LIVE-Last scan updating-53 sources active-874 signals today-RESEARCH PVBVR-Pro: A Scalable and Verifiable Suite for Native Visual Reasoning
AI Radar
Subscribe
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
2,287
matching records
Shown
10
current page
Top radar
83
http://arxiv.org/abs/2608.26094v1
Code links
2
on this page
PaperAuthorsarXiv IDCategoriesPublishedCodeRadarSummary
MyoMechanix: Biomechanically-Grounded Compositional Skilled Activity Understanding and CoachingHao Yin, Paritosh Parmar, Lijun Guhttp://arxiv.org/abs/2608.26094v1cs.CV, cs.AIAug 26, 2026NoneRDR83Existing action quality assessment (AQA) datasets and methods rely primarily on visual inputs...
Agentic Autoresearch for Cell-Edge Power Control: Radically Redefining the Researcher's RoleAhmad Khan, Akram Bin Sediq, Sara Azadegi Naeinihttp://arxiv.org/abs/2608.26093v1cs.LG, cs.ITAug 26, 2026NoneRDR74Designing machine learning algorithms for wireless resource management is labour-intensive: t...
Prefix Sliding for efficient test-time scalingNiklas Muennighoff, Zhengyang Wang, Zeyi Chenhttp://arxiv.org/abs/2608.26070v1cs.CL, cs.AIAug 26, 2026DetectedRDR81Test-time scaling uses extra test-time compute to improve performance, such as letting langua...
From Seeing to Acting: Smart Glasses as First-Person Intelligence PlatformsJiangning Zhang, Haojun Chen, Yong Liuhttp://arxiv.org/abs/2608.24877v1cs.CVAug 25, 2026NoneRDR86Smart glasses are evolving from capture and display accessories into first-person intelligenc...
LAION-BVD: A 10-Million-Hour Open Video Dataset for Multimodal Pre-trainingAndreas Hochlehnert, Marianna Nezhurina, Mehdi Chertihttp://arxiv.org/abs/2608.24845v1cs.CV, cs.AIAug 25, 2026NoneRDR84We present LAION-BVD, a large-scale open video dataset for multimodal learning, which contain...
A Geometric Theory of Robust Fairness AuditsBinita Maityhttp://arxiv.org/abs/2608.24818v1cs.LGAug 25, 2026NoneRDR83Neighborhood-based fairness audits evaluate individual fairness by comparing predictions amon...
Strictly Causal Streaming Video Anomaly Detection with a Theoretically-Grounded State-Space CoreYogesh Kumarhttp://arxiv.org/abs/2608.24810v1cs.AIAug 25, 2026NoneRDR86Recent work has applied Mamba style state space models (SSMs) to video anomaly detection, yet...
Right Diagnoses, Decorative Reasoning:A Perturbation Audit of Medical Chain-of-ThoughtMengzhu Xu, Jifan Gao, Xia Jianghttp://arxiv.org/abs/2608.24790v1cs.AIAug 25, 2026NoneRDR81Clinicians read chain-of-thought (CoT) rationales as evidence of medical reasoning, but wheth...
Property-Specific Recoverability from Contact PPG to Camera rPPG under Heterogeneous Observation ConditionsTimothy Oladunni, Farouk Ganiyu-Adewumihttp://arxiv.org/abs/2608.27392v1eess.SP, cs.AIAug 27, 2026NoneRDR80Camera-derived remote photoplethysmography (rPPG) is commonly validated through endpoint accu...
LeFlow: Generative Latent Flow Planning for World ModelsHsiang-Wei Huang, Jianxu Shangguan, Junbin Luhttp://arxiv.org/abs/2608.24855v1cs.CVAug 25, 2026DetectedRDR82Latent world models are inherently strong encoders that transform image pixel to latent embed...