6 papers
When Does an Image Determine the Answer? Benchmarking Visual Answerability across Charts and Scenes
Sungguk Cha, Mintae Kim, Youngsub Han +2
Reliable visual question answering requires correct answers when evidence is sufficient and abstention when it is not. We introduce a benchmark that connects complete-question eval…
Do Current Retrievers Cover All the Evidence? A Controlled Study of Conjunctive Cross-Page Retrieval
Sungguk Cha, DongWook Kim, Mintae Kim +3
Finding a long document relevant to a multi-part request is not the same as establishing that it contains every requested piece of evidence. We study this gap for conjunctive docum…
ReinPool: Reinforcement Learning Pooling Multi-Vector Embeddings for Retrieval System
Sungguk Cha, DongWook Kim, Mintae Kim +3
Multi-vector embedding models have emerged as a powerful paradigm for document retrieval, preserving fine-grained visual and textual details through token-level representations. Ho…
Annotation-Free Reinforcement Learning Query Rewriting via Verifiable Search Reward
Sungguk Cha, DongWook Kim, Taeseung Hahn +3
Optimizing queries for Retrieval-Augmented Generation (RAG) systems poses a significant challenge, particularly across diverse modal indices. We introduce RL-QR, a novel annotation…
ixi-GEN: Efficient Industrial sLLMs through Domain Adaptive Continual Pretraining
Seonwu Kim, Yohan Na, Kihun Kim +7
The emergence of open-source large language models (LLMs) has expanded opportunities for enterprise applications; however, many organizations still lack the infrastructure to deplo…
Leveraging Speaker Embeddings with Adversarial Multi-task Learning for Age Group Classification
Kwangje Baeg, Yeong-Gwan Kim, Young-Sub Han +1
Recently, researchers have utilized neural network-based speaker embedding techniques in speaker-recognition tasks to identify speakers accurately. However, speaker-discriminative…