Differential privacy (DP)'s effect in medical imaging is typically evaluated only through end-to-end performance, leaving the mechanism of privacy-induced utility loss unclear. We introduce Differential Privacy Representation Geometry for Medical Imaging (DP-RGMI), a framework that interprets DP as a structured transfo...
S. T. Arasteh, Marziyeh Mohammadi, S. Nebelung et al.· arXiv.org· 0 citations
Input Diversity (DI), a random resize and pad applied at each attack iteration, is a near-default ingredient of transfer-based attacks, widely assumed to improve transferability. We show this assumption is regime-dependent and, for adversarially trained surrogates, often reversed. Holding the attack fixed and varying o...
Near-surface weather varies over tens to hundreds of meters, yet remains unresolved in analyses and forecasts. We test whether this variation can be inferred without resolving atmospheric dynamics. Combining sparse weather stations, high-resolution Earth observation, and coarse atmospheric dynamics, we infer temperatur...
Jonathan Giezendanner, Qidong Yang, Ruizhe Huang et al.· 0 citations
DELTA is presented, which separates physical structure recognition, logical structure recognition, and OCR to extract both layout and content accurately, and TarQA is introduced, an LLM fine-tuned on OTSL sequences that encodes cell arrangements and textual content.
This work introduces quantum-inspired tensor-network circuits as trainable transforms for image inpainting. Among the proposed architectures, the diagonal quantum Fourier transform (QFT) relaxation is invertible with $O(N^2 \log N)$ computational cost for $N\times N$ images, inherently preserving minimum coherence thro...
Residual-aware Layer-wise Relevance Propagation (ResLRP) is introduced, a simple extension of LRP whose propagation rules explicitly account for cancellations in residual branches, are exactly conservative, and provably bound relevance explosion.
Jim Berend, Reduan Achtibat, Daniel Schäffer et al.· 0 citations
The results support frozen geospatial embeddings as a low-compute candidate for regional cropland mapping, subject to the limits of a single-state study, a 30 m-derived training reference, and a one-block human validation.
Mohammad Ammar Mughees, Giovanni Montefoschi, Zhong-Xin Chen et al.· 0 citations
Assistive autonomous systems must anticipate human goals before an observed behavior is complete. This article formulates anticipation as goal inference from a partially observed multimodal episode together with structured prediction of the remaining behavior, rather than exact motor forecasting. A compact Hierarchical...
Cranial implant generation is an important task in medical imaging. Recent point cloud based generative methods, particularly flow matching, offer strong reconstruction quality and efficient sampling, but still require multiple neural function evaluations during inference. This limits rapid generation of multiple plaus...
NeuroTS-Net is introduced, a three-dimensional encoder-decoder convolutional neural network architecture for multi-class semantic segmentation that incorporates a dual-scale raw-detail stream, adaptive low-resolution context selection, and detail-preserving multipath downsampling that efficiently modeling broader tumor...
Darius Peteleaza, Razvan-Gabriel Dumitru, Bogdan Neamtu et al.· 0 citations
TEMPO is proposed, which augments a pretrained VLA with two temporal inputs: a motion summary extracted from a frozen video foundation model to resolve motion ambiguity and a compact proprioceptive history to resolve state aliasing.
Zhen-Yang Feng, Jimin Heo, Erik B. Sudderth et al.· 2 citations· ⚡1
The scarcity in this study is constructed by subsampling a large corpus by changing only the number of real transcribed words used for fine-tuning across nine budgets from 10 to 4,000 and four initialisation regimes, with six seeds at every point.
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.
