68 citations · 228 across the 46 of their papers we have counts for
53 papers
Let Agents Design How They Search: Automatic Interface Optimization for Agentic Search
Sangjune An, Jaeyoon Jung, Yumin Choi +4
Agentic search depends on the interface through which a language-model agent accesses and explores a corpus. Existing interface designs are fixed by hand and applied unchanged to e…
Contact-Aware Imitation Learning Through Contact Factorization
Jiho Hong, Daeun Song, Sanghyun Kim +1
Generalizable contact-rich manipulation requires robots to preserve intended task behavior while adapting its physical realization to changing contact conditions. However, interact…
EvoDuet: Bilevel Co-Evolution of Web Searching and Task Solving for Scientific Discovery
Young-Jun Lee, Jinheon Baek, Soyeong Jeong +5
Evolutionary search with large language models (LLMs) can stall when progress requires external knowledge the model lacks. Supplying relevant documents helps, but simply adding web…
Knowing When Thinking Is Not Enough: Teaching Small Reasoning Models to Reason Beyond Their Parametric Knowledge
Chanuk Lee, Minki Kang, Sangwoo Park +3
Scaling test-time computation is a powerful way to improve language-model reasoning, and is particularly appealing for small reasoning models (sRMs) that are cheap to serve. Howeve…
Surprising Success, Repeated Failure: Entropy-Guided Credit Assignment for Exploration in LLM Reasoning
Woongyeong Yeo, Minki Kang, Chanuk Lee +3
Reinforcement learning with verifiable rewards (RLVR) enhances reasoning in large language models (LLMs) through outcome-level feedback, yet recent approaches to finer-grained cred…
MemRefine: LLM-Guided Compression for Long-Term Agent Memory
Minjae Kim, Jinheon Baek, Soyeong Jeong +1
Large language model (LLM) agents are increasingly expected to operate over long-term interactions, where information from past dialogues must be preserved and recalled to support…
TIDE: Proactive Multi-Problem Discovery via Template-Guided Iteration
Soyeong Jeong, Jinheon Baek, Minki Kang +1
Agents are widely deployed as assistants over documents, tools, and code. However, they typically act only on explicit user requests, which surface only the problems the user has n…
OmniRetrieval: Unified Retrieval across Heterogeneous Knowledge Sources
Jinheon Baek, Soyeong Jeong, Sangwoo Park +5
Real-world information needs require access to structurally diverse knowledge sources, from unstructured text and relational tables to knowledge graphs and property graphs. Existin…
On the limits and opportunities of AI reviewers: Reviewing the reviews of Nature-family papers with 45 expert scientists
Seungone Kim, Dongkeun Yoon, Kiril Gashteovski +55
With the advancement of AI capabilities, AI reviewers are beginning to be deployed in scientific peer review, yet their capability and credibility remain in question: many scientis…
It Takes Two: Complementary Self-Distillation for Contextual Integrity in LLMs
Sangwoo Park, Woongyeong Yeo, Seanie Lee +6
Contextual Integrity (CI) defines privacy not merely as keeping information hidden, but as governing information flows according to the norms of a given context. As large language…
PREPING: Zero-Task Agent Memory Construction via Self-Practice
Yumin Choi, Sangwoo Park, Minki Kang +2
Agent memory is typically constructed either offline from curated demonstrations or online from post-deployment interactions. However, regardless of how it is built, an agent faces…
Multimodal Prompt Optimization: Why Not Leverage Multiple Modalities for MLLMs
Yumin Choi, Dongki Kim, Jinheon Baek +1
Large Language Models (LLMs) have shown remarkable success, and their multimodal expansions (MLLMs) further unlock capabilities spanning images, videos, and other modalities beyond…
Rethinking Reward Models for Multi-Domain Test-Time Scaling
Dong Bok Lee, Seanie Lee, Sangwoo Park +12
The reliability of large language models (LLMs) during test-time scaling is often assessed with \emph{external verifiers} or \emph{reward models} that distinguish correct reasoning…
Chain of Retrieval: Multi-Aspect Iterative Search Expansion and Post-Order Search Aggregation for Full Paper Retrieval
Sangwoo Park, Jinheon Baek, Soyeong Jeong +1
Scientific paper retrieval, particularly framed as document-to-document retrieval, aims to identify relevant papers in response to a long-form query paper, rather than a short quer…
Knowledge Base Construction for Knowledge-Augmented Text-to-SQL
Jinheon Baek, Horst Samulowitz, Oktie Hassanzadeh +4
Text-to-SQL aims to translate natural language queries into SQL statements, which is practical as it enables anyone to easily retrieve the desired information from databases. Recen…
CaMMT: Benchmarking Culturally Aware Multimodal Machine Translation
Emilio Villa-Cueva, Sholpan Bolatzhanova, Diana Turmakhan +32
Translating cultural content poses challenges for machine translation systems due to the differences in conceptualizations between cultures, where language alone may fail to convey…
System Prompt Optimization with Meta-Learning
Yumin Choi, Jinheon Baek, Sung Ju Hwang
Large Language Models (LLMs) have shown remarkable capabilities, with optimizing their input prompts playing a pivotal role in maximizing their performance. However, while LLM prom…
UniversalRAG: Retrieval-Augmented Generation over Corpora of Diverse Modalities and Granularities
Woongyeong Yeo, Kangsan Kim, Soyeong Jeong +2
Retrieval-Augmented Generation (RAG) has shown substantial promise in improving factual accuracy by grounding model responses with external knowledge relevant to queries. However,…
Paper2Code: Automating Code Generation from Scientific Papers in Machine Learning
Minju Seo, Jinheon Baek, Seongyun Lee +1
Despite the rapid growth of machine learning research, corresponding code implementations are often unavailable, making it slow and labor-intensive for researchers to reproduce res…
Sketch-of-Thought: Efficient LLM Reasoning with Adaptive Cognitive-Inspired Sketching
Simon A. Aytes, Jinheon Baek, Sung Ju Hwang
Recent advances in large language models (LLMs) have enabled strong reasoning capabilities through Chain-of-Thought (CoT) prompting, which elicits step-by-step problem solving, but…
Towards Better Understanding of Program-of-Thought Reasoning in Cross-Lingual and Multilingual Environments
Patomporn Payoungkhamdee, Pume Tuchinda, Jinheon Baek +6
Multi-step reasoning is essential for large language models (LLMs), yet multilingual performance remains challenging. While Chain-of-Thought (CoT) prompting improves reasoning, it…
Efficient Real-time Refinement of Language Model Text Generation
Joonho Ko, Jinheon Baek, Sung Ju Hwang
Large language models (LLMs) have shown remarkable performance across a wide range of natural language tasks. However, a critical challenge remains in that they sometimes generate…
VideoRAG: Retrieval-Augmented Generation over Video Corpus
Soyeong Jeong, Kangsan Kim, Jinheon Baek +1
Retrieval-Augmented Generation (RAG) is a powerful strategy for improving the factual accuracy of models by retrieving external knowledge relevant to queries and incorporating it i…
Efficient Long Context Language Model Retrieval with Compression
Minju Seo, Jinheon Baek, Seongyun Lee +1
Long Context Language Models (LCLMs) have emerged as a new paradigm to perform Information Retrieval (IR), which enables the direct ingestion and retrieval of information by proces…