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/2610.13871v1

Code links

on this page

Paper	Authors	arXiv ID	Categories	Published	Code	Radar	Summary
Partially Informed Stochastic Optimization via Zeroth-Order Residual Tracking	El Mahdi Chayti, Alireza Mirrokni, Martin Jaggi	http://arxiv.org/abs/2610.13871v1	cs.LG	Oct 9, 2026	None	Score77	Many optimization problems provide direct access to only part of the gradient, while the rema...
What 30,000 Hours of Ego-centric Video Does Not Teach	Jiahua Dong, Anurag Bagchi, Yash Jangir	http://arxiv.org/abs/2610.12464v1	cs.CV	Oct 8, 2026	None	Score82	World models offer a promising alternative to physics-based simulators, yet remain far from p...
OneSearch-VL: Unified Multimodal Deep Research Agent for Image and Video	Hongyu Li, Manyuan Zhang, Kaituo Feng	http://arxiv.org/abs/2610.12419v1	cs.CV	Oct 8, 2026	Detected	Score84	Single-image, multi-image, and video deep research require different visual operations but sh...
RoboJEPA: Scaling Robotic Latent World Models	Artem Zholus, Nicolas Beltran-Velez, Jianhao Yuan	http://arxiv.org/abs/2610.10515v1	cs.AI, cs.RO	Oct 7, 2026	None	Score85	Latent world models have shown a remarkable ability to predict future states and to plan in t...
RECAST: Learning to Compute the Right Context through Adaptive Evidence Routing	Yilun Hao, Krishna Sayana, Isabella Ye	http://arxiv.org/abs/2610.10507v1	cs.AI	Oct 7, 2026	None	Score83	Large language models are increasingly applied to tasks grounded in long, heterogeneous infor...
Evolutionary Architecture Search for Chlorophyll-$a$ Prediction in Lakes using Sentinel-2	Kursat Komurcu, Linas Petkevicius	http://arxiv.org/abs/2610.10496v1	cs.NE, cs.LG	Oct 7, 2026	Detected	Score84	Small tabular datasets with expert-designed spectral features are the norm in operational Ear...
Before They Can Solve: Predicting Post-Training Coding-Agent Performance from Base Models	Tan Yu, Alexander Bukharin, Khushi Bhardwaj	http://arxiv.org/abs/2610.10478v1	cs.AI, cs.SE	Oct 7, 2026	None	Score86	How can we predict which base checkpoint is worth an expensive round of agentic post-training...
Label-free cell counting and viability prediction with brightfield imaging and deep learning	Amir Reza Vazifeh, Christian Zeigler, Sornanathan Meyyappan	http://arxiv.org/abs/2610.10473v1	cs.CV, q-bio.CB	Oct 7, 2026	None	Score83	Cell viability assessment is a core requirement in cell culture systems, with critical applic...
Sherpa: Teaching LLMs to Teach Adaptively	Weixian Xu, Yanzhe Zhang, Zora Zhiruo Wang	http://arxiv.org/abs/2610.08778v1	cs.AI, cs.CL	Oct 6, 2026	None	Score82	Large language models (LLMs) have become increasingly capable problem solvers, but being able...
A Systematic Study of Semantic ID Spaces for Generative Information Retrieval	Alexia Allal, Hicham Randrianarivo, Sylvain Lamprier	http://arxiv.org/abs/2610.08732v1	cs.IR, cs.CL	Oct 6, 2026	None	Score83	Generative Information Retrieval (GIR) has emerged as a transformative paradigm, shifting doc...