Copertina

Exact Flow Linear Attention: Exact Solution from Continuous-Time Dynamics

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Lei, Jingdi, Zhang, Di, Poria, Soujanya
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Exact Linear Attention
di: Ou, Weinuo
Pubblicazione: (2026)

Exact Inference for Continuous-Time Gaussian Process Dynamics
di: Ensinger, Katharina, et al.
Pubblicazione: (2023)

Exact Conversion of In-Context Learning to Model Weights in Linearized-Attention Transformers
di: Chen, Brian K, et al.
Pubblicazione: (2024)

ELSA: Exact Linear-Scan Attention for Fast and Memory-Light Vision Transformers
di: Hsu, Chih-Chung, et al.
Pubblicazione: (2026)

Stochastic Gradient Flow Dynamics of Test Risk and its Exact Solution for Weak Features
di: Veiga, Rodrigo, et al.
Pubblicazione: (2024)

From Lazy to Rich: Exact Learning Dynamics in Deep Linear Networks
di: Dominé, Clémentine C. J., et al.
Pubblicazione: (2024)

Two are better than one: Context window extension with multi-grained self-injection
di: Han, Wei, et al.
Pubblicazione: (2024)

Rethinking Transformer Connectivity: TLinFormer, A Path to Exact, Full Context-Aware Linear Attention
di: Tang, Zhongpan
Pubblicazione: (2025)

Exact Mean Square Linear Stability Analysis for SGD
di: Mulayoff, Rotem, et al.
Pubblicazione: (2023)

Exact Attention Sensitivity and the Geometry of Transformer Stability
di: Emadi, Seyed Morteza
Pubblicazione: (2026)

Verlet Flows: Exact-Likelihood Integrators for Flow-Based Generative Models
di: Erives, Ezra, et al.
Pubblicazione: (2024)

Exact Causal Attention with 10% Fewer Operations
di: Rybin, Dmitry, et al.
Pubblicazione: (2025)

Capturing Momentum: Tennis Match Analysis Using Machine Learning and Time Series Theory
di: Lei, Jingdi, et al.
Pubblicazione: (2024)

Learning with Exact Invariances in Polynomial Time
di: Soleymani, Ashkan, et al.
Pubblicazione: (2025)

Discrete Guidance Matching: Exact Guidance for Discrete Flow Matching
di: Wan, Zhengyan, et al.
Pubblicazione: (2025)

Exact Learning Dynamics of In-Context Learning in Linear Transformers and Its Application to Non-Linear Transformers
di: Mainali, Nischal, et al.
Pubblicazione: (2025)

Exact Solutions to the Quantum Schrödinger Bridge Problem
di: Bordyuh, Mykola, et al.
Pubblicazione: (2025)

Universal Learning of Stochastic Dynamics for Exact Belief Propagation using Bernstein Normalizing Flows
di: Amorese, Peter, et al.
Pubblicazione: (2025)

Exact Recovery of Sparse Binary Vectors from Generalized Linear Measurements
di: Mazumdar, Arya, et al.
Pubblicazione: (2025)

KL-Regularized RLHF with Multiple Reference Models: Exact Solutions and Sample Complexity
di: Aminian, Gholamali, et al.
Pubblicazione: (2025)

Balancing Learning Rates Across Layers: Exact Two-Step Dynamics and Optimal Scaling in Linear Neural Networks
di: Pang, Tianyu, et al.
Pubblicazione: (2026)

ACU: Analytic Continual Unlearning for Efficient and Exact Forgetting with Privacy Preservation
di: Tang, Jianheng, et al.
Pubblicazione: (2025)

TurboBoA: Faster and Exact Attention-aware Quantization without Backpropagation
di: Kim, Junhan, et al.
Pubblicazione: (2026)

HyperTTS: Parameter Efficient Adaptation in Text to Speech using Hypernetworks
di: Li, Yingting, et al.
Pubblicazione: (2024)

Exact Federated Continual Unlearning for Ridge Heads on Frozen Foundation Models
di: Quan, Yijun, et al.
Pubblicazione: (2026)

Amortized Linear-time Exact Shapley Value for Product-Kernel Methods
di: Mohammadi, Majid, et al.
Pubblicazione: (2025)

What Data Enables Optimal Decisions? An Exact Characterization for Linear Optimization
di: Bennouna, Omar, et al.
Pubblicazione: (2025)

Data Agent: Learning to Select Data via End-to-End Dynamic Optimization
di: Yang, Suorong, et al.
Pubblicazione: (2026)

Noise Titration: Exact Distributional Benchmarking for Probabilistic Time Series Forecasting
di: Wang, Qilin
Pubblicazione: (2026)

How Sparse Attention Approximates Exact Attention? Your Attention is Naturally $n^C$-Sparse
di: Deng, Yichuan, et al.
Pubblicazione: (2024)

Learning Exactly Linearizable Deep Dynamics Models
di: Moriyasu, Ryuta, et al.
Pubblicazione: (2023)

ExLipBaB: Exact Lipschitz Constant Computation for Piecewise Linear Neural Networks
di: Splittgerber, Tom A.
Pubblicazione: (2026)

Exact Enforcement of Temporal Continuity in Sequential Physics-Informed Neural Networks
di: Roy, Pratanu, et al.
Pubblicazione: (2024)

Beyond What to Select: A Plug-and-play Oscillatory Data-Volume Scheduling for Efficient Model Training
di: Yang, Suorong, et al.
Pubblicazione: (2026)

LinearizeLLM: An Agent-Based Framework for LLM-Driven Exact Linear Reformulation of Nonlinear Optimization Problems
di: Kandora, Paul-Niklas Ken, et al.
Pubblicazione: (2025)

Exact Fit Attention in Node-Holistic Graph Convolutional Network for Improved EEG-Based Driver Fatigue Detection
di: Xu, Meiyan, et al.
Pubblicazione: (2025)

Towards Exact Computation of Inductive Bias
di: Boopathy, Akhilan, et al.
Pubblicazione: (2024)

Training Dynamics of In-Context Learning in Linear Attention
di: Zhang, Yedi, et al.
Pubblicazione: (2025)

BELM: Bidirectional Explicit Linear Multi-step Sampler for Exact Inversion in Diffusion Models
di: Wang, Fangyikang, et al.
Pubblicazione: (2024)

Bridging Accuracy and Explainability in EEG-based Graph Attention Network for Depression Detection
di: Hazra, Soujanya, et al.
Pubblicazione: (2025)