collaborators

18 papers

cs.CV2026

Global Geometry Is Not Enough for Vision Representations

Jiwan Chung, Seon Joo Kim

A common assumption in representation learning is that globally well-distributed embeddings support robust and generalizable representations. This focus has shaped both training ob…

cs.LG2026

Rethinking State Tracking in Recurrent Models Through Error Control Dynamics

Jiwan Chung, Heechan Choi, Seon Joo Kim

The theory of state tracking in recurrent architectures has predominantly focused on expressive capacity: whether a fixed architecture can theoretically realize a set of symbolic t…

cs.CL2026

What MLLMs Learn about When they Learn about Multimodal Reasoning

Jiwan Chung, Neel Joshi, Pratyusha Sharma +2

Evaluation of multimodal reasoning models is typically reduced to a single accuracy score, implicitly treating reasoning as a unitary capability. We introduce MathLens, a benchmark…

cs.CL2026

v1: Learning to Point Visual Tokens for Multimodal Grounded Reasoning

Jiwan Chung, Junhyeok Kim, Siyeol Kim +3

When thinking with images, humans rarely rely on a single glance: they revisit visual evidence while reasoning. In contrast, most Multimodal Language Models encode an image once to…

cs.LG2026

Teaching Metric Distance to Discrete Autoregressive Language Models

Jiwan Chung, Saejin Kim, Yongrae Jo +3

Large language models (LLMs) operate as autoregressive predictors over discrete token vocabularies, a formulation that has enabled their adaptation far beyond natural language to v…

cs.CV2026

GuideDog: A Real-World Egocentric Multimodal Dataset for Blind and Low-Vision Accessibility-Aware Guidance

Junhyeok Kim, Jaewoo Park, Junhee Park +5

For people affected by blindness and low vision (BLV), safe and independent navigation remains a major challenge, impacting over 2.2 billion individuals worldwide. Although multimo…