291 citations · 957 across the 23 of their papers we have counts for
24 papers
NeuroLens: Learning Latent Embeddings of Neural Semantics from Chronic Recordings
Hanrui Lyu, Baiyuan Chen, Tianshu Tan +8
Understanding how neural activity represents higher-order cognition and how these representations evolve over time has long been a central pursuit in neuroscience. However, current…
Temporal Leakage in LLM Backtesting: Measurement, Validation, and Adjusted Scores
Zeyu Zhang, Bradly C. Stadie
The standard check for contamination in LLM backtests is simple: compare scores before and after the training cutoff. We show this check is uninformative. Four flagship models fail…
TEMPO: Temporal Enforcement via Mode-Separated Policy Optimization for Trustworthy LLM Backtesting
Zeyu Zhang, Bradly C. Stadie
Backtesting large language models on historical events requires reasoning exclusively from information available before a specified cutoff date. Yet models routinely leak post-cuto…
Evolutionary System Prompt Learning for Reinforcement Learning in LLMs
Lunjun Zhang, Ryan Chen, Bradly C. Stadie
Building agentic systems that can autonomously self-improve from experience is a longstanding goal of AI. Large language models (LLMs) today primarily self-improve via two mechanis…
All Leaks Count, Some Count More: Interpretable Temporal Contamination Detection and Mitigation in LLM Backtesting
Zeyu Zhang, Ryan Chen, Bradly C. Stadie
Backtesting LLMs on resolved events assumes models reason only from pre-cutoff knowledge, yet pretrained models inevitably leak post-cutoff knowledge. We introduce a claim-level ev…
AIA Forecaster: Technical Report
Rohan Alur, Bradly C. Stadie, Daniel Kang +11
This technical report describes the AIA Forecaster, a Large Language Model (LLM)-based system for judgmental forecasting using unstructured data. The AIA Forecaster approach combin…
D2 Actor Critic: Diffusion Actor Meets Distributional Critic
Lunjun Zhang, Shuo Han, Hanrui Lyu +1
We introduce D2AC, a new model-free reinforcement learning (RL) algorithm designed to train expressive diffusion policies online effectively. At its core is a policy improvement ob…
Of Mice and Machines: A Comparison of Learning Between Real World Mice and RL Agents
Shuo Han, German Espinosa, Junda Huang +3
Recent advances in reinforcement learning (RL) have demonstrated impressive capabilities in complex decision-making tasks. This progress raises a natural question: how do these art…
LAMP: Extracting Local Decision Surfaces From Large Language Models
Ryan Chen, Youngmin Ko, Zeyu Zhang +5
We introduce LAMP (Local Attribution Mapping Probe), a method that shines light onto a black-box language model's decision surface and studies how reliably a model maps its stated…
Wonderful Team: Zero-Shot Physical Task Planning with Visual LLMs
Zidan Wang, Rui Shen, Bradly Stadie
We introduce Wonderful Team, a multi-agent Vision Large Language Model (VLLM) framework for executing high-level robotic planning in a zero-shot regime. In our context, zero-shot h…
Cold Diffusion on the Replay Buffer: Learning to Plan from Known Good States
Zidan Wang, Takeru Oba, Takuma Yoneda +3
Learning from demonstrations (LfD) has successfully trained robots to exhibit remarkable generalization capabilities. However, many powerful imitation techniques do not prioritize…
To the Noise and Back: Diffusion for Shared Autonomy
Takuma Yoneda, Luzhe Sun, Ge Yang +2
Shared autonomy is an operational concept in which a user and an autonomous agent collaboratively control a robotic system. It provides a number of advantages over the extremes of…
Understanding Hindsight Goal Relabeling from a Divergence Minimization Perspective
Lunjun Zhang, Bradly C. Stadie
Hindsight goal relabeling has become a foundational technique in multi-goal reinforcement learning (RL). The essential idea is that any trajectory can be seen as a sub-optimal demo…
Invariance Through Latent Alignment
Takuma Yoneda, Ge Yang, Matthew R. Walter +1
A robot's deployment environment often involves perceptual changes that differ from what it has experienced during training. Standard practices such as data augmentation attempt to…
World Model as a Graph: Learning Latent Landmarks for Planning
Lunjun Zhang, Ge Yang, Bradly C. Stadie
Planning - the ability to analyze the structure of a problem in the large and decompose it into interrelated subproblems - is a hallmark of human intelligence. While deep reinforce…
Maximum Entropy Gain Exploration for Long Horizon Multi-goal Reinforcement Learning
Silviu Pitis, Harris Chan, Stephen Zhao +2
What goals should a multi-goal reinforcement learning agent pursue during training in long-horizon tasks? When the desired (test time) goal distribution is too distant to offer a u…
One-Shot Pruning of Recurrent Neural Networks by Jacobian Spectrum Evaluation
Matthew Shunshi Zhang, Bradly Stadie
Recent advances in the sparse neural network literature have made it possible to prune many large feed forward and convolutional networks with only a small quantity of data. Yet, t…
Transfer Learning for Estimating Causal Effects using Neural Networks
Sören R. Künzel, Bradly C. Stadie, Nikita Vemuri +3
We develop new algorithms for estimating heterogeneous treatment effects, combining recent developments in transfer learning for neural networks with insights from the causal infer…
Simulating the stochastic dynamics and cascade failure of power networks
Charles Matthews, Bradly Stadie, Jonathan Weare +2
For large-scale power networks, the failure of particular transmission lines can offload power to other lines and cause self-protection trips to activate, instigating a cascade of…
Some Considerations on Learning to Explore via Meta-Reinforcement Learning
Bradly C. Stadie, Ge Yang, Rein Houthooft +5
We consider the problem of exploration in meta reinforcement learning. Two new meta reinforcement learning algorithms are suggested: E-MAML and E-. Results are present…
Evolved Policy Gradients
Rein Houthooft, Richard Y. Chen, Phillip Isola +4
We propose a metalearning approach for learning gradient-based reinforcement learning (RL) algorithms. The idea is to evolve a differentiable loss function, such that an agent, whi…
One-Shot Imitation Learning
Yan Duan, Marcin Andrychowicz, Bradly C. Stadie +5
Imitation learning has been commonly applied to solve different tasks in isolation. This usually requires either careful feature engineering, or a significant number of samples. Th…
Third-Person Imitation Learning
Bradly C. Stadie, Pieter Abbeel, Ilya Sutskever
Reinforcement learning (RL) makes it possible to train agents capable of achieving sophisticated goals in complex and uncertain environments. A key difficulty in reinforcement lear…
Incentivizing Exploration In Reinforcement Learning With Deep Predictive Models
Bradly C. Stadie, Sergey Levine, Pieter Abbeel
Achieving efficient and scalable exploration in complex domains poses a major challenge in reinforcement learning. While Bayesian and PAC-MDP approaches to the exploration problem…