Junxiao Yang

yangjunxiao2021's activity

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

liked a dataset 1 day ago

yangjunxiao2021/terminal-bench-science-trajectories

Viewer • Updated 24 days ago • 2.61k • 2.55k • 1

liked a Space 5 days ago

Running on CPU Upgrade

514

The Ultimate MoE Training Handbook

🧩

514

A hands-on guide to training Mixture-of-Experts models

upvoted a paper 14 days ago

RSI Arena: Towards Recursive Self-Improvement with Human Feedback

Paper • 2610.33624 • Published 18 days ago • 27

published a dataset 24 days ago

yangjunxiao2021/terminal-bench-science-trajectories

Viewer • Updated 24 days ago • 2.61k • 2.55k • 1

updated a dataset 24 days ago

yangjunxiao2021/terminal-bench-science-trajectories

Viewer • Updated 24 days ago • 2.61k • 2.55k • 1

published a dataset about 2 months ago

yangjunxiao2021/mle-trajectories

Viewer • Updated Sep 20 • 42 • 178

updated a dataset about 2 months ago

yangjunxiao2021/mle-trajectories

Viewer • Updated Sep 20 • 42 • 178

upvoted a paper 2 months ago

Terminal-Universe: Turning Agent Trajectories into Scalable Terminal Environments

Paper • 2609.04148 • Published Sep 3 • 79

upvoted a paper 3 months ago

VoiceMem: Streaming Dual-Brain Memory for Real-Time Interaction

Paper • 2608.26005 • Published Aug 26 • 133

liked a dataset 4 months ago

ByteDance-Seed/EdgeBench

Viewer • Updated Jul 27 • 51 • 3.96k • 86

liked 3 datasets 5 months ago

aisa-group/InferenceBench-Trajectories

Updated Jun 21 • 871 • 4

aisa-group/PostTrainBench-Trajectories

Updated 1 day ago • 135k • 17

zhifeixie/StreamAudio-2M

Viewer • Updated Jun 3 • 381k • 1.1k • 32

New activity in thu-coai/Syncred-Bench 5 months ago

Add task categories, paper and code links

1

#2 opened 5 months ago by

nielsr

authored a paper 5 months ago

AgentDoG 1.5: A Lightweight and Scalable Alignment Framework for AI Agent Safety and Security

Paper • 2605.29801 • Published May 28 • 145

upvoted a paper 5 months ago

SynCred-Bench: Benchmarking Synthetic Credibility in AI-Generated Visual Misinformation

Paper • 2606.03348 • Published Jun 2 • 2

submitted a paper to Daily Papers 5 months ago

SynCred-Bench: Benchmarking Synthetic Credibility in AI-Generated Visual Misinformation

Paper • 2606.03348 • Published Jun 2 • 2

updated a dataset 5 months ago

yangjunxiao2021/Syncred-Bench

Updated Jun 3 • 5 • 2

liked 2 datasets 5 months ago

thu-coai/Syncred-Bench

Viewer • Updated Jun 7 • 2.1k • 118 • 2

yangjunxiao2021/Syncred-Bench

Updated Jun 3 • 5 • 2