论文

一个全栈系统，可从第一人称人类视频扩展灵巧 VLA 的预训练，并支持数据高效的真实机器人后训练，在 40+ 多种任务上稳健执行自由形式指令，展现出失败恢复、灵巧性与泛化能力。A full-stack system that scales dexterous VLA pre-training from egocentric human videos and enables data-efficient real-robot post-training that robustly executes free-form instructions across 40+ diverse tasks, demonstrating failure recovery, dexterity, and generalization.

提出 SpectraReward，一种无需训练的将预训练 MLLM 转化为即用型奖励模型的奖励函数，用于图像生成强化学习；并引入 Self-SpectraReward，这是统一多模态模型的一种特例，其中策略自身的理解分支充当其生成分支的奖励模型。SpectraReward is proposed, a training-free reward function that turns pretrained MLLMs into off-the-shelf reward models for image-generation reinforcement learning, and Self-SpectraReward is introduced, a special case for unified multimodal models where the policy's own understanding branch serves as the reward model for its generation branch.

本文对 OPD 的作用、病态与调控进行系统研究，厘清 OPD 作为探索催化剂的角色，并证实调控良好的信号质量（而非单纯的教师模型规模）才是 OPD 中成功探索的主导因素。A systematic study examining the role, pathologies, and regulations of OPD, clarifying the role of OPD as an exploration catalyst and confirming that well-regulated signal quality, rather than mere teacher scale, governs successful exploration in OPD.

本文提出 LongStraw，一个面向目标、感知架构的系统，用于 resident-state 虚拟化、response replay 和分布式梯度执行，它将实时训练图限制在 response 后缀范围内，同时在完整的 GRPO 组内复用代价高昂的 prompt 计算。This work presents LongStraw, an objective-aware, architecture-aware system for resident-state virtualization, response replay, and distributed-gradient execution that bounds the live training graph by the response suffix while reusing the expensive prompt computation across the complete GRPO group.

子空间对齐重连（SAR）表明，从参数几何中提取对推理有效的更新，可作为一种无需训练的机制来提升推理与多领域性能。Subspace-Aligned Rewiring (SAR) shows that extracting reasoning-effective updates from parameter geometry can serve as a training-free mechanism to improve reasoning and multi-domain performance.

Xiaomi-Robotics-1是一个强大的机器人基础策略，能在复杂灵巧任务上以高数据效率高效微调，并在多个仿真基准上超越SOTA方法。Xiao-Robotics-1 serves as a strong robot foundation policy that can be efficiently fine-tuned on complex, dexterous tasks with high data efficiency and across multiple simulation benchmarks, Xiaomi-Robotics-1 outperforms state-of-the-art methods.

提出xHC（扩展型超连接），是首个在N=4之外实现有意义扩展的HC系列方法；引入xHC-Flash，将每个子层的内存访问量从73.5C降至40C（与mHC在N=4时的34C相当），同时保留完整xHC带来的性能增益。This work proposes xHC (Expanded Hyper-Connections), the first HC-family method to achieve meaningful expansion beyond $N{=}4$ and introduces xHC-Flash, which reduces the per-sublayer memory traffic from $73.5C$ to $40C, comparable to the $34C$ required by mHC at $N{=}4$, while retaining the gains of full xHC.

BLIP-2 在多种视觉-语言任务上取得 SOTA 性能，可训练参数远少于现有方法，并展现出遵循自然语言指令进行零样本图生文的新兴能力。BLIP-2 achieves state-of-the-art performance on various vision-language tasks, despite having significantly fewer trainable parameters than existing methods, and is demonstrated's emerging capabilities of zero-shot image-to-text generation that can follow natural language instructions.

本文从参考图像中识别低秩背景特征子空间，并以闭式方式将参考与查询特征投影到其正交补空间，从而获得更清晰的语义匹配，并在 PACO-Part、FSS-1000 以及 ISIC2018 等跨域数据集的无训练方法中达到新的 SOTA，表明显式去除背景子空间是一次性定位中极为有效的原则。This paper identifies the low-rank background feature subspace from the reference image and project the reference and query features onto its orthogonal complement in closed form, yielding cleaner semantic matching, and establishes a new state of the art among training-free methods on PACO-Part, FSS-1000, and cross-domain datasets such as ISIC2018, demonstrating that explicit background subspace removal is a highly effective principle for one-shot localization.

