collections
      • Languages
      • Organizations
    • Community
      • Blog
      • Posts
      • Daily Papers
      • Hardware
      • Learn
      • Discord
      • Forum
      • GitHub
    • Solutions
      • Team & Enterprise
      • Hugging Face PRO
      • Enterprise Support
      • Inference Providers
      • Inference Endpoints
      • Storage Buckets

  • Log In
  • Sign Up
Donghyun Son's picture

Donghyun Son

DHdroid
6
·
  • DHdroid

AI & ML interests

None yet

Recent Activity

upvoted a paper 5 days ago
LoopVQ: Sub 1-bit KV Cache Quantization for Looped Transformers
upvoted a paper about 1 month ago
Prefill-Free Cross-Family KV Cache Transfer for Heterogeneous Multi-Agent LLMs
upvoted a paper about 1 month ago
Tailoring the Quantization Space for 1-Bit KV Cache Compression
View all activity

Organizations

AttentionX-ICL's profile picture

upvoted a paper 5 days ago

LoopVQ: Sub 1-bit KV Cache Quantization for Looped Transformers

Paper • 2611.05304 • Published 8 days ago • 11
upvoted 2 papers about 1 month ago

Prefill-Free Cross-Family KV Cache Transfer for Heterogeneous Multi-Agent LLMs

Paper • 2609.32259 • Published Sep 29 • 20

Tailoring the Quantization Space for 1-Bit KV Cache Compression

Paper • 2610.03027 • Published Oct 2 • 3
upvoted a collection 5 months ago

EXAONE 4.5

Collection
LG's First Open-Weight Vision-Language Model for Industrial Intelligence • 5 items • Updated Apr 22 • 47
upvoted 2 papers about 1 year ago

NSNQuant: A Double Normalization Approach for Calibration-Free Low-Bit Vector Quantization of KV Cache

Paper • 2505.18231 • Published May 23, 2025 • 3

Gaussian Weight Sampling for Scalable, Efficient and Stable Pseudo-Quantization Training

Paper • 2505.11170 • Published May 16, 2025 • 3
Company
TOS Privacy About Careers
Website
Models Datasets Spaces Pricing Docs