274 citations · 403 across the 26 of their papers we have counts for
26 papers
LLMs Get Lost in Evolving User Intent
Jihoon Tack, Philippe Laban, Jennifer Neville
As LLMs become more capable, they are increasingly deployed as collaborative agents, taking on user-delegated tasks through iterative interaction. Yet genuine interaction is inhere…
Persona-Pruner: Sculpting Lightweight Models for Role-Playing
Jinsu Kim, Jihoon Tack, Noah Lee +1
Language Models (LMs) have shown remarkable potential as role-playing chatbots, delivering consistent, stylized interactions when given a specification of a character or user perso…
Beyond Correctness: Learning Robust Reasoning via Transfer
Hyunseok Lee, Soheil Abbasloo, Jihoon Tack +1
Reinforcement Learning with Verifiable Rewards (RLVR) has recently strengthened LLM reasoning, but its focus on final answer correctness leaves a critical gap: it does not ensure t…
Scalable and Robust LLM Unlearning by Correcting Responses with Retrieved Exclusions
Junbeom Kim, Kyuyoung Kim, Jihoon Tack +2
Language models trained on web-scale corpora risk memorizing and exposing sensitive information, prompting the need for effective machine unlearning. Prior methods mainly focus on…
Think Clearly: Improving Reasoning via Redundant Token Pruning
Daewon Choi, Jimin Lee, Jihoon Tack +7
Recent large language models have shown promising capabilities in long-form reasoning, following structured chains of thought before arriving at a final answer. However, we observe…
Mamba Drafters for Speculative Decoding
Daewon Choi, Seunghyuk Oh, Saket Dingliwal +9
Speculative decoding has emerged as a promising approach to accelerating large language model (LLM) generation using a fast drafter while maintaining alignment with the target mode…
Sparsified State-Space Models are Efficient Highway Networks
Woomin Song, Jihoon Tack, Sangwoo Mo +2
State-space models (SSMs) offer a promising architecture for sequence modeling, providing an alternative to Transformers by replacing expensive self-attention with linear recurrenc…
ReGUIDE: Data Efficient GUI Grounding via Spatial Reasoning and Search
Hyunseok Lee, Jeonghoon Kim, Beomjun Kim +7
Recent advances in Multimodal Large Language Models (MLLMs) have enabled autonomous agents to interact with computers via Graphical User Interfaces (GUIs), where accurately localiz…
Learning to Contextualize Web Pages for Enhanced Decision Making by LLM Agents
Dongjun Lee, Juyong Lee, Kyuyoung Kim +4
Recent advances in large language models (LLMs) have led to a growing interest in developing LLM-based agents for automating web tasks. However, these agents often struggle with ev…
LLM Pretraining with Continuous Concepts
Jihoon Tack, Jack Lanchantin, Jane Yu +7
Next token prediction has been the standard training objective used in large language model pretraining. Representations are learned as a result of optimizing for token-level perpl…
ReVISE: Learning to Refine at Test-Time via Intrinsic Self-Verification
Hyunseok Lee, Seunghyuk Oh, Jaehyung Kim +2
Self-awareness, i.e., the ability to assess and correct one's own generation, is a fundamental aspect of human intelligence, making its replication in large language models (LLMs)…
Tabular Transfer Learning via Prompting LLMs
Jaehyun Nam, Woomin Song, Seong Hyeon Park +5
Learning with a limited number of labeled data is a central problem in real-world applications of machine learning, as it is often expensive to obtain annotations. To deal with the…
Optimized Feature Generation for Tabular Data via LLMs with Decision Tree Reasoning
Jaehyun Nam, Kyuyoung Kim, Seunghyuk Oh +3
In tabular prediction tasks, tree-based models combined with automated feature engineering methods often outperform deep learning approaches that rely on learned representations. W…
ReMoDetect: Reward Models Recognize Aligned LLM's Generations
Hyunseok Lee, Jihoon Tack, Jinwoo Shin
The remarkable capabilities and easy accessibility of large language models (LLMs) have significantly increased societal risks (e.g., fake news generation), necessitating the devel…
Unleashing the Power of Meta-tuning for Few-shot Generalization Through Sparse Interpolated Experts
Shengzhuang Chen, Jihoon Tack, Yunqiao Yang +3
Recent successes suggest that parameter-efficient fine-tuning of foundation models as the state-of-the-art method for transfer learning in vision, replacing the rich literature of…
Online Adaptation of Language Models with a Memory of Amortized Contexts
Jihoon Tack, Jaehyung Kim, Eric Mitchell +3
Due to the rapid generation and dissemination of information, large language models (LLMs) quickly run out of date despite enormous development costs. To address the crucial need t…
Modality-Agnostic Self-Supervised Learning with Meta-Learned Masked Auto-Encoder
Huiwon Jang, Jihoon Tack, Daewon Choi +2
Despite its practical importance across a wide range of modalities, recent advances in self-supervised learning (SSL) have been primarily focused on a few well-curated domains, e.g…
STUNT: Few-shot Tabular Learning with Self-generated Tasks from Unlabeled Tables
Jaehyun Nam, Jihoon Tack, Kyungmin Lee +2
Learning with few labeled tabular samples is often an essential requirement for industrial machine learning applications as varieties of tabular data suffer from high annotation co…
Learning Large-scale Neural Fields via Context Pruned Meta-Learning
Jihoon Tack, Subin Kim, Sihyun Yu +3
We introduce an efficient optimization-based meta-learning technique for large-scale neural field training by realizing significant memory savings through automated online context…
Modality-Agnostic Variational Compression of Implicit Neural Representations
Jonathan Richard Schwarz, Jihoon Tack, Yee Whye Teh +2
We introduce a modality-agnostic neural compression algorithm based on a functional view of data and parameterised as an Implicit Neural Representation (INR). Bridging the gap betw…
Meta-Learning with Self-Improving Momentum Target
Jihoon Tack, Jongjin Park, Hankook Lee +2
The idea of using a separately trained target model (or teacher) to improve the performance of the student model has been increasingly popular in various machine learning domains,…
Generating Videos with Dynamics-aware Implicit Generative Adversarial Networks
Sihyun Yu, Jihoon Tack, Sangwoo Mo +4
In the deep learning era, long video generation of high-quality still remains challenging due to the spatio-temporal complexity and continuity of videos. Existing prior works have…
Meta-Learning Sparse Implicit Neural Representations
Jaeho Lee, Jihoon Tack, Namhoon Lee +1
Implicit neural representations are a promising new avenue of representing general signals by learning a continuous function that, parameterized as a neural network, maps the domai…
Consistency Regularization for Adversarial Robustness
Jihoon Tack, Sihyun Yu, Jongheon Jeong +3
Adversarial training (AT) is currently one of the most successful methods to obtain the adversarial robustness of deep neural networks. However, the phenomenon of robust overfittin…