本文提出 Token-Level Off-Policy Labeling (TOPL)，一种将后训练重构为 token 级正确性预测任务的离线策略训练范式。其核心思路是：通过训练模型区分响应中的好 token 与坏 token，自然引导模型生成好 token，同时避免直接训练模型生成离线策略 token 所带来的缺陷。在文档摘要任务上的实验表明，TOPL 在 11 个数据集上针对多种序列级与 token 级方法实现了强大的分布外泛化能力。We propose Token-Level Off-Policy Labeling (TOPL), an off-policy training paradigm that reframes post-training as a token-level correctness prediction task. Our key intuition is that by training the model to distinguish good and bad tokens in a response, we naturally guide the model towards generating good tokens, while avoiding the pitfalls that come with directly training the model to generate off-policy tokens. Experiments on document summarization tasks show that TOPL achieves strong out-of-distribution generalization across 11 datasets against a diverse set of sequence-level and token-lev

大量实验表明，Distilled RL 在 pass@1 和 pass@k 上均显著优于标准 RL 和 OPD，并能将教师模型中此前无法获得的知识有效迁移至学生模型。Extensive experiments show that Distilled RL substantially outperforms standard RL and OPD in terms of both pass@1 and pass@k, and can effectively transfer previously unavailable knowledge from a teacher model to a student model.

本文针对中亚低资源语言构建鲁棒基础模型的挑战，提出 GigaAM Multilingual：一个基于 HuBERT 风格目标在 2M 小时音频上预训练的 Conformer encoder，并在预训练阶段引入 cluster 级的数据均衡策略，在微调阶段引入域感知采样方法，以缓解头部语言主导问题。This work addresses the challenge of building robust foundation models for underrepresented Central Asian languages by presenting GigaAM Multilingual, a Conformer encoder pre-trained on 2M hours of audio using a HuBERT-style objective, and introduces a cluster-level data balancing strategy during pre-training and a domain-aware sampling method during fine-tuning to mitigate head-language dominance.

本文研究 SkewAdam——一种基于以下观察构建的优化器：MoE 的三类参数群体在规模与梯度统计上差异足够大，不应共享相同的状态；研究表明优化器状态的存放位置至少与状态容量同等重要。SkewAdam, an optimizer built on the observation that the three parameter populations of an MoE differ enough in size and gradient statistics that they should not receive the same state, is studied, suggesting where optimizer state lives matters at least as much as how much of it there is.

研究发现，在上述多个维度上进行的指令微调可显著提升多种模型类别（PaLM、T5、U-PaLM）、多种提示设定以及多种评测基准（MMLU、BBH、TyDiQA、MGSM、开放式生成）上的表现。It is found that instruction finetuning with the above aspects dramatically improves performance on a variety of model classes (PaLM, T5, U-PaLM), prompting setups, and evaluation benchmarks (MMLU, BBH, TyDiQA, MGSM, open-ended generation).

本文为两部分组成的专题论文，介绍物理信息神经网络——一类在训练求解监督学习任务时遵循由一般非线性偏微分方程所描述的物理定律的网络；并展示如何利用这些网络推断偏微分方程的解，以及获得对所有输入坐标和自由参数完全可微的物理信息代理模型。This two part treatise introduces physics informed neural networks -- neural networks that are trained to solve supervised learning tasks while respecting any given law of physics described by general nonlinear partial differential equations and demonstrates how these networks can be used to infer solutions topartial differential equations, and obtain physics-informed surrogate models that are fully differentiable with respect to all input coordinates and free parameters.

一个能够将任意自然语言任务轻松映射为人类可读 prompt 形式的系统，并在覆盖多种任务的多任务混合数据上对预训练 encoder-decoder 模型进行微调。A system for easily mapping any natural language tasks into a human-readable prompted form and fine-tune a pretrained encoder-decoder model on this multitask mixture covering a wide variety of tasks.

