跳到正文
研踪PaperTrail

论文库

检索计算机领域论文,按研究方向、作者或关键词筛选。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+197新增论文
+151其中 AI 相关
+16已有论文修订
+91新增 AI 导读

arXiv 最近完成扫描:2026-11-22 08:44 · 全站最近入库:2026-11-21 12:19各信源进度 →

统计口径与数据新鲜度

统计 2026-11-21 10:22 — 2026-11-22 10:22(北京时间) · 点击数字查看对应简报;AI 相关包含在新增论文内。

最近完成检查:2026-11-22 08:44最近发现新增版本:2026-11-21 12:19库内论文最新更新时间:2026-11-20 02:59

每分钟刷新已保存的数据。空检查不代表采集异常;新收录可能包含历史论文。AI 导读按新增版本计数。

29,158 已收录论文24,181 AI 相关8,992 有修订112 HF 社区发现

浏览论文库

时间范围跟随排序:版本更新、本站收录或首次发表。最新收录可能包含历史论文。部分信源异常,查看状态 →

找到 23,345 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-22 08:42(北京时间)
版本更新 · v3arXiv:2610.05441

子水平 Flood 双滤过:面向可扩展的二参数持续同调

The sublevel Flood bifiltration: towards scalable 2-parameter persistent homology

Mattéo Clémot, Julie Digne, Julien Tierny

AI 速读 基于摘要

作者提出 sublevel Flood bifiltration,用可扩展的近似方式在大型点集上计算二参数持续同调,并在合成数据分类与真实时间序列任务上展示其表现。

math.AT · cs.CG · cs.LG

查看原文摘要

Multiparameter persistent homology is a rapidly developing branch of topological data analysis that improves the robustness of single-parameter persistent homology to outliers, while still capturing the metric characteristics of the data. However, a notable limitation is its lack of scalability. In this paper, we introduce a novel approach for efficiently computing 2-parameter persistent homology on large point sets. Our work extends the Flood filtration, originally developed for single-parameter persistence. Our construction, called the sublevel Flood bifiltration, offers a scalable approximation of the sublevel offset bifiltration. We show that it benefits from theoretical stability properties and describe how to compute it efficiently. We demonstrate the performance of our approach in classification tasks on low-dimensional synthetic datasets, where density awareness is critical, as well as on real-world time series datasets.

新论文 · v1arXiv:2611.26440

专家漂移下的延迟决策学习

Learning to Defer under Expert Drift

Ziyao Mou, Andrea Wynn, Eric Nalisnick

AI 速读 基于摘要

提出 EDA-L2D 框架,用序列模型根据专家近期表现历史动态调整人机决策分配,以应对专家可靠性随时间波动的问题。

cs.LG

查看原文摘要

The learning to defer (L2D) framework enables safety in machine learning and AI systems by allocating difficult or critical decisions to a human expert. However, most prior work on L2D assumes fixed expert reliability, overlooking temporal fluctuations in human performance due to factors such as fatigue and cognitive biases. Humans commonly exhibit such substantial, systematic performance shifts across a wide range of domains, from high-stakes settings such as radiology, aviation, and judicial decision-making, to everyday tasks such as crowdsourced image annotation. We propose Expert-Drift-Adapted Learning-to-Defer (EDA-L2D), a novel expert-aware L2D framework that explicitly models these temporal shifts by conditioning the deferral head on recent histories of expert outcomes via a sequence model. This history-aware approach enables adaptive deferral policies that anticipate reliability fluctuations and better allocate decisions between human and machine over time. We provide comprehensive experiments across three diverse tasks -- image classification, medical diagnosis, and hate speech detection -- including generalization analyses under realistic deferral conditions and irregular shifts in expert reliability. Our results show that EDA-L2D adapts more effectively than prior L2D methods to diverse temporal patterns of expert reliability, resulting in improved system performance and more effective deferral decisions. Code is available at https://github.com/ZiyaoMou/L2D-Expert-Drift.

版本更新 · v2arXiv:2604.27497

SST-Guard:在野检测与刻画服务端 Google Analytics

SST-Guard: Detecting and Characterizing Server-Side Google Analytics in the Wild

Muhammad Jazlan, Alexander Gamero-Garrido, Zubair Shafiq, Yash Vekaria

AI 速读 基于摘要

提出基于多模态浏览器痕迹的检测方法 SST-GUARD,用于发现和刻画绕过客户端追踪防护的服务端 Google Analytics 部署。

cs.CR · cs.CY

查看原文摘要

As web browsers increasingly implement anti-tracking features, the web tracking ecosystem has been shifting from the client-side to the server-side. Instead of sending requests directly to the tracker's endpoint, server-side tracking (SST) sends tracking requests to publisher-controlled or intermediary endpoints that then forward the information to trackers from the server-side. As a result, client-side tracking protections are becoming fragile because direct client-to-tracker requests may no longer be observed. In this paper, we investigate the server-side Google Analytics (sGA), the most widely deployed third-party tracking service on the web today. We present SST-GUARD, a multi-modal browser-based approach for detecting sGA. The key insight behind SST-GUARD is that common sGA deployments change the standard Google Analytics endpoints, but still leave semantic artifacts of data collection by Google Analytics in the browser, including identifiers, event metadata, cookies, and JavaScript state. SST-GUARD detects these artifacts using value-templates, which use regular expressions to match semantic value patterns across multiple modalities: network requests, cookies, and the window object, providing robustness against obfuscation of one modality. We validate SST-GUARD on Tranco top-10k websites, detecting 4.0% (401) sGA domains with over 93.0% accuracy across three modalities, with network request classifier demonstrating the highest accuracy (99.8%). Additionally, SST-GUARD identifies atleast 43.2% more websites that integrate sGA as compared to prior approaches. Deploying SST-GUARD at scale, we detect sGA on 6,314 of Tranco top-150K websites. Our analysis shows that many sGA deployments use first-party subdomains, direct A/AAAA records, custom paths, or encoded payloads that circumvent existing defenses. We reported our findings to the authors of EasyPrivacy, who have integrated them.

