The experiments show that the learned tree topology provides strong interpretability by consistently isolating minority subgroups, which provides a transparent mapping between the model architecture and the data's latent group structure, while yielding competitive robustness with state-of-the-art methods.
Ankur Garg, Ulrich Aivodji, S. Kahou et al.· arXiv.org· 0 citations
It is shown that pretraining an in-context learner with a Perceiver-style architecture on synthetic data yields a model that can solve new tasks from a handful of labeled bags, outperforming supervised baselines that require task-specific training.
Alexander Möllers, Marvin Sextro, Julius Hense et al.· arXiv.org· 0 citations
Adaptive Calibration is introduced, a novel calibration strategy for facial recognition that maps cosine similarity between normalized embeddings to well-calibrated probabilities and provides a practical solution for equitable facial recognition without requiring demographic group annotations.
SymTRELLIS is a method that enforces arbitrary finite point group symmetries (rotational, reflectional, and polyhedral) during the flow-based 3D generation of TRELLIS.2, without retraining the underlying VAE or flow model.
Guangda Ji, Qimin Chen, Qinchan Li et al.· arXiv.org· 1 citation· ⚡1
Reach audiences
Advertise in front of researchers, engineers, and readers.
Comparing open-weight VLMs with traditional OCR baselines on low-resource Ancient Greek critical editions, it is shown that VLM errors often remain fluent even when wrong, producing plausible Greek substitutions where traditional engines produce local recognition noise.
Antonia Karamolegkou, Nicolas Angleraud, Benoît Sagot et al.· arXiv.org· 4 citations
EPC-3D-Diff improves robustness and physics consistency, supporting HU aware synthesis for downstream radiotherapy workflows, and generalizes well, achieving substantial improvements in robustness and physics consistency.
Alzahra Altalib, Chunhui Li, Haytham Al Ewaidat et al.· arXiv.org· 1 citation
Curved Ray Expectation Positional Encoding (CRePE) is introduced, which represents each image token as a depth-aware distribution along its Unified Camera Model (UCM) ray and integrates the expected rotary positional phasor along the curved path this distribution traces when projected into each query view.
Seonghyun Jin, Young Min Kim, Sunwoo Park et al.· arXiv.org· 3 citations
WildRelight is introduced, the first in-the-wild dataset specifically created for evaluating single-image relighting models, and it is shown that the dataset allows synthetic models to align with real-world statistics on-the-fly, transforming the intractable sim-to-real challenge into a tractable self-supervised task.
Le-Zhong Wang, Mehmet Onurcan Kaya, S. Bigdeli et al.· arXiv.org· 0 citations
Aes3D, the first systematic framework for assessing the aesthetics of 3D neural rendering scenes, is proposed, and Aes3DGSNet, a lightweight model that directly predicts scene-level aesthetic scores from 3DGS representations, is presented, a lightweight model that operates solely on 3D Gaussian primitives.
The results suggest that progressive contextual conditioning is effective across heterogeneous pathology report generation settings and provides a flexible framework for integrating domain knowledge into vision-language models for computational pathology.
S. Singh, Saarthak Kapse, J. Saltz et al.· arXiv.org· 1 citation
This work presents the first deep learning approach to automatically segment 13 rPCI regions on CT and introduces an anatomically constrained pipeline that trains on merged super-regions and splits them during post-processing using TotalSegmentator landmarks at the hips and the ligament of Treitz.
Pieter C. Gort, Lotte J. S. Fleurkens-Ewals, L. D. Kampmeijer et al.· International Journal of Com...· 1 citation
MAST (Mask-Guided Attention Control for Training-Free Regional-Multi Style Transfer), a unified attention-control framework for frozen diffusion models, achieves the best average ArtFID, FID, and R-FID among all baselines, demonstrating regional style fidelity, content preservation, and scalability.
Dong-Sig Kang, Jae-Young Hwang, Junseo Park et al.· 0 citations
Exploring how generative AI could make machine vision more accessible to businesses. The post GenEye in a Box: Making Machine Vision Something You Can Just Ask For appeared first on GPT-Lab.
Jennifer Neville did not want to go into computer science—but that’s exactly where she landed. Neville discusses the starts and stops that led to her professional sweet spot and her work identifying “surprising failures” making it hard for AI to handle complexity. The post What AI gets wrong and what failure teaches us appeared first on Microsoft Research.
Computer scientist, entrepreneur, and philanthropist will collaborate with the MIT Schwarzman College of Computing to advance AI and scientific discovery.
