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
MobileGym: A Verifiable and Highly Parallel Simulation Platform for Mobile GUI Agent Research	Dingbang Wu, Rui Hao, Haiyang Wang	http://arxiv.org/abs/2605.26114v1	cs.AI, cs.CL	May 25, 2026	None	RDR83	We present MobileGym, a browser-hosted, lightweight, fully controllable environment for every...
Squeezing Capacity from Multimodal Large Language Models for Subject-driven Generation	Shuhong Zheng, Aashish Kumar Misraa, Yu-Teng Li	http://arxiv.org/abs/2605.26111v1	cs.CV, cs.AI	May 25, 2026	None	RDR83	Subject-driven image generation aims to synthesize new images that preserve the identity of t...
Beyond Summaries: Structure-Aware Labeling of Code Changes with Large Language Models	Bar Weiss, Antonio Abu-Nassar, Adi Sosnovich	http://arxiv.org/abs/2605.26100v1	cs.SE, cs.AI	May 25, 2026	None	RDR83	Code review is a critical practice in software engineering, yet the growing scale and frequen...
Active Query Synthesis for Preference Learning	Namrata Nadagouda, Nauman Ahad, Maegan Tucker	http://arxiv.org/abs/2605.26072v1	cs.LG	May 25, 2026	None	RDR83	Efficient learning of user preferences is crucial for many modern decision making systems but...
WhoSaidIt: Human-LLM Collaborative Annotation for Text-Based Multilingual Speaker-Attribute Classification	Lingyu Gao, Will Monroe, David Smith	http://arxiv.org/abs/2605.26070v1	cs.CL	May 25, 2026	None	RDR83	Annotating speaker attributes from text is inherently ambiguous, particularly in multilingual...
Lumberjack: Better Differentially Private Random Forests through Heavy Hitter Detection in Trees	Christian Janos Lebeda, David Erb, Tudor Cebere	http://arxiv.org/abs/2605.22756v1	cs.LG, cs.DS	May 21, 2026	None	RDR83	Random forests are widely used in fields involving sensitive tabular data, but existing appro...
AREA: Attribute Extraction and Aggregation for CLIP-Based Class-Incremental Learning	Zhen-Hao Xie, Yu-Cheng Shi, Da-Wei Zhou	http://arxiv.org/abs/2605.28809v1	cs.CV, cs.LG	May 27, 2026	Detected	RDR82	Class-Incremental Learning (CIL) is important in building real-world learning systems. In CLI...
Alignment Tampering: How Reinforcement Learning from Human Feedback Is Exploited to Optimize Misaligned Biases	Dongyoon Hahm, Dylan Hadfield-Menell, Kimin Lee	http://arxiv.org/abs/2605.27355v1	cs.AI, cs.CL	May 26, 2026	None	RDR82	Reinforcement Learning from Human Feedback (RLHF) is the standard method to align Large Langu...
Reinforcing Few-step Generators via Reward-Tilted Distribution Matching	Yushi Huang, Xiangxin Zhou, Ruoyu Wang	http://arxiv.org/abs/2605.26108v1	cs.CV	May 25, 2026	Detected	RDR82	Recent advances in few-step diffusion distillation have enabled efficient image generation, y...
Channel-wise Vector Quantization	Wei Song, Tianhang Wang, Yitong Chen	http://arxiv.org/abs/2605.26089v1	cs.CV, cs.AI	May 25, 2026	None	RDR82	We present Channel-wise Vector Quantization (CVQ), a novel image tokenization paradigm that r...