新论文 · v1arXiv:2611.26438

风险受控的视觉-语言-动作模型测试时自适应

Risk-Controlled Test-Time Adaptation for Vision-Language-Action Models

Zixuan Liu, Hashem Haghbayan, Zizhan Zheng, Siavash Khajavi

AI 速读 基于摘要

R2-VLA 通过不确定性预测与任务级风险控制,在检索增强的 VLA 测试时自适应中按用户指定成功率要求决定自主行动或请求专家协助。

cs.CV

查看原文摘要

Retrieval-augmented vision-language-action (VLA) models enable efficient test-time adaptation by leveraging expert demonstrations as additional context without updating model parameters. However, even when retrieved demonstrations are relevant to the current task, the VLA may fail to effectively utilize the retrieved information, ultimately leading to task failure. To address this challenge, we propose R2-VLA, a risk-controlled retrieval-augmented VLA framework that enables reliable test-time adaptation by satisfying a user-specified task success rate requirement with minimal expert assistance. Specifically, R2-VLA learns an uncertainty predictor that estimates the uncertainty of the VLA's predicted actions given the retrieved demonstrations, guiding when to act autonomously or request expert assistance. We further introduce a task-level risk-control procedure that calibrates the uncertainty threshold to satisfy a user-specified task-failure risk requirement. Moreover, R2-VLA continually incorporates expert corrections into its retrieval memory to improve future adaptation while preserving the prescribed task-level risk guarantee. Experiments across three VLA backbones and four LIBERO benchmark suites demonstrate that R2-VLA improves average task success by 9.2--11.2 percentage points, achieving the desired target with fewer expert requests. These results highlight the effectiveness of connecting the usefulness of retrieved demonstrations with task-level risk control to enable successful robotic manipulation.

新论文 · v1arXiv:2611.26436

When lies look like noise: certifying untrusted entanglement swapping

Maria Gragera Garces, Chris Heunen, Mahesh K. Marina

原文摘要

Entanglement swapping lets quantum repeaters distribute entanglement over long distances, a prerequisite for the quantum internet. We study its security in a noisy network whose intermediate nodes perform the quantum operations faithfully but may misreport the classical outcome that end users rely on. We show that the ideal functionality of entanglement swapping cannot be realised, because it gives the adversary no influence over the delivered state, whereas a node that relabels its report does have such influence. Including honest noise in the ideal setting does not help unless it also concedes a bounded fraction of misreported pairs. We therefore propose a cut-and-choose protocol that tests a random subset of pairs to certify the rest. Since no test can distinguish a misreport from readout noise, the protocol certifies the error above a pre-agreed minimum noise level, which is the misreport rate under our threat model. This yields a quality-of-service guarantee, in which a failure witnesses that the node did not deliver as agreed. Unlike verification schemes that consume the state they certify, the untested pairs remain available for use, with a finite-size guarantee. Certifying a 1% misreport rate on 10^6 pairs costs 10^4 to 1.7x10^5 test pairs, for minimum noise levels ranging from 0 to 5%. The main cost is memory, since 1% requires holding 10^5 to 10^6 pairs at once, far beyond the capacity of today's quantum memories. Verifying and releasing in blocks ties the memory to the block size at the cost of a weaker rate: a (10^4)-qubit memory certifies 14% on 4.7x10^5 delivered pairs.

quant-ph · cs.DC

新论文 · v1arXiv:2611.26435

Aggron:在请求队列队头阻塞期间对智能体 KV 缓存进行激进压缩

Aggron: Aggressive Compression of Agentic KV Caches during Head-of-Line Stalls in the Request Queue

Rishabh Ravi, Tony Hong, Chen Wang, Yue Zhu, Mengmei Ye, Hubertus Franke, Fan Lai, Josep Torrellas

AI 速读 基于摘要

Aggron 通过在请求队列发生队头阻塞时利用空闲算力与显存,对智能体请求的 KV 缓存逐轮进行选择性摘要压缩,从而降低延迟并提升吞吐。

cs.DC · cs.AR

查看原文摘要

LLM agents run long, multi-turn programs whose contexts grow at every step, and serving them is limited by KV cache capacity. To alleviate this limitation, systems use context compression techniques, which typically wait until the KV cache crosses a large threshold and then summarize large spans of history at once, either in the background while the agent progresses or on the critical path. These summarizations can be done using the same model running on the same engine, or using the same or a different model running on extra hardware. When running on the same engine, summarization competes with the requests being served for both compute and memory capacity. To maximize the cost-effectiveness of summarization, this paper presents a new serving system called {\em Aggron}. Aggron summarizes agentic requests at every turn and selectively summarizes only certain parts of the KV cache. As a result, Aggron retains accuracy and keeps summarization requests lightweight. Moreover, Aggron launches summarization requests from a separate {\em Summarization Queue} while the corresponding agentic request whose KV cache we want to compress is stalled in the main request queue due to head-of-line stalls. The Summarization queue utilizes compute and memory capacity left over by the head-of-line stalls in the main queue. Further, to maximize efficiency, the server issues summarizations only when it predicts that they can complete before the corresponding agentic request will finally execute. In our evaluation, we compare Aggron to state-of-the-art asynchronous summarization. At high load, Aggron reduces P99 program latency by $27$--$31\%$, and raises throughput by $1.34$--$1.40\times$.

新论文 · v1arXiv:2611.26434

HumanCOIN:面向第一人称操作中人类意图的12,500小时数据集

HumanCOIN: A 12,500-Hour Dataset for Human Intent in Egocentric Manipulation

Shihan Wu, You Liu, Chunyu He, Minghui Qin, Longhan Jiao, Jinbang Guo, Shaoxuan Xie, Kaixi Tian 等 51 位作者

AI 速读 基于摘要

HumanCOIN 是一个围绕人类意图构建的第一人称操作数据集,通过三层代理信号(注视、肌电、脑电)在万小时规模上记录从决策到动作的意图通路。

cs.CV · cs.RO

查看原文摘要

First-person manipulation datasets treat the observation-action pair as the atomic unit and compress the generation and execution of an action into a policy network's weights, rendering the intent state behind the action unobservable. Human motor control research shows that intent mediates between observation and action and leaves observable traces along the intent pathway from decision to effect: gaze reaches the target before the hand, muscle load builds before contact, and cortical activity precedes the motor command. To record this pathway at scale, we present HumanCOIN, a first-person manipulation dataset built around human intent: 12,500 hours across 38 scene classes with three tiers of proxies. At the output end, the L1 attention tier (10,000 h) infers gaze from headband camera video, exposing the operator's next object of attention and reach before the hand moves. Midway, the L2 exertion tier (2,000 h) records surface EMG from armbands, making load expectations readable before execution is complete. At the origin, the L3 cognition tier (500 h) records scalp EEG, giving early readouts of task decisions and monitoring. Each tier inherits all proxies from the tiers below. The dataset further provides multi-view RGB images, depth maps and point clouds, 6-DoF head and wrist pose, and step-level action and object annotations. The controlled L3 setting additionally measures gaze, hand pose and finger kinematics directly. Clock and calibration data are released with the dataset so that any read rate can be re-aligned. The three tiers cover three stations, from visual orienting to cortical preparation, making the process behind visual-action pairs available for modeling at dataset scale. Project page: https://flagopen.github.io/HumanCOIN.

