Category
4,009 papers
Experiments show that SMDDFNet achieves competitive accuracy against recent detectors while retaining real-time throughput, and a multi-scale feature fusion neck further aggregates pyramid features for robust localization of small signs.
Latent world models that integrate a flow in a frozen self supervised latent space train stably and cheaply, yet silently lose the property manipulation depends on most: motion. The pretrained flow never moves the manipulated object; retraining it with latent-only losses only trades stillness for teleport-like motion....
AnchorReasoning is introduced, a visually grounded reasoning dataset built on WOD-E2E, containing 416,119 annotated frames and 395,379 decision-critical elements across four major categories and 19 fine-grained types and a curriculum supervised fine-tuning strategy that progressively learns these hierarchical capabilit...
Findings support MemBodied as a practical alternative to expanding the policy context for history-dependent manipulation, a fixed-size episodic memory with two complementary components: an associative state that records interactions across policy calls and an episode anchor that preserves a compact representation of th...
Reach audiences
Advertise in front of researchers, engineers, and readers.
Pathology foundation models (PFMs) have transformed computational pathology through powerful representation learning from histopathological images. PFMs provide rich, discriminative representations for whole slide image (WSI) analysis, enabling tasks such as slide-level classification under multiple instance learning (...
A three-stage framework that consists of an implicit neural representation (INR) for estimating missing parts of the truncated projection data, an iterative reconstruction for generating a secondary volumetric image with improved anatomical consistency and a fast diffusion model for image enhancement is proposed.
Multimodal large language models (MLLMs) fre- quently generate text that is inconsistent with the input image. While object- and attribute-level hallucinations have received considerable attention, relational hallucinations (incorrect de- scriptions of spatial or interactive relationships between objects) remain largel...
TopoGS is a topology-aware anchor feature aggregation framework with two lightweight components that establishes bidirectional cross-level gradient pathways by fusing per-level context triplets with a residual MLP and applies soft weighting to accommodate varying topological sparsity.
This is the first comprehensive evaluation of ADC-only breast cancer pipelines for classification, detection, and segmentation tasks and evaluates the application of different state-of-the-art deep learning techniques for detection and segmentation of breast cancer using ADC-only images.
The Inner Guardrail (InGuard) is proposed, a safety framework that works inside the pipeline on the model's own representations, leaving base-model parameters untouched and the RevGen Safety Benchmark to evaluate T2I safety under realistic conditions.
SGCA-Net is proposed, a spinning radar place recognition framework that combines rotation-robust feature extraction with Spatially Gated Correlation Aggregation (SGCA) and consistently outperforms SOTA methods across urban, campus, and open-road environments, while remaining robust to substantial heading variation.
Results show that GFM-derived geometry can provide a persistent structural prior for VPR when visual appearance becomes unreliable, with the largest gains under reverse traversal and long-term appearance variation.
Professor Paris Smaragdis develops computers with superhuman hearing for applications like speech recognition, music understanding, and environmental monitoring.
GPT-Lab
· gpt-lab.eu
Oct 8, 2026
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.
A Blog post by H company on Hugging Face
A Blog post by Liquid AI on Hugging Face
Computer scientist, entrepreneur, and philanthropist will collaborate with the MIT Schwarzman College of Computing to advance AI and scientific discovery.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
