7 papers · 1 filter
AReA: Adaptive Receptive-Field Attention for Efficient High-Resolution Diffusion Transformers
Javad Rajabi, Koorosh Roohi, David B. Lindell +1
Generating images beyond the training resolution of Diffusion Transformers (DiTs) remains challenging, as the number of tokens grows rapidly with resolution, full attention becomes…
SCOPD: Sparse-Context On-Policy Self-Distillation for Efficient Vision-Language Models
Ahmadreza Jeddi, Enming Zhang, Jasper Gerigk +12
Reasoning vision-language models (VLMs) process images and videos as long sequences of visual tokens, making inference expensive. Training-free token pruning reduces this cost, but…
OpenVAM: Open-World Visual Attention Modeling with VLMs
Kiana Hooshanfar, Amirhossein Kazerouni, Alireza Hosseini +2
Predicting human gaze is a core capability for applications ranging from web/UI design analysis to robotics and human-computer interaction. Yet, most visual attention modeling meth…
PhotoQuilt: Training-Free Arbitrary-Resolution Photomosaics via Bootstrapped Tiled Denoising
Koorosh Roohi, Javad Rajabi, Andrew Fleet +1
Photomosaics are large images whose local regions are seen as independent tiles while their overall arrangement forms a coherent scene. Generating them at high resolution, with eve…
AVIS: Adaptive Test-Time Scaling for Vision-Language Models
Ahmadreza Jeddi, Minh Ngoc Le, Amirhossein Kazerouni +8
Modern Vision-Language Models (VLMs) benefit from chain-of-thought prompting and test-time scaling, but these gains often come with prohibitive inference cost due to large visual c…
SEGA: Spectral-Energy Guided Attention for Resolution Extrapolation in Diffusion Transformers
Javad Rajabi, Kimia Shaban, Koorosh Roohi +2
Diffusion transformers (DiTs) have emerged as a dominant architecture for text-to-image generation, yet their performance drops when generating at resolutions beyond their training…
Face2Scene: Using Facial Degradation as an Oracle for Diffusion-Based Scene Restoration
Amirhossein Kazerouni, Maitreya Suin, Tristan Aumentado-Armstrong +6
Recent advances in image restoration have enabled high-fidelity recovery of faces from degraded inputs using reference-based face restoration models (Ref-FR). However, such methods…