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

1,289

1 arXiv sources

Top radar

http://arxiv.org/abs/2607.13027v1

Published 24h

by paper date

Rate limit

1/3s

arXiv policy

Paper	Authors	arXiv ID	Categories	Published	Code	Radar	Summary
Max Out GRPO Signal: Adaptive Trace Prefix Control for Hard Reasoning Problems	Vladislav Beliaev	http://arxiv.org/abs/2607.07674v1	cs.LG, cs.CL	Jul 8, 2026	None	RDR64	Group Relative Policy Optimization (GRPO) stalls on a model's hardest problems: when no rollo...
Rethinking Indic AI from a Lens of Cultural Heritage Preservation	Aparna Madva, Sharath Srivatsa, Srinath Srinivasa	http://arxiv.org/abs/2607.06544v1	cs.AI, cs.CL	Jul 7, 2026	None	RDR64	As Artificial Intelligence (AI) makes inroads into different parts of the Indian subcontinent...
Pitwall: Faithful Natural-Language Race-Strategy Briefings from a Calibrated Real-Time Monte Carlo Engine	Juan S. Santillana	http://arxiv.org/abs/2607.06495v1	cs.CL, cs.AI	Jul 7, 2026	None	RDR64	Live sports commentary is grounded generation under a deadline: statements concern real, name...
A Definition and Roadmap for World Models	Xinyuan Chen, Haoyu Guo, Shi Guo	http://arxiv.org/abs/2607.06401v1	cs.AI	Jul 7, 2026	None	RDR64	World models -- internal simulators that learn the structure and dynamics of an environment -...
A Function-Space Dichotomy for Compositional Learning: Exponential Sub-Optimality of the Neural Tangent Kernel	Arkaprabha Ganguli, Emil Constantinescu	http://arxiv.org/abs/2607.06382v1	stat.ML, cs.LG	Jul 7, 2026	None	RDR65	A persistent empirical observation is that trained neural networks outperform their neural ta...
SynCity 3000: Bootstrapping Scene-Scale 3D Diffusion	Paul Engstler, Iro Laina, Christian Rupprecht	http://arxiv.org/abs/2607.05392v1	cs.CV	Jul 6, 2026	None	RDR60	We present SynCity 3000, a framework for generating 3D scenes that are globally coherent whil...
On the Convergence of Adam, Revisited	Steven Heilman, Sampad Mohanty	http://arxiv.org/abs/2607.03519v1	cs.LG, math.OC	Jul 3, 2026	None	RDR62	We show that projected Adam for online optimization with arbitrary moment decay parameters $β...
WildSplat: Feedforward Gaussian Splatting from Unposed In-the-Wild Images	Xiyu Zhang, Jingyu Zhuang, Hongjia Zhai	http://arxiv.org/abs/2607.05347v1	cs.CV	Jul 6, 2026	None	RDR60	While feedforward 3D reconstruction excels at efficient novel view synthesis, it typically fa...
G-RRM: Guiding Symbolic Solvers with Recurrent Reasoning Models	Timo Bertram, Sidhant Bhavnani, Richard Freinschlag	http://arxiv.org/abs/2607.02491v1	cs.AI	Jul 2, 2026	None	RDR61	In this work, we focus on SE-RRMs, a symbol-equivariant instantiation of RRMs that exhibits i...
Factor-Augmented Machine Learning Panel Regressions	Andrii Babii, Luca Barbaglia, Eric Ghysels	http://arxiv.org/abs/2607.06368v1	econ.EM, math.ST	Jul 7, 2026	None	RDR61	This paper develops the asymptotic theory for high-dimensional panel data regressions in sett...