Explore Research Products in the PAR
It may take a few hours for recently added research products to appear in PAR search results.


  • Home
  • Search Results
  • Page 1 of 4

Search for: All records

Creators/Authors contains: "Lee, Kangwook"

Note: When clicking on a Digital Object Identifier (DOI) number, you will be taken to an external site maintained by the publisher. Some full text articles may not yet be available without a charge during the embargo (administrative interval).
What is a DOI Number?

Some links on this page may take you to non-federal websites. Their policies may differ from this site.

  1. ; ; (, Proceedings of Machine Learning Research (PMLR))
    The paper provides a theoretical analysis of how fine-tuning affects in-context learning in linear attention models, characterizing conditions under which fine-tuning degrades or preserves few-shot performance. 
    more » « less
    Free, publicly-accessible full text available May 31, 2027
  2. ; ; ; (, arXiv)
    This posted content studies fine-tuning a vision-language model for fracture-surface morphology recognition in materials characterization. 
    more » « less
    Free, publicly-accessible full text available May 8, 2027
  3. ; ; ; ; (, Proceedings of Machine Learning Research (PMLR))
    This paper analyzes how LLM-as-a-judge evaluations should be reported and provides guidance for correct, reliable evaluation reporting. 
    more » « less
    Free, publicly-accessible full text available May 31, 2027
  4. ; ; (, ICLR 2026 Workshop on Agentic AI in the Wild)
    This paper introduces TAPE, a tool-guided framework for adaptive planning and constrained execution in language model agents. 
    more » « less
    Free, publicly-accessible full text available February 24, 2027
  5. ; ; ; ; ; (, ICML 2026 AIWILD Workshop)
    This paper presents Meta-Harness, an approach for end-to-end optimization of model harnesses. 
    more » « less
    Free, publicly-accessible full text available March 30, 2027
  6. ; ; ; ; ; (, arXiv)
    This posted content introduces controllable environments and metrics for measuring exploration and exploitation errors in language model agents. 
    more » « less
    Free, publicly-accessible full text available April 14, 2027
  7. ; ; ; ; ; ; ; (, Transactions on Machine Learning Research)
    This article studies how transformer-based models navigate unknown search spaces using bandit feedback. 
    more » « less
    Free, publicly-accessible full text available March 25, 2027
  8. ; ; ; ; ; (, International Conference on Learning Representations)
    This paper develops draft-based approximate inference methods for large language models. 
    more » « less
    Free, publicly-accessible full text available February 2, 2027
  9. ; ; ; ; ; ; ; ; (, Association for Computational Linguistics)
    This paper proposes TABED, a test-time adaptive ensemble drafting approach for robust speculative decoding in large vision-language models. 
    more » « less
    Free, publicly-accessible full text available January 28, 2027
  10. ; ; ; ; ; ; ; ; ; ; et al (, International Conference on Learning Representations)
    This paper presents Orak, a benchmark for training and evaluating large language model agents across diverse video games. 
    more » « less
    Free, publicly-accessible full text available April 14, 2027