arXiv Machine Learning July 2, 2026 By Egor Serov, Ilya Kuleshov, Alexey Zaytsev

Efficient Neural Controlled Differential Equations via Attentive Kernel Smoothing

Read the original on arXiv Machine Learning →

arXiv:2602. 02157v2 Announce Type: replace Abstract: Neural Controlled Differential Equations (Neural CDEs) provide a powerful continuous-time framework for sequence modeling, yet the roughness of the driving control path often restricts their efficiency.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

benchmarks

arXiv AI

Jun 6

CLEAR: Cognition and Latent Evaluation for Adaptive Routing in End-to-End Autonomous Driving

arXiv:2606. 06219v1 Announce Type: cross Abstract: End-to-end autonomous driving models often struggle to balance multi-modal maneuver generation with real-time inference constraints.

By Yining Xing, Zehong Ke, Zhiyuan Liu, Yanbo Jiang, Wenhao Yu, Jianqiang Wang

agents diffusion robotics fine-tuning multimodal benchmarks safety

arXiv AI

Jul 2

FlowPath: Learning Data-Driven Manifolds with Invertible Flows for Robust Irregularly-sampled Time Series Classification

arXiv:2511. 10841v3 Announce Type: replace-cross Abstract: Modeling continuous-time dynamics from sparse and irregularly-sampled time series remains a fundamental challenge.

By YongKyung Oh, Dong-Young Lim, Sungil Kim

benchmarks safety

arXiv AI

Jun 11

ConsistencyPlanner: Real-time Planning with Fast-Sampling Consistency Models

arXiv:2606. 11569v1 Announce Type: cross Abstract: Closed-loop planning in complex, real-world driving scenarios presents a critical challenge for autonomous driving systems.

By Qichao Zhang, Xing Fang, Jiaqi Fang, Zhenwen Cai, Jie Ling, Qiankun Yu, Dongbin Zhao

agents robotics multimodal safety

arXiv Machine Learning

Jun 5

Function-Space Priors for Bayesian Neural ODEs with Application to Vessel Trajectory Prediction

arXiv:2606. 06351v1 Announce Type: cross Abstract: Vessel trajectory prediction from Automatic Identification System (AIS) data is essential for maritime situational awareness, yet it remains challenging due to irregular sampling, missing reports, and complex dynamics.

By Jaeyeong Lee, Wonmo Koo, Heeyoung Kim

arXiv AI

Jun 19

Bi-Anchor Interpolation Solver for Accelerating Generative Modeling

arXiv:2601. 21542v3 Announce Type: replace-cross Abstract: Flow Matching (FM) models have emerged as a leading paradigm for high-fidelity synthesis.

By Hongxu Chen, Hongxiang Li, Zhen Wang, Long Chen

diffusion

arXiv AI

Jun 30

Diff-MN: Diffusion Parameterized MoE-NCDE for Continuous Time Series Generation with Irregular Observations

arXiv:2601. 13534v3 Announce Type: replace-cross Abstract: Time series generation (TSG) is widely used across domains, yet most existing methods assume regular sampling and fixed output resolutions.

By Xu Zhang, Junwei Deng, Chang Xu, Hao Li, Jiang Bian

diffusion

Related stories

CLEAR: Cognition and Latent Evaluation for Adaptive Routing in End-to-End Autonomous Driving

FlowPath: Learning Data-Driven Manifolds with Invertible Flows for Robust Irregularly-sampled Time Series Classification

ConsistencyPlanner: Real-time Planning with Fast-Sampling Consistency Models

Function-Space Priors for Bayesian Neural ODEs with Application to Vessel Trajectory Prediction

Bi-Anchor Interpolation Solver for Accelerating Generative Modeling

Diff-MN: Diffusion Parameterized MoE-NCDE for Continuous Time Series Generation with Irregular Observations