Kianté Brantley

Computer Science · Physical Sciences

8h-index279citations41works0.52yr avg
OpenAlex↗ORCID↗Google Scholar↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Topic Modeling(12), Reinforcement Learning in Robotics(12), Multimodal Machine Learning Applications(11), Natural Language Processing Techniques(10), Advanced Bandit Algorithms Research(8)

Publications41 total

LLMs Can Learn to Reason Via Off-Policy RL
ArXiv.org·2026Open Access
LLMs Can Learn to Reason Via Off-Policy RL
arXiv (Cornell University)·2026Open Access
Breadcrumbs Reasoning: Memory-Efficient Reasoning with Compression Beacons
arXiv (Cornell University)·2025Open Access
Expressive Value Learning for Scalable Offline Reinforcement Learning
arXiv (Cornell University)·2025Open Access
Scaling Offline RL via Efficient and Expressive Shortcut Models
arXiv (Cornell University)·2025Open Access
Accelerating RL for LLM Reasoning with Optimal Advantage Regression
arXiv (Cornell University)·2025Open Access
$Q\sharp$: Provably Optimal Distributional RL for LLM Post-Training
arXiv (Cornell University)·2025Open Access
Diffusing States and Matching Scores: A New Framework for Imitation Learning
arXiv (Cornell University)·2024· 1 citedOpen Access
LLMs Are In-Context Bandit Reinforcement Learners
arXiv (Cornell University)·2024Open Access
Regressing the Relative Future: Efficient Policy Optimization for Multi-turn RLHF
arXiv (Cornell University)·2024Open Access
REBEL: Reinforcement Learning via Regressing Relative Rewards
arXiv (Cornell University)·2024· 2 citedOpen Access
Dataset Reset Policy Optimization for RLHF
arXiv (Cornell University)·2024· 1 citedOpen Access
Adversarial Imitation Learning via Boosting
arXiv (Cornell University)·2024Open Access
RL for Consistency Models: Faster Reward Guided Text-to-Image Generation
arXiv (Cornell University)·2024Open Access
Ranking with Long-Term Constraints
2024· 1 citedOpen Access
Reviewer2: Optimizing Review Generation Through Prompt Generation
arXiv (Cornell University)·2024· 3 citedOpen Access
REBEL: Reinforcement Learning via Regressing Relative Rewards
2024
Policy-Gradient Training of Language Models for Ranking
arXiv (Cornell University)·2023Open Access
lilGym: Natural Language Visual Reasoning with Reinforcement Learning, model files
Zenodo (CERN European Organization for Nuclear Research)·2023Open Access
lilGym: Natural Language Visual Reasoning with Reinforcement Learning, model files
Zenodo (CERN European Organization for Nuclear Research)·2023Open Access
page 1 of 3Next →

Frequent Co-authors

Jonathan Chang(9), Owen Oertell(7), Hal Daumé(6), Yoav Artzi(6), Wen Sun(5), Thorsten Joachims(5), Jason D. Lee(5), Sobhan Miryoosefi(4), Miroslav Dudı́k(4), Zhaolin Gao(4), Gokul Swamy(4), Wen Sun(4), Anne Wu(4), Noriyuki Kojima(4), Soroush Mehri(3), Wenhao Zhan(3), Sean Welleck(2), Kyunghyun Cho(2), Rajkumar Ramamurthy(2), Robert E. Schapire(2)