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

3,367

matching records

Shown

current page

Top radar

http://arxiv.org/abs/2610.06784v1

Code links

on this page

Paper	Authors	arXiv ID	Categories	Published	Code	Radar	Summary
How to scale your HEP ML models: A recipe for robust architecture comparisons at scale	Matthias Vigl, Nikita Pond, Jackson Barr	http://arxiv.org/abs/2610.06784v1	hep-ex, cs.LG	Oct 5, 2026	None	Score75	Much of the recent progress in machine learning domains such as language models has come from...
Finite-Sample Distribution Theory and Efficient Large-Scale Inference for Online Quantile Regression	Ziyang Wei, Jiaqi Li, Lan Wang	http://arxiv.org/abs/2610.05869v1	stat.ML, cs.LG	Oct 5, 2026	None	Score66	This paper studies online quantile regression for large-scale and streaming data using Stocha...
The Blind Spot Paradox: When Adaptive Classifiers Defeat Drift Detectors	Raphaël Minato, Fabrice Popineau, Arpad Rimmel	http://arxiv.org/abs/2610.05853v1	cs.LG, stat.ML	Oct 5, 2026	None	Score74	Monitoring concept drift from an adaptive classifier's error stream creates an operational co...
Less Decoder is More Encoder: Geometric Representation Learning from Novel View Synthesis	Keerthi Kaashyap, Dennis Anthony, Akshay Krishnan	http://arxiv.org/abs/2610.03717v1	cs.CV, cs.AI	Oct 2, 2026	None	Score75	This paper examines the role of Novel View Synthesis (NVS) in geometric representation learni...
RNADyn: A Benchmark for Generating and Understanding RNA Dynamics	Yiming Huang, Lennart Bastian, Hanqun Cao	http://arxiv.org/abs/2610.03712v1	cs.LG, physics.bio-ph	Oct 2, 2026	None	Score70	Ribonucleic acid (RNA) functions through conformational changes that are not fully captured b...
LapMerge: Differentiable Exact-Budget Token Merging in Linear Time	Magdalena Trędowicz, Aleksandra Nowak, Tomasz Steifer	http://arxiv.org/abs/2610.13858v1	cs.CV	Oct 9, 2026	None	Score58	Modern vision and language models process ever longer token sequences, and reducing them is t...
On the Computational Tractability of Robust Bandits	Vanessa Kosoy, Vinayak Pathak	http://arxiv.org/abs/2610.08740v1	cs.LG	Oct 6, 2026	None	Score63	Learning when the environment does not belong to the learner's hypothesis class is typically...
AnchorPose for Geometry-Aware MOF Assembly through Meso-Grained Pose Generation	Zhonglong Peng, Rui Jiao, Chang Chen	http://arxiv.org/abs/2610.05843v1	cs.CE, cond-mat.mtrl-sci	Oct 5, 2026	None	Score73	Predicting metal-organic framework (MOF) structures from given building blocks requires recov...
Dual-Rate Force-Image Control with Model-Based Orientation Limits for Robotic Ultrasound	Tyler Foster, Qiang Zhang, A B M Tahidul Haque	http://arxiv.org/abs/2610.05839v1	cs.RO, cs.CV	Oct 5, 2026	None	Score70	Robotic ultrasound couples a high-rate contact-force loop with slower, delayed image feedback...
Plan Canvas: Fixed Reasoning Regions for Continuous Language Flows	Miaohe Niu, Pengxiang Li, Jingbo Zhu	http://arxiv.org/abs/2610.05815v1	cs.CL	Oct 5, 2026	None	Score73	Continuous language flows generate text by denoising all positions of a target canvas togethe...