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
MUSE-Autoskill: Self-Evolving Agents via Skill Creation, Memory, Management, and Evaluation	Huawei Lin, Peng Li, Jie Song	http://arxiv.org/abs/2605.27366v1	cs.AI, cs.CL	May 26, 2026	None	RDR79	Large language model (LLM) agents rely on reusable skills to solve complex tasks. However, ex...
Looped Diffusion Language Models	Sanghyun Lee, Chunsan Hong, Seungryong Kim	http://arxiv.org/abs/2605.26106v1	cs.LG	May 25, 2026	None	RDR79	Masked diffusion models (MDMs) have emerged as a promising alternative to autoregressive mode...
MotiMotion: Motion-Controlled Video Generation with Visual Reasoning	Lee Hsin-Ying, Hanwen Jiang, Yiqun Mei	http://arxiv.org/abs/2605.22818v1	cs.CV	May 21, 2026	None	RDR79	Current motion-controlled image-to-video generation models rigidly follow user-provided traje...
GesVLA: Gesture-Aware Vision-Language-Action Model Embedded Representations	Wenxuan Guo, Ziyuan Li, Meng Zhang	http://arxiv.org/abs/2605.22812v1	cs.RO, cs.CV	May 21, 2026	None	RDR79	Vision-Language-Action (VLA) models have shown strong potential for general-purpose robot man...
SDPM: Survival Diffusion Probabilistic Model for Continuous-Time Survival Analysis	Stanislav R. Kirpichenko, Andrei V. Konstantinov, Lev V. Utkin	http://arxiv.org/abs/2605.22776v1	cs.LG, cs.AI	May 21, 2026	None	RDR79	Survival analysis aims to estimate a time-to-event distribution from data with censored obser...
Multi-Mixer Models: Flexible Sequence Modeling with Shared Representations	Kevin Y. Li, Asher Trockman, Ananda Theertha Suresh	http://arxiv.org/abs/2605.28769v1	cs.LG	May 27, 2026	None	RDR78	Softmax attention is the cornerstone of modern large language models, but its memory scales l...
CubePart: An Open-Vocabulary Part-Controllable 3D Generator	Yiheng Zhu, Kangle Deng, Jean-Philippe Fauconnier	http://arxiv.org/abs/2605.28763v1	cs.AI	May 27, 2026	None	RDR78	Interactive 3D assets used in games and simulation are typically decomposed into specific sem...
Maat: The Agentic Legal Research Assistant for Competition Protection	Basant Mounir, Farida Madkour, Amira Abdelaziz	http://arxiv.org/abs/2605.27331v1	cs.AI	May 26, 2026	None	RDR78	Competition law experts conducting legal research must review extensive volumes of cases, dec...
EVIDENT: Routing MLLM Adaptation through Entity-Grounded Visual Evidence for Cross-Domain Video Temporal Grounding	Geo Ahn, Jiwook Han, Youngrae Kim	http://arxiv.org/abs/2605.26104v1	cs.CV	May 25, 2026	None	RDR78	Fine-tuning MLLMs for Video Temporal Grounding (VTG) often improves in-domain performance but...
OrpQuant: Geometric Orthogonal Residual Projection for Multiplier-Free Power-of-Two Transformer Quantization	Maoyang Xiang, Bo Wang, Tao Luo	http://arxiv.org/abs/2605.26092v1	cs.LG, cs.AI	May 25, 2026	None	RDR78	The deployment of Large Language Models (LLMs) and Vision Transformers (ViTs) on edge devices...