hackcv · 实时 AI 资讯聚合

研究进展 · 学界与业界突破

全部生成式 AI Agent / 智能体多模态计算机视觉自然语言处理强化学习 AI 安全编程助手公司与产品政策与监管研究进展 AI 视频

论文精选 60已解读

Dex-One2Many: Learning Dexterous Manipulation from a Single Human Demonstration· Dex-One2Many：从单一人类演示学习灵巧操控

While learning dexterous manipulation from a single human video offers a promising alterna…

AI 解读从单一人类演示学习灵巧操控的机器人政策。

领域：cs.RO作者：Jusuk Lee、Sungha Kim、Yeonsoo Park

#cs.RO

📎 arXiv🕒 10-09 01:59🔗 arxiv.org

论文精选 60已解读

DreamTrue: Action-Faithful Robot World Model with Counterfactual Post-Training· DreamTrue: 基于反事实后训练的动作忠实机器人世界模型

We present DreamTrue, a multi-view, cross-embodiment robot world model for action-faithful…

AI 解读提出DreamTrue，增强机器人动作忠实性和物理可信度的视频预测模型。

领域：cs.RO作者：Junyan Li、Ruizhi Li、Yu Liu

#cs.RO

📎 arXiv🕒 10-09 01:59🔗 arxiv.org

论文精选 60已解读

CSF: Contextual Safety Filtering for Motion Generators· 场景上下文安全过滤

Text-conditioned motion generators produce trackable whole-body motion, but they have no n…

AI 解读提出场景上下文安全过滤技术，提升动作生成的安全性。

领域：cs.RO作者：Lizhi Yang、Yiling Hou、Yao Tang

#cs.RO

📎 arXiv🕒 10-09 01:59🔗 arxiv.org

论文精选 60已解读

A Balanced Data Diet: Addressing the Exploration Bottleneck in Mega-Scale RL for Robot Control· 大规模机器人控制RL中的探索瓶颈解决方案

General-purpose robots must perform a wide range of tasks from agile locomotion to dextero…

AI 解读大型机器人RL探索瓶颈的解决方案

领域：cs.RO作者：Octi Zhang、Mateo Guaman Castro、Patrick Yin

#cs.RO

📎 arXiv🕒 10-09 01:59🔗 arxiv.org

论文精选 60已解读

From Reactive Containment to Proactive Assurance: Lessons from OpenAI, Anthropic, and Google Agent Security Incidents· 从被动防护到主动保障：AI代理安全事件的教训

In 2026, cybersecurity evaluations involving OpenAI, Anthropic, and Google agents reached …

AI 解读研究提出主动保障AI代理安全的新框架。

领域：cs.CR作者：Abbas Raftari

#cs.CR

📎 arXiv🕒 10-09 01:59🔗 arxiv.org

论文精选 60已解读

Hybrid Cinematography: Previsualizing and Managing Hallucination Risk in Generative Video Reshooting

On a film set, the camera move is committed during a take. Generative video reshooting let…

AI 解读通过混合电影摄影技术预览和管理生成视频重拍中的幻觉风险。

领域：cs.HC作者：Nhan、Tran、Neal Wadhwa

#cs.HC

📎 arXiv🕒 10-09 01:59🔗 arxiv.org

论文精选 82

Bi-FORK: Generative Modeling of High-Dimensional Bifurcating Systems· Bi-FORK: 高维分岔系统的生成建模

Bifurcations are ubiquitous in physical systems, from structural buckling to fluid and cli…

领域：cs.LG作者：Anna Zimmel、Fleur Hendriks、Markus Holzleitner

#cs.LG

📎 arXiv🕒 10-09 01:58🔗 arxiv.org

论文精选 84

Caught in the Act: Probes Effectively Detect Sabotage and Catch Unverbalized Deception· 行动中的监视：探测器有效检测欺骗

Recent incidents have highlighted the challenge of monitoring LLM agents and the danger of…

