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

Video generation models can now depict remarkably realistic motion. Yet it is unclear how to use this motion beyond pixels: to animate a specific 3D asset and replay the animation in its 3D scene. For

Noam Rotstein, Yoad Tewel, Chen Tessler

Agentic artificial intelligence (AI) systems hold immense potential for automating complex workflows in materials discovery and design, but extending them to domain-intensive mechanistic investigation

Yazhuo Liu, Kunqing Ding, Xiaoguo Gong

Dexterous multi-finger hands hold promise to unlock diverse skills like functional grasps, in-hand reorientation, and dynamic handover that the human-designed world assumes, yet existing learning reci

Yuxuan Kuang, Jiashun Wang, Yixuan Sun

Motivated by the human ability to integrate experience across language, perception, and action, we introduce UniWALM, a unified world-action-language model that learns video, action, and language in a

Rahul Sajnani, Diego Romeres, Mingyuan Zhang

Warehouse robot fleets continuously observe operational conditions, but preserving these observations as reusable semantic memory incurs substantial computation, communication, and storage costs. For

Jad Yammine, Malek Wahidi, Abrar Anwar

Planning under uncertain control execution noise requires reliable feedback policies across diverse environments. We introduce Planning Under Noise (PUN), a neural operator that learns noise-aware val

Michael Chen, Hong Chul Nam, Xi Deng

Spatial intelligence has recently been assessed through generative tasks such as spatially grounded image editing, yet language-guided generation of spatially consistent views from partial multi-view

Yanbo Wang, Siqi Luo, Siyu Zhang

Multi-token prediction (MTP) can accelerate language-model decoding by drafting several tokens and verifying them in a single target-model pass. However, the best speculation horizon changes with cont

Emile Anand, Mohammed Rehan Parwani, Xinyuan Cao

Graph generative models commonly use graph-specific Transformer architectures to jointly update node and edge features. However, these architectures do not directly benefit from recent hardware-aware

Vincent Jung, Alba Carballo-Castro, Yiming Qin

Modern distributed microservice deployments generate massive volumes of heterogeneous, multi-format observability logs across physically and logically partitioned infrastructure. Isolating root causes

Jitendra Solanki, Anand Todkar, Ziran Min

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