Showing 2025Show all
3 papers · 1 filter
cs.CV2025
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…
cs.CV2025
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…
cs.CV2025
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…