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

http://arxiv.org/abs/2605.30352v1

Published 24h

by paper date

Rate limit

1/3s

arXiv policy

Paper	Authors	arXiv ID	Categories	Published	Code	Radar	Summary
MambaGaze: Bidirectional Mamba with Explicit Missing Data Modeling for Cognitive Load Assessment from Eye-Gaze Tracking Data	Amir Mousavi, Mohammad Sadegh Sirjani, Erfan Nourbakhsh	http://arxiv.org/abs/2605.22775v1	cs.LG, cs.AI	May 21, 2026	None	RDR84	Real-time cognitive load assessment from eye-tracking signals could potentially enable adapti...
CogAdapt: Transferring Clinical ECG Foundation Models to Wearable Cognitive Load Assessment via Lead Adaptation	Amir Mousavi, Mohammad Sadegh Sirjani, Erfan Nourbakhsh	http://arxiv.org/abs/2605.22774v1	cs.LG, cs.AI	May 21, 2026	None	RDR84	Real-time cognitive load assessment is essential for adaptive human-computer interaction but...
Understanding Data Temporality Impact on Large Language Models Pre-training	Pilchen Hippolyte, Fabre Romain, Signe Talla Franck	http://arxiv.org/abs/2605.22769v1	cs.CL, cs.AI	May 21, 2026	Detected	RDR84	Large language models (LLMs) are typically trained on shuffled corpora, yielding models whose...
RoboWits: Unexpected Challenges for Robotic Creative Problem Solving	Chunru Lin, Hongxin Zhang, Fenghao Yu	http://arxiv.org/abs/2605.30326v1	cs.RO, cs.AI	May 28, 2026	None	RDR83	The ability to reason, adapt, and creatively solve problems under unexpected challenges is es...
VLMs May Not Globally Enhance Human Alignment over LLMs During Natural Reading	Jinzhou Wu, Zhengwu Ma, Jixing Li	http://arxiv.org/abs/2605.28818v1	cs.CL, q-bio.NC	May 27, 2026	None	RDR83	Large language models (LLMs) have become increasingly useful computational models of human la...
Ω-QVLA: Robust Quantization for Vision-Language-Action Models via Composite Rotation and Per-step Scaling	Xinyu Wang, Mingze Li, Sicheng Lyu	http://arxiv.org/abs/2605.28803v1	cs.CV, cs.LG	May 27, 2026	Detected	RDR83	Vision-Language-Action (VLA) models unify perception, reasoning, and control within a single...
Do Agents Need Semantic Metadata? A Comparative Study in Agentic Data Retrieval	Shiyu Chen, Tarfah Alrashed, Alon Halevy	http://arxiv.org/abs/2605.28787v1	cs.IR, cs.AI	May 27, 2026	None	RDR83	In the era of autonomous agents, machine-actionable data is critical for data-driven workflow...
Principled Algorithms for Optimizing Generalized Metrics in Multi-Label Learning	Mehryar Mohri, Yutao Zhong	http://arxiv.org/abs/2605.28767v1	cs.LG, stat.ML	May 27, 2026	None	RDR83	Many real-world classification tasks require predicting multiple labels per instance, necessi...
LLM Zeroth-Order Fine-Tuning is an Inference Workload	Zelin Li, Caiwen Ding	http://arxiv.org/abs/2605.28760v1	cs.LG	May 27, 2026	None	RDR83	Zeroth-order (ZO) fine-tuning is attractive for large language models because it replaces bac...
Governed Evolution of Agent Runtimes through Executable Operational Cognition	Mariano Garralda-Barrio	http://arxiv.org/abs/2605.27328v1	cs.SE, cs.AI	May 26, 2026	None	RDR83	Recent advances in agentic systems increasingly treat code as an executable operational subst...