This is the first systematic evaluation of UQ methods applied to a foundation model for semantic segmentation and highlights both the promise and the current limitations of uncertainty-aware foundation models, pointing to the need for future work that jointly optimizes accuracy, robustness, and efficiency for real-world deployment.
S. Landgraf, Joceline Hinz, M. Ulrich· ISPRS Annals of the Photogra...· 0 citations
A local traditional OCR pipeline is introduced that can be iteratively fine-tuned on the target manuscript at the layout-level and the appearance-level, causing iterative reduction in human annotation effort, which is expensive and time-consuming as it requires historical domain expertise.
This paper proposes Temporally Decomposable Image Representations (TDIR), a representation learning algorithm that decomposes historical photographs into separate date and content components through orthogonal subspaces, and defines and proves the conditions under which such a decomposition is achievable.
Adria Molina Rodr'iguez, O. R. Terrades, Josep Lladós Canet· 0 citations
OmniHandwritingOCR provides a challenging testbed for diagnosing language, content, structural, and visual-grounding failure modes of multimodal models in handwritten OCR scenarios.
Zinuo Guo, Min Zhang, Bo Jiang· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
MR-IQA-2 is introduced, an actor-editor-judge framework that operationalizes reasoning-editing-reflection that achieves competitive rating alignment with humans and uses fine-grained credit assignment to decouple reasoning and rating supervision.
Yuan Li, Youyuan Lin, Chenhui Chu et al.· 0 citations
Strong sensitivity to the training prior, data-efficiency of moment-based heads, and representation dependence of Gaussian shift metrics, motivating (prior, encoder, head)-level reporting and stronger analytical baselines for AIGI transfer are quantified.
Shashank Kotyan, Makoto Shing, Yuki Imajuku et al.· 0 citations
Precise segmentation of the optic disc and cup is critical for the early detection and diagnosis of glaucoma. However, achieving consistently high performance across datasets while maintaining low computational requirements remains a significant challenge. In glaucoma detection, low-computation methods are crucial for enabling rapid, large-scale screening and facilitating deployment in resource-limited clinical environments. While deep learning models such as UNets, Vision Transformers (ViTs), and Diffusion models have demonstrated strong segmentation performance but these methods often come with substantial computational overhead. UNets are efficient at capturing local features but are limited in modeling global contextual information. Conversely, ViTs excel at long-range dependency modeling but are computationally intensive. Hybrid architectures, such as UNetR, which combine transformer-based encoders with UNet-style decoders, have shown improved performance but while incurring additional complexity. Considering these, in this work, we propose OptiModNet, a light weight novel hybrid architecture tailored for optic disc and cup segmentation. The model integrates diverse attention mechanisms at multiple stages of the network to enhance both local and global feature representation. We include an Aggregated Pyramid Loss that supervises predictions at multiple decoder depths, to promote better gradient flow and structural consistency. We evaluate OptiModNet on the REFUGE2 dataset for both optic disc and cup segmentation tasks. Our method achieves state-of-the-art performance, exceeding existing approaches by over 2.5\%, while maintaining high efficiency with only 3.73 GFLOPs and 1.93M parameters. The code is available at https://github.com/SG1947/OptiModNet.
Soumili Ghosh, Debapriya Roy, Aryan Das et al.· 0 citations
This work introduces SparsePR, which combines Response-Coupled Partitioning with Probe-Fitted Residual Reconstruction and consistently reduces attention-reconstruction error across four heterogeneous video generation and world models.
P. Taghavi, Reza Langari, Gaurav Pandey· 0 citations
A unified adaptation-restoration design consistently outperforms entropy-based adaptation, RAG, and perplexity-based generation over long adaptation horizons, where baselines without restoration progressively degrade while TTSD-FAR remains consistent.
Muhammad Haseeb Aslam, A. Koerich, Marco Pedersoli et al.· 0 citations
This work proposes a principled VLM TTA method called \algname, and theoretically reveals that the InfoNCE loss can be neatly reformulated as a Wasserstein OT formulation, thereby unifying the objectives of the inference and adaptation of VLMs to achieve their mutual benefits.
Qi Yu, Zhichen Zeng, Katherine Tieu et al.· 0 citations
Two distinct effects are reported: paired-example FedAvg partially recovers the missing-ECG gap, while validation-selected completion is a task-specific classifier-logit correction rather than literal ECG recovery.
Fine-grained wildlife re-identification remains a challenging area in research. Current state-of-the-art approaches apply a detection and re-identification pipeline. We propose a one-stage end-to-end detection and re-identification model that performs identity searching within the latent space. We adopt DINOv2 for robust spatial geometry and MegaDescriptor for wildlife re-identification. We enhance latent queries with prompt re-identification features. A detection decoder queries the scene latent space to establish object boundaries around the target identity. Preliminary findings reflect a competitive mean average precision score of 30.584% compared to the state-of-the-art two stage approach of 44.89%. Qualitative results depict effective bounding and identification of animal identities.
Mufhumudzi Muthivhi, Jiahao Huo, Terence van Zyl et al.· 0 citations
The visionary PhysioNet platform launched 25 years ago, based on a system developed at MIT in the 1970s. It has become one of the most comprehensive biomedical and clinical data repositories in existence.
Known for his clear and elegant writing style, Bertsekas shaped fields from control and optimization to large-scale computation and artificial intelligence.
MIT News · Artificial Intelligence· news.mit.eduJul 6, 2026
PhD student Rachel Sava, winner of the Envisioning the Future of Computing Prize, explores transformative improvements and dystopian risks of neural technology.
MIT News · Artificial Intelligence· news.mit.eduJun 30, 2026
Computer scientist Phillip Isola cuts through the hype to explain how AI agents work and what the future might hold for this rapidly advancing technology.
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
