arXiv 论文速递

Personalization is essential for general-purpose robots to transition into household environments and achieve true practicality. While general robotic manipulation has been extensi…

用大语言模型发现先进量子电路，为大规模量子信息处理器的实用化提供新路径，跨领域意义显著。

Significant efforts are currently being directed toward the implementation of large-scale quantum information processors, but realizing useful quantum advantage also requires the d…

在测试时优化环境隐变量，使机器人世界模型能推断不可见环境因素，提升动作预测的鲁棒性与泛化能力。

Predicting how the world responds to an action requires more than what can be seen: robots must account for environmental factors that are neither directly observable nor explicitl…

Generative simulation can automate robot environment construction, but physically valid environments are not necessarily useful for training. The challenge is to identify environme…

Time series foundation models are becoming increasingly popular for general-purpose forecasting. However, most leading models predict marginal quantiles, leaving the dependence str…

重新审视现代MoE架构中的路由探索问题，对提升大模型参数扩展效率与训练稳定性具有基础性价值。

Mixture-of-experts (MoE) models have become an important approach for scaling model parameters. Modern MoE architectures increasingly combine two design choices: fine-grained exper…

Existing agent benchmarks typically evaluate agents on well-specified tasks defined by issue reports, specifications, or task tickets. Real-world customer delivery is different: fo…

构建自主进行机器学习工程的通用智能体，将LLM从辅助科研扩展到自动开发改进AI系统，代表AI自我进化方向。

Large language models (LLMs) are expanding from assisting scientific research and engineering to autonomously developing and improving AI systems, advancing AI for AI (AI4AI) as a …

Recent 3D world models increasingly use features from geometry foundation models (GFMs) as predictive world states, benefiting from their rich geometric priors. However, the view d…

We introduce 3DCodeVerse, a research ecosystem that enables coding agents to create editable and verifiable 3D content at scale. 3DCodeVerse comprises large-scale, high-quality dat…

提出DSP方法让机器人自主采集接触丰富的灵巧操作经验，解决数据获取瓶颈，对通用灵巧操作学习有重要推动作用。

How can robots autonomously collect the contact-rich experience needed to learn dexterous manipulation? We present DSP: Dexterity from supervised play, a framework in which a robot…

Retrieving relevant lemmas is crucial for formal theorem proving, enabling provers to build machine-checkable proofs from established mathematical results. Recent retrieval systems…