本文提出 Anchor-Align，通过两个目标增强 BC：Vision-Language Anchoring 从冻结 VLM 副本中蒸馏逐层表示以防止该漂移；Language-Action Alignment 将每个动作目标转换为离散的运动方向标签，并在同一机器人观测上联合训练语言与动作预测。Anchor-Align is proposed, which augments BC with two objectives: Vision-Language Anchoring distills layer-wise representations from a frozen VLM copy to prevent this drift, and Language-Action Alignment converts each action target into a discrete motion-direction label and jointly trains language and action prediction on the same robot observation.

本文开发并发布了 Llama 2，这是一系列参数规模从 70 亿到 700 亿不等的预训练与微调大语言模型（LLMs），有望成为闭源模型的合适替代品。This work develops and releases Llama 2, a collection of pretrained and fine-tuned large language models (LLMs) ranging in scale from 7 billion to 70 billion parameters, which may be a suitable substitute for closed-source models.

本研究证实了激活函数之间存在统计显著的性能差异，从而再次确认了非饱和函数在深度架构中的必要性，并恢复了对此前文献的恰当历史归属。This study confirms a statistically significant performance variance among activations, thus reaffirming the necessity of non-saturating functions in deep architectures, and restores proper historical attribution to prior literature.

一种基于二部交互图上可微分消息传递的图自编码器框架，在标准协同过滤基准上表现出竞争力，并优于近期的 SOTA 方法。A graph auto-encoder framework based on differentiable message passing on the bipartite interaction graph that shows competitive performance on standard collaborative filtering benchmarks and outperforms recent state-of-the-art methods.

本文介绍 MLlib，Spark 的开源分布式机器学习库，可为多种学习场景提供高效功能，并包含若干底层的统计、优化和线性代数原语。MLlib is presented, Spark's open-source distributed machine learning library that provides efficient functionality for a wide range of learning settings and includes several underlying statistical, optimization, and linear algebra primitives.

结果表明，基于逻辑的神经架构成为资源受限脑机接口的实用范式，在原生满足便携式边缘部署的延迟和内存约束的同时，取得了有竞争力甚至更优的性能。The results establish logic-based neural architectures as a practical paradigm for resource-constrained brain-computer interfaces, achieving competitive or superior performance while natively satisfying the latency and memory constraints of portable edge deployment.

本文描述了一份以模式形式呈现的 prompt 工程技巧目录，这些技巧已被用于解决与 LLMs 对话时的常见问题，以改进 LLM 对话的输出。A catalog of prompt engineering techniques presented in pattern form that have been applied to solve common problems when conversing with LLMs to improve the outputs of LLM conversations is described.

本文提出通过熵正则化对 Wasserstein 距离进行平滑处理，由此得到一个严格凸的目标函数，其梯度可借助矩阵缩放算法以显著更低的计算代价求得。The Wasserstein distance is proposed to be smoothed with an entropic regularizer and recover in doing so a strictly convex objective whose gradients can be computed for a considerably cheaper computational cost using matrix scaling algorithms.

本综述尝试连接并系统化现有迁移学习研究，全面总结与阐释迁移学习的机制与策略，帮助读者更好地理解当前研究现状与思路。This survey attempts to connect and systematize the existing transfer learning research studies, as well as to summarize and interpret the mechanisms and the strategies of transfer learning in a comprehensive way, which may help readers have a better understanding of the current research status and ideas.

本综述旨在阐明 PFMs 在可扩展性、安全性、逻辑推理能力、跨领域学习能力以及面向 AGI 的友好交互能力方面的研究。This survey aims to shed light on the research of the PFMs on scalability, security, logical reasoning ability, cross-domain learning ability, and the user-friendly interactive ability for artificial general intelligence.

本综述从数据管理视角对数据收集进行全面研究，提供了相关操作的研究全景图、何时使用何种技术的指导原则，并识别出值得关注的研究挑战。This survey performs a comprehensive study of data collection from a data management point of view, providing a research landscape of these operations, guidelines on which technique to use when, and identify interesting research challenges.

