34 citations · 56 across the 67 of their papers we have counts for
76 papers
Bias Control and Injection for Multi-Agent Aggregation
Sungjae Lee, Soheil Abbasloo, Jabin Koo +1
Multi-agent reasoning with large language models (LLMs) raises a central question for collective decision-making: when agents disagree, whose decision should be trusted? Resolving…
Language Model Fingerprinting Requires Rethinking Watermark Teachers
Jeongyeon Hwang, Anshul Nasery, Sewoong Oh +1
LLM fingerprinting via watermark distillation embeds a statistical watermark signal into model weights, enabling model owners to identify their models behind black-box APIs. Revisi…
Dynamic Expert Pruning for Multi-Agent Systems
Jabin Koo, Soheil Abbasloo, Sungjae Lee +1
Mixture-of-Experts (MoE) architectures scale language models efficiently by activating only a few experts per token, but the saving is confined to computation: every expert must st…
Retrospective Distillation Attribution via Normalized Response Similarity
Minwoo Jang, Jaechang Kim, Minhyeon Oh +2
Model distillation transfers capabilities through supervised fine-tuning (SFT) on teacher responses, often collected from commercial APIs, raising questions of model provenance. Ex…
Confidence-Gated Transductive Test Generation for Code Reranking
Sungjae Lee, Youngsik Yoon, Seockbean Song +3
Test case synthesis is crucial for evaluating and ranking programs generated by large language models (LLMs). However, constructing high-quality test cases remains challenging beca…
AdaBoosting Text Prompts for Vision-Language Models
Seokhee Jin, Changhwan Sung, Sunung Mun +2
The classification accuracy of pretrained Vision-Language Models (VLMs) relies on the quality of the text prompts. Handcrafted templates and Large Language Model (LLM)-generated de…
Segment-level Tree Search for Long Meeting Document Summarization
Sangwon Ryu, Heejin Do, Jun Seo +4
Meeting documents are challenging to summarize due to their length and complex conversational structure. Existing approaches typically adopt multi-stage pipelines that extract info…
Understanding LLM Behavior in Multi-Target Cross-Lingual Summarization
Sangwon Ryu, Yihong Liu, Mingyang Wang +4
Multi-target cross-lingual text summarization (MTXLS), which summarizes a source document into multiple target languages, is increasingly important as users consume content in dive…
Federated Variational Preference Alignment with Gumbel-Softmax Prior for Personalized User Preferences
Jabin Koo, Hoyoung Kim, Minwoo Jang +1
Federated Learning (FL) offers a privacy-preserving pathway for aligning Large Language Models (LLMs); however, existing frameworks typically enforce a monolithic reward model, ine…
Towards Faithful Agentic XAI: A Verification Method and an Open-World Benchmark for Better Model Faithfulness
Jaechang Kim, Sunung Mun, Seungjoon Lee +2
Explainable AI (XAI) helps users interpret model behavior and identify potential faults. Agentic XAI systems use Large Language Models (LLMs) to make explanations more accessible t…
Interaction-Aware Influence Functions for Group Attribution
Jaeseung Heo, Kyeongheung Yun, Youngbin Choi +3
Influence functions approximate how removing a training example changes a quantity of interest, called the target function, such as a held-out loss. To estimate the influence of a…
ProCompNav: Proactive Instance Navigation with Comparative Judgment for Ambiguous User Queries
Junhyuk Kwon, Seungjoon Lee, Hyejin Park +2
Natural-language instance navigation becomes challenging when the initial user request does not uniquely specify the target instance. A practical agent should reduce the user's bur…
EPIC: Efficient Predicate-Guided Inference-Time Control for Compositional Text-to-Image Generation
Sunung Mun, Sunghyun Cho, Jungseul Ok
Recent text-to-image (T2I) generators can synthesize realistic images, but still struggle with compositional prompts involving multiple objects, counts, attributes, and relations.…
MMTB: Evaluating Terminal Agents on Multimedia-File Tasks
Chiyeong Heo, Jaechang Kim, Junhyuk Kwon +4
Terminals provide a powerful interface for AI agents by exposing diverse tools for automating complex workflows, yet existing terminal-agent benchmarks largely focus on tasks groun…
When Are Experts Misrouted? Counterfactual Routing Analysis in Mixture-of-Experts Language Models
Youngsik Yoon, Siwei Wang, Wei Chen +1
Mixture-of-Experts (MoE) language models route each token to a small subset of experts, but whether the routes selected by a trained top- router are good ones is rarely evaluate…
PaT: Planning-after-Trial for Efficient Test-Time Code Generation
Youngsik Yoon, Sungjae Lee, Seockbean Song +3
Beyond training-time optimization, scaling test-time computation has emerged as a key paradigm to extend the reasoning capabilities of Large Language Models (LLMs). However, most e…
POS-ISP: Pipeline Optimization at the Sequence Level for Task-aware ISP
Jiyun Won, Heemin Yang, Woohyeok Kim +2
Recent work has explored optimizing image signal processing (ISP) pipelines for various tasks by composing predefined modules and adapting them to task-specific objectives. However…
ChimeraLoRA: Multi-Head LoRA-Guided Synthetic Datasets
Hoyoung Kim, Minwoo Jang, Jabin Koo +2
Beyond general recognition tasks, specialized domains and fine-grained settings often encounter data scarcity, especially for tail classes. To obtain less biased and more reliable…
Visual Prompt Discovery via Semantic Exploration
Jaechang Kim, Yotaro Shimose, Zhao Wang +3
LVLMs encounter significant challenges in image understanding and visual reasoning, leading to critical perception failures. Visual prompts, which incorporate image manipulation co…
Rising Multi-Armed Bandits with Known Horizons
Seockbean Song, Chenyu Gan, Youngsik Yoon +3
Rising Multi-Armed Bandits (RMABs) model sequential decision problems where each arm's expected reward improves with repeated pulls. In such problems, the value of investing in an…
Edge-Aware Image Manipulation via Diffusion Models with a Novel Structure-Preservation Loss
Minsu Gong, Nuri Ryu, Jungseul Ok +1
Recent advances in image editing leverage latent diffusion models (LDMs) for versatile, text-prompt-driven edits across diverse tasks. Yet, maintaining pixel-level edge structures-…
Making Models Unmergeable via Scaling-Sensitive Loss Landscape
Minwoo Jang, Hoyoung Kim, Jabin Koo +1
The rise of model hubs has made it easier to access reusable model components, making model merging a practical tool for combining capabilities. Yet, this modularity also creates a…
VIRO: Robust and Efficient Neuro-Symbolic Reasoning with Verification for Referring Expression Comprehension
Hyejin Park, Junhyuk Kwon, Suha Kwak +1
Referring Expression Comprehension (REC) aims to localize the image region corresponding to a natural language query. Recent neuro-symbolic REC approaches leverage large language m…
Improving Generative Behavior Cloning via Self-Guidance and Adaptive Chunking
Junhyuk So, Chiwoong Lee, Shinyoung Lee +2
Generative Behavior Cloning (GBC) is a simple yet effective framework for robot learning, particularly in multi-task settings. Recent GBC methods often employ diffusion policies wi…