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

1,230

1 arXiv sources

Top radar

http://arxiv.org/abs/2607.11862v1

Published 24h

by paper date

Rate limit

1/3s

arXiv policy

Paper	Authors	arXiv ID	Categories	Published	Code	Radar	Summary
Evidence-Backed Video Question Answering	Shijie Wang, Honglu Zhou, Ziyang Wang	http://arxiv.org/abs/2607.11862v1	cs.CV, cs.AI	Jul 13, 2026	Detected	RDR87	Current Video Large Language Models (Video LLMs) excel in question answering (QA) but largely...
MicroCharNet: Less is More for License Plate Character Detection	Huy Che, Dinh-Duy Phan, Duc-Lung Vu	http://arxiv.org/abs/2607.11830v1	cs.CV	Jul 13, 2026	Detected	RDR86	License plate character detection is a crucial component of intelligent transportation system...
MM-ToolSandBox: A Unified Framework for Evaluating Visual Tool-Calling Agents	Kaixin Ma, Di Feng, Alexander Metz	http://arxiv.org/abs/2607.11818v1	cs.CV, cs.AI	Jul 13, 2026	Detected	RDR87	We introduce MM-ToolSandBox, a benchmark and evaluation framework for visually grounded tool-...
A Durability and Cross-Language Transfer Benchmark for a Validated Teaching-Feedback Classification Protocol	Esteban U. Vega Barajas	http://arxiv.org/abs/2607.11873v1	cs.CL, cs.LG	Jul 13, 2026	None	RDR87	Institutions collect far more open-ended teaching-evaluation feedback than they read. A prior...
AdvancedMathBench: A Benchmark Suite for Advanced Mathematical Proof Generation and Verification	Lingkai Kong, Zijian Wu, Yuzhe Gu	http://arxiv.org/abs/2607.11849v1	cs.CL	Jul 13, 2026	None	RDR84	Large language models (LLMs) have achieved remarkable performance on high-school and olympiad...
LoRA-Based Cascaded Multimodal Fusion for Action Recognition in Medical Training Environments	Divya Mereddy, Jeevan Beedareddy	http://arxiv.org/abs/2607.11839v1	cs.CV, cs.AI	Jul 13, 2026	Detected	RDR87	This paper presents a cascaded Low-Rank Adaptation (LoRA)-based multimodal fusion framework f...
HASTE: A Platform for Rapid Post-Disaster Building Damage Assessment	Caleb Robinson, Anthony Ortiz, Simone Fobi Nsutezo	http://arxiv.org/abs/2607.11838v1	cs.CV	Jul 13, 2026	Detected	RDR83	When a large disaster strikes, responders need a map of which buildings are damaged within ho...
StoryTeller: Training-Free Narrative Grounding for Long-Form Audio Description	Seung Hyun Hahm, Minh T. Dinh, SouYoung Jin	http://arxiv.org/abs/2607.11798v1	cs.CV, cs.AI	Jul 13, 2026	None	RDR84	Long-form audio description (AD) requires more than describing visible actions: it must prese...
Read It Back: Pretrained MLLMs Are Zero-Shot Reward Models for Text-to-Image Generation	Runhui Huang, Qihui Zhang, Zhe Liu	http://arxiv.org/abs/2607.11886v1	cs.CV	Jul 13, 2026	None	RDR79	In this paper, we propose SpectraReward, a training-free reward function that turns pretraine...
Requential Coding: Pushing the Limits of Model Compression with Self-Generated Training Data	Shikai Qiu, Marc Finzi, Yujia Zheng	http://arxiv.org/abs/2607.11883v1	cs.LG	Jul 13, 2026	None	RDR79	Compression is fundamental to intelligence. A model that can represent its training data as a...