领域：cs.LG作者：Oskar J. Hollinsworth、Alex F. Spies、Tigist Diriba

#cs.LG

📎 arXiv🕒 10-09 01:58🔗 arxiv.org

论文精选 82

Rounding in Preconditioner Space: Redesigning 4-bit AdamW Optimizer-State Quantization

Quantizing AdamW's optimizer states reduces persistent storage, but quantization errors pr…

领域：cs.LG作者：Hanyang Li、Shao Tang、Daniel Thomas Braithwaite

#cs.LG

📎 arXiv🕒 10-09 01:58🔗 arxiv.org

论文精选 82

Density Ratio Estimation with Stein Displacement Fields· Stein 位移场的密度比估计

Density ratios quantify distribution shift from a probability-mass point of view, whereas …

领域：stat.ML作者：Song Liu

#stat.ML

📎 arXiv🕒 10-09 01:57🔗 arxiv.org

论文精选 82

VioLA: Learning Generalist Humanoid Control Policies from Human Data· VioLA：从人类数据学习通用人形控制策略

Teaching a humanoid to follow instructions with its whole body runs into two obstacles. It…

领域：cs.RO作者：Mert Albaba、Jens Beißwenger、Anna Manasyan

#cs.RO

📎 arXiv🕒 10-09 01:57🔗 arxiv.org

论文精选 82

FAITH: Feasibility-Aware Safety-Filtered RL for High-Dimensional Systems· FAITH: 面向可行性的安全过滤强化学习

Safe reinforcement learning commonly places safety and task performance in the same policy…

领域：cs.RO作者：Songyuan Zhang、Baljeet Singh、Sarthak Ranjeet Kaingade

#cs.RO

📎 arXiv🕒 10-09 01:57🔗 arxiv.org

论文精选 82

Toward Joint Optimization of Circuit Depth and Training Data Size in Adaptively Grown Quantum Classifiers· 量子分类器的联合优化

Building a quantum model involves a tradeoff: how complex the circuit should be, and how m…

领域：quant-ph作者：Saeefa Rubaiyet Nowmi、Md Mahmuduzzaman Kamol、Mohammad Saidur Rahman

#quant-ph

📎 arXiv🕒 10-09 01:55🔗 arxiv.org

论文精选 60已解读

Robust PAC Learning of Concurrent Stochastic Games· 并发随机游戏的鲁棒 PAC 学习

We introduce the first Probably Approximately Correct (PAC) learning framework for general…

AI 解读并发随机游戏的鲁棒 PAC 学习框架，解决纳什均衡存在性问题。

领域：cs.LG作者：Angel Y. He、David Parker

#cs.LG

📎 arXiv🕒 09-04 01:58🔗 arxiv.org

论文精选 60已解读

Para-Pipe: Exploiting Hierarchical Operator Parallelism of ML Computational Graphs on SoCs· Para-Pipe：利用 SoC 上 ML 计算图的层次并行性

As edge-based deep learning applications become more complex, optimizing performance on he…

AI 解读通过层次并行性优化 SoC 上的 ML 计算图性能。

领域：cs.DC作者：Yujie Zhang、Huiying Lan、Ehsan Aghapour

#cs.DC

📎 arXiv🕒 09-04 01:53🔗 arxiv.org

论文精选 60已解读

SWE-Gate: Passing Functional Tests Is Not Enough for Software Engineering Agents· SWE-Gate: 代码代理仅通过功能测试不够

Repository-level software engineering benchmarks have significantly advanced the evaluatio…

AI 解读功能测试不足以评估代码代理的全面能力。

领域：cs.SE作者：Xin He、Yanlin Wang、Mingwei Liu

#cs.SE

📎 arXiv🕒 09-04 01:53🔗 arxiv.org

论文精选 60已解读

Parameterised graph theory for tensor networks: entanglement rerouting, structural simplification, and agnostic tomography· 参数化图论与张量网络

Parameterised graph theory studies how the complexity of graph-theoretic problems depends …

