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

180

1 arXiv sources

Top radar

http://arxiv.org/abs/2605.30352v1

Published 24h

by paper date

Rate limit

1/3s

arXiv policy

Paper	Authors	arXiv ID	Categories	Published	Code	Radar	Summary
It's the humans, not the data: Geopolitical bias in LLMs originates in post-training, amplified by the language of the prompt	Stuart Bladon, Brinnae Bent	http://arxiv.org/abs/2605.23825v1	cs.LG, cs.AI	May 22, 2026	None	RDR70	It has generally been assumed that geopolitical bias in language models originates from the t...
Deep Neural Networks for Doubly Robust Estimation with Nonprobability Survey Samples	Yufang Dai, Shihua Luo, Wendy Lou	http://arxiv.org/abs/2605.28762v1	math.ST, stat.AP	May 27, 2026	None	RDR69	Integrating probability and nonprobability survey samples is an important problem in modern s...
Q-GeoMem: Question-Guided Geometric Memory for Video Spatial Reasoning	Xianqiang Gao, Qizhi Chen, Delin Qu	http://arxiv.org/abs/2605.27318v1	cs.CV	May 26, 2026	None	RDR69	Video spatial reasoning requires accumulating viewpoint-dependent evidence over time while re...
Geo-Align: Video Generation Alignment via Metric Geometry Reward	Zizun Li, Haoyu Guo, Runzhe Teng	http://arxiv.org/abs/2605.23903v1	cs.CV	May 22, 2026	None	RDR69	Camera-controlled video generation has achieved remarkable progress in recent years. However,...
Learning a Particle Dynamics Model with Real-world Videos	Chanho Kim, Suhas V. Sumukh, Li Fuxin	http://arxiv.org/abs/2605.23845v1	cs.CV	May 22, 2026	None	RDR69	Data-driven learning approaches for physics simulation, sometimes referred to as world models...
DecQ: Detail-Condensing Queries for Enhanced Reconstruction and Generation in Representation Autoencoders	Tianhang Wang, Yitong Chen, Wei Song	http://arxiv.org/abs/2605.22777v1	cs.CV	May 21, 2026	None	RDR69	Representation Autoencoders (RAEs) leverage frozen vision foundation models (VFMs) as tokeniz...
Synthetic Data Alone is Enough? Rethinking Data Scarcity in Pediatric Rare Disease Recognition	Ganlin Feng, Yuxi Long, Erin Lou	http://arxiv.org/abs/2605.22767v1	cs.CV	May 21, 2026	None	RDR69	Children with rare genetic diseases often exhibit distinctive facial phenotypes, yet developi...
From Activation to Causality: Discovery of Causal Visual Representations in the Human Brain	Yuval Golbari, Navve Wasserman, Matias Cosarinsky	http://arxiv.org/abs/2605.23895v1	cs.CV	May 22, 2026	None	RDR68	Identifying which brain regions represent a visual concept in the human brain is a central ch...
OmniVerifier-M1: Multimodal Meta-Verifier with Explicit Structured Recalibration	Xinchen Zhang, Bowei Liu, Jiale Liu	http://arxiv.org/abs/2605.28805v1	cs.CL, cs.AI	May 27, 2026	None	RDR67	Visual outcomes are increasingly central to multimodal large language models, making reliable...
Affective Music Recommendation: A Rollout-Based World Model for Offline Preference Optimization	Audrey Chan, Aaron Labbé, Jacob Lavoie	http://arxiv.org/abs/2605.28810v1	cs.LG, cs.IR	May 27, 2026	None	RDR65	Functional music applications, from consumer focus and sleep aids to clinical interventions,...