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/2610.05872v1

Code links

on this page

Paper	Authors	arXiv ID	Categories	Published	Code	Radar	Summary
Off-Policy Merging Beats On-Policy Self-Distillation for Continual Learning	Chen Henry Wu, Thomas Zhang, Aditi Raghunathan	http://arxiv.org/abs/2610.05872v1	cs.LG, cs.AI	Oct 5, 2026	None	Score65	A long-standing goal of AI is a model that can continually learn and improve itself. On post-...
On the Sequentially Semiseparable Structure of SDE-Induced Kernels and Efficient Algorithms for Kernel-Based Estimation Problems	Mikkel Paltorp, Luigi Caglio, Tianshi Chen	http://arxiv.org/abs/2610.05856v1	stat.ML, math.NA	Oct 5, 2026	None	Score62	We study kernel functions induced by a linear time-invariant (LTI) stochastic differential eq...
Feature identification for parameter extraction and defect detection using machine learning	Yan Guo, Helda Pahlavani, Artem Khachaturiants	http://arxiv.org/abs/2610.05812v1	cs.LG	Oct 5, 2026	None	Score64	Process control of advanced semiconductor nodes is not only pushing the limits of metrology e...
Broken scale symmetries in undercomplete linear autoencoders	Farhad Pashakhanloo, Jacob A. Zavatone-Veth	http://arxiv.org/abs/2610.03640v1	cs.LG, q-bio.NC	Oct 2, 2026	None	Score72	Neural network loss landscapes have many symmetries, which are preserved by gradient flow but...
Transporting Unsecured Stacked Payloads with a Quadrupedal Robot via Multi-Objective Reinforcement Learning	Nobuo Namura, Masayuki Hiromoto, Kento Uemura	http://arxiv.org/abs/2610.05819v1	cs.RO, cs.LG	Oct 5, 2026	None	Score64	Transporting unsecured payloads with legged robots over uneven terrain requires balancing loc...
Moore, Escher, Penrose: A Conformal Golden Braid	Sophia Feldman, Assaf Shocher	http://arxiv.org/abs/2610.02210v1	cs.CV	Oct 1, 2026	None	Score58	I don't think I have ever done anything as peculiar in my life. Among other things, it shows...
Every Ablation Is a Dose: Counterweights and the Semblance of Self-Repair	Areeb Ahmad, Pratinav Seth, Vinay Kumar Sankarapu	http://arxiv.org/abs/2610.02173v1	cs.LG, cs.CL	Oct 1, 2026	None	Score61	Ablate a component of a language model, and other components often appear to adjust and compe...
When May a Bandit Leave Its Anchor? E-Process-Authorized Thompson Sampling under Non-stationarity	Mayand Gulati, Kerong Wang, WeiChen Au	http://arxiv.org/abs/2610.03646v1	cs.LG, stat.ML	Oct 2, 2026	None	Score61	Stationarity rewards memory, but after a change the same history can mislead. We ask when for...
On the Convergence of Success Conditioning for Policy Optimization	Matthew Brun, Xu Andy Sun	http://arxiv.org/abs/2610.03642v1	cs.LG, math.OC	Oct 2, 2026	None	Score61	Success conditioning is a strategy for improving decision-making policies in stochastic envir...
Private online learning and prediction for Littlestone classes	Amartya Sanyal	http://arxiv.org/abs/2610.06822v1	cs.LG, cs.CR	Oct 5, 2026	None	Score64	We study mistake bounds for differentially private online learning and online prediction unde...