activity
20242026
collaborators
Showing cs.CVShow all

14 papers · 1 filter

cs.CV2026

Memory-Efficient Fine-Tuning Diffusion Transformers via Dynamic Patch Sampling and Block Skipping

Sunghyun Park, Jeongho Kim, Hyoungwoo Park +6

Diffusion Transformers (DiTs) have significantly enhanced text-to-image (T2I) generation quality, enabling high-quality personalized content creation. However, fine-tuning these mo…

cs.CV2026

ForeSea: AI Forensic Search with Multi-modal Queries for Video Surveillance

Hyojin Park, Yi Li, Janghoon Cho +8

Despite decades of work, surveillance still struggles in searching and reasoning about specific targets across long, multi-camera videos. Existing methods - tracking, retrieval, an…

cs.CV2025

Do-Undo Bench: Reversibility for Action Understanding in Image Generation

Shweta Mahajan, Shreya Kadambi, Hoang Le +4

We introduce the Do-Undo task and benchmark to address a critical gap in vision-language models: understanding and generating plausible scene transformations driven by real-world a…

cs.CV2025

Attention Guided Alignment in Efficient Vision-Language Models

Shweta Mahajan, Hoang Le, Hyojin Park +3

Large Vision-Language Models (VLMs) rely on effective multimodal alignment between pre-trained vision encoders and Large Language Models (LLMs) to integrate visual and textual info…

cs.CV2025

Ar2Can: An Architect and an Artist Leveraging a Canvas for Multi-Human Generation

Shubhankar Borse, Phuc Pham, Farzad Farhadzadeh +6

Despite recent advances in personalized image generation, existing models consistently fail to produce reliable multi-human scenes, often merging or losing facial identity. We pres…

cs.CV2025

FLoC: Facility Location-Based Efficient Visual Token Compression for Long Video Understanding

Janghoon Cho, Jungsoo Lee, Munawar Hayat +3

Recent studies in long video understanding have harnessed the advanced visual-language reasoning capabilities of Large Multimodal Models (LMMs), driving the evolution of video-LMMs…