6 citations · 23 across the 46 of their papers we have counts for
9 papers · 1 filter
ThinkFuse: Trajectory-Aware Test-Time Fusion for Small Reasoning Models
Myunghoon Kang, Jungseob Lee, Jaehyung Seo +1
Small reasoning models (SRMs) have shown strong performance on complex reasoning tasks by generating extended chain-of-thought trajectories, but they often fail to recover once the…
Generalizable Lifelong Model Editing via Preference Optimization
Dahyun Jung, Suhyune Son, Heuiseok Lim
Knowledge editing enables rapid updates of specific factual knowledge in large language models (LLMs) without full retraining. However, more realistic scenarios call for a lifelong…
Vision Is Not Overhead: One-Pass Block Drafting for Lossless Speculative Decoding in Vision-Language Models
Jungseob Lee, Seongtae Hong, Dongyub Jude Lee +4
Speculative decoding accelerates generation without changing its output, but on vision-language models (VLMs) a self-reinforcing cycle holds it back. Because an autoregressive draf…
HiKEY: Hierarchical Multimodal Retrieval for Open-Domain Document Question Answering
Joongmin Shin, Gyuho Shim, Jeongbae Park +2
Retrieval-augmented generation (RAG) for document-based Open-domain Question Answering (ODQA) on large-scale industrial corpora faces two critical bottlenecks: routing failure in l…
MultiDocFusion: Hierarchical and Multimodal Chunking Pipeline for Enhanced RAG on Long Industrial Documents
Joongmin Shin, Chanjun Park, Jeongbae Park +2
RAG-based QA has emerged as a powerful method for processing long industrial documents. However, conventional text chunking approaches often neglect complex and long industrial doc…
Revise: A Framework for Revising OCRed text in Practical Information Systems with Data Contamination Strategy
Gyuho Shim, Seongtae Hong, Heuiseok Lim
Recent advances in Large Language Models (LLMs) have significantly improved the field of Document AI, demonstrating remarkable performance on document understanding tasks such as q…
TORSO: Template-Oriented Reasoning Towards General Tasks
Minhyuk Kim, Seungyoon Lee, Heuiseok Lim
The approaches that guide Large Language Models (LLMs) to emulate human reasoning during response generation have emerged as an effective method for enabling them to solve complex…
Debate Only When Necessary: Adaptive Multiagent Collaboration for Efficient LLM Reasoning
Sugyeong Eo, Hyeonseok Moon, Evelyn Hayoon Zi +2
Multiagent collaboration has emerged as a promising framework for enhancing the reasoning capabilities of large language models (LLMs). Despite improvements in reasoning, the appro…
Find the Intention of Instruction: Comprehensive Evaluation of Instruction Understanding for Large Language Models
Hyeonseok Moon, Jaehyung Seo, Seungyoon Lee +2
One of the key strengths of Large Language Models (LLMs) is their ability to interact with humans by generating appropriate responses to given instructions. This ability, known as…