Category
3,363 papers
It is proved that automatically generated domain-specific datasets lead to better pretraining than large-scale supervised datasets such as ImageNet-1k and ImageNet-21k and proves the superiority of PaS datasets over existing traditional domain-specific datasets in terms of diversity, scale, and effectiveness.
This work proposes an instance-wise linearization approach to reformulates the forward computation process of a neural network prediction and discusses the application of this technique in both supervise classification and unsupervised neural network learning parametric t-SNE dimension reduction.
As web agents close the gap with humans on benchmarks, one question arises: Do today's agents perform just as well on tomorrow's web? We introduce TimeWarp, a benchmark that emulates the evolving web. TimeWarp consists of three web environments, each with six UI versions spanning UI design, frontend code, and workflows...
Visual encoders construct a representation of the image input for Vision-Language models. How much conceptual, as opposed to immediately visible, information does this representation contain? We use canonical color as a controlled test case to ask whether vision encoders make canonical-color information linearly access...
Reach audiences
Advertise in front of researchers, engineers, and readers.
Open vocabulary 3D semantic segmentation methods typically lift CLIP features into 3D. This embeds points in a joint vision-language space known to behave like a bag-of-words on compositional tasks. Furthermore, even annotation free variants often require a large 3D training corpus and a dedicated 3D encoder per domain...
This work presents Hi-FLoop, a branch-consistent multi-timescale state-feedback framework for multi-agent traffic simulation, which induces a sparse directed future graph and uses conflict probabilities and signed arrival-time differences to refine interaction-aware motion.
Kairos is introduced, a video dataset for video-language modeling with time-resolved annotations that supports fine-grained evaluation, long-range modeling and reasoning, instruction data construction, representation learning, and video generation.
CausalChapter is an intervention-inspired framework for long-video chaptering that estimates prediction-level influence through lightweight masking and removal interventions that improves boundary localization, chapter description quality, and cross-chapter coherence.
TriCCOT is introduced, a tri-part architecture for robust and deployable onboard object detection that combines a convolutional region proposal network, a conformal prediction stage, and Aper-GATES, the authors' hardware-friendly attention-based classifier, enabling unified CNN-Transformer inference for spaceborne embe...
This work introduces Coherent4D, a large-scale egocentric dataset for continuous 4D interaction forecasting, comprising approximately 233K samples across three domains, and proposes HIGFlow, a Hand Interaction Guided Residual Flow framework that models forecasting as a cascaded where-to-how process.
The proposed SynthRCT enables patient-specific sampling of plausible anatomical transformations beyond predefined robustness scenarios, and is validated on respiratory 4DCT data with multiple breathing-phase anatomies per subject.
AirAnchor is proposed, a new paradigm that bridges local and global spatial information through spatial anchors and integrates both into a shared navigation framework, enabling comprehensive spatial grounding for decision-making.
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.
Human-Computer Interaction and Visualization
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
