Instruction-guided image editors have become highly capable, yet improving them further still depends on human-edited training pairs or external reward models. Such supervision is costly to obtain and can reward plausible failures: a realistic output may leave the requested change undone or alter content that should be...
Ritesh Thawkar, Shubham Patle, Shravan Venkatraman et al.· 0 citations
SonoCorpus, an open resource unifying 456,963 images and 1,626,085 expert masks from 53 public datasets spanning 24 clinical applications and 17 countries, and SonoBase, an interactive segmentation foundation model pretrained on it are presented, locating the advantage in ultrasound-specific pretraining rather than any...
Chao Qin, F. Khan, Salman H. Khan et al.· 0 citations
Instruction-guided image editors have become highly capable, yet improving them further still depends on human-edited training pairs or external reward models. Such supervision is costly to obtain and can reward plausible failures: a realistic output may leave the requested change undone or alter content that should be...
Ritesh Thawkar, Shubham Patle, Shravan Venkatraman et al.· 0 citations
Ultrasound is the most widely deployed imaging modality worldwide, yet clinical AI remains fragmented into narrow single-task models that fail when device, operator, or anatomy changes. Here we present SonoCorpus, an open resource unifying 456,963 images and 1,626,085 expert masks from 53 public datasets spanning 24 cl...
Chao Qin, F. Khan, Salman H. Khan et al.· 0 citations
Agricultural visual models are typically evaluated for either recognition or localization, but reliable diagnosis requires identifying what is present and localizing the evidence. Agricultural visual question answering (VQA) datasets carry rich semantic labels but rarely link them to image regions, and adding such anno...
Abdulla Alshehhi, Zong-Yan Han, R. Anwer· 0 citations
3D Gaussian Splatting (3DGS) represents 3D content with anisotropic primitives that jointly encode geometry and appearance. Fixed-budget encoders consume sampled observations of Gaussian assets, so the same object may be observed through different primitive realizations. Existing self-supervised methods mainly reconstr...
An AVQA-specific two-stage framework that adapts established cross-modal reconstruction and dependency-modeling principles to the supervision constraints of TM-AVQA is developed, a setting in which modality-complete, audio-missing, and visual-missing samples may occur during both training and testing.
Jin-Xing Zhou, Zhang-Bin Li, Di Hu et al.· IEEE Transactions on Pattern...· 0 citations
Results show that adaptively orchestrating foundation-model capabilities can combine scalable retrieval with fine-grained reasoning without task-specific training, and are shown to be state-of-the-art among training-free approaches.
Dmitry Demidov, Muhammad Zaigham Zaheer, Omkar Thawakar et al.· 0 citations
This work introduces CVPD (Contrastive Counterfactual Visual Process Distillation), which is the first fully self-contained framework for dense, on-policy, token-level visual self-distillation for MLLMs, and proposes a three-gate Counterfactual Criterion that identifies visual blind spots where zooming into a region ch...
Shravan Venkatraman, Omkar Thawakar, Ritesh Thawkar et al.· 2 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.