Hongyu Wang

hongyuw's activity

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

commented a paper 29 days ago

MoTE: Mixture of Ternary Experts for Memory-efficient Large Multimodal Models

Paper • 2506.14435 • Published Jun 17 • 8 •

2

New activity in hongyuw/bitvla-bitsiglipL-224px-bf16 about 1 month ago

Can we ge just the pretrained version?

1

#1 opened about 1 month ago by

nicolollo

Improve model card: Add robotics pipeline tag and library name

#2 opened about 1 month ago by

nielsr

commented a paper about 1 month ago

BitVLA: 1-bit Vision-Language-Action Models for Robotics Manipulation

Paper • 2506.07530 • Published Jun 9 • 20 •

2

commented 3 papers 3 months ago

BitNet v2: Native 4-bit Activations with Hadamard Transformation for 1-bit LLMs

Paper • 2504.18415 • Published Apr 25 • 46 •

2

BitNet b1.58 2B4T Technical Report

Paper • 2504.12285 • Published Apr 16 • 74 •

2

The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits

Paper • 2402.17764 • Published Feb 27, 2024 • 620 •

143

commented 2 papers 8 months ago

BitNet a4.8: 4-bit Activations for 1-bit LLMs

Paper • 2411.04965 • Published Nov 7, 2024 • 69 •

6

BitNet a4.8: 4-bit Activations for 1-bit LLMs

Paper • 2411.04965 • Published Nov 7, 2024 • 69 •

6

commented 2 papers over 1 year ago

The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits

Paper • 2402.17764 • Published Feb 27, 2024 • 620 •

143

The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits

Paper • 2402.17764 • Published Feb 27, 2024 • 620 •

143