新论文 · v1arXiv:2611.26433

AdaPixFlow:从稀疏多视角观测中学习跨场景的连续时间三维动力学

AdaPixFlow: Learning Continuous-Time 3D Dynamics Across Scenes from Sparse Multi-view Observations

Hrishikesh Viswanath, Aniket Bera

AI 速读 基于摘要

提出AdaPixFlow,从多视角RGB-D观测中学习跨场景的连续时间速度场算子,无需逐场景优化或预定义运动模型,即可预测物体在观测间及观测后的位置。

cs.CV

查看原文摘要

Understanding how objects move in dynamic scenes requires recovering their 3D motion from visual observations and predicting their positions at unobserved times. Existing methods either optimize scene-specific velocity fields or impose predefined physical and kinematic assumptions. We instead study learning a continuous-time dynamics operator across scenes, mapping multi-view visual observations to 3D object kinematics. We introduce Adaptive Pixel Flows (\ours{}), which learns this operator from multi-view RGB-D observations without per-scene optimization or predefined motion models. The method fuses observations from all cameras into a shared voxel grid in world coordinates, from which the network predicts a continuous-time velocity field. Because the operator is trained across scenes, it learns motion priors that carry over to unseen scenes. The field can then be integrated from observed states to predict object positions between observations and beyond the observed sequence. On held-out PhysInOne scenes, \ours{} improves F1 over the strongest competing method by 2.5\% for in-between prediction and 15\% for future prediction. Compared with per-scene velocity-field methods, the improvements are 30\% and 85\%, respectively. Applied zero-shot to Spring-Gaus, it improves future-prediction F1 by 12\%.

新论文 · v1arXiv:2611.26431

FFGaussType:将字形与SVG几何前馈转换为紧凑高斯资产

FFGaussType: Feed-Forward Conversion of Glyph and SVG Geometry into Compact Gaussian Assets

Haoan Feng, Tianfu Wang, Peimeng Guan, Dae Yeol Lee, Guan-ming Su

AI 速读 基于摘要

FFGaussType 通过单次前向传播将挤压字形和 SVG 轮廓转换为高斯资产,避免逐资产迭代优化,实现快速且紧凑的交付。

cs.CV · cs.GR

查看原文摘要

Immersive 3D content allows text and graphical elements, such as subtitles, annotations, and icons, to be placed inside a scene rather than displayed as flat overlays. Placed this way, they respect occlusion and perspective and take on user-assigned materials and lighting while preserving their original shapes. In Gaussian scenes, however, each new glyph or icon requires its own iterative optimization, which limits scalable content creation. We present FFGaussType, which converts extruded glyph and SVG outlines into Gaussian assets in a single forward pass. A point encoder maps anchors sampled on the known surface to a single feature plane, from which a decoder shared by all assets predicts neural Gaussians carrying surface normals. This separates geometric conversion from material and lighting choices, and the feature plane supports image and video coding for compact delivery. We construct a paired dataset of 27,221 glyph and SVG icon assets with anchors and calibrated normal and silhouette renderings, holding out font families for evaluation. Conversion from prepared anchors takes 9.1 ms per asset, at a fraction of the compute and memory of prior baselines. On unseen font families and test icons, FFGaussType achieves $1.62^\circ$ normal error and $0.985$ silhouette IoU, the best among the compared feed-forward converters, matching the fidelity that per-asset fitting needs thousands of steps to reach. The code and dataset will be released after publication.

版本更新 · v2arXiv:2611.19597

具有可控约束复杂度的合成神经符号任务生成

Synthetic Neurosymbolic Task Generation with Controlled Constraint Complexity

Mykhailo Buleshnyi, Zsolt Zombori, Michael Benedikt

AI 速读 基于摘要

NeSySy 是一个合成神经符号学习任务生成器,能联合生成逻辑约束和一致数据集,并精细控制约束结构、紧密度、输入依赖等属性,用于系统研究学习与逻辑结构的交互。

cs.LG · cs.AI · cs.LO · cs.NE · cs.SC

查看原文摘要

We introduce NeSySy, a synthetic generator for neurosymbolic learning tasks that jointly produces logical constraints and consistent datasets. Unlike existing benchmarks, NeSySy provides fine-grained control over key properties such as constraint structure, tightness, input dependence, and data generation and alignment strategies. In particular, it allows the use of rich constraints over infinite domains, and uses solvers to ensure that the constraints are meaningful and that generated samples satisfy the constraints. We design NeSySy to support both learning with declarative constraints and learning from distant supervision. Across a range of constraint families, we provide evidence that its parameters induce systematic and largely independent effects on task difficulty. Using NeSySy, we study constraint-aware learning methods, identifying regimes where explicit constraint enforcement is beneficial and where expressive unconstrained models can instead learn constraint structure directly from data. Our results establish NeSySy as a controlled testbed for analysing the interaction between learning and logical structure. NeSySy is built around a pipeline that incorporates solvers. Satisfiability checkers (CNFgen and Z3) generate and certify constraints. Constrained optimizers (RC2 for MaxSAT, Z3 for OMT) compute optimal repairs that guarantee every generated sample is consistent.

版本更新 · v4arXiv:2302.14834

允许异步的并发算法的性质

Properties of Concurrent Algorithms that Allow Asynchrony

Arya Tanmay Gupta, Sandeep S Kulkarni

AI 速读 基于摘要

论文研究并发系统在无同步下确定性收敛的条件,提出局部状态偏序是允许异步的充要条件,并区分PO诱导与非PO诱导问题。

cs.DS · cs.DC

查看原文摘要

In this paper, we investigate the conditions under which a concurrent system is able to guarantee convergence deterministically even without synchronization. In general, an algorithm is deemed asynchrony-tolerant iff the global states form a DAG even if the nodes can execute based on outdated/stale values from each other. In this paper, we show that the induction of a partial order (PO) among the local states visited by individual nodes is necessary and sufficient to allow asynchrony. There are certain problems for which the predicate that defines the problem, itself, induces a partial order among the local states (called \textit{PO-inducing problems}). On the other hand, \textit{non-PO-inducing problems} is another class of problems in which a predicate defining the problem cannot induce a partial order among local states. We introduce these classes of problems. We study example PO-inducing and non-PO-inducing problems, and provide example PO-inducing (in other words, asynchrony-tolerant) algorithms (algorithms under which any node traverses a partial order of local states) for all these problems.

