Cole Harrison

jcoleharrison's activity

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

upvoted a collection 5 days ago

FLUX 3 Action

Collection

Open weights 7B world action model: base and shared encoders, SO-101 and DROID policies. Code: https://github.com/black-forest-labs/flux-action • 3 items • Updated 2 days ago • 41

upvoted a paper 19 days ago

Breaking the Vision-Action Shortcut: Latent Interface Training for Generalizable Robotics Foundation Models

Paper • 2609.12641 • Published 24 days ago • 71

upvoted a paper 5 months ago

MolmoAct2: Action Reasoning Models for Real-world Deployment

Paper • 2605.02881 • Published May 4 • 358

upvoted a paper 7 months ago

TOPReward: Token Probabilities as Hidden Zero-Shot Rewards for Robotics

Paper • 2602.19313 • Published Feb 22 • 26

upvoted a paper 8 months ago

VLS: Steering Pretrained Robot Policies via Vision-Language Models

Paper • 2602.03973 • Published Feb 3 • 22

upvoted an article 12 months ago

view article

Article

How I Trained Action Chunking Transformer (ACT) on SO-101: My Journey, Gotchas, and Lessons

• 

sherryxychen

•

Sep 30, 2025

• 84

upvoted an article over 1 year ago

view article

Article

Open-R1: a fully open reproduction of DeepSeek-R1

• 
• 
• +1

eliebak, lvwerra, lewtun

•

Jan 28, 2025

• 891