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

Agentic robotics places a large language model (LLM) agent in the robot control loop, where it composes perception, motion, and vision-language-action (VLA) tools under the guidance of a memory and th

Bingxin Xu, Wenrui Bao, Xinxin Liu

Sparse-to-dense motion completion recovers dense mesh motion from sparse vertex displacements. Residual priors trained on one geometry family frequently fail to beat parameter-free harmonic extension

Chih-Hai Su, Tsung-Wei Ke, Yu-Lun Liu

How should demonstration quality be used during vision-language-action (VLA) pretraining to improve performance after target-task fine-tuning? We compare weighting, filtering, and conditioning across

Mingxuan Yan, Litian Gong, Dihong Huang

Long-horizon agents have drawn growing attention for their ability to work autonomously -- from hours to days -- on economically valuable tasks, a capability essential to automated discovery and recur

Wenbo Hu, Shraman Pramanick, Krishna Kumar Singh

Sampling equilibrium field configurations remains a major computational bottleneck in lattice field theory, motivating the development of generative samplers that can produce independent configuration

Dennis Grinwald, Ankur Singha, Khaled Kahouli

Reasoning models achieve strong performance through long chains of thought (CoT), but often spend more tokens than needed to solve a problem. Existing ways to shorten the CoT require additional traini

Minghao Luo, Liang Chen

Generating information-rich visual artifacts such as slides, posters, and dashboards as code is appealing because the outputs are structured, editable, and verifiable. Yet code models cannot see how t

Xin Gao, Yifan Yang, Xin Li

How can we build an agent that thinks beyond human language, yet still acts through it in the external environment? Modern LLM agents still reason and interact through text, while latent reasoning off

Jiaru Zou, Yunzhe Qi, Sirui Chen

Persistent homology summarizes the topological evolution of a graph as persistence diagrams (PDs). Generating graphs whose topology matches a target descriptor is increasingly important, yet existing

Mattie Ji, Indradyumna Roy, Vikas Garg

Reinforcement learning with verifiable rewards (RLVR) relies on costly model-generated responses, motivating larger rollout batches and square-root learning-rate scaling. Reported to approximately pre

Yuante Li, Junwei Quan, Kai Qiu

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