论文

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.

提出 pi-r2-flow，使 action-chunking flow 策略具备实时响应能力，同时保留大型 backbone、表达力强的多模态策略与多动作预测能力，并给出延迟自适应 flow 调度，将 in-flight 动作作为 inpainting 条件，每次调用仅需一步去噪即可输出动作。This work presentspi-r2-flow, which makes action-chunking flow policies reactive and real-time while retaining large backbones, expressive multi-modal policies, and multi-action prediction, and a latency-adaptive flow schedule that treats in-flight actions as inpainting conditioning and emits actions in one denoising step per call.

本文提出 CADENA（西班牙语意为"链"），一种将 3D 网格重建为参数化 CAD 程序的模型，按顺序逐个生成操作序列，并在每一步将目标与当前预测几何进行对比。This work introduces CADENA (Spanish for"chain"), a model that reconstructs a 3D mesh as a parametric CAD program, growing its sequence of operations one at a time and comparing the target with the currently predicted geometry at every step.

本文提出 Wnuan 三阶段流程：从文档构建任务导向监督，结合通用数据回放进行监督微调，对残余误差应用强化学习，阐述分阶段企业适配的收益与通用能力代价Wnuan, a three-stage pipeline that constructs task-oriented supervision from documents, performs supervised fine-tuning with general-data replay, and applies reinforcement learning to residual errors is presented, describing both the gains and the general-capability cost of staged enterprise adaptation.

提出 Knowledge-Geometry Decoupling (KGD) 并引入 Behavioral Multi-Token Prediction (BMTP)，仅将协作或语义相关的未来项作为监督，从而得到更干净、更可迁移的行为知识。Knowledge-Geometry Decoupling (KGD) is proposed and Behavioral Multi-Token Prediction (BMTP) is introduced to retain only collaboratively or semantically related future items as supervision, yielding cleaner and more transferable behavioral knowledge.

提出 Semantic-Temporal WAM (ST-WAM)，使用 DINOv3 作为未来预测与历史检索的共享语义表示，同时保留细粒度 VAE 动力学，以提升动作鲁棒性；证明语义-时间建模能有效补充像素生成动力学，实现稳健的操作。Semantic-Temporal WAM (ST-WAM) is proposed to improve action robustness by using DINOv3 as a shared semantic representation for future prediction and history retrieval while retaining fine-grained VAE dynamics, demonstrating that semantic-temporal modeling effectively complements pixel-generative dynamics for robust manipulation.

提出 BERTopic，一种通过开发类内 TF-IDF 变体来提取一致性主题表示，从而扩展主题建模流程的主题模型BERTopic is presented, a topic model that extends the process of topic modeling by extracting coherent topic representation through the development of a class-based variation of TF-IDF.

提出一种从校正后的图像对中提取深度信息的方法，使用卷积神经网络在小图像块上学习相似性度量，并针对该任务考察了两种网络架构：一种面向速度优化，另一种面向精度优化This work presents a method for extracting depth information from a rectified image pair by learning a similarity measure on small image patches using a convolutional neural network and examines two network architectures for this task: one tuned for speed, the other for accuracy.

在训练过程中，Random Erasing 在图像中随机选择一个矩形区域并以随机值擦除其像素，在图像分类、目标检测与行人重识别任务中相较于强基线均带来稳定提升In training, Random Erasing randomly selects a rectangle region in an image and erases its pixels with random values and yields consistent improvement over strong baselines in image classification, object detection and person re-identification.

提出 CALVER (Causal Axiom-Level VERification)，一种无需训练的对称验证器，根据 Pearl 的因果准则（包括 d-分离、backdoor 调整与干预）对结构化 trace 评分，并在不参考标准答案的情况下选择得分最高的候选。This work introduces CALVER (Causal Axiom-Level VERification), a training-free symbolic verifier that scores structured traces against Pearl's causal criteria, including -separation, backdoor adjustment, and intervention, and selects the highest-scoring candidate without consulting a reference answer.

提出 ReflectRL，一个轻量级即插即用框架，在 on-policy 训练中从 Golden Negative Trajectories 中学习：先利用这些 trajectory 引出 Reflective Reasoning，再通过 Reflective-to-Direct Policy Transition 将所学到的推理行为迁移回 Direct Reasoning。ReflectRL is proposed, a lightweight plug-and-play framework that learns from Golden Negative Trajectories during on-policy training, and first uses these trajectories to elicit Reflective Reasoning, then applies Reflective-to-Direct Policy Transition to transfer the acquired reasoning behavior back to Direct Reasoning.

K-EXAONE 2.0 在 K-EXAONE 基础上进一步提升，并保持与开源权重模型的竞争力，其最大提升体现在 agentic coding 与长上下文理解上，在长上下文检索与安全性方面优势最为明显。K-EXAONE 2.0 improves over K-EXAONE and remains competitive with open-weight models, showing its largest gains in agentic coding and long-context understanding and its clearest strengths in long-context retrieval and safety.

