RLHF Workflow: From Reward Modeling to Online RLHF
Hanze Dong, Xiong, Wei, Pang, Bo, Wang, Haoxiang, Zhao, Han, Zhou, Yingbo, Jiang, Nan, Sahoo, Doyen and 2 more
Who it is from
- Salesforceaffiliation declared by the authors, according to OpenAlex
Other papers from the same organizations
- A comprehensive survey on pretrained foundation models: a history from BERT to ChatGPTBeihang University · 1,211 citations
- BLIP3-o: A Family of Fully Open Unified Multimodal Models-Architecture, Training and DatasetNew York University · 437 citations
- A Survey on Test-Time Scaling in Large Language Models: What, How, Where, and How Well?McGill University · 363 citations
- ULIP-2: Towards Scalable Multimodal Pre-Training for 3D UnderstandingSalesforce · 351 citations
- Spider 2.0: Evaluating Language Models on Real-World Enterprise Text-to-SQL WorkflowsSalesforce · 314 citations
- Not All Experts are Equal: Efficient Expert Pruning and Skipping for Mixture-of-Experts Large Language ModelsSalesforce · 247 citations