5 papers
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…
Decomposed Attention Fusion in MLLMs for Training-Free Video Reasoning Segmentation
Su Ho Han, Jeongseok Hyun, Pilhyeon Lee +3
Multimodal large language models (MLLMs) demonstrate strong video understanding by attending to visual tokens relevant to textual queries. To directly adapt this for localization i…
GenOL: Generating Diverse Examples for Name-only Online Learning
Minhyuk Seo, Seongwon Cho, Minjae Lee +4
Online learning methods often rely on supervised data. However, under data distribution shifts, such as in continual learning (CL), where continuously arriving online data streams…
Autoregressive Universal Video Segmentation Model
Miran Heo, Sukjun Hwang, Min-Hung Chen +4
Recent video foundation models such as SAM2 excel at prompted video segmentation by treating masks as a general-purpose primitive. However, many real-world settings require unpromp…
Multi-Granular Spatio-Temporal Token Merging for Training-Free Acceleration of Video LLMs
Jeongseok Hyun, Sukjun Hwang, Su Ho Han +6
Video large language models (LLMs) achieve strong video understanding by leveraging a large number of spatio-temporal tokens, but suffer from quadratic computational scaling with t…