提出 MultiPathFormer，一种自回归基础模型，将每条发射端–接收端链路表示为连续值路径 token 的有序序列，并通过下一路径预测进行预训练，证明路径级预训练可学习无线传播的可复用表征。MultiPathFormer, an autoregressive foundation model that represents each transmitter-receiver link as an ordered sequence of continuous-valued path tokens and pretrains with next-path prediction, is presented, showing that path-level pretraining can learn reusable representations of wireless propagation.

实验表明，在 Ego2Robot 合成数据与机器人数据上的联合预训练在多种扰动类型上一致提升分布外泛化能力，并在真实机器人部署中得到验证。Experiments show that joint pretraining on Ego2Robot-synthesized and robot data consistently improves out-of-distribution generalization across multiple perturbation types, with benefits validated on real-robot deployment.

文章介绍了一种自监督视觉表征模型 BEiT（Bidirectional Encoder representation from Image Transformers），在图像分类和语义分割上的结果表明，该模型取得了与先前预训练方法相当的竞争性结果。A self-supervised vision representation model BEiT, which stands for Bidirectional Encoder representation from Image Transformers, is introduced, and results on image classification and semantic segmentation show that the model achieves competitive results with previous pre-training methods.

本文提出一种多任务深度学习的原则性方法，通过考虑各任务的同方差不确定性来加权多个损失函数，从而在分类与回归场景下同时学习具有不同单位或尺度的多种量。A principled approach to multi-task deep learning is proposed which weighs multiple loss functions by considering the homoscedastic uncertainty of each task, allowing us to simultaneously learn various quantities with different units or scales in both classification and regression settings.

基于该三轴框架，系统梳理代表性方法，追踪持续学习的演进趋势，并讨论由此引发的关键挑战、更广泛的影响以及未来方向。Anchored by this tri-axial framework, representative methods are systematically surveyed, the ongoing transition of continual learning is traced, and the key challenges, broader implications, and future directions arising from this paradigm shift are discussed.

结果表明，使用人类反馈进行微调是使语言模型与人类意图对齐的一个有前景的方向，在真实性方面有所提升，并减少了有毒输出的生成，同时在公开 NLP 数据集上的性能回归极小。The results show that fine-tuning with human feedback is a promising direction for aligning language models with human intent and showing improvements in truthfulness and reductions in toxic output generation while having minimal performance regressions on public NLP datasets.

GaussianSelector 在选择质量上与 SOTA 的多视角 SAM 方法相当，同时所需交互视角显著更少、计算开销明显更低，因而非常适合真实场景下 human-in-the-loop 的 3D 场景编辑与 3D 资产提取。GaussianSelector achieves competitive selection quality against state-of-the-art multi-view SAM-based methods, while requiring significantly fewer interaction views and substantially lower computational overhead, which makes it well suited for human-in-the-loop 3D scene editing and 3D asset extraction in real-world deployment scenarios.

本文详细阐述了驱动 PyTorch 实现的原则及其在架构中的体现，并解释了 runtime 关键组件的精心且务实的实现如何使其协同工作以获得出色的性能。This paper details the principles that drove the implementation of PyTorch and how they are reflected in its architecture, and explains how the careful and pragmatic implementation of the key components of its runtime enables them to work together to achieve compelling performance.

本文提出了一种基于迭代模型平均的深度网络联邦学习实践方法，并进行了广泛的实证评估，考虑了五种不同的模型架构和四个数据集。This work presents a practical method for the federated learning of deep networks based on iterative model averaging, and conducts an extensive empirical evaluation, considering five different model architectures and four datasets.

本文提出了一种通过创建在所有边缘设备之间全局共享的小型数据子集来改进非独立同分布数据训练的策略，并表明在 CIFAR-10 数据集上，仅共享 5% 的全局数据即可将准确率提升 30%。This work presents a strategy to improve training on non-IID data by creating a small subset of data which is globally shared between all the edge devices, and shows that accuracy can be increased by 30% for the CIFAR-10 dataset with only 5% globally shared data.

采用迭代的在线训练模式，按周节奏用新的人类反馈数据更新偏好模型与 RL 策略，并发现 RL 奖励与策略相对其初始化的 KL 散度平方根之间近似呈线性关系。An iterated online mode of training, where preference models and RL policies are updated on a weekly cadence with fresh human feedback data, and a roughly linear relation between the RL reward and the square root of the KL divergence between the policy and its initialization is identified.

研究发现，微调后的 AO 可能变成概念特异的 anti-reader：它们会选择性地无法恢复自身训练过程中持续存在的概念，从而对习得的可解释性接口提出可靠性担忧。It is found that fine-tuned AOs can become concept-specific anti-readers: they selectively fail to recover the concept persistently present during their own training, raising a reliability concern for learned interpretability interfaces.