AI 解读参数化图论在张量网络中的应用，优化状态表示与学习复杂度

领域：quant-ph作者：Matthias C. Caro、Natalie McHugh、Sergii Strelchuk

#quant-ph

📎 arXiv🕒 09-04 01:50🔗 arxiv.org

论文精选 82

SENTINEL-RL: Offloading Topological Reasoning from LLM Agents in the Security Operations Center· SENTINEL-RL: 从LLM代理中卸载拓扑推理

Large language model (LLM) agents are increasingly proposed as autonomous SOC analysts, bu…

领域：cs.CR作者：Uday Vallabhaneni、Cassie L. Cagwin、David J. Wild

#cs.CR

📎 arXiv🕒 09-04 01:49🔗 arxiv.org

行业资讯精选 75

Grok 4.6 scores 61 on the Artificial Analysis Intelligence Index· Grok 4.6 在 AI 分析智能指数上的评分

Grok 4.6 在人工智能分析智能指数上得分为 61。

#hacker-news

📎 Hacker News🕒 08-13 00:54🔗 artificialanalysis.ai

行业资讯精选 70

Opus 5 is currently #1 on Artificial Analysis Intelligence Leaderboard· Opus 5 居人工分析智能排行榜首位

Opus 5 在人工分析智能排行榜上位居第一。

#hacker-news

📎 Hacker News🕒 07-25 03:45🔗 artificialanalysis.ai

论文精选 75

How Much of a 10-K Matters? Aggregation-Dependent Value of Full-Text versus Risk-Factor Sentiment· 10-K报告的情感信息价值

Financial sentiment extraction has largely relied on news text and supervised extraction a…

领域：cs.LG

#cs.LG

📎 arXiv🕒 07-18 12:00🔗 arxiv.org

论文精选 85

RENEW: Towards Learning World Models and Repairing Model Exploitation from Preferences

World models are widely used in offline reinforcement learning (RL) to improve sample effi…

领域：cs.LG

#cs.LG

📎 arXiv🕒 07-18 12:00🔗 arxiv.org

论文精选 82

Closed-Loop Knowledge Dynamics: An Operational Framework for Saturation and Escape· 闭环知识动态：饱和与逃脱的框架

Feedback-driven loops support iterative improvement in large language models, reinforcemen…

领域：cs.LG

#cs.LG

📎 arXiv🕒 07-18 12:00🔗 arxiv.org

论文精选 83

Certified Domain Consistency for Multi-Domain Retrieval: Label-Free Per-Domain Contamination Control with Conformal Risk Guarantees· 多域检索的领域一致性控制

Retrieval over corpora that mix several domains often returns relevant but wrong-domain ev…

领域：cs.LG

#cs.LG

📎 arXiv🕒 07-18 12:00🔗 arxiv.org

论文精选 75

Low-Latency Relay Selection in NR-V2X Vehicular Communications via Graph Isomorphism Networks with Edge Features· NR-V2X 车载通信中的低延迟中继选择

Reliable, low-latency uplink connectivity is a key requirement for C-V2X networks in dense…

领域：cs.LG

#cs.LG

📎 arXiv🕒 07-18 12:00🔗 arxiv.org

论文精选 85

Branching Policy Optimization: Sandbox-Native Language Agent Reinforcement Learning· 分支策略优化：沙箱原生语言代理强化学习

Reinforcement learning has emerged as the dominant paradigm for training large language mo…

领域：cs.LG

#cs.LG

📎 arXiv🕒 07-18 12:00🔗 arxiv.org

论文精选 82

QFireNet: A Quantum-Enhanced U-Net for Wildfire Segmentation from Sentinel-2 Imagery· QFireNet：用于Sentinel-2图像野火分割的量子增强U-Net

Wildfire detection from satellite imagery is a semantic image segmentation problem that ha…

