arXiv 论文速递

针对人形机器人在杂乱室内环境中的全身导航难题，提出视觉-语言-动作模型，突破传统2D路径规划局限，对具身智能落地具有重要意义。

We study the problem of navigating cluttered indoor environments with a humanoid robot. Unlike conventional methods that model navigation as a 2D path planning problem, humanoid tr…

循环模型天然适合长上下文，但BPTT训练常无法外推。该研究突破此瓶颈，对高效长序列处理有重要价值。

Recurrent models provide a natural path to long-context modeling, yet models trained with backpropagation through time (BPTT) often fail beyond their training horizon. Classical an…

针对LLM智能体长程规划中动作选择缺乏结构化的问题，提出自演化执行图，提升复杂任务中的决策效率与鲁棒性。

Large language models are increasingly deployed as agents that plan over long horizons and act through external tools. Most agents select actions through unconstrained generation o…

在光滑凸优化中证明Silver步长几乎最优，为梯度下降加速提供理论下界，深化对非负步长加速机制的理解。

We study how far gradient descent (GD) can be accelerated by predetermined nonnegative stepsizes in smooth convex optimization. Writing $p_{\mathrm{sil}}=\log_2(1+\sqrt{2})$, we pr…

面向医疗数字化产生的纵向多模态患者数据，提出时间感知模型以全面表征和预测患者病程，对精准医疗和临床决策有重要价值。

The digitization of healthcare has generated vast, longitudinal, and multimodal patient records over a lifetime, yet fully exploiting these data to represent and predict patient st…

Robotic Process Automation (RPA) is widely used to reduce administrative burden in United States hospitals, yet an estimated 30-50% of RPA initiatives underperform because processe…

Existing methods for test-time reinforcement learning (TTRL) derive rewards from answer-level self-voting on unlabeled test-time tasks with canonical answers, but this breaks down …

Agent harnesses (the system prompt, tool set, execution hooks, and context-management scaffolding around a model) are a critical determinant of agentic task success. Automated harn…

Execution feedback can guide coding agents toward correct repository repairs, but only when the tests capture the behavior requested by the issue. Agent-generated tests can encode …

An input may activate few hidden units even when different inputs collectively use an entire network. We study the statistical complexity of this input-dependent sparsity in the on…

Amari's contributions to information geometry and machine learning are well known. Here, we revisit Amari's work on Bayesian duality which has not received as much attention. We co…

Visual encoders construct a representation of the image input for Vision-Language models. How much conceptual, as opposed to immediately visible, information does this representati…