1-bit Vision-Language-Action Models for Robotics Manipulation
Hongyu Wang
hongyuw
AI & ML interests
Language Model Pre-training
Recent Activity
authored
a paper
15 days ago
M4U: Evaluating Multilingual Understanding and Reasoning for Large
Multimodal Models
authored
a paper
15 days ago
Bitnet.cpp: Efficient Edge Inference for Ternary LLMs
authored
a paper
15 days ago
BitVLA: 1-bit Vision-Language-Action Models for Robotics Manipulation
Organizations
models
7
hongyuw/ft-bitvla-bitsiglipL-224px-libero_goal-bf16
Robotics
•
3B
•
Updated
•
7
hongyuw/ft-bitvla-bitsiglipL-224px-libero_spatial-bf16
Robotics
•
3B
•
Updated
•
5
hongyuw/ft-bitvla-bitsiglipL-224px-libero_object-bf16
Robotics
•
3B
•
Updated
•
5
hongyuw/ft-bitvla-bitsiglipL-224px-libero_long-bf16
Robotics
•
3B
•
Updated
•
6
hongyuw/bitvla-siglipL-224px-bf16
Image-Text-to-Text
•
Updated
•
15
•
4
hongyuw/bitvla-bitsiglipL-224px-bf16
Image-Text-to-Text
•
Updated
•
14
•
5
hongyuw/bitnet-b1.58-2B-4T-bf16
Text Generation
•
2B
•
Updated
•
1