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
How and What to Imagine? Visual Thinking in Unified Multimodal Models for Cross-View Spatial Reasoning	Qian Yang, Ankur Sikarwar, Huy Le	http://arxiv.org/abs/2605.27310v1	cs.CV	May 26, 2026	None	RDR75	Cross-view spatial reasoning remains a weak spot for vision-language models (VLMs): they ofte...
Language Models Need Sleep	Sangyun Lee, Sean McLeish, Tom Goldstein	http://arxiv.org/abs/2605.26099v1	cs.CL, cs.AI	May 25, 2026	None	RDR75	Transformer-based large language models are increasingly used for long-horizon tasks; however...
From Raw Experience to Skill Consumption: A Systematic Study of Model-Generated Agent Skills	Zisu Huang, Jingwen Xu, Yifan Yang	http://arxiv.org/abs/2605.23899v1	cs.AI	May 22, 2026	None	RDR75	Language agents increasingly improve by reusing \emph{skills} -- structured procedural artifa...
Smart-Insertion-V: Photorealistic Video Insertion via a Closed-Loop Feedback Dual-Stream Framework	Xiao Cao, Yansong Qu, Xiangzhen	http://arxiv.org/abs/2605.23891v1	cs.CV	May 22, 2026	None	RDR75	Mask-free video object insertion has emerged as a challenging task, requiring harmonious inte...
Multilingual Knowledge Transfer under Data Constraints via Lexical Interventions	Anastasiia Sedova, Natalie Schluter, Skyler Seto	http://arxiv.org/abs/2605.23885v1	cs.CL	May 22, 2026	None	RDR75	Cross-lingual knowledge transfer is critical for building high-performing multilingual langua...
Evaluating Commercial AI Chatbots as News Intermediaries	Mirac Suzgun, Emily Shen, Federico Bianchi	http://arxiv.org/abs/2605.22785v1	cs.CL	May 21, 2026	None	RDR75	AI chatbots are rapidly shaping how people encounter the news, yet no prior study has systema...
Advancing Mathematics Research with AI-Driven Formal Proof Search	George Tsoukalas, Anton Kovsharov, Sergey Shirobokov	http://arxiv.org/abs/2605.22763v1	cs.AI	May 21, 2026	None	RDR75	Large language models (LLMs) increasingly excel at mathematical reasoning, but their unreliab...
NeuROK: Generative 4D Neural Object Kinematics	Chen Geng, Guangzhao He, Yue Gao	http://arxiv.org/abs/2605.30347v1	cs.CV, cs.GR	May 28, 2026	None	RDR74	Data-driven approaches have revolutionized 3D vision, enabling transformers to effectively re...
Efficient Test-Time Finetuning of LLMs via Convex Reconstruction and Gradient Caching	Alaa Khamis, Alaa Maalouf	http://arxiv.org/abs/2605.30337v1	cs.LG	May 28, 2026	None	RDR74	Test-time finetuning (TTFT) is a rapidly evolving paradigm that adapts a language model to ea...
When, why, and how do diffusion posterior samplers fail? A finite-sample lens	Benjamin A. Burns, Sara Fridovich-Keil	http://arxiv.org/abs/2605.30330v1	cs.LG	May 28, 2026	None	RDR74	Diffusion models have excellent capacity to model complex distributions of natural data, whic...