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/2610.12470v1

Code links

on this page

Paper	Authors	arXiv ID	Categories	Published	Code	Radar	Summary
Dex-One2Many: Learning Dexterous Manipulation from a Single Human Demonstration	Jusuk Lee, Sungha Kim, Yeonsoo Park	http://arxiv.org/abs/2610.12470v1	cs.RO, cs.CV	Oct 8, 2026	None	Score67	While learning dexterous manipulation from a single human video offers a promising alternativ...
CSF: Contextual Safety Filtering for Motion Generators	Lizhi Yang, Yiling Hou, Yao Tang	http://arxiv.org/abs/2610.12467v1	cs.RO, cs.LG	Oct 8, 2026	None	Score70	Text-conditioned motion generators produce trackable whole-body motion, but they have no noti...
FAITH: Feasibility-Aware Safety-Filtered RL for High-Dimensional Systems	Songyuan Zhang, Baljeet Singh, Sarthak Ranjeet Kaingade	http://arxiv.org/abs/2610.12432v1	cs.RO, cs.LG	Oct 8, 2026	None	Score69	Safe reinforcement learning commonly places safety and task performance in the same policy ob...
QF3: Fast Flow RL with Filtered Q-Gradients	Chung Min Kim, Brent Yi, David McAllister	http://arxiv.org/abs/2610.08789v1	cs.RO, cs.LG	Oct 6, 2026	None	Score78	Flow policies have become a standard policy class for learning robot behaviors from demonstra...
Rapid Fredholm stabilization of the Kuramoto--Sivashinsky equation with unrestricted, spatially-varying anti-diffusion	Luke Bhan, Miroslav Krstic, Yuanyuan Shi	http://arxiv.org/abs/2610.08764v1	eess.SY, cs.LG	Oct 6, 2026	None	Score74	We develop the first feedback design for rapid stabilization of the Kuramoto--Sivashinsky equ...
EgoLAP: Learning from Egocentric Human Data through Language-Action Reasoning	Lihan Zha, Shresth Grover, Tenny Yin	http://arxiv.org/abs/2610.08726v1	cs.RO, cs.AI	Oct 6, 2026	None	Score71	Egocentric human data offer a path to scaling robot learning beyond costly robot demonstratio...
BiasFlow: Geometric Monitoring and Backbone Regularization for Spurious Feature Reliance	Haojin Deng, Zhiping Lin, Yimin Yang	http://arxiv.org/abs/2610.06846v1	cs.AI	Oct 5, 2026	None	Score77	Worst-group accuracy (WGA) evaluates a trained predictor but does not characterize how its fr...
Recursive Video In-Context Learning for Agentic Robot	Wenrui Bao, Xinxin Liu, Bingxin Xu	http://arxiv.org/abs/2610.06843v1	cs.RO, cs.AI	Oct 5, 2026	None	Score65	LLM agents that orchestrate frozen vision-language-action (VLA) policies improve across episo...
Hierarchical Reinforcement Learning for Collision-Free Locomotion of an Underactuated Biped	Jagannath Prasad Sahoo, Saurabh Kumar, Surya Prakash S. K.	http://arxiv.org/abs/2610.05855v1	cs.RO, cs.AI	Oct 5, 2026	None	Score78	A bipedal robot cannot deviate from its path to avoid an obstacle without disturbing its bala...
Data-Driven Personas for Survey Simulation: Insights into Simulation Alignment Across Data-Access Regimes	Dongryeol Lee, Weronika Łajewska, Leonardo Perelli	http://arxiv.org/abs/2610.05828v1	cs.AI	Oct 5, 2026	None	Score74	However, many existing steering approaches rely on target-domain human data for fine-tuning o...