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
HumanForge: A Human-Centric Deepfake Video Benchmark with Multi-Agent Forgery Rationales	Wenbo Xu, Zhimin Chen, Xiaojie Liang	http://arxiv.org/abs/2607.08705v1	cs.CV	Jul 9, 2026	None	RDR81	Rapid advancements in video diffusion models and temporal editing tools have enabled the gene...
Institutional Red-Teaming: Deployment Rules, Not Just Models, Causally Shape Multi-Agent AI Safety	Yujiao Chen	http://arxiv.org/abs/2607.07695v1	cs.AI, cs.GT	Jul 8, 2026	None	RDR81	We introduce institutional red-teaming, an evaluation methodology for testing deployment rule...
PeTeR: Post-Training Robustification of Probabilistic Circuits	Adrian Ciotinga, Yeming Dai, YooJung Choi	http://arxiv.org/abs/2607.07671v1	cs.LG	Jul 8, 2026	None	RDR81	Probabilistic circuits (PCs) can model complex joint distributions while supporting exact and...
MonoIR-RS: Infrared Remote Sensing Vision-Language Learning with CLIP and VLM Adaptation	Jiaju Han, Ma Yaqi, Yahui Chai	http://arxiv.org/abs/2607.06552v1	cs.CV	Jul 7, 2026	None	RDR79	Infrared remote-sensing imagery captures intensity structure, object-background contrast, and...
Graph Convolutional Attention: A Spectral Perspective on Graph Denoising and Diffusion	Shervin Khalafi, Igor Krawczuk, Sergio Rozada	http://arxiv.org/abs/2607.06546v1	cs.LG, cs.AI	Jul 7, 2026	None	RDR81	Denoising graphs is a fundamental problem in graph learning and the core operation of graph d...
FootsiesGym: A Fighting Game Benchmark for Two-Player Zero-Sum Imperfect-Information Games	Chase McDonald, Nathan Tsang, Wesley N. Kerr	http://arxiv.org/abs/2607.06514v1	cs.AI, cs.GT	Jul 7, 2026	Detected	RDR85	We present FootsiesGym, an open-source environment for learning in a non-trivial two-player,...
DynaKRAG: A Unified Framework for Learnable Evidence Control in Multi-Hop Retrieval-Augmented Generation	Yaqi Wu, Xiaolei Guo, Chenyu Zhou	http://arxiv.org/abs/2607.06507v1	cs.CL, cs.IR	Jul 7, 2026	None	RDR83	Multi-hop retrieval-augmented generation (RAG) acquires evidence sequentially, with each new...
Industry Classification of GitHub Repositories Using the North American Industry Classification System (NAICS)	Kevin Xu, Alexander Quispe	http://arxiv.org/abs/2607.06505v1	cs.SE, cs.AI	Jul 7, 2026	None	RDR86	GitHub hosts hundreds of millions of public repositories, but the platform exposes no native...
RMISC: A Large-scale Real-world Multivariate Corpus for Time Series Foundation Models	Qian Sun, Yong-Ming Tian, Jia-Wei Huang	http://arxiv.org/abs/2607.06504v1	cs.AI	Jul 7, 2026	None	RDR83	Recent years have witnessed the emergence of multivariate modeling using time series foundati...
From Voting to Agent Collaboration: Answer-Type-Aware LLM Pipelines for BioASQ 14b	Taeyun Roh, Eunha Lee, Wonjune Jang	http://arxiv.org/abs/2607.06452v1	cs.CL, cs.AI	Jul 7, 2026	None	RDR79	Biomedical question answering requires not only accurate extraction of information from scien...