Get started
Author

David Brandfonbrener

Observed name: Brandfonbrener, David
OpenAlex ID: A5037978510
Offline RL Without Off-Policy Evaluation
2021 · Brandfonbrener, David, Whitney, William F., et al. · arXiv (Cornell University) · 38
PDF
PsychRNN: An Accessible and Flexible Python Package for Training Recurrent Neural Network Models on Cognitive Tasks
2020 · Daniel B. Ehrlich, Jasmine T. Stone, et al. · eNeuro · 27
PDF
Don't Change the Algorithm, Change the Data: Exploratory Data for Offline Reinforcement Learning
2022 · Yarats, Denis, Brandfonbrener, David, et al. · arXiv (Cornell University) · 22
PDF
Frequentist Regret Bounds for Randomized Least-Squares Value Iteration
2019 · Zanette, Andrea, Brandfonbrener, David, et al. · arXiv (Cornell University) · 18
PDF
When Does Return-Conditioned Supervised Learning Work for Offline Reinforcement Learning?
2022 · David Brandfonbrener, Alberto Bietti, et al. · neural information processing systems · 14
PDF
Evaluating representations by the complexity of learning low-loss predictors
2020 · Whitney, William F., Song, Min Jae, et al. · arXiv (Cornell University) · 11
PDF
Geometric Insights into the Convergence of Nonlinear TD Learning
2019 · Brandfonbrener, David, Bruna, Joan · arXiv (Cornell University) · 9
PDF
Visual Backtracking Teleoperation: A Data Collection Protocol for Offline Image-Based Reinforcement Learning
2023 · David Brandfonbrener, Stephen Tu, et al. · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · 4
PDF
Inverse Dynamics Pretraining Learns Good Representations for Multitask Imitation
2023 · David Brandfonbrener, Ofir Nachum, et al. · neural information processing systems · 4
PDF
On the Expected Dynamics of Nonlinear TD Learning.
2019 · David Brandfonbrener, Joan Bruna · arXiv (Cornell University) · 4
Deconstructing What Makes a Good Optimizer for Language Models
2024 · Zhao, Rosie, Morwani, Depen, et al. · arXiv (Cornell University) · 3
PDF
Repeat After Me: Transformers are Better than State Space Models at Copying
2024 · Jelassi, Samy, Brandfonbrener, David, et al. · arXiv (Cornell University) · 3
PDF
Two-Vertex Generators of Jacobians of Graphs
2018 · David Brandfonbrener, Pat Devlin, et al. · The Electronic Journal of Combinatorics · 3
SOAP: Improving and Stabilizing Shampoo using Adam
2024 · Vyas, Nikhil, Morwani, Depen, et al. · arXiv (Cornell University) · 2
PDF
CoLoR-Filter: Conditional Loss Reduction Filtering for Targeted Language Model Pre-training
2024 · David Brandfonbrener, Hanlin Zhang, et al. · neural information processing systems · 2
PDF
Incorporating Explicit Uncertainty Estimates into Deep Offline Reinforcement Learning
2022 · Brandfonbrener, David, Combes, Remi Tachet des, et al. · arXiv (Cornell University) · 2
PDF
Quantile Filtered Imitation Learning
2021 · Brandfonbrener, David, Whitney, William F., et al. · arXiv (Cornell University) · 2
PDF
The Art of Scaling Reinforcement Learning Compute for LLMs
2025 · Khatri, Devvrit, Madaan, Lovish, et al. · arXiv (Cornell University) · 1
PDF
Mixture of Parrots: Experts improve memorization more than reasoning
2024 · Jelassi, Samy, Mohri, Clara, et al. · arXiv (Cornell University) · 1
PDF
Offline Contextual Bandits with Overparameterized Models
2020 · Brandfonbrener, David, Whitney, William F., et al. · arXiv (Cornell University) · 1
PDF
Interleaved Head Attention
2026 · Duvvuri, Sai Surya, Ekbote, Chanakya, et al. · arXiv (Cornell University)
PDF
GQ-VAE: A gated quantized VAE for learning variable length tokens
2025 · Datta, Theo, Huang, Kayla, et al. · arXiv (Cornell University)
PDF
Let's (not) just put things in Context: Test-Time Training for Long-Context LLMs
2025 · Bansal, Rachit, Zhang, Aston, et al. · arXiv (Cornell University)
PDF
Generalized Parallel Scaling with Interdependent Generations
2025 · Dong, Harry, Brandfonbrener, David, et al. · arXiv (Cornell University)
PDF
Loss-to-Loss Prediction: Scaling Laws for All Datasets
2024 · Brandfonbrener, David, Anand, Nikhil, et al. · arXiv (Cornell University)
PDF
Works count: 32
Citation count: 171
H-index: 7
I10-index: 6
Year
Topic
Type