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
PGT: Procedurally Generated Tasks for improving visual grounding in MLLMs	Rim Assouel, Amir Bar, Michal Drozdzal	http://arxiv.org/abs/2605.23883v1	cs.CV, cs.AI	May 22, 2026	None	RDR72	Despite remarkable progress in Multimodal Large Language Models (MLLMs), these models still s...
Entrywise Error Bounds for Spectral Ranking with Semi-Random Adversaries	Dongmin Lee, Anuran Makur, Japneet Singh	http://arxiv.org/abs/2605.23854v1	cs.LG, math.ST	May 22, 2026	None	RDR72	Bradley-Terry-Luce (BTL) model estimation is a well-established strategy to rank a collection...
Cambrian-P: Pose-Grounded Video Understanding	Jihan Yang, Zifan Zhao, Xichen Pan	http://arxiv.org/abs/2605.22819v1	cs.CV	May 21, 2026	None	RDR72	Camera pose matters. The position and orientation of each viewpoint define a shared spatial c...
Towards a General Intelligence and Interface for Wearable Health Data	Girish Narayanswamy, Maxwell A. Xu, A. Ali Heydari	http://arxiv.org/abs/2605.22759v1	cs.AI	May 21, 2026	None	RDR72	While ubiquitous wearable sensors capture a wealth of behavioral and physiological informatio...
AdaState: Self-Evolving Anchors for Streaming Video Generation	Yusuf Dalva, Pinar Yanardag	http://arxiv.org/abs/2605.30349v1	cs.CV	May 28, 2026	None	RDR71	Autoregressive video diffusion models generate streaming video by producing frames sequential...
Semantic Gradients Interactions in SSD: A Case Study in Racial Identity and Hate Speech	Felix Ostrowicki, Hubert Plisiecki	http://arxiv.org/abs/2605.27322v1	cs.CL	May 26, 2026	None	RDR71	We introduce interaction SSD, an extension of Supervised Semantic Differential that models ho...
Training-Free Looped Transformers	Lizhang Chen, Jonathan Li, Chen Liang	http://arxiv.org/abs/2605.23872v1	cs.LG, math.NA	May 22, 2026	None	RDR71	We introduce training-free looped transformers, in which a lightweight inference-time wrapper...
Reducing Political Manipulation with Consistency Training	Long Phan, Devin Kim, Alexander Pan	http://arxiv.org/abs/2605.22771v1	cs.CL, cs.AI	May 21, 2026	None	RDR71	Large language models (LLMs) exhibit systematic political bias across a variety of sensitive...
PiD: Fast and High-Resolution Latent Decoding with Pixel Diffusion	Yifan Lu, Qi Wu, Jay Zhangjie Wu	http://arxiv.org/abs/2605.23902v1	cs.CV	May 22, 2026	None	RDR70	Most practical high-resolution text-to-image systems, including latent diffusion and autoregr...
HorizonStream: Long-Horizon Attention for Streaming 3D Reconstruction	Chong Cheng, Peilin Tao, Nanjie Yao	http://arxiv.org/abs/2605.23889v1	cs.CV	May 22, 2026	None	RDR70	Online 3D reconstruction requires estimating camera pose and scene geometry under strict caus...