ai&

ai-and's activity

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

Weyaxi 

in ai-and/termgrade-trajectories 3 days ago

45 passing trials where a required permission test was skipped

4

#1 opened 8 days ago by

EagleEdge

Weyaxi 

updated 2 datasets 4 days ago

ai-and/termgrade-trajectories

Viewer • Updated 4 days ago • 217k • 844 • 2

ai-and/termgrade-environments

RL Environment • Updated 4 days ago • 8.03k • 4.81k • 10

Weyaxi 

published 2 models 27 days ago

ai-and/termgrade-gemma4-31b-merged

Text Generation • 31B • Updated 27 days ago • 173 • 3

ai-and/termgrade-gemma4-31b-lora

Text Generation • Updated 27 days ago • 79 • 3

Weyaxi 

published 3 datasets 27 days ago

ai-and/termgrade-bandcentral-gemma4-31b-bash

RL Environment • Updated 27 days ago • 271 • 803 • 3

ai-and/termgrade-trajectories

Viewer • Updated 4 days ago • 217k • 844 • 2

ai-and/termgrade-environments

RL Environment • Updated 4 days ago • 8.03k • 4.81k • 10

Weyaxi 

updated 2 models 27 days ago

ai-and/termgrade-gemma4-31b-merged

Text Generation • 31B • Updated 27 days ago • 173 • 3

ai-and/termgrade-gemma4-31b-lora

Text Generation • Updated 27 days ago • 79 • 3

Weyaxi 

updated a dataset 27 days ago

ai-and/termgrade-bandcentral-gemma4-31b-bash

RL Environment • Updated 27 days ago • 271 • 803 • 3

Weyaxi 

updated a collection 27 days ago

TermGrade

Collection

1k graded terminal environments, 36k trajectories, and the RL run they trained. • 5 items • Updated 27 days ago • 6

jwu323 

authored a paper 3 months ago

Macaron-V1: Towards Open Continual Learning with Self-Improvement and Mixture-of-LoRA

Paper • 2608.09819 • Published Aug 10 • 113

jwu323 

authored a paper 9 months ago

Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces

Paper • 2601.11868 • Published Jan 17 • 38

jwu323 

authored a paper over 1 year ago

Control-R: Towards controllable test-time scaling

Paper • 2506.00189 • Published May 30, 2025 • 6

jwu323 

authored a paper almost 2 years ago

Critic-V: VLM Critics Help Catch VLM Errors in Multimodal Reasoning

Paper • 2411.18203 • Published Nov 27, 2024 • 40