Yisong Yue

A Decision Tree Framework for Spatiotemporal Sequence Prediction

2015

We study the problem of learning to predict a spatiotemporal output sequence given an input sequence. In contrast to conventional sequence prediction problems such as part-of-speech tagging (where output sequences are selected using a relatively …

Empirical Study of Off-Policy Policy Evaluation for Reinforcement Learning

2019 · arXiv (Cornell University)

We offer an experimental benchmark and empirical study for off-policy policy evaluation (OPE) in reinforcement learning, which is a key problem in many safety critical applications. Given the increasing interest in deploying learning-based methods, there …

Active Learning under Label Shift

2021 · CaltechAUTHORS (California Institute of Technology)

We address the problem of active learning under label shift: when the class proportions of source and target domains differ. We introduce a "medial distribution" to incorporate a tradeoff between importance weighting and class-balanced sampling …

Strategist: Self-improvement of LLM Decision Making via Bi-Level Tree Search

2024 · arXiv (Cornell University)

Traditional reinforcement learning and planning typically requires vast amounts of data and training to develop effective policies. In contrast, large language models (LLMs) exhibit strong generalization and zero-shot capabilities, but struggle with tasks that require …

DISC: Dynamic Decomposition Improves LLM Inference Scaling

2025 · arXiv (Cornell University)

Inference scaling methods for LLMs often rely on decomposing problems into steps (or groups of tokens), followed by sampling and selecting the best next steps. However, these steps and their sizes are often predetermined or …