3 papers
cs.CV2025
Hummingbird: High Fidelity Image Generation via Multimodal Context Alignment
Minh-Quan Le, Gaurav Mittal, Tianjian Meng +5
While diffusion models are powerful in generating high-quality, diverse synthetic data for object-centric tasks, existing methods struggle with scene-aware tasks such as Visual Que…
cs.CV2025
DDS: Decoupled Dynamic Scene-Graph Generation Network
A S M Iftekhar, Raphael Ruschel, Satish Kumar +2
Scene-graph generation involves creating a structural representation of the relationships between objects in a scene by predicting subject-object-relation triplets from input data.…
cs.LG2024
BLoad: Enhancing Neural Network Training with Efficient Sequential Data Handling
Raphael Ruschel, A. S. M. Iftekhar, B. S. Manjunath +1
The increasing complexity of modern deep neural network models and the expanding sizes of datasets necessitate the development of optimized and scalable training methods. In this w…