新论文 · v1arXiv:2611.26426

基于特征函数的精确贝叶斯层

Exact Bayesian layers via characteristic functions

William H. W. Thompson, Guillaume St-Onge, Laurent Hébert-Dufresne, Jean-Gabriel Young

AI 速读 基于摘要

提出CF-Prop方法,利用特征函数精确计算贝叶斯ReLU层的输出分布,并实现无需采样的变分推断算法CF-VI。

stat.ML · cs.LG · stat.CO

查看原文摘要

Bayesian neural networks provide principled uncertainty estimates, but training them with Monte Carlo sampling can be expensive. Sampling-free variational inference algorithms make training Bayesian neural networks feasible, but existing approaches assume a Gaussian output distribution, which can be inaccurate in applied problems. Here, we introduce CF-Prop, an uncertainty propagation method that uses characteristic functions to compute the exact output distribution of a Bayesian ReLU layer, without any sampling, even in non-Gaussian settings. Because CF-Prop propagates characteristic functions, the evidence lower bound---the objective of variational training---can be computed in closed form for a broad class of likelihoods, including the Gaussian, Poisson, and Gamma. This allows to implement an efficient resulting variational inference algorithm, CF-VI. On CIFAR-100, CF-VI achieves the lowest calibration error of any tested method, improving on the next best method by about 35%. On a heavy-tailed insurance claim dataset, CF-VI accurately captures tail uncertainty that is severely underestimated by both other sampling-free methods and Monte Carlo methods.

新论文 · v1arXiv:2611.26423

Seer:用共享决策模型引导小型深度研究智能体

Seer: Guiding Small Deep-Research Agents with Shared Decision Models

Yuhao Zhou, Yang Zhou, Yuanxi Li, Jindi Lv, Dan Si, Qing Ye, Jiancheng Lv

AI 速读 基于摘要

Seer 在推理阶段把智能体的动作提议与后果预测、价值估计分离,用离线训练、可跨智能体复用的模拟器与价值估计器为小型本地深度研究智能体提供引导。

cs.AI

查看原文摘要

Deep-research agents repeatedly decide what to search, read, and verify, often using large cloud-hosted language models for action proposal. However, privacy and local control motivate running agents on users' devices, where limited memory and compute favor smaller models and complicate on-device training. Yet inference-time guidance faces three obstacles: exploring alternatives through real execution adds tool calls, prompted self-evaluation is bounded by the agent's judgment, and model-specific guidance risks repeated adaptation costs. We introduce Seer, an inference-time framework providing local guidance that separates the agent's action proposal from learned consequence prediction and value estimation. From a shared corpus of real research trajectories, we train two models: a tool-response simulator on observed call--response pairs and a value estimator on histories labeled with discounted terminal correctness. The simulator and estimator are trained offline and reused across agents without further training. Moreover, Seer executes only the selected action and adds only real tool responses to the committed history, avoiding tool calls on discarded candidates at additional inference cost. Across multiple deep-research benchmarks, Seer substantially improves agent performance for different language models. For instance, GAIA accuracy rises from 13.6% to 41.7% for Qwen3.5-4B and from 22.3% to 50.5% for Qwen3.5-9B. Furthermore, our analyses suggest that broader candidate coverage can compensate for imperfect simulation, while prediction and scoring errors limit the benefits of wider imagined search. These findings highlight the potential of reusable models for prediction and evaluation to strengthen small research agents through extra local computation without the real execution of the discarded candidates.

新论文 · v1arXiv:2611.26422

基于大语言模型推理轨迹分析的可解释Q矩阵构建

Reasoning-Trace Analysis Using Large Language Models for Interpretable Q-Matrix Construction

Jihong Zhang, Zijing Jin, Mingfeng Xue

AI 速读 基于摘要

提出推理轨迹分析(RTA)框架,通过链式思维提示让大语言模型生成属性标注的推理步骤,以重建、比较和检查Q矩阵的每个项目-属性分配,并报告了模拟与实证研究结果。

cs.AI

查看原文摘要

Large language models (LLMs) can generate Q-matrices for diagnostic classification models that approximate expert specifications, but evaluations have focused on the final matrices, leaving the basis of individual item-attribute assignments unexamined. This opacity limits the responsible use of AI in measurement. We propose Reasoning-Trace Analysis (RTA), a framework in which an LLM generates attribute-labeled reasoning steps through chain-of-thought (CoT) prompting and these steps are analyzed to reconstruct, compare, and inspect each assignment. RTA is intended to supplement expert review and empirical validation. In a simulation study with perturbed fraction subtraction items, four LLMs recovered the required attributes and withheld attributes the items did not require. In an empirical study with 11 fraction subtraction items, responses from 536 examinees, four LLMs, up to three temperatures, and 100 replications per condition, CoT-derived Q-matrices overlapped substantially with the reference Q-matrix (mean overlap .809) but less than directly generated Q-matrices (.877), and they varied more across replications. Inspection of the traces linked disagreements to item-type coding, labeling rules, and how operations were expressed as steps. Q-matrices with similar overlap differed in fit to examinee responses. RTA provides inspectable evidence that matrix-level agreement and fit do not.

新论文 · v1arXiv:2611.26420

Awaken-HI:利用全身人类经验扩展人形智能

Awaken-HI: Scaling Humanoid Intelligence with Whole-Body Human Experience

EngineAI

AI 速读 基于摘要

构建约5万小时同步全身运动的自中心视频数据集Awaken-Human,并训练共享动作专家的视觉-语言-动作模型Awaken-HI,实现人形机器人移动操作技能从人到机器人的有效迁移。

cs.RO · cs.AI · cs.CV

查看原文摘要

A central goal of humanoid robotics is for robots to perform the everyday work people do in homes and workplaces. Existing egocentric video datasets cover many of these activities but provide little synchronized whole-body motion data for learning loco-manipulation at scale. We build Awaken-Human, which pairs approximately 50,000 hours of egocentric stereo video with synchronized whole-body human motion and covers more than 100 skills. Building on this, we also introduce Awaken-HI (Humanoid Intelligence), a vision-language-action model for humanoid loco-manipulation that jointly predicts original human motion and retargeted robot actions through a shared action expert. We show that loco-manipulation skills transfer more effectively from people to humanoids when human trajectories directly supervise the shared action expert. Increasing human pretraining data reduces held-out robot action prediction error according to an empirical scaling law and raises the mean success rate on downstream real-robot tasks. After full-corpus pretraining and T800 adaptation, Awaken-HI achieves a mean success rate of 93.75% across eight individual tasks and outperforms GR00T N1.7 and $π_{0.5}$ in both individual and long-horizon evaluations. The same policy generalizes to objects unseen during robot post-training and to new pairings of familiar objects and destinations.

