12 papers
From Awareness to Adherence: Bridging the Context Gap in Spoken Dialogue Systems via Context-Aware Decoding
Che Hyun Lee, Heeseung Kim, Sungroh Yoon
Despite the success of end-to-end (E2E) spoken dialogue systems, maintaining strict context adherence in multi-round conversations remains a challenge. While prior works attribute…
Diagnosing and Correcting Concept Omission in Multimodal Diffusion Transformers
Kanghyun Baek, Jaihyun Lew, Chaehun Shin +2
Multimodal Diffusion Transformers (MM-DiTs) have achieved remarkable progress in text-to-image generation, yet they frequently suffer from concept omission, where specified objects…
R2R2: Robust Representation for Intensive Experience Reuse via Redundancy Reduction in Self-Predictive Learning
Sanghyeob Song, Donghyeok Lee, Jinsik Kim +1
For reinforcement learning in data-scarce domains like real-world robotics, intensive data reuse enhances efficiency but induces overfitting. While prior works focus on critic bias…
Omni-Persona: Systematic Benchmarking and Improving Omnimodal Personalization
Yeongtak Oh, Dongwook Lee, Sangkwon Park +2
While multimodal large language models have advanced across text, image, and audio, personalization research has remained primarily vision-language, with unified omnimodal benchmar…
Metacognitive Behavioral Tuning of Large Language Models for Multi-Hop Question Answering
Ik-hwan Kim, Hyeongrok Han, Mingi Jung +5
Large Language Models (LLMs) often produce incorrect answers on multi-hop question answering even when the reasoning trace already contains a correct intermediate conclusion. We at…
Knowledge Integration Decay in Search-Augmented Reasoning of Large Language Models
Sangwon Yu, Ik-hwan Kim, Donghun Kang +6
Modern Large Language Models (LLMs) have demonstrated remarkable capabilities in complex tasks by employing search-augmented reasoning to incorporate external knowledge into long c…