慣性聚合 高效追蹤和閱讀你感興趣的部落格、新聞、科技資訊
閱讀原文 在慣性聚合中打開

推薦訂閱源

WordPress大学
WordPress大学
有赞技术团队
有赞技术团队
J
Java Code Geeks
S
Secure Thoughts
T
Tailwind CSS Blog
P
Proofpoint News Feed
V
V2EX - 技术
月光博客
月光博客
人人都是产品经理
人人都是产品经理
MyScale Blog
MyScale Blog
D
Docker
Schneier on Security
Schneier on Security
Security Latest
Security Latest
PCI Perspectives
PCI Perspectives
S
Security Archives - TechRepublic
SecWiki News
SecWiki News
MongoDB | Blog
MongoDB | Blog
cs.CV updates on arXiv.org
cs.CV updates on arXiv.org
Attack and Defense Labs
Attack and Defense Labs
H
Hacker News: Front Page
F
Fortinet All Blogs
小众软件
小众软件
cs.AI updates on arXiv.org
cs.AI updates on arXiv.org
博客园_首页
N
News and Events Feed by Topic
L
LangChain Blog
V
Visual Studio Blog
A
Arctic Wolf
NISL@THU
NISL@THU
B
Blog
L
LINUX DO - 热门话题
Threat Intelligence Blog | Flashpoint
Threat Intelligence Blog | Flashpoint
Simon Willison's Weblog
Simon Willison's Weblog
CTFtime.org: upcoming CTF events
CTFtime.org: upcoming CTF events
V
Vulnerabilities – Threatpost
Application and Cybersecurity Blog
Application and Cybersecurity Blog
Scott Helme
Scott Helme
The GitHub Blog
The GitHub Blog
P
Privacy & Cybersecurity Law Blog
Malwarebytes
Malwarebytes
The Hacker News
The Hacker News
T
Tor Project blog
C
Comments on: Blog
S
Securelist
雷峰网
雷峰网
宝玉的分享
宝玉的分享
Spread Privacy
Spread Privacy
博客园 - 叶小钗
G
GRAHAM CLULEY
T
The Blog of Author Tim Ferriss

