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

3,367

matching records

Shown

current page

Top radar

http://arxiv.org/abs/2610.12427v1

Code links

on this page

Paper	Authors	arXiv ID	Categories	Published	Code	Radar	Summary
FastBench: Can Streaming VLMs Perceive High-Dynamic Real-World Streams?	Yuxuan Hu, Weikang Shi, Yang Bo	http://arxiv.org/abs/2610.12427v1	cs.CV, cs.CL	Oct 8, 2026	Detected	Score84	Streaming Video Large Language Models (VLMs) enable continuous video understanding, yet exist...
Beyond Spatio-Temporal Priors: A Generalizable Approach for Dense Correspondence Matching	Luping Liu, Bingyi Kang, Yifan Wang	http://arxiv.org/abs/2610.12421v1	cs.CV, cs.LG	Oct 8, 2026	Detected	Score84	Dense correspondence matching has historically been bounded by simplifying spatio-temporal pr...
QuadTok: Quadtree Visual Tokenizer for Autoregressive Image Generation	Yucheng Mao, Zeyuan Chen, Xiaojun Shan	http://arxiv.org/abs/2610.10497v1	cs.CV	Oct 7, 2026	Detected	Score83	We introduce QuadTok, a novel framework for visual tokenization and autoregressive image gene...
Data Leakage in Patch-Based Hyperspectral Image Classification: Quantifying the Impact of Spatial Overlap	Mohammed Q. Alkhatib	http://arxiv.org/abs/2610.08770v1	cs.CV	Oct 6, 2026	Detected	Score84	Patch-based learning improves hyperspectral image (HSI) classification by exploiting local sp...
The Missing Minimal Pair: Stereotype Evaluation in LLMs	Nataliya Stepanova, Ivan Titov, Emily Allaway	http://arxiv.org/abs/2610.08747v1	cs.CL	Oct 6, 2026	Detected	Score86	A common approach to measuring bias in Large Language Models is to compare the log-likelihood...
Denoising Hierarchical Representations: Joint Continuous Diffusion for Language Modeling	Mathias Ollu, Nikos Komodakis	http://arxiv.org/abs/2610.08738v1	cs.CL, cs.LG	Oct 6, 2026	Detected	Score85	Diffusion Language Models (DLMs) hold the promise of order-agnostic, parallel text generation...
WorldSolver: Can LLM Agents Simulate the Physical Dynamics via Solver Generation?	Siru Jiang, Yongzhe Lyu, Shuo Lu	http://arxiv.org/abs/2610.08720v1	cs.AI	Oct 6, 2026	Detected	Score86	LLM-based agents are increasingly advancing scientific and engineering problem solving, with...
AI Models Can Provably Hide Arbitrary Capabilities	Andis Draguns, Sumeet Ramesh Motwani, Raymond Douglas	http://arxiv.org/abs/2610.13928v1	cs.LG, cs.CR	Oct 9, 2026	None	Score77	Capability evaluations aim to surface dangerous model behaviors before deployment, but their...
DyssomniaNN: Multi-Scale Spiking Neural Modeling of Human Sleep Disorders and Perceived Restedness	Daniel Szelogowski	http://arxiv.org/abs/2610.13918v1	cs.NE, cs.ET	Oct 9, 2026	None	Score72	Clinical sleep medicine repeatedly documents profound divergences between objective sleep dur...
Structural Automata for Neural Semantic Parsing	Xiao Zhang	http://arxiv.org/abs/2610.13896v1	cs.CL	Oct 9, 2026	None	Score72	Neural semantic parsers generate meaning representations token by token, yet well-formedness...