Jaesik Choi

Layer-wise Learning of Stochastic Neural Networks with Information Bottleneck

2017 · arXiv (Cornell University)

Information Bottleneck (IB) is a generalization of rate-distortion theory that naturally incorporates compression and relevance trade-offs for learning. Though the original IB has been extensively studied, there has not been much understanding of multiple bottlenecks …

Explaining the Decisions of Deep Policy Networks for Robotic Manipulations

2021 · 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

Deep policy networks enable robots to learn behaviors to solve various real-world complex tasks in an end-to-end fashion. However, they lack transparency to provide the reasons of actions. Thus, such a black-box model often results …

Refining Diffusion Planner for Reliable Behavior Synthesis by Automatic Detection of Infeasible Plans

2023 · arXiv (Cornell University)

Diffusion-based planning has shown promising results in long-horizon, sparse-reward tasks by training trajectory diffusion models and conditioning the sampled trajectories using auxiliary guidance functions. However, due to their nature as generative models, diffusion models are …

Memorizing Documents with Guidance in Large Language Models

2024 · arXiv (Cornell University)

Training data plays a pivotal role in AI models. Large language models (LLMs) are trained with massive amounts of documents, and their parameters hold document-related contents. Recently, several studies identified content-specific locations in LLMs by …