领域：cs.LG

#cs.LG

📎 arXiv🕒 07-18 12:00🔗 arxiv.org

论文精选 82

Explainable Geospatial AI for Satellite Ground Station Siting Using LiDAR-Derived Terrain Intelligence· 使用地形智能的解释性地理空间 AI 优化卫星地面站选址

Representative clutter height (RCH) is a key parameter in radio propagation and interferen…

领域：cs.LG

#cs.LG

📎 arXiv🕒 07-18 12:00🔗 arxiv.org

论文精选 82

CARPRT: Class-Aware Zero-Shot Prompt Reweighting for Black-Box Vision-Language Models· CARPRT: 类别感知零样本提示重加权

Pre-trained vision-language models (VLMs) enable zero-shot image classification by computi…

领域：cs.LG

#cs.LG

📎 arXiv🕒 07-18 12:00🔗 arxiv.org

论文精选 82

Position: Explainability Research Must Prioritize Foundations over Ad-hoc Methods· AI解释性研究应优先考虑基础

Despite the proliferation of Explainable AI (XAI) techniques -- from feature attributions …

领域：cs.LG

#cs.LG

📎 arXiv🕒 07-18 12:00🔗 arxiv.org

论文精选 65已解读

RoboTTT: Context Scaling for Robot Policies· RoboTTT: 扩展机器人策略的上下文规模

Recent robot foundation models operate with single-step or short-history visuomotor contex…

AI 解读机器人模型 RoboTTT 实现了 8K 时间步的上下文扩展，大幅提升多阶段任务性能。

领域：cs.RO作者：Yunfan Jiang、Yevgen Chebotar、Ruijie Zheng

#cs.RO

📎 arXiv🕒 07-17 01:59🔗 arxiv.org

论文精选 65已解读

Beyond Success Rate: Cost-Aware Evaluation of Offensive and Defensive Security Agents· 超越成功率：成本感知的安全代理评估

Security-agent evaluations commonly measure peak offensive capability under generous infer…

AI 解读通过成本感知评估安全代理的进攻与防御性能

领域：cs.CR作者：Paul Kassianik、Blaine Nelson、Yaron Singer

#cs.CR

📎 arXiv🕒 07-17 01:54🔗 arxiv.org

论文精选 65已解读

Decoding Market Emotion from Blockchain Activity: A Data-Driven Sentiment Classifier· 从区块链活动解码市场情绪：数据驱动的情绪分类器

The growing use of Bitcoin as a decentralized digital asset and investment tool has sparke…

AI 解读通过区块链交易、比特币历史价格和推特情绪分析来预测市场情绪的新方法。

领域：cs.LG作者：Arthur G. Bubolz、Abreu Quevedo、Giancarlo Lucca

#cs.LG

📎 arXiv🕒 07-17 01:52🔗 arxiv.org

论文精选 82

Bridge Evidence: Static Retrieval Utility Does Not Predict Causal Utility in Multi-Step Agentic Search· 静态检索效用无法预测多步骤代理搜索中的因果效用

Retrieval systems are trained and evaluated on a static idea of usefulness: hand a documen…

领域：cs.IR作者：Debayan Mukhopadhyay、Utshab Kumar Ghosh、Shubham Chatterjee

#cs.IR

📎 arXiv🕒 07-17 01:48🔗 arxiv.org

论文精选 84

Mutable Low-Rank Sketches for Retrain-Free Recommendation· 无需重新训练的推荐系统

A common bottleneck in two-stage recommendation is embedding staleness: when a user rates …

领域：cs.LG作者：Hector J. Garcia、Nick Clayton

#cs.LG

📎 arXiv🕒 07-17 01:39🔗 arxiv.org

论文精选 82

Data Driven Block Replacement Scheduling· 数据驱动的块替换调度

We develop data-driven algorithms for maintaining $N$ independent identical machines under…

