LIVE-Last scan updating-53 sources active-131 signals today-AI TOOLSOpen-KNEAD: Framework for Agentic Nutrition Estimation from Meal Images
Research radar

arXiv preprints, filtered for developer impact.

Concise summaries of new AI papers, ranked for how likely they are to change how production systems are built. arXiv collection remains rate-limited.

Papers tracked
1,289
1 arXiv sources
Top radar
86
http://arxiv.org/abs/2607.13027v1
Published 24h
59
by paper date
Rate limit
1/3s
arXiv policy
PaperAuthorsarXiv IDCategoriesPublishedCodeRadarSummary
Using AI-based Learning Assistants in Higher Education: A Large-Scale Descriptive AnalysisKristina Schaaff, Quintus Stierstorfer, Valerie Heckelhttp://arxiv.org/abs/2607.08748v1cs.AI, cs.HCJul 9, 2026NoneRDR61In this study, we present a large-scale descriptive analysis of the use of an AI-based learni...
Vision as Unified Multimodal GenerationXiaoyang Han, Jianhua Li, Kewang Denghttp://arxiv.org/abs/2607.06560v1cs.CVJul 7, 2026NoneRDR63We formulate computer vision as unified multimodal generation, where heterogeneous visual tas...
ProxyPose: 6-DoF Pose Tracking via Video-to-Video TranslationRuihang Zhang, Felix Taubner, Pooja Ravihttp://arxiv.org/abs/2607.06555v1cs.CVJul 7, 2026NoneRDR72Tracking the six-degree-of-freedom (6-DoF) pose of objects and surfaces from monocular video...
ELSA3D: Elastic Semantic Anchoring for Unified 3D Understanding and GenerationTianjiao Yu, Xinzhuo Li, Yifan Shenhttp://arxiv.org/abs/2607.06565v1cs.CV, cs.AIJul 7, 2026NoneRDR65Unified 3D foundation models aspire to generate 3D assets and reason about them in language w...
Life Style Levels: Neighborhood Delineation using Geospatial DataSrivatsa Kulkarni, Debarag Banerjeehttp://arxiv.org/abs/2607.06529v1cs.CLJul 7, 2026NoneRDR74Fine-scale socioeconomic information is often unavailable across rapidly ur-banizing regions...
Bridging Physical Reasoning and Task Generalization via Visual Action Outcome Reasoning AlignmentHan-Jun Ko, Jr-Jen Chen, Haobo Yuanhttp://arxiv.org/abs/2607.06522v1cs.AI, cs.CVJul 7, 2026NoneRDR64Vision-language models (VLMs) struggle to generalize in interactive physical reasoning, parti...
Assessing the Operational Impact of Poisoning Attacks over Augmented 3D Point Cloud Public Datasets for Connected and Autonomous VehiclesMarwan Lazrag, Badis Hammi, Lorena Gonzalez-Manzanohttp://arxiv.org/abs/2607.06484v1cs.CR, cs.CVJul 7, 2026NoneRDR74Poisoning attacks against public datasets lead to major concerns, such as (i) misclassificati...
Characterization of the basin of convexity for multi-snapshot spike deconvolution via variable projectionMeghna Kalra, Maxime Ferreira Da Costa, Kiryung Leehttp://arxiv.org/abs/2607.09593v1stat.ML, eess.SPJul 10, 2026NoneRDR58We study the problem of multi-snapshot spike deconvolution, where the goal is to recover the...
Rethinking Indic AI from a Lens of Cultural Heritage PreservationAparna Madva, Sharath Srivatsa, Srinath Srinivasahttp://arxiv.org/abs/2607.06544v1cs.AI, cs.CLJul 7, 2026NoneRDR64As Artificial Intelligence (AI) makes inroads into different parts of the Indian subcontinent...
Pitwall: Faithful Natural-Language Race-Strategy Briefings from a Calibrated Real-Time Monte Carlo EngineJuan S. Santillanahttp://arxiv.org/abs/2607.06495v1cs.CL, cs.AIJul 7, 2026NoneRDR64Live sports commentary is grounded generation under a deadline: statements concern real, name...