5 papers
On-Policy Self-Distillation for Multi-Turn Image Editing
Liangbing Zhao, Le Zhuo, Mohamed Elhoseiny
Instruction-based image editing has achieved strong performance in single-turn settings, yet practical editing is often iterative, with each instruction applied to the output of th…
LongVU-TTT: Causal Test-Time Training for Visual Resampling in Long Video Understanding
Mahmoud Ahmed, Sameh Abdulah, Olatunji Ruwase +3
Long-video MLLMs must model temporal change before a limited visual-token budget removes most frame evidence. We introduce LongVU-TTT, which inserts a convolutional Test-Time Train…
Cross-Layer Energy Analysis of Multimodal Training on Grace Hopper Superchips
Mahmoud Ahmed, Sameh Abdulah, Olatunji Ruwase +4
Multimodal deep learning models enable joint learning across heterogeneous data sources, including text, images, and video, but their rapid scaling introduces significant memory an…
From Reflection to Perfection: Scaling Inference-Time Optimization for Text-to-Image Diffusion Models via Reflection Tuning
Le Zhuo, Liangbing Zhao, Sayak Paul +6
Recent text-to-image diffusion models achieve impressive visual quality through extensive scaling of training data and model parameters, yet they often struggle with complex scenes…
GPU-Framework for Teamwork Action Recognition
Mohamed Elhoseiny, Hossam Faheem, Taymour Nazmy +1
Real time processing for teamwork action recognition is a challenge, due to complex computational models to achieve high system performance. Hence, this paper proposes a framework…