16 papers
WASD: Wasserstein-based Knowledge Distillation for Large Language Models
Byeonghu Na, Donghyeok Shin, Yeongmin Kim +2
Autoregressive large language models (LLMs) have rapidly advanced in capability, but their increasing scale comes with substantial computational and memory costs at inference time.…
Best-of- Guidance for Test-time Diffusion Alignment
Richard Lee Kim, Yeongmin Kim, Gyuwon Sim +3
Diffusion models achieve strong generative performance but often struggle to align generated samples with human preferences measured by a reward model. A simple yet effective algor…
Multi-Agent Debate and Visual Information Extraction for SeePhys Pro: A 1st-Place Technical Report from ICML 2026 AI4Math Track 3 Challenge
Jiseok Kwak, Suhyeon Jo, Taewoo Kim +3
This technical report presents our approach to Challenge Track~3: SeePhys Pro at the 3rd AI for Math Workshop, where the task is to answer college-level physics questions whose sta…
Missing Pattern Recognized Diffusion Imputation Model for Missing Not At Random
Gyuwon Sim, Sumin Lee, Heesun Bae +5
Missing data frequently arises across diverse domains, including time-series and image domains. In the real world, missing occurrences often depend on the unobservable values thems…
Semantic-aware Wasserstein Policy Regularization for Large Language Model Alignment
Byeonghu Na, Hyungho Na, Yeongmin Kim +4
Large language models (LLMs) are commonly aligned with human preferences using reinforcement learning from human feedback (RLHF). In this method, LLM policies are generally optimiz…
Lookahead Sample Reward Guidance for Test-Time Scaling of Diffusion Models
Yeongmin Kim, Donghyeok Shin, Byeonghu Na +3
Diffusion models have demonstrated strong generative performance; however, generated samples often fail to fully align with human intent. This paper studies an efficient test-time…
Prompt-Based Safety Guidance Is Ineffective for Unlearned Text-to-Image Diffusion Models
Jiwoo Shin, Byeonghu Na, Mina Kang +2
Recent advances in text-to-image generative models have raised concerns about their potential to produce harmful content when provided with malicious input text prompts. To address…
Training-Free Safe Text Embedding Guidance for Text-to-Image Diffusion Models
Byeonghu Na, Mina Kang, Jiseok Kwak +6
Text-to-image models have recently made significant advances in generating realistic and semantically coherent images, driven by advanced diffusion models and large-scale web-crawl…
Diffusion Adaptive Text Embedding for Text-to-Image Diffusion Models
Byeonghu Na, Minsang Park, Gyuwon Sim +6
Text-to-image diffusion models rely on text embeddings from a pre-trained text encoder, but these embeddings remain fixed across all diffusion timesteps, limiting their adaptabilit…
AMiD: Knowledge Distillation for LLMs with -mixture Assistant Distribution
Donghyeok Shin, Yeongmin Kim, Suhyeon Jo +2
Autoregressive large language models (LLMs) have achieved remarkable improvement across many tasks but incur high computational and memory costs. Knowledge distillation (KD) mitiga…
Distillation of Large Language Models via Concrete Score Matching
Yeongmin Kim, Donghyeok Shin, Mina Kang +2
Large language models (LLMs) deliver remarkable performance but are costly to deploy, motivating knowledge distillation (KD) for efficient inference. Existing KD objectives typical…
Preference Optimization by Estimating the Ratio of the Data Distribution
Yeongmin Kim, Heesun Bae, Byeonghu Na +1
Direct preference optimization (DPO) is widely used as a simple and stable method for aligning large language models (LLMs) with human preferences. This paper investigates a genera…
Reward-based Input Construction for Cross-document Relation Extraction
Byeonghu Na, Suhyeon Jo, Yeongmin Kim +1
Relation extraction (RE) is a fundamental task in natural language processing, aiming to identify relations between target entities in text. While many RE methods are designed for…
Diffusion Rejection Sampling
Byeonghu Na, Yeongmin Kim, Minsang Park +3
Recent advances in powerful pre-trained diffusion models encourage the development of methods to improve the sampling performance under well-trained diffusion models. This paper in…
Diffusion Bridge AutoEncoders for Unsupervised Representation Learning
Yeongmin Kim, Kwanghyeon Lee, Minsang Park +2
Diffusion-based representation learning has achieved substantial attention due to its promising capabilities in latent representation and sample generation. Recent studies have emp…
Training Unbiased Diffusion Models From Biased Dataset
Yeongmin Kim, Byeonghu Na, Minsang Park +4
With significant advancements in diffusion models, addressing the potential risks of dataset bias becomes increasingly important. Since generated outputs directly suffer from datas…