新论文 · v1arXiv:2611.26419

面向缺陷与变异性高效建模的复合世界模型与脉冲神经网络记忆模块的有限元求解器集成

FEA solver integration of a composite World Model with a Spiking Neural Network memory Block for computationally efficient modelling of defects and variabilities

Bassam El Said, Adam Sobey

AI 速读 基于摘要

作者提出一种基于多模态脉冲Transformer的复合材料世界模型,将其拆解后耦合到非线性有限元求解器,用于含缺陷复合材料结构的高效多尺度模拟。

cs.LG

查看原文摘要

Each fibre-reinforced composite structure has a unique material architecture. The manufacturing methods used and the presence of defects lead to local variations which require material-scale models that can resolve the response in real time at every location in the structure. Concurrent multi-scale schemes provide this capability, but at a prohibitive computational cost for large structures as the number of integration points and time increments scales with size. Surrogates have been studied extensively as replacements for material-scale models to mitigate these computational limitations. A surrogate must represent an arbitrary local architecture including defects, track the irreversible material state over an unknown number of increments, remain stable when driven recursively by its own predictions, and fit within the memory available at every integration point. Here, a Composites World Model based on a Multi-Modal Spiking Transformer architecture is designed to meet these requirements. The proposed architecture combines a material encoder, a Spiking Neural Network memory block that tracks the long-term internal state of the material, and transformer blocks that learn the short-term applied strain state. The system is trained in three stages: material architecture encoding, base training on short time windows, and recursive fine-tuning with scheduled sampling to suppress cumulative error drift. The trained model is disassembled at inference and coupled to a non-linear FE solver, enabling structural scale simulation of composites containing embedded defects. Benchmarks against experimental results for IM7/8552 laminates under tension, compression and transverse shear, for pristine and wrinkled composites, show that the SNN memory block successfully tracks the material internal state and results in prediction errors between 0.4% and 4.8%.

新论文 · v1arXiv:2611.26414

ZeroVLN:无需对VLM大脑进行监督微调的导航学习

ZeroVLN: Learning to Navigate without Supervised Fine-Tuning of the VLM Brain

Zixuan Huang, Yang Zhou, Guli Zhang, Sunzhu Li, Hongyan Xie, Zehao Chen, Fuzhen Zhuang, Kaixuan Wang 等 11 位作者

AI 速读 基于摘要

ZeroVLN 提出慢-快导航框架,让 VLM 大脑通过语义工具调用接口下达自然语言移动指令,并在不对 VLM 大脑做导航域监督微调的情况下,用闭环强化学习联合优化大脑决策与动作专家执行。

cs.AI

查看原文摘要

Representative vision-language navigation (VLN) methods typically couple a vision-language model (VLM) brain with a learnable action head and fine-tune the VLM brain on navigation-domain data to predict geometric goals. However, such adaptation can substantially alter base VLM weights and degrade general visual capabilities. We introduce ZeroVLN, a slow-fast navigation framework that achieves effective navigation with zero navigation-domain SFT of the VLM brain. Rather than teaching the brain to predict geometric goals, we equip it with a semantic tool-calling interface for conveying movement decisions to an action expert in natural language. We first adapt the action expert to carry out these movement requests, then jointly improve the brain's movement decisions and the action expert's continuous execution through closed-loop reinforcement learning (RL). Trained on the same navigation episodes, ZeroVLN substantially outperforms representative SFT-based hierarchical VLN methods on standard VLN-CE (continuous environments) benchmarks, while inducing only minor changes to the brain's weights and largely preserving its general capabilities. To our knowledge, ZeroVLN is the first slow-fast VLN framework with zero navigation-domain SFT of the VLM brain, and the first to jointly optimize its slow and fast policies through closed-loop agentic RL in VLN-CE.

新论文 · v1arXiv:2611.26413

用于高效推理时对齐的序贯任意时间有效检验

Sequential Anytime Valid Tests for Efficient Inference-Time Alignment

Vishesh Kumar Singh, Sayak Ray Chowdhury

AI 速读 基于摘要

提出e-RWSC方法,用e-process替代Wald检验,为推理时对齐提供具有任意时间统计保证的早停规则,在更低token成本下提升准确率。

cs.LG

查看原文摘要

Inference-time alignment methods, such as Best-of-N (BoN), improve language model outputs by generating multiple candidates per prompt and selecting among them using a reward model. Much of this cost is wasted: a fixed budget is applied to every prompt, although the computation required by prompts varies widely. Adaptive methods halt once sampled answers appear settled, but their thresholds are tuned heuristics with no statistical control over early-stopping errors. We instead seek an anytime-valid stopping rule that takes an error tolerance $α$ as input and halts only once an answer is certified to hold a majority ($θ_a > 1/2$) under the generator's distribution. We aggregate candidates by final answer with a reward-weighted self-consistency (RWSC) score and treat stopping as a sequential test over the resulting clusters. Applying Wald's sequential probability ratio test to these clusters yields SPRT-RWSC, which performs well empirically, but its guarantee fails because the leading answer shifts during sampling, and the run is continuously monitored. Our main contribution, e-RWSC, replaces Wald's test with a betting supermartingale (an e-process) for every answer the policy produces, bounding the probability of ever certifying a non-dominant answer by $α$, uniformly over time and across all answers. The RWSC scores drive the bets, so they affect only how quickly a dominant answer $a^\star$ is certified, not validity; certification takes $O(\log(1/α)/d_{\mathrm{KL}}(θ_{a^\star}\|1/2))$ samples. Experiments across several language models, datasets, and reward models confirm the predicted $1/d_{\mathrm{KL}}$ scaling of cost and show that accuracy improves over baselines at substantially lower token cost.

