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/2608.26067v1

Code links

on this page

Paper	Authors	arXiv ID	Categories	Published	Code	Radar	Summary
StreamPI: Streaming Multimodal Temporal Modeling for Vision-Language-Action Models	Zhe Liu, Jinghua Hou, Yuxiang Lu	http://arxiv.org/abs/2608.26067v1	cs.CV	Aug 26, 2026	None	RDR74	Vision-Language-Action (VLA) models have demonstrated effectiveness in robot manipulation, ye...
UltraPIPS: Improving model perception in B-mode ultrasound with foundation models	Tal Grutman, Tali Ilovitsh	http://arxiv.org/abs/2608.26033v1	cs.CV, eess.IV	Aug 26, 2026	Detected	RDR80	In medical imaging, it is common to use learned perceptual image patch similarity (LPIPS) to...
VISA: Agentic Self-Evolving Data Synthesis for Multimodal Instruction Following	Min Zeng, Guanxin Tan, Libin Cen	http://arxiv.org/abs/2608.26013v1	cs.CL	Aug 26, 2026	None	RDR78	Multimodal instruction-following models require training data that is accurate, diverse, veri...
A Self-Evolving Multi-Agent Framework Defense against LLM Jailbreak Attacks	Tongyan Hu, Bryan Hooi	http://arxiv.org/abs/2608.26008v1	cs.CR, cs.CL	Aug 26, 2026	None	RDR76	Large language models (LLMs) remain vulnerable to jailbreak attacks that exploit techniques s...
VoiceMem: Streaming Dual-Brain Memory for Real-Time Interaction	Zhifei Xie, Jiaqi Lang, Ze An	http://arxiv.org/abs/2608.26005v1	eess.AS, cs.AI	Aug 26, 2026	None	RDR81	Conversational systems, such as duplex speech language models (SLMs), still lack a streaming,...
AsymSpec: Context-Asymmetric Speculative Decoding for Agentic LLMs	Sheng Liang, Yongyue Zhang, Nathanael Brian	http://arxiv.org/abs/2608.26004v1	cs.AI, cs.CL	Aug 26, 2026	None	RDR78	Agentic LLM pipelines face escalating inference costs as context accumulates across retrieval...
Recursive Experiential-Working Memory Evolution for Long-Horizon Agent Harnesses	Zhaochen Yu, Yingcheng Wu, Zhenfei Yin	http://arxiv.org/abs/2608.24876v1	cs.AI, cs.CL	Aug 25, 2026	Detected	RDR86	Recursive self-improvement (RSI) remains hard in long-horizon tasks, where growing histories...
UrbanGround: From Local Perception to Spatial Agency in a Real-Scale City	Tianjie Ju, Zheng Wu, Yueqing Sun	http://arxiv.org/abs/2608.27456v1	cs.CV	Aug 27, 2026	None	RDR64	Multimodal large language models (MLLMs) can interpret a street view, but urban agency depend...
How Language Models Organize and Structure Moral Knowledge	Orion Reblitz-Richardson	http://arxiv.org/abs/2608.27402v1	cs.CL, cs.AI	Aug 27, 2026	None	RDR77	How do large language models (LLMs) organize moral knowledge? Models detect moral content bro...
Successive Capacity Growth: Task-Complexity-Driven Width and Depth Expansion for Vision Transformer Encoders in JEPA World Models	Frederik Berenz	http://arxiv.org/abs/2608.27367v1	cs.CV, cs.AI	Aug 27, 2026	None	RDR77	Joint-Embedding Predictive Architectures (JEPAs) for world modeling typically employ fixed-si...