cs.LG updates on arXiv.org

Personalized Generative Models for Contextual Debiasing From Privacy to Generalization: Linear Max-Information Bounds for DP-SGD When Does Deep RL Beat Calibrated Baselines? A Benchmark Study on Adaptive Resource Control Amortized Factor Inference Networks for Posterior Inference Classification and detection of multiple UAVs using rational Gaussian wavelet neural networks Planning Neural Dynamics with Lie Group Embedding through Supervised Projective Manifold Learning Modeling Dynamic Mixtures of Time-Delay Systems from Streaming Time Series AirCast-SR: A Foundation Model for Kilometer-Scale Atmospheric Super-Resolution via Latent Consistency Diffusion Neural Bayesian Sequential Routing GAC: Noise-Aware Adaptive Mixing for Hybrid SFT-RL Post-Training Provably Communication-Efficient and Privacy-Preserving Federated Graph Neural Networks Function-Valued Causal Influence in Nonlinear Time Series The Bridge-Garden Dilemma in LLM Distillation: Why Mixing Hard and Soft Labels Works Balancing Plasticity and Stability with Fast and Slow Successor Features InfoQuant: Shaping Activation Distributions for Low-Bit LLM Quantization FM-fMRI: Event Conditioned Flow Matching for Rest-to-Task fMRI Time-Series Synthesis TrackRef3D: Multi-View Consistent Track-then-Label for Open-World Referring Segmentation in 3D Gaussian Splatting TSFMAudit: Data Contamination Auditing in Forecasting Time Series Foundation Models On the Push-Based Asynchronous Federated Learning: A Bias-Correction Aggregation Approach CSV-ViT: A Vision Transformer with the Variable-sized Cortical Supervertices for Detection of Alzheimer's Disease Pathologies Max-Window Scale Estimation for Near-Lossless HiF8 W8A8 Quantization-Aware Training Online Learning on Hidden-Convex Losses via Algorithmic Equivalence: Optimal Regret, Geometric Barrier, and Bandit Feedback Curriculum Learning for Safety Alignment A PAC-Bayesian View of Generalisation for Physics-Informed Machine Learning Dynamic Link Prediction with Temporally Enhanced Signed Graph Neural Networks GEM: Geometric Entropy Mixing for Optimal LLM Data Curation Reparametrizing Shampoo and SOAP for Subspace Basis Updates and BFloat16 Storage Unified Neural Scaling Laws Semigroup Consistency as a Diagnostic for Learned Physics Simulators QAM-W: Joint 2D Codebook Quantization for LLM Weights via Hadamard Rotation and Activation-Aware Scaling HRVConformer: Neonatal Hypoxic-Ischemic Encephalopathy Classification from the Heart Rate signals Scaling World-Model Reinforcement Learning Through Diffusion Policy Optimization A Hybrid Vision-Language Architecture for Automated Defect Reasoning and Report Generation in Industrial Inspection Quantized Keys Steal Attention: Bias Correction for KV-Cache Compression in Video Diffusion BioFact-MoE: Biologically Factorized Mixture of Experts for Vision-Language Prognostic Modeling in Hepatocellular Carcinoma Bridging Classification and Reconstruction: Cooperative Time Series Anomaly Detection SilIF: Silhouette-Augmented Isolation Forest for Unsupervised Transaction Fraud Detection Co-folding model guided by structural proteomics Energy-Gated Attention and Wavelet Positional Encoding: Complementary Inductive Biases for Transformer Attention Stateful Inference for Low-Latency Multi-Agent Tool Calling Two-Parameter Flows for Learning Population Dynamics of Physical Systems On the Role of Inductive Bias in Time-Series Pretraining: A Case Study in Learning Generalizable Representations for Clinical Time Series A Fast and Generic Energy-Shifting Transformer for Hybrid Monte Carlo Radiotherapy Calculation ARBITER: Reasoning Trajectory Basins and Majority Vote Failures in Test-Time Sampling When Rule Violations Are Rare: Chimera Training for Logical Anomaly Detection The Constraint Tax: Measuring Validity-Correctness Tradeoffs in Structured Outputs for Small Language Models When Correct Demonstrations Hurt: Rethinking the Role of Exemplars in In-Context Learning Benchmarking Convolutional, Transformer, Hybrid, and Vision Language Models for Multi Disease Retinal Screening Rotation-Invariant Spherical Watermarking via Third-Order SO(3) Representation Coupling MULTISEISMO: A Multimodal Seismic Dataset and Model for Cross-Modal Seismic Understanding
Chat2Workflow:用自然語言生成可執行視覺工作流程的基準測試
Yi Zhong, Bu · 2026-04-22 · via cs.LG updates on arXiv.org

檢視 PDF HTML (實驗性)

摘要: 目前,可執行的視覺工作流程已經成為實際工業部署中的主流範式,提供強大的可靠性和可控性。然而,在當前實踐中,這類工作流程幾乎完全是通過手動工程構建的:開發人員必須仔細設計工作流程,為每個步驟編寫提示,並隨著需求的演變不斷修訂邏輯——這使得開發成本高昂、耗時且容易出錯。為了研究大型語言模型能否自動化這個多輪互動過程,我們引入了Chat2Workflow,這是一個直接從自然語言生成可執行視覺工作流程的基準,並提出了一個強健的代理基線來提高性能。該基準由大量真實業務工作流程構建而成,每個實例都設計為使得生成的工作流程可以轉換並直接部署到實際工作流程平台,如Dify和Coze。實驗結果顯示,雖然最先進的語言模型通常能夠捕捉高層次意圖,但它們在生成正確、穩定且可執行的工 作流程方面遇到困難,尤其是在面對複雜和演變的需求時。儘管我們的代理基線實現了最高6.05%的解決率提升,但剩餘的真實世界差距將Chat2Workflow作為推進工業級自動化的基礎。代碼可在此 https URL
評論: 進行中
主題: 計算與語言 (cs.CL); 人工智慧 (cs.AI); 計算機視覺與模式識別 (cs.CV); 驅動學習 (cs.LG); 多智能體系統 (cs.MA)
引用格式: arXiv:2604.19667 [cs.CL]
  (or arXiv:2604.19667v2 [cs.CL] for this version)
  https://doi.org/10.48550/arXiv.2604.19667

arXiv-發行的 DOI 透過 DataCite

提交通過歷史

来自:張寧宇 [查看郵件]
[v1] 二, 21 四月 2026 16:49:11 UTC (29,273 KB)
[v2] 二, 26 五月 2026 16:14:10 UTC (9,804 KB)