版本更新 · v3arXiv:2610.09186

模式识别与逐步推理的二分法

The Dichotomy Between Pattern Recognition and Step-by-Step Reasoning

Amrut Nadgir, Vijay Balasubramanian, Pratik Chaudhari

AI 速读 基于摘要

论文提出模式识别与逐步推理是同一谱系的两端,其区分取决于下一个词元所依赖的上下文长度,并证明逐步推理具有样本效率,且状态频率可平衡准确性与鲁棒性。

cs.LG · cond-mat.dis-nn

查看原文摘要

We argue that pattern recognition and step-by-step reasoning are two ends of a spectrum. A large language model (LLM) learns to reason step-by-step when data is structured such that the next token depends on a small amount of preceding context. Inference in LLMs resembles pattern recognition when the next token depends on a large amount of preceding context. If the next token depends on only the $c$ most recent tokens, reasoning traces are paths on a de Bruijn graph whose nodes are $c$-length contexts and edges are next-token transitions between contexts. The set of reasoning traces of a task forms a directed acyclic subgraph of the de Bruijn graph. An LLM that has learned all edges of this subgraph can compose them to solve longer, unseen tasks, i.e., it reasons step-by-step. We prove that the number of edges is vanishingly small compared to the number of reasoning traces. We also prove and show empirically that the number of training samples a transformer needs is a linear in the number of edges, so learning to reason step-by-step is sample efficient. We can induce de Bruijn structure in any task by maintaining a ``state'' that makes future reasoning independent of the past. The frequency of states in the reasoning trace determines $c$. We show, by fine-tuning Qwen2.5-1.5B-Instruct to solve equations and answer questions about stories, that frequent states (small $c$) result in higher accuracy but greater fragility to perturbations at test time. LLMs trained with a large $c$ are only as good as models that perform pattern recognition without reasoning. A moderate density of states balances accuracy and robustness. Real-world data has de Bruijn structure: Qwen3-14B and Qwen3-32B retain over 75\% of their accuracy on GSM8K, MATH-500 and GPQA-Diamond when attention is restricted to a sliding window less than 15\% as long as the full reasoning trace.

新论文 · v1arXiv:2611.26410

病态随机权重神经网络筛的统计推断

Statistical Inference with Ill-Conditioned Random Weight Neural Network Sieves

Giovanni Ballarin, Lyudmila Grigoryeva, Lukas Gonon

AI 速读 基于摘要

论文证明随机权重神经网络筛随维度增长必然病态,并为此建立显式处理病态的近似、估计与推断理论。

stat.ME · cs.LG · econ.EM · stat.ML

查看原文摘要

Random weight neural networks (RWNNs) are shallow networks whose hidden-layer parameters are randomly generated and then kept fixed, while only the output coefficients are estimated. Conditional on the sampled parameters, RWNN regression is a linear sieve problem with random approximation space. We show that such random sieves cannot remain uniformly well-conditioned as their dimension grows. For parametrized feature families satisfying polynomial covering and Lipschitz conditions, the eigenvalues of the population covariance matrix are proven to have polynomial upper bounds determined by the covering geometry of the parameter space, leading to a vanishing smallest eigenvalue. We develop approximation, estimation, and inference theory that explicitly treats the ill-conditioning. Under a $β$-Hölder source condition, we obtain both faster-than-Monte-Carlo $L^2$ approximation rates and new $L^\infty$ approximation bounds based on stratified sampling. We then derive improved consistency guarantees for ridge-regularized least squares driven by ridge effective dimension, spectral, and leverage-based stability conditions. For inference, we establish asymptotic linearity and Gaussian limits for linear functional directions while allowing the smallest eigenvalue of the population covariance matrix to vanish. Nondegeneracy is directional: we characterize it with a ridge-normalized Rayleigh quotient and extend it to smooth functionals via Riesz representation. Consistency of ridge-adjusted variance estimators is proved, yielding feasible studentized inference. Numerical experiments illustrate the deterioration of random-feature conditioning and the finite-sample behavior of the resulting estimation and inference procedures.

新论文 · v1arXiv:2611.26409

WeMM-Video: Pushing the Frontiers of Open-Source Omni-Modal Video Understanding

Changli Tang, Jie Yang, Tianyi Wang, Lei Li, Daoze Zhang, Zijie Xin, Zhan Liu, Li Li 等 12 位作者

原文摘要

Video understanding, particularly with accompanying audio, remains a central challenge in multimodal intelligence. In this report, we introduce \textbf{WeMM-Video}, a family of Chinese-English bilingual omni-modal foundation models spanning 2B, 4B, 9B, and 35B-A3B variants. Centering on joint audio-visual perception and reasoning, WeMM-Video unifies text, image, audio, and video processing within a hybrid-thinking paradigm, seamlessly supporting both a non-thinking instruct mode for fast, direct responses and a thinking mode for explicit step-by-step reasoning. The models are trained on a large-scale multimodal corpus of approximately 1.2 trillion tokens through progressive pre-training and a multi-stage post-training pipeline incorporating multi-teacher OPD, anti-repetition MrDPO, and specialist RL. Evaluated across more than 120 benchmarks, WeMM-Video demonstrates superior performance in omni-modal video understanding and reasoning, while maintaining highly competitive capabilities across general audio, silent video, image, and text tasks. Specifically, in omni-modal video evaluations, our flagship WeMM-Video-35B-A3B establishes a new open-source state of the art, substantially outperforming proprietary models such as Qwen3.5-Omni-Flash and Seed2.0-Mini-0428 while narrowing the gap with the strong Gemini-3.0-Flash, and our compact WeMM-Video-9B surpasses the larger open-source Qwen3-Omni-30B-A3B-Instruct. We publicly release the WeMM-Video family along with our evaluation and reproduction pipeline to foster further research and development in the open-source community.

cs.CV · eess.AS

版本更新 · v2arXiv:2608.02044

Déjà Cue:通过词汇相对坐标在物体历史中定位状态

Déjà Cue: Localizing States in Object Histories via Vocabulary-Relative Coordinates

Haofan Cao, Zhichao You, Yunkai Yang, Liang Guo, Jie Wang, Chongshou Li

AI 速读 基于摘要

提出免训练框架Déjà Cue,利用状态词汇的相对参考校准视觉-语言相似度,在物体历史中定位状态时刻,并构建MS-VOST基准。

cs.CV · cs.LG · cs.MM

查看原文摘要

Object tracking preserves identity through visual changes, but cannot tell when an object is whole, cut, or peeled. We study state-moment retrieval: locating when a tracked object exhibits each state in a supplied set of descriptions. However, absolute image--text similarity can favor shared object semantics, obscuring the distinctions needed to localize individual states. Our insight is that the alternatives themselves provide a reference for measuring state evidence. We introduce Déjà Cue, a training-free framework that centers description embeddings on a state-balanced vocabulary mean, producing query directions that compare each state against its alternatives. Using frozen vision--language encoders, Déjà Cue calibrates frame scores and retrieves intervals at multiple durations within contiguous visible runs. We construct MS-VOST by annotating 620 object histories with 2,465 states. With the encoder and temporal search fixed, Déjà Cue improves all three localization metrics over absolute scoring across eight encoder configurations, raising Top-1 temporal IoU by 0.42--1.14 percentage points. These gains persist across four text constructions, and candidate-ranking analysis shows that the vocabulary reference brings relevant intervals forward within the same search space. These results establish the supplied state vocabulary as an object-specific reference for localizing semantic states from frozen visual representations.

