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
Deep Gaussian Processes on Directed Acyclic Graphs	Federico L. Perlino, Oliver Hamelijnck, Adam M. Johansen	http://arxiv.org/abs/2607.09645v1	stat.ML, cs.LG	Jul 10, 2026	None	RDR62	Many real-world processes can be represented as compositions of functions along a directed ac...
A censoring-aware target interface for tabular foundation models in survival prediction	Yue Lyu, Steven H. Lin, Xuelin Huang	http://arxiv.org/abs/2607.09577v1	stat.ME, stat.ML	Jul 10, 2026	None	RDR69	Time-to-event prediction from tabular patient data is central to prognosis and biomedical dec...
Large-Scale Portfolio Optimization Problem Under Cardinality Constraint With Enhanced Multi-Objective Evolutionary Algorithms	Danial Ramezani, Mostafa Abouei Ardakan	http://arxiv.org/abs/2607.09566v1	cs.CE, cs.AI	Jul 10, 2026	None	RDR70	Decision-making is posing an increasingly formidable challenge to investors because of the gr...
Unsupervised Domain Adaptation for Calcification Classification in Mammography Across Multi-Site Datasets	Xuan Liu, Derek L. Nguyen, Emily C. Barre	http://arxiv.org/abs/2607.06549v1	cs.CV	Jul 7, 2026	None	RDR76	Deep learning-based computer-aided diagnosis (CAD) systems have shown strong performance in b...
Hierarchical Acoustic-Semantic Modeling: Modality Separation and Semantic Coherence for Full-Duplex SLMs	Zhenyu Liu, Yunxin Li, Xuanyu Zhang	http://arxiv.org/abs/2607.06540v1	cs.CL	Jul 7, 2026	None	RDR74	Developing seamless, high-performance, native intelligent full-duplex Spoken Language Models...
CAIRN: Cross-Room 3D Scene Understanding with Topology-Aware Large Multimodal Models	He Liang, Chenyang Ma, Yiming Zhang	http://arxiv.org/abs/2607.06534v1	cs.CV	Jul 7, 2026	None	RDR76	Existing 3D scene-grounded Large Language Models (3D-LLMs) focus on answering questions groun...
Dynamic Frechet Regression with Feature Selection for Distributional Data	Kiran Adhikari, Amrutha Dinesh, Mathew Kuttolamadom	http://arxiv.org/abs/2607.09613v1	stat.ME, stat.ML	Jul 10, 2026	None	RDR59	Many scientific and engineering applications generate responses that are not scalars or vecto...
Conceptual Networks for Cross-Linguistic Idiomatic Expressions:A Feature-Based Graph Approach	Kiran Pala, Punam Silu, Lixun Yu	http://arxiv.org/abs/2607.09576v1	cs.CL, cs.AI	Jul 10, 2026	None	RDR62	We present an interpretable network-based framework for representing idiomatic and figurative...
Super Weights in LLMs and the Failure of Selective Training	Shreyas Subramanian, Adewale Akinfaderin, Akarsha Sehwag	http://arxiv.org/abs/2607.08733v1	cs.LG	Jul 9, 2026	None	RDR62	Recent work identified Super Weights, individual parameters whose removal degrades model perf...
Does Bielik Know What It Doesn't Know? Activation Dispersion Separates Entity Familiarity from Factual Reliability Across Model Scale	Grzegorz Brzezinka	http://arxiv.org/abs/2607.07670v1	cs.CL, cs.LG	Jul 8, 2026	None	RDR64	Large language models hallucinate most about entities they have never seen. We ask whether a...