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
Invariant Learning Dynamics of Transformers in Inductive Reasoning Tasks	Tiberiu Musat, Tiago Pimentel, Nicholas Zucchet	http://arxiv.org/abs/2607.11875v1	cs.LG, cs.AI	Jul 13, 2026	None	RDR65	We present a theoretical framework to explain the emergence of inductive reasoning abilities...
A Minimalist Retargeting-Guided Reinforcement Learning Recipe for Dexterous Manipulation	Yunhai Feng, Natalie Leung, Jiaxuan Wang	http://arxiv.org/abs/2607.11874v1	cs.RO, cs.AI	Jul 13, 2026	None	RDR79	Recent work in humanoid whole-body control has found success with a simple recipe: retarget h...
Evolution of Accuracy and Visual-Cognitive Errors in a Decade of Vision-Language AI Models	Shravan Murlidaran, Miguel P. Eckstein	http://arxiv.org/abs/2607.09654v1	cs.CV, cs.AI	Jul 10, 2026	None	RDR84	Vision language models (VLMs) have made remarkable progress in visual reasoning during the la...
Semantic Pareto-DQN: A Multi-Objective Reinforcement Learning Framework for Financial Anomaly Detection	Cláudio Lúcio do Val Lopes, Lucca Machado da Silva	http://arxiv.org/abs/2607.09641v1	cs.LG, cs.AI	Jul 10, 2026	None	RDR83	Financial anomaly detection suffers from extreme class imbalance, causing traditional single-...
4DR360: State Reasoning for Joint 3D Detection and Occupancy Prediction in 4D Radar-Camera Full-Scene Perception	Xiaokai Bai, Lianqing Zheng, Runwei Guan	http://arxiv.org/abs/2607.09629v1	cs.CV, cs.AI	Jul 10, 2026	None	RDR83	Reliable autonomous driving requires full-scene perception that couples foreground objects wi...
Tokenizer Transplantation: Mitigating Autoregressive Collapse in Edge-Efficient Bengali ASR	Sanjid Hasan, Md. Abdur Rahman	http://arxiv.org/abs/2607.09598v1	cs.CL	Jul 10, 2026	None	RDR82	Lightweight speech recognition models are critical for edge deployment, yet highly optimized...
Promptable Concept Segmentation from Above: Evaluating SAM 3's Zero-Shot and One-Shot Capabilities in Remote Sensing	Mohammad Dabaja, Turgay Celik	http://arxiv.org/abs/2607.09583v1	cs.CV	Jul 10, 2026	None	RDR83	The deployment of large-scale foundation models, such as the Segment Anything Model 3 (SAM 3)...
ARDY: Autoregressive Diffusion with Hybrid Representation for Interactive Human Motion Generation	Kaifeng Zhao, Mathis Petrovich, Haotian Zhang	http://arxiv.org/abs/2607.08741v1	cs.GR, cs.CV	Jul 9, 2026	None	RDR84	Generating realistic 3D human motions in real-time within interactive applications is key for...
WaspMOT: A Benchmark for Long-Term Multi-Object Tracking of Trichogramma Wasps	Tomasz Stanczyk, Yuan Gao, Hardik Agarwal	http://arxiv.org/abs/2607.08729v1	cs.CV	Jul 9, 2026	Detected	RDR82	Multi-object tracking (MOT) has achieved strong performance on benchmarks dominated by short...
Pose-to-Biomechanics: Bridging 3D Human Pose Estimation and Biomechanical Attribute Prediction	Ayda Eghbalian, Kevin Desai	http://arxiv.org/abs/2607.08725v1	cs.CV, cs.AI	Jul 9, 2026	None	RDR84	Recent progress in 3D human pose estimation has made markerless recovery of skeletal motion i...