版本更新 · v4arXiv:2504.10399

半对抗性错误下Reed-Solomon及相关码的唯一解码

Unique Decoding of Reed-Solomon and Related Codes for Semi-Adversarial Errors

Joshua Brakensiek, Yeyuan Chen, Manik Dhar, Zihan Zhang

AI 速读 基于摘要

作者提出半对抗性错误模型,并为交织Reed-Solomon码、折叠Reed-Solomon码和单变量重数码设计近线性时间的唯一解码算法,在多数随机与对抗错误混合比例下达到信息论最优。

cs.IT · cs.DS

查看原文摘要

Motivated by recent developments in coding theory, particular in list-decoding, we introduce a new error model which we call semi-adversarial errors. This error model bridges between fully random errors and fully adversarial errors by allowing some symbols of a message to be corrupted by an adversary while others are replaced with uniformly random symbols. We seek to understand optimal efficient unique decoding algorithms in the semi-adversarial model. For interleaved Reed--Solomon (IRS), folded Reed--Solomon (FRS) and univariate multiplicity codes, we design decoding algorithms running in near-linear time for most mixtures of random and adversarial errors. Our analysis matches the information-theoretic optimum for semi-adversarial errors. Our algorithm for interleaved Reed--Solomon codes is an improved implementation of the decoding algorithm by Bleichenbacher--Kiayias--Yung (BKY) for fully random errors. We use a monomial-tracking technique to analyze its performance in this new semi-adversarial errors. Inspired by the BKY algorithm, we use interpolations to extend our approach to the settings of folded Reed--Solomon and multiplicity codes, resulting in fast algorithms for unique decoding against semi-adversarial errors. Our new decoders for FRS and multiplicity codes replace the sophisticated root-finding step in traditional algorithms, such as the Guruswami--Wang algorithm, with a straightforward polynomial long division. Analysis of these algorithms requires more robust monomial-tracking arguments than IRS codes.

新论文 · v1arXiv:2611.26405

TacInno:让视觉-语言-动作模型学习视觉与动作之外的接触动力学

TacInno: Teaching Vision-Language-Action Models the Contact Dynamics Beyond Vision and Action

Weile Li, Yunfan Lou, Muqing Shi, Zihao Zhang, Zhenbiao Huang, Boxian Yao, Xiyu Zhu, Zhibo Pang

AI 速读 基于摘要

TacInno 把视觉观测与已执行动作无法解释的触觉变化(触觉创新)作为训练目标,让 VLA 策略预测该离散编码,部署时不增加额外模块。

cs.RO · cs.CV

查看原文摘要

Vision-Language-Action (VLA) models have recently been equipped with tactile sensing to perceive visually subtle contact events in contact-rich manipulation. However, adding tactile input yields inconsistent gains, and some visuo-tactile VLA models rely little on tactile input, because much of the tactile change, such as the gel deformation during gripper closure, is predictable from visual observations and executed actions. To address this problem, we introduce TacInno, which isolates the contact dynamics that vision and executed actions cannot explain, termed tactile innovation, and uses tactile innovation only as a training target. Specifically, the TacInno tokenizer, conditioned on visual observations and executed actions, compresses the future tactile change into a discrete code, and the policy, TacInno-VLA, learns to predict the code, adding no module for the code at deployment. TacInno-VLA achieves average success rates of 87.5% across six simulation tasks and 70.5% across four real-world tasks, outperforming the strongest visuo-tactile baseline by 10.7 and 9.0 percentage points, respectively. Ablation studies validate the contributions of visual and action conditioning, multi-frame encoding, and auxiliary code prediction. Together, these results demonstrate the effectiveness of tactile innovation as a supervision signal for contact-rich manipulation.

版本更新 · v4arXiv:2608.30044

Balance of Benchmarks: Evidence Retention and Multiplicity-Aware Model Comparison

Jhen-Ke Lin, Hong-Yun Lin

原文摘要

Benchmark aggregation requires decisions about how much evidence to use and how much influence each benchmark receives. Curated suites control influence through selection, which can exclude informative observations. A broader pool can retain those observations. With equal weighting, repeated or closely related benchmarks gain influence as their number grows. We introduce Balance of Benchmarks (BoB) to retain eligible observations and control their influence separately. We fit benchmark-specific response curves to place different difficulty ranges on a shared ability scale and use description similarity to downweight benchmarks in crowded neighborhoods. We test retention and density weighting in separate interventions on WildScores, a sparse collection of 148 developer-reported benchmarks, using 14 Artificial Analysis benchmarks as a controlled reference. With the model population fixed and entire source-lineage families held out, suite expansion improves held-out prediction under BoB and equal-weight equating on both WildScores and BIG-bench. Under substantial reporting overlap, density weighting improves robustness to multiplicity. Complete re-listings yield smaller mean rank displacement under BoB (0.63 versus 1.95 for equal-weight equating), with benefits also in paraphrased re-listings and supported affine fits. The benefit can reverse if models report different benchmarks, because a single weight per column gives models that report only part of a group less than its intended share. We therefore compute each model's weights from the benchmarks it reports. This rule removes the reversal in controlled re-listings and keeps held-out prediction close to that of equal weighting. These comparisons separate evidence retention, benchmark influence, and reporting coverage and show why repeated entries need to be handled per model.

cs.AI · cs.CL · cs.LG

版本更新 · v2arXiv:2602.10510

量子局部差分隐私下的隐私-效用权衡

Privacy-Utility Tradeoffs with Quantum Local Differential Privacy

Theshani Nuradha, Sujeet Bhalerao, Felix Leditzky

AI 速读 基于摘要

研究在(ε,δ)-量子局部差分隐私下,通用与特定任务中隐私与效用的最优权衡,并给出学习可观测量期望的样本复杂度。

quant-ph · cs.CR · cs.IT · cs.LG

查看原文摘要

When sensitive information is encoded in data, it is important to ensure the privacy of information when attempting to learn useful information from the data. There is a natural tradeoff whereby increasing privacy requirements may decrease the utility of a learning protocol. In the quantum setting of differential privacy, such tradeoffs between privacy and utility have so far remained largely unexplored. In this work, we study optimal privacy-utility tradeoffs for both generic and application-specific utility metrics when privacy is quantified by $(\varepsilon,δ)$-quantum local differential privacy. In the generic setting, we focus on optimizing fidelity and trace distance between the original state and the privatized state. We show that the depolarizing mechanism achieves the optimal utility for given privacy requirements. We then study the specific application of learning the expectation of an observable with respect to an input state when only given access to privatized states. We derive a lower bound on the number of samples of privatized data required to achieve a fixed accuracy guarantee with high probability. To prove this result, we employ existing lower bounds on private quantum hypothesis testing, thus showcasing the first operational use of them. We also devise private mechanisms that achieve optimal sample complexity with respect to the privacy parameters and accuracy parameters, demonstrating that utility can be significantly improved for specific tasks in contrast to the generic setting. In addition, we show that the number of samples required to privately learn observable expectation values scales as $Θ((\varepsilon β)^{-2})$, where $\varepsilon \in (0,1)$ is the privacy parameter and $β$ is the accuracy tolerance. We conclude by initiating the study of private classical shadows, which promise useful applications for private learning tasks.

