技术雷达TECH RADAR · GITHUB · ARXIV · HACKER NEWS

Recent advances in automatic rigging now deliver animation-ready 3D assets at scale, yet generating the motion to drive them remains a bottleneck. Existing learned animators are topology-constrained:

Linzhan Mou, Jiahui Lei, Zhiyang Dou

Diffusion TV is an interactive AI art installation that offers a tangible and embodied experience of diffusion models through a modified CRT TV. By physically manipulating the TV's antenna, audiences

Sihwa Park

Retail search systems serve diverse geographic regions with distinct query patterns, vocabularies, and product preferences, creating significant data heterogeneity that challenges both privacy-preserv

Quoc H. Nguyen, Ali Lafzi, Abhijeet Phatak

Wireless signals with position-related labels are pivotal for both performance evaluation and model training in the realm of wireless sensing. However, acquiring real-world datasets is often challenge

Yuxiao Li, Keke Hu, Santiago Mazuelas

Data-sovereignty regulations increasingly require public institutions to deploy open-source, on-premise LLM agents that chain multiple tool-calls across live government APIs. However, open-source mode

Dain Kim, Eungi Cho, Kyumin Kim

LLM decision components that can operate within agent workflows often produce action-relevant recommendations or judgements together with explanations. Operators may use the named factors to monitor a

Urja Pawar, Rajitha Ramanayake, Nabeel Kemal

We propose Ref-GeNVS, a training-free, reflection-aware method for generative novel view synthesis (NVS) in mirror scenes. Existing multi-view diffusion models often fail to recognize the mirror in th

GeonU Kim, Shin Dong-Yeon, Tae-Hyun Oh

Large language models (LLMs) are increasingly evaluated on molecular property benchmarks, but accuracy cannot distinguish a model that predicts a property from one that retrieves a published number. W

Matthias Busch, Marius Tacke, Sviatlana V. Lamaka

Visuomotor imitation policies can achieve high performance under in-distribution visual conditions yet fail when visually similar objects or receptacles are introduced. We study this behavior as a pro

Vivek Chavan, Pengtao Xie, Yahuan Shi

Computer-use agents have advanced on benchmarks like OSWorld and AndroidWorld, but still act mostly through the GUI, often producing inefficient trajectories. Real-world computer work is hybrid, combi

Haoting Shi, Wenhao Wang, Weicheng Fang

原文 · 讨论

原文 · 讨论

原文 · 讨论

原文 · 讨论

原文 · 讨论

原文 · 讨论

原文 · 讨论

原文 · 讨论

原文 · 讨论

原文 · 讨论