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/2610.08735v1

Code links

on this page

Paper	Authors	arXiv ID	Categories	Published	Code	Radar	Summary
Optimal and Efficient Online Inverse Optimization	Anupam Gupta, Guru Guruganesh, Honghao Lin	http://arxiv.org/abs/2610.08735v1	cs.LG, cs.DS	Oct 6, 2026	None	Score64	In online inverse linear optimization, a learner recommends an action and then observes the c...
Towards Looped Models Done Right, Part II: Rethinking at Fixed Points	Benhao Huang, Chufan Shi, Junlin Chen	http://arxiv.org/abs/2610.06833v1	cs.LG	Oct 5, 2026	None	Score65	Every recurrence of a looped language model adds cost in training, decoding, prefill, and rei...
Certification of Real Images through Calibrated Content Authentication	Sarim Hashmi, Abdelrahman Elsayed, Mohammed Talha Alam	http://arxiv.org/abs/2610.05870v1	cs.CV	Oct 5, 2026	None	Score75	Generative models can synthesize high-quality inauthentic multimedia content that is already...
WorldGuide: Goal-Directed Video World Model for Procedural Task Execution	Ankan Deria, Komal Kumar, Hisham Cholakkal	http://arxiv.org/abs/2610.12459v1	cs.CV	Oct 8, 2026	None	Score58	Video generators and video-based world models can synthesize plausible visual trajectories, b...
Toward Joint Optimization of Circuit Depth and Training Data Size in Adaptively Grown Quantum Classifiers	Saeefa Rubaiyet Nowmi, Md Mahmuduzzaman Kamol, Mohammad Saidur Rahman	http://arxiv.org/abs/2610.12428v1	quant-ph, cs.LG	Oct 8, 2026	None	Score61	Building a quantum model involves a tradeoff: how complex the circuit should be, and how much...
Oracle-Efficient and Parameter-Free Agnostic Smoothed Online Learning	Sasha Voitovych, Adam Block, Alexander Rakhlin	http://arxiv.org/abs/2610.10499v1	cs.LG, stat.ML	Oct 7, 2026	None	Score64	Online learning is an attractive framework in many domains because it permits well-defined le...
How assigned AI use before class shapes active student engagement in class	Dan J. Wang, Neelam Modi Jain, Vanessa Burbano	http://arxiv.org/abs/2610.10463v1	cs.HC, cs.AI	Oct 7, 2026	None	Score63	AI learning tools are rapidly entering classrooms, but evidence about whether they help stude...
Backend-Agnostic Sparse Attention for Fast High-Resolution Visual Generation	Liao Ma, Jiayi Song, Yunfeng Wu	http://arxiv.org/abs/2610.08772v1	cs.CV	Oct 6, 2026	None	Score61	Diffusion Transformers (DiTs) have achieved strong performance in image and video generation,...
Neural Petri flows for chemical reactions	Jose Eduardo Escrig Molina, Daniel Probst	http://arxiv.org/abs/2610.08750v1	cs.LG, physics.chem-ph	Oct 6, 2026	None	Score63	Petri nets have been used to describe chemical processes such as reactions.They map well to c...
A Response Theory Probe for Learned Stochastic AI Simulators, Tested on Lorenz-63	João Böger, Simon Driscoll, Niccolò Zagli	http://arxiv.org/abs/2610.06798v1	math.DS, cs.LG	Oct 5, 2026	None	Score72	Machine-learning emulators of chaotic and stochastic systems are usually validated on forecas...