3 papers
cs.CV2026
Rebalancing Reference Frame Dominance to Improve Motion in Image-to-Video Models
Wooseok Jeon, Seungho Park, Seunghyun Shin +3
Image-to-video models often generate videos that remain overly static, compared to text-to-video models. While prior approaches mitigate this issue by weakening or modifying the im…
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…
cs.CL2025
Are Any-to-Any Models More Consistent Across Modality Transfers Than Specialists?
Jiwan Chung, Janghan Yoon, Junhyeong Park +4
Any-to-any generative models aim to enable seamless interpretation and generation across multiple modalities within a unified framework, yet their ability to preserve relationships…