10 citations · 15 across the 6 of their papers we have counts for
6 papers
Clip-Low Increases Entropy and Clip-High Decreases Entropy in Reinforcement Learning of Large Language Models
Jaesung R. Park, Junsu Kim, Gyeongman Kim +4
Reinforcement learning with verifiable rewards (RLVR) has recently emerged as the leading approach for enhancing the reasoning capabilities of large language models (LLMs). However…
Beyond RLHF: A Unified Theoretical Framework of Alignment
Jihun Yun, Juno Kim, Jongho Park +4
Alignment via reinforcement learning from human feedback (RLHF) has become the dominant paradigm for controlling the quality of outputs from large language models (LLMs). However,…
Lexico: Extreme KV Cache Compression via Sparse Coding over Universal Dictionaries
Junhyuck Kim, Jongho Park, Jaewoong Cho +1
We introduce Lexico, a novel KV cache compression method that leverages sparse coding with a universal dictionary. Our key finding is that key-value cache in modern LLMs can be acc…
Task Diversity Shortens the ICL Plateau
Jaeyeon Kim, Sehyun Kwon, Joo Young Choi +4
In-context learning (ICL) describes a language model's ability to generate outputs based on a set of input demonstrations and a subsequent query. To understand this remarkable capa…
Can Mamba Learn How to Learn? A Comparative Study on In-Context Learning Tasks
Jongho Park, Jaeseung Park, Zheyang Xiong +5
State-space models (SSMs), such as Mamba (Gu & Dao, 2023), have been proposed as alternatives to Transformer networks in language modeling, by incorporating gating, convolutions, a…
Image Clustering Conditioned on Text Criteria
Sehyun Kwon, Jaeseung Park, Minkyu Kim +3
Classical clustering methods do not provide users with direct control of the clustering results, and the clustering results may not be consistent with the relevant criterion that a…