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

1,230

1 arXiv sources

Top radar

http://arxiv.org/abs/2607.11862v1

Published 24h

by paper date

Rate limit

1/3s

arXiv policy

Paper	Authors	arXiv ID	Categories	Published	Code	Radar	Summary
Accurate, Interdisciplinary and Transparent Structure-property Understanding with Deep Native Structural Reasoning	Chen Tang, Yizhou Wang, Jianyu Wu	http://arxiv.org/abs/2607.07708v1	cs.CL, cs.AI	Jul 8, 2026	None	RDR82	Structure-property relationships are foundational to biology, chemistry and materials science...
Breaking Database Lock-in: Agentic Regeneration of High Performance Storage Readers for Database Bypass	Victor Giannakouris, Immanuel Trummer	http://arxiv.org/abs/2607.07696v1	cs.DB, cs.AI	Jul 8, 2026	None	RDR86	Analytical workloads operating on data stored in external database systems face a fundamental...
MedPMC: A Systematic Framework for Scaling High-Fidelity Medical Multimodal Data for Foundation Models	Hyunjae Kim, Dain Kim, Pan Xiao	http://arxiv.org/abs/2607.07673v1	cs.CV, cs.LG	Jul 8, 2026	None	RDR86	Medicine is inherently multimodal, requiring clinicians to synthesize information across dive...
DiaLLM: An Investigation into the Robustness-Generation Gap in English Dialect Adaptation	Jordan Painter, Dipankar Srirag, Adarsh Kappiyath	http://arxiv.org/abs/2607.07669v1	cs.CL, cs.AI	Jul 8, 2026	None	RDR86	Large language models increasingly \emph{understand} dialectal English, yet still \emph{produ...
Future Confidence Distillation in Large Language Models	Sahil Kale	http://arxiv.org/abs/2607.07626v1	cs.CL, cs.AI	Jul 8, 2026	None	RDR82	Reliable confidence estimation is essential for deploying large language models (LLMs) in con...
DepthWeave-KV: Token-Adaptive Cross-Layer Residual Factorization for Long-Context KV Cache Compression	Anna Cordoba, Adam Puente Tercero, Nerea Angulo Hijo	http://arxiv.org/abs/2607.06523v1	cs.AI	Jul 7, 2026	None	RDR85	Long-context language model inference is increasingly limited by the memory bandwidth and cap...
FreqDepthKV: Frequency-Guided Depth Sharing for Robust KV Cache Compression in Long-Context LLM Inference	Anna Córdoba, Adam Puente Tercero, Nerea Angulo Hijo	http://arxiv.org/abs/2607.06519v1	cs.AI	Jul 7, 2026	None	RDR83	Long-context LLM inference is increasingly limited by the memory and bandwidth cost of KV cac...
Point as Skeleton: Accumulated Point Cloud Enhanced Autoregressive Generation for Closed-Loop Autonomous Driving Simulation	Songbur Wong, Xiaosong Jia, Junqi You	http://arxiv.org/abs/2607.06516v1	cs.CV	Jul 7, 2026	Detected	RDR83	Evaluating end-to-end autonomous driving (E2E-AD) remains challenging, as existing driving si...
Danus: Orchestrating Mathematical Reasoning Agents with Fact-Graph Memory	Jihao Liu, Guoxiong Gao, Zeming Sun	http://arxiv.org/abs/2607.06447v1	cs.AI, cs.CL	Jul 7, 2026	Detected	RDR87	Recent LLM-based mathematical reasoning agents have begun to tackle research-level problems a...
PIPBench: A Profile-Inclusive Framework for Personalized Image Generation Evaluation	Yuhang Wu, Shuxiang Zhang, Wee Hian Ching	http://arxiv.org/abs/2607.06440v1	cs.CV	Jul 7, 2026	None	RDR87	Recent text-to-image models such as DALLE-3 excel at following diverse prompts yet remain bli...