领域：cs.LG作者：Aniruddhan Ganesaraman、VIdyadhar Kulkarni

#cs.LG

📎 arXiv🕒 07-17 01:31🔗 arxiv.org

论文精选 65已解读

Leveraging unlabelled data for generalizable neural population decoding· 利用未标记数据进行泛化神经群体解码

Robust and accurate neural decoders are integral to neurotechnologies such as brain-comput…

AI 解读利用未标记数据增强神经解码模型，提高泛化性能。

领域：cs.LG作者：Ximeng Mao、Nanda H. Krishna、Avery Hee-Woon Ryoo

#cs.LG

📎 arXiv🕒 07-16 01:58🔗 arxiv.org

论文精选 65已解读

Linear Independent Component Analysis via Optimal Transport· 通过最优传输实现线性独立成分分析

Linear Independent Component Analysis (ICA) recovers jointly independent source signals fr…

AI 解读通过最优传输距离优化线性独立成分分析，提高信号恢复准确性。

领域：cs.LG作者：Ashutosh Jha、Michel Besserve、Simon Buchholz

#cs.LG

📎 arXiv🕒 07-16 01:56🔗 arxiv.org

论文精选 65已解读

MetaPerch: Learning from metadata for bioacoustics foundation models· MetaPerch: 利用元数据的生物声学基础模型

Bioacoustic foundation models rely on large-scale citizen science platforms like Xeno-Cant…

AI 解读生物声学模型利用元数据提升物种识别性能。

领域：cs.LG作者：Mustafa Chasmai、Vincent Dumoulin、Jenny Hamer

#cs.LG

📎 arXiv🕒 07-16 01:42🔗 arxiv.org

论文精选 65已解读

Screening of Biosecurity Features in Metagenomic Data with Evo 2 Probes· 宏基因组数据中使用 Evo 2 探针筛选生物安全特征

Genomic foundation models such as Evo 2 learn rich sequence representations, but their val…

AI 解读使用 Evo 2 探针在宏基因组数据中筛查生物安全特征，如抗微生物耐药性。

领域：q-bio.GN作者：Jeremy Guntoro、Alexander Dack、Dylan Danno

#q-bio.GN

📎 arXiv🕒 07-16 01:38🔗 arxiv.org

论文精选 85

Early Adoption of Agentic Coding Tools by GitHub Projects· GitHub 项目早期采用自主编码工具

Agentic coding tools are increasingly capable of generating and submitting pull requests (…

领域：cs.SE作者：Maliha Noushin Raida、Daqing Hou

#cs.SE

📎 arXiv🕒 07-16 01:05🔗 arxiv.org

论文精选 81

Improving Wind and Solar Power Prediction with Efficient Wrapper-based Feature Selection: An Empirical Study· 提高风能和光伏预测准确度的高效特征选择方法

With rising global energy demand and growing awareness of climate change and its impacts, …

领域：cs.LG作者：Daniel Grillmeyer、Marius Hadry、Michael Stenger

#cs.LG

📎 arXiv🕒 07-16 00:55🔗 arxiv.org

论文精选 82

Transforming Rank: How Architecture Navigates the Spectral Pathologies of Depth· Transformer的Rank机制

We investigate how each component of the Transformer feedforward block architecture design…

领域：cs.LG作者：Katie Everett

#cs.LG

📎 arXiv🕒 07-16 00:50🔗 arxiv.org

论文精选 83

Lighthouse RL: Sample-Efficient Circuit Optimization via Strategic Reset Points· Lighthouse RL：通过战略重置点实现样本高效的电路优化

In this paper, we introduce Lighthouse RL, a sample-efficient reinforcement learning (RL) …

领域：cs.LG作者：Mustafa Emre Gürsoy、Stefan Uhlich、Ryoga Matsuo

#cs.LG

📎 arXiv🕒 07-16 00:37🔗 arxiv.org

论文精选 82

Rethinking Penetration Testing for AI-Enabled Systems: From Resource Compromise to Behavioral Objective Violation· AI系统渗透测试新视角：从资源破坏到行为目标违规

