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

2,287

matching records

Shown

current page

Top radar

http://arxiv.org/abs/2608.21317v1

Code links

on this page

Paper	Authors	arXiv ID	Categories	Published	Code	Radar	Summary
From Regulation to Implementation: A Critical Evaluation of LLM-Assisted Regulatory Compliance in Industry	Adriana Watson, Marco Bücheler, Grant Richards	http://arxiv.org/abs/2608.21317v1	cs.AI	Aug 21, 2026	None	RDR84	The European Union (EU) has emerged as a leading regulatory body in the development of sustai...
When Adaptation Hurts: Connecting Representational Drift to OOD Failures in MedSAM Fine-Tuning	Marko Haralović, Sounic Akkaraju, Carlo Baretta	http://arxiv.org/abs/2608.21300v1	cs.CV	Aug 21, 2026	Detected	RDR82	Foundation models for medical image segmentation, like prompt-based MedSAM, generalize well a...
Beyond Teacher Likelihood: Group-Calibrated On-Policy Distillation for Long-Context Reasoning	Zhu Zhang, Jixun Wang, Xiaoang Xu	http://arxiv.org/abs/2608.19181v1	cs.LG, cs.AI	Aug 19, 2026	Detected	RDR86	On-policy distillation (OPD) trains a student on its own responses using dense token-level gu...
Beyond the Transcript: Detecting Covert Co ordination in Latent Multi-Agent Communication	Ramneet Kaur, Pradyumna Chari, Ramesh Raskar	http://arxiv.org/abs/2608.19161v1	cs.AI, cs.CR	Aug 19, 2026	None	RDR86	Language-model agents can communicate through continuous hidden states that are invisible in...
DualOPSD: Adaptive Privileged Teachers for On-Policy Self-Distillation	Yutong Chen, Guangfu Guo, Zhichao Xu	http://arxiv.org/abs/2608.26019v1	cs.LG, cs.AI	Aug 26, 2026	None	RDR64	On-policy self-distillation (OPSD) uses a privileged copy of the student model to provide den...
LION: A Clifford Neural Paradigm for Multimodal-Attributed Graph Learning	Xunkai Li, Zekai Chen, Zhengyu Wu	http://arxiv.org/abs/2608.24795v1	cs.LG	Aug 25, 2026	None	RDR75	Recently, the rapid advancement of multimodal domains has driven a data-centric paradigm shif...
When Names Cross Scripts: A Source-Grounded Benchmark for Historical Entity Reconciliation in the Mongol World	Xiang Chen, Zeyu Zhang	http://arxiv.org/abs/2608.23507v1	cs.CL, cs.AI	Aug 24, 2026	None	RDR73	Historical people may appear under different languages, scripts, and transcription traditions...
AI with Authority, from Application to Silicon	Jason Hickey	http://arxiv.org/abs/2608.21356v1	cs.SE, cs.AI	Aug 21, 2026	None	RDR76	For sixty years, machine verification has been a major cost overhead, affordable only for exc...
Rethinking Expressivity and Efficiency in Test-Time Training	Zeyun Zhong, Joya Chen, Manuel Martin	http://arxiv.org/abs/2608.21308v1	cs.LG	Aug 21, 2026	Detected	RDR83	Test-Time Training (TTT) enables long-context processing via continuous weight updates during...
VT-MUSE: Multimodal Unified Sequential Visuotactile Representation Learning for Manipulation	Congsheng Xu, Qiaochu Yang, Fangyuan Shi	http://arxiv.org/abs/2608.21290v1	cs.RO, cs.CV	Aug 21, 2026	None	RDR80	We propose VT-MUSE, a Multimodal Unified SEquential representation learning framework for vis...