wd1: Weighted Policy Optimization for Reasoning in Diffusion Language Models
Xiaohang Tang, Rares Dolga, Sangwoong Yoon, Ilija Bogunovic
De quem é
- Ulsan National Institute of Science and Technologyafiliação declarada pelos autores, segundo o OpenAlex
Outros papers das mesmas organizações
- A Survey of Graph Neural Networks for Social Recommender SystemsGeorgia Institute of Technology · 399 citações
- Exploiting Style Latent Flows for Generalizing Deepfake Video DetectionChung-Ang University · 169 citações
- Text2HOI: Text-Guided 3D Motion Generation for Hand-Object InteractionUlsan National Institute of Science and Technology · 126 citações
- SDDGR: Stable Diffusion-Based Deep Generative Replay for Class Incremental Object DetectionUlsan National Institute of Science and Technology · 109 citações
- FinDER: Financial Dataset for Question Answering and Evaluating Retrieval-Augmented GenerationUlsan National Institute of Science and Technology · 83 citações