Cover Image

BlackGoose Rimer: Harnessing RWKV-7 as a Simple yet Superior Replacement for Transformers in Large-Scale Time Series Modeling

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	weile, Li, Xiao, Liu
Format:	Preprint
Published:	2025
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

RWKV-7 "Goose" with Expressive Dynamic State Evolution
by: Peng, Bo, et al.
Published: (2025)

State Tuning: State-based Test-Time Scaling on RWKV-7
by: Xiao, Liu, et al.
Published: (2025)

Rethinking Irregular Time Series Forecasting: A Simple yet Effective Baseline
by: Liu, Xvyuan, et al.
Published: (2025)

SOLAR 10.7B: Scaling Large Language Models with Simple yet Effective Depth Up-Scaling
by: Kim, Dahyun, et al.
Published: (2023)

Channel-Imposed Fusion: A Simple yet Effective Method for Medical Time Series Classification
by: Hu, Ming, et al.
Published: (2025)

Millions of States: Designing a Scalable MoE Architecture with RWKV-7 Meta-learner
by: Xiao, Liu, et al.
Published: (2025)

RWKV-TS: Beyond Traditional Recurrent Neural Network for Time Series Tasks
by: Hou, Haowen, et al.
Published: (2024)

Belief-State RWKV for Reinforcement Learning under Partial Observability
by: Xiao, Liu
Published: (2026)

Scaling Transformers for Time Series Forecasting: Do Pretrained Large Models Outperform Small-Scale Alternatives?
by: Chakraborty, Sanjay, et al.
Published: (2025)

Timer: Generative Pre-trained Transformers Are Large Time Series Models
by: Liu, Yong, et al.
Published: (2024)

SEER: Transformer-based Robust Time Series Forecasting via Automated Patch Enhancement and Replacement
by: Qiu, Xiangfei, et al.
Published: (2026)

Video RWKV:Video Action Recognition Based RWKV
by: Yin, Zhuowen, et al.
Published: (2024)

RWKV-edge: Deeply Compressed RWKV for Resource-Constrained Devices
by: Choe, Wonkyo, et al.
Published: (2024)

Poodle: Seamlessly Scaling Down Large Language Models with Just-in-Time Model Replacement
by: Strassenburg, Nils, et al.
Published: (2025)

FISformer: Replacing Self-Attention with a Fuzzy Inference System in Transformer Models for Time Series Forecasting
by: Haznedar, Bulent, et al.
Published: (2026)

Harnessing Contrastive Learning and Neural Transformation for Time Series Anomaly Detection
by: Chen, Katrina, et al.
Published: (2023)

Simple yet Effective: Low-Rank Spatial Attention for Neural Operators
by: Yang, Zherui, et al.
Published: (2026)

Simple yet Effective Graph Distillation via Clustering
by: Lai, Yurui, et al.
Published: (2025)

The FreshPRINCE: A Simple Transformation Based Pipeline Time Series Classifier
by: Middlehurst, Matthew, et al.
Published: (2022)

SimVPv2: Towards Simple yet Powerful Spatiotemporal Predictive Learning
by: Tan, Cheng, et al.
Published: (2022)

GraSP: Simple yet Effective Graph Similarity Predictions
by: Zheng, Haoran, et al.
Published: (2024)

Pruned Adaptation Modules: A Simple yet Strong Baseline for Continual Foundation Models
by: Yildirim, Elif Ceren Gok, et al.
Published: (2026)

Scaling Law for Large-Scale Pre-Training Using Chaotic Time Series and Predictability in Financial Time Series
by: Takemoto, Yuki
Published: (2025)

Conv-like Scale-Fusion Time Series Transformer: A Multi-Scale Representation for Variable-Length Long Time Series
by: Zhang, Kai, et al.
Published: (2025)

Empowering Time Series Analysis with Large-Scale Multimodal Pretraining
by: Chen, Peng, et al.
Published: (2026)

Towards Efficient Large Scale Spatial-Temporal Time Series Forecasting via Improved Inverted Transformers
by: Sun, Jiarui, et al.
Published: (2025)

AverageTime: Enhance Long-Term Time Series Forecasting with Simple Averaging
by: Zhao, Gaoxiang, et al.
Published: (2024)

RAM: Replace Attention with MLP for Efficient Multivariate Time Series Forecasting
by: Guo, Suhan, et al.
Published: (2024)

Graph Ranking Contrastive Learning: A Extremely Simple yet Efficient Method
by: Hu, Yulan, et al.
Published: (2023)

Transformers and Their Roles as Time Series Foundation Models
by: Wu, Dennis, et al.
Published: (2025)

Simple Contrastive Representation Learning for Time Series Forecasting
by: Zheng, Xiaochen, et al.
Published: (2023)

A Simple State Space Model Excels at Multivariate Time Series Classification
by: Saadatmand, Hassan, et al.
Published: (2026)

MSDformer: Multi-scale Discrete Transformer For Time Series Generation
by: Feng, Shibo, et al.
Published: (2025)

A Simple yet Effective DDG Predictor is An Unsupervised Antibody Optimizer and Explainer
by: Wu, Lirong, et al.
Published: (2025)

LENS: Large Pre-trained Transformer for Exploring Financial Time Series Regularities
by: Xu, Yuanjian, et al.
Published: (2024)

Generative Pretrained Hierarchical Transformer for Time Series Forecasting
by: Liu, Zhiding, et al.
Published: (2024)

E2USD: Efficient-yet-effective Unsupervised State Detection for Multivariate Time Series
by: Lai, Zhichen, et al.
Published: (2024)

LightDiC: A Simple yet Effective Approach for Large-scale Digraph Representation Learning
by: Li, Xunkai, et al.
Published: (2024)

Cut out and Replay: A Simple yet Versatile Strategy for Multi-Label Online Continual Learning
by: Wang, Xinrui, et al.
Published: (2025)

AdaMixT: Adaptive Weighted Mixture of Multi-Scale Expert Transformers for Time Series Forecasting
by: Zhang, Huanyao, et al.
Published: (2025)