Prati
Kianté Brantley
Kianté Brantley
Assistant Professor, Harvard University
Potvrđena adresa e-pošte na g.harvard.edu - Početna stranica
Naslov
Citirano
Citirano
Godina
Is reinforcement learning (not) for natural language processing?: Benchmarks, baselines, and building blocks for natural language policy optimization
R Ramamurthy, P Ammanabrolu, K Brantley, J Hessel, R Sifa, ...
The Eleventh International Conference on Learning Representations, 2023
230*2023
Non-monotonic sequential text generation
S Welleck, K Brantley, HD Iii, K Cho
International Conference on Machine Learning, 6716-6726, 2019
1382019
Disagreement-regularized imitation learning
K Brantley, W Sun, M Henaff
International Conference on Learning Representations, 2019
1202019
Reinforcement learning with convex constraints
S Miryoosefi, K Brantley, H Daume III, M Dudik, RE Schapire
Advances in neural information processing systems 32, 2019
1062019
Constrained episodic reinforcement learning in concave-convex and knapsack settings
K Brantley, M Dudik, T Lykouris, S Miryoosefi, M Simchowitz, A Slivkins, ...
Advances in Neural Information Processing Systems 33, 16315-16326, 2020
602020
Ldaexplore: Visualizing topic models generated using latent dirichlet allocation
A Ganesan, K Brantley, S Pan, J Chen
arXiv preprint arXiv:1507.06593, 2015
332015
Learning to Generate Better Than Your LLM
JD Chang, K Brantley, R Ramamurthy, D Misra, W Sun
arXiv preprint arXiv:2306.11816, 2023
322023
Active imitation learning with noisy guidance
K Brantley, A Sharaf, H Daumé III
arXiv preprint arXiv:2005.12801, 2020
232020
Dataset Reset Policy Optimization for RLHF
JD Chang, W Shan, O Oertell, K Brantley, D Misra, JD Lee, W Sun
arXiv preprint arXiv:2404.08495, 2024
192024
REBEL: Reinforcement Learning via Regressing Relative Rewards
Z Gao, JD Chang, W Zhan, O Oertell, G Swamy, K Brantley, T Joachims, ...
arXiv preprint arXiv:2404.16767, 2024
162024
Successor feature sets: Generalizing successor representations across policies
K Brantley, S Mehri, GJ Gordon
Proceedings of the AAAI Conference on Artificial Intelligence 35 (13), 11774 …, 2021
142021
Interactive text generation
F Faltings, M Galley, B Peng, K Brantley, W Cai, Y Zhang, J Gao, B Dolan
arXiv preprint arXiv:2303.00908, 2023
52023
Reviewer2: Optimizing Review Generation Through Prompt Generation
Z Gao, K Brantley, T Joachims
arXiv preprint arXiv:2402.10886, 2024
42024
The umd neural machine translation systems at wmt17 bandit learning task
A Sharaf, S Feng, K Nguyen, K Brantley, H Daumé III
arXiv preprint arXiv:1708.01318, 2017
42017
RL for Consistency Models: Faster Reward Guided Text-to-Image Generation
O Oertell, JD Chang, Y Zhang, K Brantley, W Sun
arXiv preprint arXiv:2404.03673, 2024
32024
Ranking with Long-Term Constraints
K Brantley, Z Fang, S Dean, T Joachims
Proceedings of the 17th ACM International Conference on Web Search and Data …, 2024
32024
Policy-Gradient Training of Language Models for Ranking
G Gao, JD Chang, C Cardie, K Brantley, T Joachim
arXiv preprint arXiv:2310.04407, 2023
32023
A Surprising Failure? Multimodal LLMs and the NLVR Challenge
A Wu, K Brantley, Y Artzi
arXiv preprint arXiv:2402.17793, 2024
22024
lilGym: Natural Language Visual Reasoning with Reinforcement Learning
A Wu, K Brantley, N Kojima, Y Artzi
arXiv preprint arXiv:2211.01994, 2022
22022
LLMs Are In-Context Reinforcement Learners
G Monea, A Bosselut, K Brantley, Y Artzi
arXiv preprint arXiv:2410.05362, 2024
12024
Sustav trenutno ne može provesti ovu radnju. Pokušajte ponovo kasnije.
Članci 1–20