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

180

1 arXiv sources

Top radar

http://arxiv.org/abs/2605.30352v1

Published 24h

by paper date

Rate limit

1/3s

arXiv policy

Paper	Authors	arXiv ID	Categories	Published	Code	Radar	Summary
On Language Generation in the Limit with Bounded Memory	Jon Kleinberg, Anay Mehrotra, Amin Saberi	http://arxiv.org/abs/2605.30324v1	cs.DS, cs.AI	May 28, 2026	None	RDR64	We study language generation in the limit under bounded memory. In this task, a learner obser...
From Scores to Gibbs Correctors: Accelerating Uniform-Rate Discrete Diffusion Models	Yuchen Liang, Ness Shroff, Yingbin Liang	http://arxiv.org/abs/2605.27352v1	cs.LG, stat.ML	May 26, 2026	None	RDR64	Discrete diffusion models have achieved strong empirical performance in text and other symbol...
Modeling Agentic Technical Debt and Stochastic Tax: A Standalone Framework for Measurement, Simulation, and Dashboarding	Muhammad Zia Hydari, Raja Iqbal, Narayan Ramasubbu	http://arxiv.org/abs/2605.27320v1	cs.AI, cs.CY	May 26, 2026	None	RDR64	Agentic AI systems combine probabilistic reasoning with delegated action through tools, conte...
When Does Demographic Information Help? Data and Modeling Regimes for Perspective-Aware Hate Speech Detection	Weibin Cai, Reza Zafarani	http://arxiv.org/abs/2605.27313v1	cs.CL	May 26, 2026	None	RDR64	Demographic information is often used to model annotator perspectives in subjective tasks suc...
Greening AI Inference with Accuracy and Latency-aware User Incentives	Vasilios A. Siris, Adamantia Stamou, George D. Stamoulis	http://arxiv.org/abs/2605.27309v1	cs.LG, cs.OH	May 26, 2026	None	RDR64	The widespread use of AI services has raised concerns for its environmental sustainability, t...
Goal-driven Bayesian Optimal Experimental Design for Robust Decision-Making Under Model Uncertainty	Jinwoo Go, Xiaoning Qian, Byung-Jun Yoon	http://arxiv.org/abs/2605.26093v1	cs.LG, stat.ML	May 25, 2026	None	RDR64	Bayesian optimal experimental design (BOED) selects experiments to maximize information gain...
Global Convergence of Wasserstein Policy Gradient for Entropy-Regularized Reinforcement Learning	Zhaoyu Zhu, Rui Gao, Shuang Li	http://arxiv.org/abs/2605.26078v1	cs.LG	May 25, 2026	None	RDR64	Wasserstein policy gradient (WPG) is a policy optimization method for reinforcement learning...
Conditional KRR: Injecting Unpenalized Features into Kernel Methods with Applications to Kernel Thresholding	Rustem Takhanov, Zhenisbek Assylbekov	http://arxiv.org/abs/2605.26067v1	cs.LG, cs.AI	May 25, 2026	None	RDR64	Conditionally positive definite (CPD) kernels are defined with respect to a function class $\...
ETCHR: Editing To Clarify and Harness Reasoning	Beichen Zhang, Yuhong Liu, Jinsong Li	http://arxiv.org/abs/2605.23897v1	cs.CV, cs.AI	May 22, 2026	None	RDR64	Multimodal Large Language Models have advanced visual reasoning, yet a purely textual chain o...
Leveraging Foundation Models for Causal Generative Modeling	Aneesh Komanduri, Xintao Wu	http://arxiv.org/abs/2605.23861v1	cs.LG, cs.AI	May 22, 2026	None	RDR64	Causal generative modeling is essential for developing reliable and transparent AI systems ca...