activity
20242026
collaborators

8 papers

cs.MA2026

Naive Visual Memory is Not Enough: A Failure-Mode Study of GUI Agents

Seoyoung Choi, Minseok Ko, Hyunseok Lee +4

Graphical User Interface (GUI) agents are increasingly used to automate complex computer tasks across applications, websites, and operating systems. To improve their reliability, r…

cs.CV2026

Benchmarking Visual State Tracking in Multimodal Video Understanding

Sihyun Yu, Nanye Ma, Pinzhi Huang +8

Understanding a video requires more than recognizing isolated moments, as humans continuously track entities, states, and events over time. This capacity for visual state tracking…

cs.CV2026

Vision-aligned Latent Reasoning for Multi-modal Large Language Model

Byungwoo Jeon, Yoonwoo Jeong, Hyunseok Lee +2

Despite recent advancements in Multi-modal Large Language Models (MLLMs) on diverse understanding tasks, these models struggle to solve problems which require extensive multi-step…

cs.CV2026

Cog3DMap: Multi-View Vision-Language Reasoning with 3D Cognitive Maps

Chanyoung Gwak, Yoonwoo Jeong, Byungwoo Jeon +3

Precise spatial understanding from multi-view images remains a fundamental challenge for Multimodal Large Language Models (MLLMs), as their visual representations are predominantly…

cs.LG2026

Beyond Correctness: Learning Robust Reasoning via Transfer

Hyunseok Lee, Soheil Abbasloo, Jihoon Tack +1

Reinforcement Learning with Verifiable Rewards (RLVR) has recently strengthened LLM reasoning, but its focus on final answer correctness leaves a critical gap: it does not ensure t…

cs.LG2025

ReVISE: Learning to Refine at Test-Time via Intrinsic Self-Verification

Hyunseok Lee, Seunghyuk Oh, Jaehyung Kim +2

Self-awareness, i.e., the ability to assess and correct one's own generation, is a fundamental aspect of human intelligence, making its replication in large language models (LLMs)…