Penetration testing traditionally evaluates whether adversaries can exploit weaknesses in …

领域：cs.CR作者：Mohammad Allahbakhsh、Mohammad Hassan Bahari、Moslem Attar-Raouf

#cs.CR

📎 arXiv🕒 07-16 00:36🔗 arxiv.org

论文精选 82

Lyapunov Exponent as Physics-Informed Dense Reward: RL Discovery of Stabilization Beyond the Kapitza Pendulum· 李雅普诺夫指数作为物理信息密集奖励：超越卡皮察摆的 RL 稳定

We suggest using the Lyapunov characteristic exponent (LCE) as a dense reward signal for t…

领域：cs.LG作者：Slava Andrejev

#cs.LG

📎 arXiv🕒 07-16 00:29🔗 arxiv.org

论文精选 82

The Dynamic Verifiable Multi-Agent Human Agentic Loyalty Loop (DVM-HALL) Model and the Net Human-Agent Score (NHAS) in Autonomous Commerce· DVM-HALL 模型与 NHAS 在自主商业中的应用

The rapid proliferation of Agentic Artificial Intelligence fundamentally disrupts traditio…

领域：cs.SI作者：Sai Srikanth Madugula、Peplluis Esteva de la Rosa、Daya Shankar

#cs.SI

📎 arXiv🕒 07-16 00:27🔗 arxiv.org

论文精选 82

TRACE: Turn-level Reward Assignment via Credit Estimation for Long-Horizon Agents· TRACE：通过信用估计为长期代理分配逐轮奖励

Multi-turn agents solve complex tasks through extended sequences of tool interactions befo…

领域：cs.LG作者：Leitian Tao、Baolin Peng、Wenlin Yao

#cs.LG

📎 arXiv🕒 07-16 00:16🔗 arxiv.org

论文精选 85

Multimodal Empirical Bayes Variational Autoencoders for Joint Longitudinal and Time-to-Event Modeling· 多模态贝叶斯变分自编码器联合纵向和事件时间建模

Longitudinal tumor measurements, dropout information, and genetic covariates provide compl…

领域：stat.ML作者：Anders Sjöberg、Nils Olsson、Marcus Baaz

#stat.ML

📎 arXiv🕒 07-16 00:13🔗 arxiv.org

论文精选 65已解读

The Seriality Gap in Video Diffusion Models· 视频扩散模型的串行性差距

When one ball strikes another, then another, video models should predict the consequences …

AI 解读视频扩散模型在因果链长时预测表现下降，串行计算结构需改进。

领域：cs.LG作者：Jorge Diaz Chao、Konpat Preechakul、Yuxi Liu

#cs.LG

📎 arXiv🕒 07-15 01:59🔗 arxiv.org

论文精选 65已解读

TerraZero: Procedural Driving Simulation for Zero-Demonstration Self-Play at Scale· TerraZero: 零演示大规模自玩的程序化驾驶仿真器

Training robust autonomous driving agents requires a simulator that is fast enough for rei…

AI 解读TerraZero：零演示自玩训练的高效程序化驾驶仿真器。

领域：cs.LG作者：Zhouchonghao Wu、Akshay Rangesh、Weixin Li

#cs.LG

📎 arXiv🕒 07-15 01:59🔗 arxiv.org

论文精选 65已解读

A Shortcut to Statistically Steady-State Turbulence with Flow Matching· 流匹配快速达到稳态湍流

Many nonlinear physical systems exhibit an initial transient phase in which perturbations …

AI 解读直接生成稳态湍流分布，绕过瞬态过程，提高效率。

领域：physics.plasm-ph作者：Gianluca Galletti、Gerald Gutenbrunner、William Hornsby

#physics.plasm-ph

📎 arXiv🕒 07-15 01:58🔗 arxiv.org

论文精选 65已解读

FlowWAM: Optical Flow as a Unified Action Representation for World Action Models· FlowWAM：光流作为统一动作表示的世界模型

