LIVE-Last scan updating-52 sources active-152 signals today-AGENTSPeakflo's 20x: A Self-Improving AI Agent Orchestrator for Knowledge Work
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
86
http://arxiv.org/abs/2605.30352v1
Published 24h
0
by paper date
Rate limit
1/3s
arXiv policy
PaperAuthorsarXiv IDCategoriesPublishedCodeRadarSummary
Good Token Hunting: A Hitchhiker's Guide to Token Selection for Visual Geometry TransformersShuhong Zheng, Michael Oechsle, Erik Sandströmhttp://arxiv.org/abs/2605.23892v1cs.CV, cs.AIMay 22, 2026NoneRDR74Visual geometry transformers have become powerful architectures for multi-view 3D reconstruct...
Human Decision-Making with Persuasive and Narrative LLM ExplanationsLaura R. Marusich, Mary Grace Kozuch Dhooghe, Jonathan Z. Bakdashhttp://arxiv.org/abs/2605.23867v1cs.HC, cs.AIMay 22, 2026NoneRDR74Large language models (LLMs) have the potential to aid and improve human decision-making in c...
Vector Policy Optimization: Training for Diversity Improves Test-Time SearchRyan Bahlous-Boldi, Isha Puri, Idan Shenfeldhttp://arxiv.org/abs/2605.22817v1cs.LG, cs.AIMay 21, 2026NoneRDR74Language models must now generalize out of the box to novel environments and work inside infe...
Colored Noise Diffusion SamplingHadar Davidson, Noam Issachar, Sagie Benaimhttp://arxiv.org/abs/2605.30332v1cs.CVMay 28, 2026NoneRDR73Diffusion models achieve state-of-the-art image synthesis, with their generative trajectories...
Supercharging Thermal Gaussian Splatting with Depth EstimationManoj Biswanath, Chenxin Cai, Hannah Schieberhttp://arxiv.org/abs/2605.30328v1cs.CVMay 28, 2026NoneRDR73Efficient and robust 3D scene representation is crucial in autonomous driving, robotics, and...
AnyScene: Towards Highly Controllable Driving Scene Generation at Anywhere and BeyondHaiming Zhang, Junfei Zhou, Feng Jianghttp://arxiv.org/abs/2605.26113v1cs.RO, cs.CVMay 25, 2026NoneRDR73Generating high-fidelity and controllable synthetic data is critical for advancing end-to-end...
Hierarchical Concept Geometry in Language Models Emerges from Word Co-occurrenceAndres Nava, Matthieu Wyarthttp://arxiv.org/abs/2605.23821v1cs.CL, cs.LGMay 22, 2026NoneRDR73We propose a distributional theory of how hypernymy -- the ``is-a'' relation between general...
AwareVLN: Reasoning with Self-awareness for Vision-Language NavigationWenxuan Guo, Xiuwei Xu, Yichen Liuhttp://arxiv.org/abs/2605.22816v1cs.RO, cs.CVMay 21, 2026NoneRDR73Vision-and-Language Navigation (VLN) requires an agent to ground language instructions to its...
Remember to be Curious: Episodic Context and Persistent Worlds for 3D ExplorationLily Goli, Justin Kerr, Daniele Redahttp://arxiv.org/abs/2605.22814v1cs.LGMay 21, 2026NoneRDR73Exploration is a prerequisite for learning useful behaviors in sparse-reward, long-horizon ta...
Probabilistic Smoothing with Ratio-Monotone Transforms for Global OptimizationKukyoung Jang, Taehyun Cho, Junrui Zhanghttp://arxiv.org/abs/2605.27316v1cs.LG, math.OCMay 26, 2026NoneRDR72Probabilistic smoothing is a standard tool for global optimization, but existing methods rely...