Official collection for paper "Reward Modeling from Natural Language Human Feedback".
AI & ML interests
LLM, Conversational AI, Agent
Recent Activity
View all activity
Papers
HarnessRL: Co-Evolving Policies with a Just-in-Time Training Harness for Open-Ended RL
What Makes a Social Agent's Interactions Effective? Learning from Verifiable Outcomes in Paired Worlds
Organization Card
Tongyi-ConvAI: The official repository containing the Alibaba Tongyi Conversational AI models and datasets.
models 13
Tongyi-ConvAI/Cold-Start-MetaRM-RM-NLHF-Qwen-32B
32B • Updated • 6 • 1
Tongyi-ConvAI/Cold-Start-MetaRM-RM-NLHF-Qwen-7B
7B • Updated • 18
Tongyi-ConvAI/Final-MetaRM-RM-NLHF-Qwen-7B
7B • Updated • 14
Tongyi-ConvAI/Final-MetaRM-RM-NLHF-Qwen-32B
32B • Updated • 18
Tongyi-ConvAI/RM-NLHF-Qwen-32B
33B • Updated • 12
Tongyi-ConvAI/Baseline-Outcome-Reward-Qwen-7B
8B • Updated • 20
Tongyi-ConvAI/RM-NLHF-Qwen-7B
8B • Updated • 16 • 2
Tongyi-ConvAI/P-GenRM-8B-ChatbotArena
8B • Updated • 14 • 2
Tongyi-ConvAI/P-GenRM-8B-PRISM
8B • Updated • 18 • 1
Tongyi-ConvAI/OmniCharacter-7B
Updated
datasets 7
Tongyi-ConvAI/VibeMemBench
Viewer • Updated • 111 • 1.59k
Tongyi-ConvAI/RM-NLHF
Viewer • Updated • 49.5k • 69 • 2
Tongyi-ConvAI/OmniCharacter
Viewer • Updated • 10.1k • 294 • 2
Tongyi-ConvAI/EPO-RL-data
Viewer • Updated • 9.38k • 50 • 1
Tongyi-ConvAI/OpenOmni
Preview • Updated • 180 • 4
Tongyi-ConvAI/SDPO
Preview • Updated • 91 • 5
Tongyi-ConvAI/MMEvol
Preview • Updated • 948 • 15