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
LTM: Large-scale Terrain Model for Wildfire-prone Landscapes	Xiao Fu, Yue Hu, Meida Chen	http://arxiv.org/abs/2607.08711v1	cs.CV, cs.LG	Jul 9, 2026	None	RDR75	Accurate 3D terrain maps are essential for emergency response when assessing wildfire hazards...
ECGLight: Compute-Light Framework For Paper ECG Digitization and Myocardial Infarction Screening	Shreyasvi Natraj, Cyrus Achtari, Felice Gragnano	http://arxiv.org/abs/2607.07683v1	cs.LG	Jul 8, 2026	None	RDR79	Electrocardiography (ECG) is one of the most widely used tests for diagnosing cardiovascular...
Recursive Self-Improvement in AI: From Bounded Self-Refinement to Autonomous Research Loops	Mingguang Chen, Licheng Wang, Bo Qu	http://arxiv.org/abs/2607.07663v1	cs.AI	Jul 8, 2026	None	RDR81	AI systems increasingly participate in their own improvement: revising their outputs, adaptin...
Scalable Visual Pretraining for Language Intelligence	Yiming Zhang, Zhonghan Zhao, Wenwei Zhang	http://arxiv.org/abs/2607.09657v1	cs.CV, cs.AI	Jul 10, 2026	None	RDR71	The rapid progress of large foundation models has been driven predominantly by pretraining on...
The Illusion of Equivalency: Statistical Characterization of Quantization Effects in LLMs	Baha Rababah, Cuneyt Gurcan Akcora, Carson K. Leung	http://arxiv.org/abs/2607.08734v1	cs.AI	Jul 9, 2026	None	RDR75	Post-training quantization is widely used to deploy large language models in resource-constra...
Do You Need a Frontier Model as a Citation Verifier? Benchmarking Rubric LLMs for Deep-Research Source Attribution	Ethan Leung, Elias Lumer, Corey Feld	http://arxiv.org/abs/2607.08700v1	cs.CL	Jul 9, 2026	None	RDR74	Reinforcement learning increasingly relies on an LLM judge to score each rubric criterion, an...
ProjAgent: Procedural Similarity Retrieval for Repository-Level Code Generation	QiHong Chen, Aaron Imani, Iftekhar Ahmed	http://arxiv.org/abs/2607.08691v1	cs.SE, cs.AI	Jul 9, 2026	None	RDR77	Repository-level code generation requires implementing target functions while accounting for...
Selective Timestep Weighting and Advantage-Based Replay for Sample-Efficient Diffusion RLHF	Eric Zhu, Abhinav Shrivastava, Soumik Mukhopadhyay	http://arxiv.org/abs/2607.07693v1	cs.LG, cs.AI	Jul 8, 2026	None	RDR82	Reinforcement learning from human feedback (RLHF) has emerged as a powerful paradigm for alig...
Any-Dimensional Learning by Sampling	Eitan Levin, Venkat Chandrasekaran	http://arxiv.org/abs/2607.07680v1	math.ST, cs.LG	Jul 8, 2026	None	RDR73	Many machine learning models are defined for inputs of different sizes, such as point clouds...
Efficient Sequential Calibration with $O(T^{2/3-ε})$ Error Bound	Zihan Zhang	http://arxiv.org/abs/2607.12928v1	cs.LG	Jul 14, 2026	None	RDR64	We study the online binary sequential calibration problem. A recent breakthrough by \citet{da...