在大规模复杂的移动边缘网络中，涉及具有不同约束的异构设备，这为大规模 FL 实施带来了通信成本、资源分配以及隐私安全方面的挑战。In a large-scale and complex mobile edge network, heterogeneous devices with varying constraints are involved, this raises challenges of communication costs, resource allocation, and privacy and security in the implementation of FL at scale.

本综述旨在通过对基本思想与关键原则的系统回顾以及对不同算法与技术的合理分类，提供在线机器学习文献的全面综述。This survey aims to provide a comprehensive survey of the online machine learning literatures through a systematic review of basic ideas and key principles and a proper categorization of different algorithms and techniques.

提出 Manhattan NMF（MahNMF），通过最小化 $X$ 与 $W^T H$ 之间的 Manhattan 距离建模重尾 Laplacian 噪声，并以迭代方式提升 MahNMF 及其扩展的近似精度。Manhattan NMF (MahNMF) is presented which minimizes the Manhattan distance between $X and $W^T H$ for modeling the heavy tailed Laplacian noise and improves the approximation accuracy iteratively for both MahNMF and its extensions.

总结了利用人工智能以及语音与语言处理预测阿尔茨海默病相关认知衰退的现有研究发现。The existing findings on the use of artificial intelligence, speech, and language processing to predict cognitive decline in the context of Alzheimer’s disease are summarized.

提出一种全可微、样本级影响力估计器，可在不进行耗时的逆 Hessian 乘积或凸性假设的前提下，量化因添加或移除数据而产生的参数变化。A fully differentiable, sample-level influence estimator that quantifies parameter shifts from adding or removing data, without time-consuming inverse-Hessian products or convexity assumptions is introduced.

实验跟踪器能够展示训练的进展，但更改正在运行的训练通常仍需编写特定于训练器的代码。我们提出了 Interactive Training 2，一个通过共享协议引导训练的开源控制平面。训练应用声明其暴露的设置和操作，人类与自动化控制器通过同一接口提交请求，训练循环在安全的控制点对请求进行验证并应用。定制的 Aim 工作区将实时指标与控制面板以及请求和结果的时序记录整合在一起。我们在 a[……]上展示了该系统。Experiment trackers show how training is progressing, but changing a live run still usually requires trainer-specific code. We present Interactive Training 2, an open-source control plane for steering training through a shared protocol. Training applications declare which settings and actions they expose, humans and automated controllers submit requests through the same interface, and the training loop validates and applies them at safe control points. A customized Aim workspace combines live metrics and controls with a chronological record of requests and outcomes. We demonstrate the system a

提出 DataPrep-Bench，首个统一基准，在共享的下游任务 grounding 协议下，对 LLM 驱动的数据准备在六个领域、多种 base model 上的两类能力进行联合评估。DataPrep-Bench is introduced, the first unified benchmark that jointly evaluates both capabilities under a shared downstream-grounded protocol over six domains and multiple base models of LLM-driven data preparation.

提出一个统一且受控的多轮环境，可在三阶段精确控制长程规划；研究表明，多教师 on-policy 蒸馏 (MOPD) 通过收敛到跨环境共享的规划模式来整合多种能力。A unified and controlled multi-turn environment that enables precise control of long-horizon planning across three stages is introduced and it is shown that multi-teacher on-policy distillation (MOPD) integrates capabilities by converging to shared planning-pattern across environments.

本文提出问题：与其缩减真实机器人数据占比，不如提高无机器人 UMI 数据的保真度，从而在后训练阶段移除该 anchor；并开源 HiFi-UMI，一套面向轨迹精度、夹爪间相对位姿、同步与视场协同设计的便携式 UMI 数据生产系统。It is asked whether raising the fidelity of robot-free UMI data, rather than shrinking the real-robot fraction, can remove that anchor at post-training, and open-source HiFi-UMI, a portable UMI data-production system co-designed for trajectory accuracy, inter-gripper relative pose, synchronization, and field of view.