Manifold Mixup 在监督学习、对单步对抗攻击的鲁棒性、半监督学习以及留出样本的负对数似然（NLL）上，相较强基线均取得了大幅提升。Manifold Mixup achieves large improvements over strong baselines in supervised learning, robustness to single-step adversarial attacks, semi-supervised learning, and Negative Log-Likelihood on held out samples.

本文提出 Omega-S——一种仅由权重矩阵计算得到的即插即用惩罚，无需先前任务数据、无需 Fisher 矩阵、无需保存旧权重副本，且单步开销不足 4%。Omega-S, a drop-in penalty computed from the weight matrix alone, is presented, a drop-in penalty computed from the weight matrix alone that needs no previous-task data, no Fisher matrix and no stored copy of the old weights and adds under 4% to the cost of a step.

对抗性 Fréchet 距离 (AdvFD) 用经过校准的对抗性学习表示来补充 FD-Loss 中的静态表示目标，通过对抗方式最大化真实样本与生成样本之间的 Fréchet 差异；同时引入真实特征白化，对尺度与协方差几何进行归一化，从而稳定极小极大优化。Adversarial Fr\'echet Distance (AdvFD), which complements the static representation targets in FD-Loss with a calibrated adversarially learned representation that adversarially maximizes the Fr\'echet discrepancy between real and generated samples, and introduces real-feature whitening, which normalizes its scale and covariance geometry and stabilizes the min--max optimization.

本文研究基于开源大语言模型的无参考多语言机器翻译后训练，发现 on-policy 蒸馏能够达到但无法超越结合 checkpoint 插值的强化学习所确立的质量前沿。This work studies reference-free post-training for multilingual machine translation with open large language models and finds that on-policy distillation reaches, but does not surpass, the quality frontier achieved by RL with checkpoint interpolation.

本文引入静止状态 (rest-state) 公式化方法，从单一闭合构型重建关节物体——这是一种固有的不适定设定，几何、语义与运动先验在此弥补运动线索的缺失。This work introduces a rest-state formulation that reconstructs articulated objects from a single closed configuration, an inherently ill-posed setting where geometry, semantics, and motion priors compensate for the absence of motion cues.

本工作提出在海量文本语料上使用新的自监督目标 PEGASUS 对大型 Transformer 编码器-解码器模型进行预训练，并证明其在所有 12 个下游数据集上按 ROUGE 分数衡量均取得 SOTA 性能This work proposes pre-training large Transformer-based encoder-decoder models on massive text corpora with a new self-supervised objective, PEGASUS, and demonstrates it achieves state-of-the-art performance on all 12 downstream datasets measured by ROUGE scores.

提出了能够平衡"延迟告警的上下文敏感成本"与"打断成本"的模型与推理流程，并通过对用户活动与通知内容的分析，描述了在不确定性下推理此类成本所面临的挑战Models and inference procedures that balance the context-sensitive costs of deferring alerts with the cost of interruption are presented and the challenge of reasoning about such costs under uncertainty via an analysis of user activity and the content of notifications is described.

本文提供了参数空间探索能够改进 LLM 强化学习的证据，并提出称为扰动参数策略优化（3PO）的方法族，使用不同的采样策略和不同的 rollout 分组进行 reward 估计。Evidence that parameter-space exploration can improve reinforcement learning for LLMs is presented, and a family of methods called Perturbed Parameter Policy Optimization (3PO) is introduced which use different sampling strategies and different rollout grouping for reward estimation.

本工作训练了一个预测的计算最优模型 Chinchilla，使用与 Gopher 相同的计算预算，但参数量为 70B、数据量为 4 倍，达到 SOTA 平均准确率，比 Gopher 提升超过 7%。This work trains a predicted compute-optimal model, Chinchilla, that uses the same compute budget as Gopher but with 70B parameters and 4$\times$ more more data, and reaches a state-of-the-art average accuracy, greater than a 7% improvement over Gopher.

一种具有固定大小记忆的循环 Transformer 架构，可泛化 sliding-window attention，同时在训练期间保持并行性，并在验证 loss 和下游预训练 benchmark 上优于 sliding-window 和 latent recurrent Transformer 基线。A recurrent Transformer architecture with fixed-size memory that generalizes sliding-window attention while remaining parallelizable during training and improves validation loss and downstream pretraining benchmarks over sliding-window and latent recurrent transformer baselines.

本文提出一种权重裁剪的替代方案：对 critic 相对于其输入的梯度范数施加惩罚。其性能优于标准 WGAN，能以几乎无需调参的方式稳定训练多种 GAN 架构。This work proposes an alternative to clipping weights: penalize the norm of gradient of the critic with respect to its input, which performs better than standard WGAN and enables stable training of a wide variety of GAN architectures with almost no hyperparameter tuning.

首个同时使用 LLM 推理和 tag-aware 翻译来明确处理并评估英罗 MT 中性别偏见的方法。This is the first method to explicitly address and evaluate gender bias in English-Romanian MT using both LLM inference and tag-aware translation.