15 citations · 18 across the 17 of their papers we have counts for
17 papers
HABIT: Human-Aware Behavior and Interaction Training Dataset for Robot Manipulation
Jaehwi Song, Suchae Jeong, Byeongguk Jeon +4
Large-scale demonstration datasets have been central to recent progress in general-purpose robot policies. However, existing datasets are collected in human-absent settings, and po…
Understanding and Enhancing Mamba-Transformer Hybrids for Memory Recall and Language Modeling
Hyunji Lee, Wenhao Yu, Hongming Zhang +4
Hybrid models that combine state space models (SSMs) with attention mechanisms have shown strong performance by leveraging the efficiency of SSMs and the high recall ability of att…
Instruction Tuning with and without Context: Behavioral Shifts and Downstream Impact
Hyunji Lee, Seunghyun Yoon, Yunjae Won +7
Instruction tuning is a widely used approach to improve the instruction-following ability of large language models (LLMs). Instruction-tuning datasets typically include a mixture o…
Differential Information Distribution: A Bayesian Perspective on Direct Preference Optimization
Yunjae Won, Hyunji Lee, Hyeonbin Hwang +1
Direct Preference Optimization (DPO) has been widely used for aligning language models with human preferences in a supervised manner. However, several key questions remain unresolv…
Generative Prompt Internalization
Haebin Shin, Lei Ji, Yeyun Gong +3
Prompts used in recent large language model based applications are often fixed and lengthy, leading to significant computational overhead. To address this challenge, we propose Gen…
Latent Action Pretraining from Videos
Seonghyeon Ye, Joel Jang, Byeongguk Jeon +13
We introduce Latent Action Pretraining for general Action models (LAPA), an unsupervised method for pretraining Vision-Language-Action (VLA) models without ground-truth robot actio…
Knowledge Entropy Decay during Language Model Pretraining Hinders New Knowledge Acquisition
Jiyeon Kim, Hyunji Lee, Hyowon Cho +6
In this work, we investigate how a model's tendency to broadly integrate its parametric knowledge evolves throughout pretraining, and how this behavior affects overall performance,…
RouterRetriever: Routing over a Mixture of Expert Embedding Models
Hyunji Lee, Luca Soldaini, Arman Cohan +2
Information retrieval methods often rely on a single embedding model trained on large, general-domain datasets like MSMARCO. While this approach can produce a retriever with reason…
Self-Explore: Enhancing Mathematical Reasoning in Language Models with Fine-grained Rewards
Hyeonbin Hwang, Doyoung Kim, Seungone Kim +2
Training on large amounts of rationales (i.e., CoT Fine-tuning) is effective at improving the reasoning capabilities of large language models (LLMs). However, acquiring human-autho…
Semiparametric Token-Sequence Co-Supervision
Hyunji Lee, Doyoung Kim, Jihoon Jun +4
In this work, we introduce a semiparametric token-sequence co-supervision training method. It trains a language model by simultaneously leveraging supervision from the traditional…
INSTRUCTIR: A Benchmark for Instruction Following of Information Retrieval Models
Hanseok Oh, Hyunji Lee, Seonghyeon Ye +4
Despite the critical need to align search targets with users' intention, retrievers often only prioritize query information without delving into the users' intended search context.…
Aligning Large Language Models by On-Policy Self-Judgment
Sangkyu Lee, Sungdong Kim, Ashkan Yousefpour +3
Existing approaches for aligning large language models with human preferences face a trade-off that requires a separate reward model (RM) for on-policy learning. In this paper, we…
Rethinking the Role of Proxy Rewards in Language Model Alignment
Sungdong Kim, Minjoon Seo
Learning from human feedback via proxy reward modeling has been studied to align Large Language Models (LLMs) with human values. However, achieving reliable training through that p…
LangBridge: Multilingual Reasoning Without Multilingual Supervision
Dongkeun Yoon, Joel Jang, Sungdong Kim +3
We introduce LangBridge, a zero-shot approach to adapt language models for multilingual reasoning tasks without multilingual supervision. LangBridge operates by bridging two models…
How Well Do Large Language Models Truly Ground?
Hyunji Lee, Sejune Joo, Chaeeun Kim +4
To reduce issues like hallucinations and lack of control in Large Language Models (LLMs), a common method is to generate responses by grounding on external contexts given as input,…
KTRL+F: Knowledge-Augmented In-Document Search
Hanseok Oh, Haebin Shin, Miyoung Ko +2
We introduce a new problem KTRL+F, a knowledge-augmented in-document search task that necessitates real-time identification of all semantic targets within a document with the aware…
Prometheus: Inducing Fine-grained Evaluation Capability in Language Models
Seungone Kim, Jamin Shin, Yejin Cho +8
Recently, using a powerful proprietary Large Language Model (LLM) (e.g., GPT-4) as an evaluator for long-form responses has become the de facto standard. However, for practitioners…