Conversational AI (CoAI) group from Tsinghua University

thu-coai's activity

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

chujiezheng 

authored 2 papers about 2 months ago

QwenGyre: An Elastic Reinforcement Learning Framework for Training xLong-Horizon Agents

Paper • 2609.33848 • Published Sep 27 • 45

Outcome Accuracy is Not Enough: Aligning the Reasoning Process of Reward Models

Paper • 2602.04649 • Published Feb 4 • 14

JaneGreen 

published a dataset about 2 months ago

thu-coai/ScopeInstruct

Viewer • Updated Sep 29 • 18k • 80 • 1

JaneGreen 

updated 2 datasets about 2 months ago

thu-coai/ScopeInstruct

Viewer • Updated Sep 29 • 18k • 80 • 1

thu-coai/MTAC-IFBench

Viewer • Updated Sep 15 • 120 • 168 • 1

JaneGreen 

published a dataset 2 months ago

thu-coai/MTAC-IFBench

Viewer • Updated Sep 15 • 120 • 168 • 1

SahandSab 

authored a paper 3 months ago

PatientAct: Theory-Grounded Mental Health Client Simulation

Paper • 2608.12750 • Published Aug 13

aliezlo 

updated 2 models 4 months ago

thu-coai/SeTox-Qwen2.5-7B

Text Generation • 333k • Updated Jul 5 • 17 • 1

thu-coai/SeTox-Qwen2.5-3B

Text Generation • 242k • Updated Jul 5 • 1.33k • 1

aliezlo 

updated a dataset 4 months ago

thu-coai/SeTox

Updated Jul 5 • 52

aliezlo 

published a model 4 months ago

thu-coai/SeTox-Qwen2.5-7B

Text Generation • 333k • Updated Jul 5 • 17 • 1

aliezlo 

published a model 5 months ago

thu-coai/SeTox-Qwen2.5-3B

Text Generation • 242k • Updated Jul 5 • 1.33k • 1

aliezlo 

published a dataset 5 months ago

thu-coai/SeTox

Updated Jul 5 • 52

chujiezheng 

authored a paper 5 months ago

Deeper is Not Always Better: Mitigating the Alignment Tax via Confident Layer Decoding

Paper • 2606.21906 • Published Jun 20 • 27

yangjunxiao2021 

in thu-coai/Syncred-Bench 5 months ago

Add task categories, paper and code links

1

#2 opened 5 months ago by

nielsr

yangjunxiao2021 

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

yangjunxiao2021 

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

Solaria-Z 

updated a dataset 5 months ago

thu-coai/Syncred-Bench

Viewer • Updated Jun 7 • 2.1k • 111 • 2

yangjunxiao2021 

published a dataset 5 months ago

thu-coai/Syncred-Bench

Viewer • Updated Jun 7 • 2.1k • 111 • 2

JinfengZhou 

published a model 7 months ago

thu-coai/CogFlow-8B

Updated Apr 21