新论文 · v1arXiv:2611.26400

论条件分支的语义

On the semantics of conditional branching

Fredrik Dahlqvist

AI 速读 基于摘要

受概率与量子程序中if-then-else非标准解释的启发,作者提出一个统一的条件分支范畴结构,并揭示GKAT与重心代数的斜结合律是同一规则的两个实例。

cs.LO · cs.PL

查看原文摘要

Motivated by the non-standard interpretations of if-then-else in probabilistic and quantum programs we review the different semantics of conditional branching and propose a unifying categorical structure for the interpretation of if-then-else. We show that many semantically important categories possess this structure, covering inter alia classical, probabilistic, quantum or non-deterministic computations. We examine algebraic structures related to and generated by this categorical structure, in particular on collections of predicates. In this setting we show that the skew-associativity rules of GKATs and barycentric algebras are two instances of a common skew-associativity rule.

新论文 · v1arXiv:2611.26398

面向水治理与气候韧性的跨项目知识民主化:一个智能体AI生态系统

Democratizing Cross-Project Knowledge for Transforming Water Governance and Climate Resilience: an Agentic AI Ecosystem

Oriol Alàs, Ian Palacín, Iván Cester, Edgar Rubión

AI 速读 基于摘要

作者提出一个智能体AI生态系统,将三个欧盟项目的水与气候文档整合为领域知识库,并用ReAct式控制器编排检索以支持跨项目知识综合。

cs.IR · cs.AI · cs.CL

查看原文摘要

EU-funded projects produce extensive evidence in the form of deliverables, reports, and case studies. However, this knowledge is typically scattered across projects and document structures, making it difficult to locate relevant, contextual information when making decisions. This paper introduces an Agentic AI Ecosystem that consolidates heterogeneous project documentation into a domain-aware knowledge base and provides adaptive access through an agentic Retrieval-Augmented Generation pipeline. Documents from three EU-funded projects (IMPETUS, NATALIE, and InnWater) are reconstructed into hierarchical section trees and indexed with structured metadata. Retrieval is supported by two domain-specific embedding models fine-tuned on domain data (water and climate). On top of this knowledge base, a ReAct-style controller iteratively orchestrates retrieval actions by allocating retrieval budget across domain collections and accumulating evidence until a stopping criterion is met. In a retrieval benchmark over the corpus, the proposed approach improves Mean Reciprocal Rank by 26.7% (relative) compared to a single-domain embedding baseline, indicating more consistent retrieval of relevant evidence to support cross-project knowledge synthesis and climate-resilient decision-making.

新论文 · v1arXiv:2611.26396

重新思考差分隐私可视化的效用:以视觉通道为中心的视角

Rethinking Utility in Differentially Private Visualization: A Channel-Centric Perspective

Jing Yang, Sarayu Pacca, Zhaocong Yang, Liyue Fan

AI 速读 基于摘要

本文提出以视觉通道为中心的视角,重新组织差分隐私可视化中噪声如何影响视觉表示的零散发现,并提出通道—读取机制假设。

cs.HC

查看原文摘要

Differential privacy (DP) is increasingly adopted to protect sensitive data in visualization, but understanding how privacy-induced noise affects visual representations remains fragmented. Prior work has examined the impact of DP noise on specific chart types, yet these findings are typically tied to particular chart types and evaluation settings, making it difficult to generalize across contexts. In parallel, visualization research has long established that visual channels, the visual properties of marks that encode data attributes, differ in perceptual effectiveness under noise-free conditions. However, these principles have not been systematically revisited under DP, where noise is deliberately introduced into the data to protect privacy. In this paper, we present a channel-centric perspective to reframe prior empirical and theoretical results. Our synthesis drawson prior findings to motivate a channel-read-mechanism hypothesis: the utility of DP visualizations may depend on the task-relevant reads made salient by visual channel configurations and DP mechanism choice jointly. Moreover, this perspective highlights the role of channel choice throughout the privacy-preserving visualization pipeline, from disclosure framing and DP algorithm design to utility evaluation and interpretation of noisy outputs. The synthesis also identifies gaps in the existing evaluation literature and highlights research opportunities for channel-aware DP visualization.

新论文 · v1arXiv:2611.26395

非二元探测器错误模型

Non-Binary Detector Error Models

Stefano Tinelli, Francisco Lázaro, Francisco García Herrero

AI 速读 基于摘要

作者提出用非二元随机变量精确刻画综合征提取电路中的错误,并给出从任意 Clifford 电路构建紧凑非二元 DEM 的拆分-合并-重组变换,报告其在图规模与 BP 解码性能上的优势。

quant-ph · cs.IT

查看原文摘要

A key challenge in fault-tolerant quantum error correction (QEC) is that the syndrome extraction circuits are themselves faulty. Such circuit-level noise is commonly described by a detector error model (DEM). In Stim and in almost all related works, DEMs are binary: every non-binary circuit error (e.g., CNOT gate), is decomposed into independent binary error mechanisms. In this work, we introduce non-binary DEMs, in which each fault location of the syndrome extraction circuit is modeled by one random variable over its original alphabet, e.g., the 16 two-qubit Pauli errors after a CNOT gate. We also propose a split-merge-regroup transformation that builds a compact non-binary DEM from any Clifford circuit by merging the error components that flip the same detectors and observables. Non-binary DEMs represent any Pauli channel exactly, whereas binary DEMs are exact only for channels that factorize into independent binary parts. When the channels factorize, we prove that binary and non-binary DEMs are equivalent under degenerate quantum maximum-a-posteriori (MAP) decoding, but not under quantum MAP decoding. Although the variables are non-binary, belief propagation (BP) still exchanges a single scalar message per edge. Our numerical results with surface, color and bivariate bicycle codes show that non-binary DEMs have two main advantages. First, their Tanner graphs have four to five times fewer edges, which is advantageous for hardware implementations. Second, their performance under BP, with and without OSD post-processing, is better than that of their binary counterparts, and BP with OSD runs up to $9.4\times$ faster in a CPU.