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

3,427

matching records

Shown

current page

Top radar

http://arxiv.org/abs/2609.31612v1

Code links

on this page

Paper	Authors	arXiv ID	Categories	Published	Code	Radar	Summary
First-Order Stationarity of Reverse Diffusions	Zhifeng Chen, Chenyang Jiang, Yazhen Wang	http://arxiv.org/abs/2609.31612v1	stat.ML, cs.LG	Sep 25, 2026	None	Score62	Recent literature has shown a strong connection between optimization and sampling. We develop...
Minimally Invasive Steering of Language Models	Taha Entesari, Jingyu Zhang, Daniel Khashabi	http://arxiv.org/abs/2609.30218v1	cs.LG, cs.AI	Sep 24, 2026	None	Score72	Pre-logit steering adapts a frozen language model to a test-time reward by adding vectors to...
Lagrangian--Hamiltonian Flows for Video Prediction and Image Generation: A Symplectic Perspective	Jiawei Hu	http://arxiv.org/abs/2609.35710v1	cs.CV	Sep 28, 2026	None	Score60	We introduce LHFM, a geometric framework for learning image dynamics. Drawing on structures c...
Position Aware Layer Queries for Test Time Training in Vision Language Models	Rajat Modi, Priyank Pathak, Xin Liang	http://arxiv.org/abs/2609.34021v1	cs.CV	Sep 27, 2026	None	Score60	Test-Time Training (TTT) adapts models to incoming test samples (e.g. out-of-distribution, (O...
Generalization behavior of OPTQ and the role of regularization	Erin George, Rayan Saab	http://arxiv.org/abs/2609.31560v1	cs.LG	Sep 25, 2026	None	Score72	Large neural networks can be compressed by rounding or "quantizing" their weights to numbers...
Riemannian Gradient Descent for Gaussian Mixture Models with unknown diagonal covariances	Romane Giard, Yohann De Castro, Roland Denis	http://arxiv.org/abs/2609.30220v1	math.OC, math.ST	Sep 24, 2026	None	Score69	This paper investigates the numerical resolution of the Beurling-LASSO (BLASSO), a convex opt...
Adapting for AI: How elementary teachers adjust their practices for an AI-integrated curriculum	Fasika Melese, Ruiyang Wu, Xinyue Cui	http://arxiv.org/abs/2609.31569v1	cs.HC, cs.AI	Sep 25, 2026	None	Score61	Conversational AI tools are entering children's everyday experiences, and schools are interes...
A Nearly Quadratic Lower Bound for Linear Optimization over Convex Bodies in the Membership Oracle Model	Santosh S. Vempala	http://arxiv.org/abs/2609.30215v1	cs.DS, cs.LG	Sep 24, 2026	None	Score61	We prove nearly quadratic lower bounds for randomized algorithms for linear optimization and...
Even Sharper Bounds for Transductive Learning and Its Applications	Yingzhen Yang	http://arxiv.org/abs/2609.28459v1	cs.LG, cs.IT	Sep 23, 2026	None	Score63	We introduce Sharper Transductive Local Complexity (STLC), a localized complexity method for...
Gap-free Differentially Private PCA for Gaussian Data	Alina Ene, Huy L. Nguyen	http://arxiv.org/abs/2609.31614v1	cs.DS, cs.LG	Sep 25, 2026	None	Score61	We give a gap-free differentially private algorithm for the principal component analysis (PCA...