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
GMOS: Grounding Moving Object Segmentation in 3D Space and Time	Junyu Xie, Tengda Han, Weidi Xie	http://arxiv.org/abs/2605.30352v1	cs.CV	May 28, 2026	None	RDR86	Moving Object Segmentation (MOS) aims to discover, segment, and track objects that move indep...
GPIC: A Giant Permissive Image Corpus for Visual Generation	Keshigeyan Chandrasegaran, Kyle Sargent, Suchir Agarwal	http://arxiv.org/abs/2605.30341v1	cs.CV, cs.AI	May 28, 2026	Detected	RDR86	Studying scalable methods for visual generative modeling requires large, accessible, and stab...
Fairness-Aware Federated Learning with Trajectory Shapley Value	Daniel Kuznetsov, Ziqi Wang	http://arxiv.org/abs/2605.30336v1	cs.LG	May 28, 2026	None	RDR86	Federated learning is an emerging distributed paradigm that addresses the challenges posed by...
COMPOSE: Composing Future Theorems from Citations and Formal Structure	David Busbib, Michael Werman	http://arxiv.org/abs/2605.30333v1	cs.CL	May 28, 2026	None	RDR86	A plausible future mathematical claim must satisfy two constraints: it should follow the dire...
Self-Improving Language Models with Bidirectional Evolutionary Search	Guowei Xu, Zhenting Qi, Huangyuan Su	http://arxiv.org/abs/2605.28814v1	cs.CL	May 27, 2026	Detected	RDR86	Search has been proposed as an effective method for self-improving language models and agenti...
Skill-Conditioned Gated Self-Distillation for LLM Reasoning	Jiazhen Huang, Xiao Chen, Xiao Luo	http://arxiv.org/abs/2605.28791v1	cs.CL, cs.AI	May 27, 2026	Detected	RDR86	On-policy self-distillation (SD) improves LLM reasoning by using teacher-side privileged info...
Rethinking Memory as Continuously Evolving Connectivity	Jizhan Fang, Buqiang Xu, Zhixian Wang	http://arxiv.org/abs/2605.28773v1	cs.CL, cs.AI	May 27, 2026	Detected	RDR86	Existing memory-augmented LLM agents often treat memory as a static repository with pre-defin...
LocateAnything: Fast and High-Quality Vision-Language Grounding with Parallel Box Decoding	Shihao Wang, Shilong Liu, Yuanguo Kuang	http://arxiv.org/abs/2605.27365v1	cs.CV, cs.AI	May 26, 2026	None	RDR86	Vision-language models (VLMs) commonly formulate visual grounding and detection as a coordina...
MATCHA: Matching Text via Contrastive Semantic Alignment	Siran Li, Ece Sena Etoglu, Carsten Eickhoff	http://arxiv.org/abs/2605.27345v1	cs.CL	May 26, 2026	Detected	RDR86	Reliable evaluation is essential for understanding large language model (LLM) performance, ye...
2-ASP(Q) programs with weak constraints: Complexity and efficient implementation	Andrea Cuteri, Giuseppe Mazzotta, Francesco Ricca	http://arxiv.org/abs/2605.27338v1	cs.AI, cs.CC	May 26, 2026	None	RDR86	ASP(Q) extends Answer Set Programming (ASP) with Quantifiers over answer sets. In this paper...