Scholar
Kianté Brantley
Google Scholar ID: 8S5AOggAAAAJ
Assistant Professor, Harvard University
machine learning
natural language processing
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
1,101
H-index
13
i10-index
14
Publications
20
Co-authors
20
list available
Contact
Email
kdbrantley@g.harvard.edu
CV
Open ↗
Twitter
Open ↗
GitHub
Open ↗
LinkedIn
Open ↗
Publications
9 items
LLMs Can Learn to Reason Via Off-Policy RL
2026
Cited
0
Scaling Reward Modeling without Human Supervision
2026
Cited
0
The Emergence of Complex Behavior in Large-Scale Ecological Environments
2025
Cited
0
Breadcrumbs Reasoning: Memory-Efficient Reasoning with Compression Beacons
2025
Cited
0
Scaling Offline RL via Efficient and Expressive Shortcut Models
2025
Cited
0
$Qsharp$: Provably Optimal Distributional RL for LLM Post-Training
2025
Cited
0
Diffusing States and Matching Scores: A New Framework for Imitation Learning
arXiv.org · 2024
Cited
2
LLMs Are In-Context Bandit Reinforcement Learners
2024
Cited
2
Load more
Resume (English only)
Academic Achievements
2025 preprint: 'Scaling Offline RL via Efficient and Expressive Shortcut Models'
2025 preprint: 'Accelerating RL for LLM Reasoning with Optimal Advantage Regression'
2025 preprint: 'Value-Guided Search for Efficient Chain-of-Thought Reasoning'
2025 preprint: 'Q#: Provably Optimal Distributional RL for LLM Post-Training'
Gave multiple talks in 2025 at INFORMS, CCC Computing Futures Symposium, Google, and Berkeley Simons Institute
Miscellany
Email: kdbrantley@g.harvard.edu
Twitter: @xkianteb
GitHub: @xkianteb
LinkedIn: kiate
Office: 150 Western Av., Room 6.141, Allston MA 02134
Pronouns: He/Him/His
Co-authors
20 total
Wen Sun
Assistant Professor, Cornell University
Hal Daumé III
Associate Professor of Computer Science, University of Maryland
Jonathan D. Chang
Research Scientist, Databricks Mosaic
Prithviraj Ammanabrolu
Assistant Professor, University of California, San Diego
Gokul Swamy
PhD Candidate, Carnegie Mellon University
Thorsten Joachims
Professor of Computer Science, Cornell University
Miroslav Dudik
Microsoft Research
Dipendra Misra
Staff Research Scientist, Mosaic Team, Databricks
×
Welcome back
Sign in to Agora
Welcome back! Please sign in to continue.
Email address
Password
Forgot password?
Continue
Do not have an account?
Sign up