Supawit Chockchowwat — accepted AI-conference papers

2026

LazyAttention: Efficient Retrieval-Augmented Generation with Deferred Positional Encoding

Haocheng Xia, Mihir Pamnani, Hanxi Fang, Supawit Chockchowwat, Yongjoo Park

ICML 2026poster

Key-value (KV) caching accelerates inference of large language models (LLMs) by reusing past computations for generated tokens. Its importance becomes even greater in long-context applications such as retrieval-augmented generation (RAG) and in-context learning (ICL). However, conventional KV cachin…

Cited by 0 Source ↗Scholar ↗

2020

Hypothesis-Driven Skill Discovery for Hierarchical Deep Reinforcement Learning

Caleb Chuck, Supawit Chockchowwat, Scott Niekum

IROS 2020poster

Deep reinforcement learning (DRL) is capable of learning high-performing policies on a variety of complex high-dimensional tasks, ranging from video games to robotic manipulation. However, standard DRL methods often suffer from poor sample efficiency, partially because they aim to be entirely proble…

Cited by 9 Source ↗Scholar ↗