World Action Models (WAMs) are able to leverage pretrained video generators for both world…

AI 解读使用光流作为统一动作表示提升世界模型性能。

领域：cs.RO作者：Yixiang Chen、Peiyan Li、Yuan Xu

#cs.RO

📎 arXiv🕒 07-15 01:57🔗 arxiv.org

论文精选 65已解读

The Spectrum Is Not Enough: When Context Helps Time-Series Forecasting· 光谱不足：上下文如何帮助时序预测

A growing family of indices scores how predictable a series is from its spectrum. Practiti…

AI 解读光谱预测的价值不如添加上下文有效。

领域：cs.LG作者：Mert Onur Cakiroglu、Mehmet Dalkilic、Hasan Kurban

#cs.LG

📎 arXiv🕒 07-15 01:50🔗 arxiv.org

论文精选 65已解读

Watermark Forensics for Generative Models: An Information-Theoretic Perspective· 生成模型的水印法医视角

A watermark in a generative model's output is usually asked only whether a text is machine…

AI 解读生成模型输出水印的法医鉴定方法及其代价分析

领域：cs.CR作者：Xiaoyu Li、Zheng Gao、Xiaoyan Feng

#cs.CR

📎 arXiv🕒 07-15 01:49🔗 arxiv.org

论文精选 65已解读

Ensemble Controlled-Flow Filtering for Implicit Data Assimilation· 隐式数据同化的集成控制流过滤方法

Data assimilation estimates the state of a dynamical system from model forecasts and incom…

AI 解读提出一种新的数据同化方法，适用于非高斯、多对一的隐式观测模型。

领域：stat.ML作者：Zhuoyuan Li、Yue Zhao、Ming Li

#stat.ML

📎 arXiv🕒 07-15 01:16🔗 arxiv.org

论文精选 65已解读

Form, Not Content? A Preregistered, Placebo-Controlled Evaluation of Learned Error-Conditioned Self-Repair Through Prompts and Weights in Frozen Small Code Models· 形式而非内容？

Frozen small code LLMs are deployed locally, yet the information guiding a retry after a f…

AI 解读研究冻结小规模代码模型在自我修正时的形式作用.

领域：cs.SE作者：Mehmet Iscan

#cs.SE

📎 arXiv🕒 07-15 00:59🔗 arxiv.org

论文精选 65已解读

Robustness of Deep Learning Models for PV Power Forecasting under NWP Forecast Errors: A Spatiotemporal and Physically Interpretable Analysis· 光伏功率预测中深度学习模型的鲁棒性分析

Engineering use of AI forecasting models requires not only high nominal accuracy but also …

AI 解读分析深度学习模型在光伏功率预测中的鲁棒性

领域：physics.ao-ph作者：Dandan Chen、Yan Zhao、Xuepeng Chen

#physics.ao-ph

📎 arXiv🕒 07-15 00:48🔗 arxiv.org

论文精选 65已解读

ViHoRec: A Quality-Controlled Vietnamese Hotel Recommendation Dataset and Cold-Start Benchmark· ViHoRec：控制质量的越南酒店推荐数据集和冷启动基准

Recommender-system research for Vietnamese remains limited by the absence of a public, wel…

AI 解读控制质量的越南酒店推荐数据集，解决冷启动问题

领域：cs.IR作者：Minh Hoang Nguyen

#cs.IR

📎 arXiv🕒 07-15 00:28🔗 arxiv.org

论文精选 65已解读

Exact and Calibrated Diffusion Reconstruction for Digital Breast Tomosynthesis· 用于数字乳腺断层合成的精确校准扩散重建

Limited-angle digital breast tomosynthesis (DBT) reconstructs a volume from a few low-dose…

AI 解读使用精确校准的扩散模型改善数字乳腺断层合成的质量和不确定性。

领域：eess.IV作者：Imade Bouftini

#eess.IV

📎 arXiv🕒 07-15 00:10🔗 arxiv.org