Zobrazeno 1 - 10
of 37
pro vyhledávání: '"Rafailov, Rafael"'
Autor:
Chen, Zhaorun, Du, Yichao, Wen, Zichen, Zhou, Yiyang, Cui, Chenhang, Weng, Zhenzhen, Tu, Haoqin, Wang, Chaoqi, Tong, Zhengwei, Huang, Qinglan, Chen, Canyu, Ye, Qinghao, Zhu, Zhihong, Zhang, Yuqing, Zhou, Jiawei, Zhao, Zhuokai, Rafailov, Rafael, Finn, Chelsea, Yao, Huaxiu
While text-to-image models like DALLE-3 and Stable Diffusion are rapidly proliferating, they often encounter challenges such as hallucination, bias, and the production of unsafe, low-quality output. To effectively address these issues, it is crucial
Externí odkaz:
http://arxiv.org/abs/2407.04842
Autor:
Kim, Moo Jin, Pertsch, Karl, Karamcheti, Siddharth, Xiao, Ted, Balakrishna, Ashwin, Nair, Suraj, Rafailov, Rafael, Foster, Ethan, Lam, Grace, Sanketi, Pannag, Vuong, Quan, Kollar, Thomas, Burchfiel, Benjamin, Tedrake, Russ, Sadigh, Dorsa, Levine, Sergey, Liang, Percy, Finn, Chelsea
Large policies pretrained on a combination of Internet-scale vision-language data and diverse robot demonstrations have the potential to change how we teach robots new skills: rather than training new behaviors from scratch, we can fine-tune such vis
Externí odkaz:
http://arxiv.org/abs/2406.09246
Autor:
Rafailov, Rafael, Chittepu, Yaswanth, Park, Ryan, Sikchi, Harshit, Hejna, Joey, Knox, Bradley, Finn, Chelsea, Niekum, Scott
Reinforcement Learning from Human Feedback (RLHF) has been crucial to the recent success of Large Language Models (LLMs), however, it is often a complex and brittle process. In the classical RLHF framework, a reward model is first trained to represen
Externí odkaz:
http://arxiv.org/abs/2406.02900
Reinforcement Learning from Human Feedback (RLHF) has enabled significant advancements within language modeling for powerful, instruction-following models. However, the alignment of these models remains a pressing challenge as the policy tends to ove
Externí odkaz:
http://arxiv.org/abs/2406.01013
Autor:
Richemond, Pierre Harvey, Tang, Yunhao, Guo, Daniel, Calandriello, Daniele, Azar, Mohammad Gheshlaghi, Rafailov, Rafael, Pires, Bernardo Avila, Tarassov, Eugene, Spangher, Lucas, Ellsworth, Will, Severyn, Aliaksei, Mallinson, Jonathan, Shani, Lior, Shamir, Gil, Joshi, Rishabh, Liu, Tianqi, Munos, Remi, Piot, Bilal
The dominant framework for alignment of large language models (LLM), whether through reinforcement learning from human feedback or direct preference optimisation, is to learn from preference data. This involves building datasets where each element is
Externí odkaz:
http://arxiv.org/abs/2405.19107
We tackle the problem of policy learning from expert demonstrations without a reward function. A central challenge in this space is that these policies fail upon deployment due to issues of distributional shift, environment stochasticity, or compound
Externí odkaz:
http://arxiv.org/abs/2405.13193
Autor:
Tajwar, Fahim, Singh, Anikait, Sharma, Archit, Rafailov, Rafael, Schneider, Jeff, Xie, Tengyang, Ermon, Stefano, Finn, Chelsea, Kumar, Aviral
Learning from preference labels plays a crucial role in fine-tuning large language models. There are several distinct approaches for preference fine-tuning, including supervised learning, on-policy reinforcement learning (RL), and contrastive learnin
Externí odkaz:
http://arxiv.org/abs/2404.14367
Autor:
Fränken, Jan-Philipp, Zelikman, Eric, Rafailov, Rafael, Gandhi, Kanishk, Gerstenberg, Tobias, Goodman, Noah D.
When prompting a language model (LM), users often expect the model to adhere to a set of behavioral principles across diverse tasks, such as producing insightful content while avoiding harmful or biased language. Instilling such principles (i.e., a c
Externí odkaz:
http://arxiv.org/abs/2404.14313
Reinforcement Learning From Human Feedback (RLHF) has been a critical to the success of the latest generation of generative AI models. In response to the complex nature of the classical RLHF pipeline, direct alignment algorithms such as Direct Prefer
Externí odkaz:
http://arxiv.org/abs/2404.12358
Autor:
Gerstgrasser, Matthias, Schaeffer, Rylan, Dey, Apratim, Rafailov, Rafael, Sleight, Henry, Hughes, John, Korbak, Tomasz, Agrawal, Rajashree, Pai, Dhruv, Gromov, Andrey, Roberts, Daniel A., Yang, Diyi, Donoho, David L., Koyejo, Sanmi
The proliferation of generative models, combined with pretraining on web-scale data, raises a timely question: what happens when these models are trained on their own generated outputs? Recent investigations into model-data feedback loops proposed th
Externí odkaz:
http://arxiv.org/abs/2404.01413