N. Kwak

Fractional Power-of-Two Quantization for Efficient and Effective Multiplier-Free LLM Inference

Sunghyun Wee, Geunjae Choi, Hyeonjin Kim +2

Large Language Models (LLMs) demand efficient inference, where the multiply-accumulate (MAC) operations in linear projections dominate compute and energy cost. Post-training quanti…

Discriminative Score Function: Turning Pretrained Models into Functional Generative Priors

Junhoo Lee, Hyeonjin Kim, Sangbum Han +1

Discriminative models are trained with task-specific objectives such as classification, detection, or representation learning, yet their practical utility depends on generalizing b…

3DROID: A Renderable 3D Gaussian Dataset with Measured Per-Scene Reliability

Wonguen Cho, Junhoo Lee, Nojun Kwak

Robot manipulation models primarily reason from 2D observations while acting in the 3D physical world. To bridge this gap, recent work has augmented robot data with geometric prior…

Bootstrapping Video Interaction Generation with Synthetic State Transitions

Jiho Jang, Jinyoung Kim, Nojun Kwak +2

While recent video generative models can synthesize high-fidelity videos, they struggle to portray plausible physical interactions and the resulting state transitions, a critical b…

Efficient Task Adaptation in Large Language Models: A Survey of Weight-Based, Prompt-Based, and Embedding-Based Adaptations

Jungwon Park, Changin Choi, Jimyeong Kim +2

As large language models are increasingly deployed across diverse downstream tasks, efficient task adaptation has emerged as a central challenge. In response, a wide range of task…

$μ^{2}$ -Bench: A Multilingual Machine Unlearning Benchmark

Kyomin Hwang, Hyeonjin Kim, Hyunho Lee +3

Undesired information such as harmful content and private data propagates through Multilingual Large Language Models (LLMs) via direct training and indirect cross-linguistic spread…

MoARa: Module-Aware Rank Allocation and Structure-Preserving Decomposition for Low-Rank LLM Pre-training

Keunyoung Kim, Nojun Kwak

Low-rank gradient projection reduces the optimizer-state memory cost of large language model (LLM) pretraining, but the steps and wall-clock time needed to reach a target quality r…

Zero-Shot Quantization for Object Detectors using Off-the-Shelf Generative Models

Hyunho Lee, Kyomin Hwang, Hyeonjin Kim +3

With an increasing number of Object Detection (OD) models being deployed on edge devices, Zero-Shot Quantization for OD (ZSQ-OD) aims to quantize these models when access to the or…

Team MKC at CLPsych 2026: Capturing and Characterizing Mental Health Changes through Social Media Timeline Dynamics

Kyomin Hwang, Hyeonjin Kim, Hyunho Lee +1

Recent advances in Large Language Models (LLMs) have motivated their adoption across a wide range of domains, including Artificial Intelligence (AI) for mental health. Given the gr…

ReSpinQuant: Efficient Layer-Wise LLM Quantization via Subspace Residual Rotation Approximation

Suyoung Kim, Sunghyun Wee, Hyeonjin Kim +3

Rotation-based Post-Training Quantization (PTQ) has emerged as a promising solution for mitigating activation outliers in the quantization of Large Language Models (LLMs). Global r…

Knowledge Beyond Language: Bridging the Gap in Multilingual Machine Unlearning Evaluation

Kyomin Hwang, Hyeonjin Kim, Sangyeon Cho +1

While LLMs are increasingly used in commercial services, they pose privacy risks such as leakage of sensitive personally identifiable information (PII). For LLMs trained on multili…

Toward Structural Multimodal Representations: Specialization, Selection, and Sparsification via Mixture-of-Experts

Hahyeon Choi, Nojun Kwak

We propose S3 (Specialization, Selection, Sparsification), a framework that rethinks multimodal learning through a structural perspective. Instead of encoding all signals into a fi…

When Confidence Misleads: Suffix Anchoring and Anchor-Proximity Confidence Modulation for Diffusion Language Models

Jungwon Park, Jimyeong Kim, Jungmin Ko +2

Diffusion language models generate text by iteratively selecting and denoising masked positions, making position selection a central inference-time decision. Most training-free met…

From Local to Global to Mechanistic: An iERF-Centered Unified Framework for Interpreting Vision Models

Yearim Kim, Sangyu Han, Nojun Kwak

Modern vision models achieve remarkable accuracy, but explaining where evidence arises, what the model encodes, and how internal computations assemble that evidence remains fragmen…

Retrieval-Augmented Generation Based Nurse Observation Extraction

Kyomin Hwang, Nojun Kwak

Recent advancements in Large Language Models (LLMs) have played a significant role in reducing human workload across various domains, a trend that is increasingly extending into th…

cs.CR2026

CSF: Black-box Fingerprinting via Compositional Semantics for Text-to-Image Models

Junhoo Lee, Mijin Koo, Nojun Kwak

Text-to-image models are commercially valuable assets often distributed under restrictive licenses, but such licenses are enforceable only when violations can be detected. Existing…