Copertina

Sparse-VQ Transformer: An FFN-Free Framework with Vector Quantization for Enhanced Time Series Forecasting

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Zhao, Yanjun, Zhou, Tian, Chen, Chao, Sun, Liang, Qian, Yi, Jin, Rong
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Machine Learning Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Does Vector Quantization Fail in Spatio-Temporal Forecasting? Exploring a Differentiable Sparse Soft-Vector Quantization Approach
di: Chen, Chao, et al.
Pubblicazione: (2023)

FusionSF: Fuse Heterogeneous Modalities in a Vector Quantized Framework for Robust Solar Power Forecasting
di: Ma, Ziqing, et al.
Pubblicazione: (2024)

Attention as Robust Representation for Time Series Forecasting
di: Niu, PeiSong, et al.
Pubblicazione: (2024)

BeamVQ: Beam Search with Vector Quantization to Mitigate Data Scarcity in Physical Spatiotemporal Forecasting
di: Wang, Weiyan, et al.
Pubblicazione: (2025)

PENGUIN: Enhancing Transformer with Periodic-Nested Group Attention for Long-term Time Series Forecasting
di: Sun, Tian, et al.
Pubblicazione: (2025)

Bridging Past and Future: Distribution-Aware Alignment for Time Series Forecasting
di: Hu, Yifan, et al.
Pubblicazione: (2025)

VQ4DiT: Efficient Post-Training Vector Quantization for Diffusion Transformers
di: Deng, Juncan, et al.
Pubblicazione: (2024)

Transformer-VQ: Linear-Time Transformers via Vector Quantization
di: Lingle, Lucas D.
Pubblicazione: (2023)

CommVQ: Commutative Vector Quantization for KV Cache Compression
di: Li, Junyan, et al.
Pubblicazione: (2025)

Integer-only Quantized Transformers for Embedded FPGA-based Time-series Forecasting in AIoT
di: Ling, Tianheng, et al.
Pubblicazione: (2024)

VQ-SAD: Vector Quantized Structure Aware Diffusion For Molecule Generation
di: Noravesh, Farshad, et al.
Pubblicazione: (2026)

Mitigating Time Discretization Challenges with WeatherODE: A Sandwich Physics-Driven Neural ODE for Weather Forecasting
di: Liu, Peiyuan, et al.
Pubblicazione: (2024)

ArcVQ-VAE: A Spherical Vector Quantization Framework with ArcCosine Additive Margin
di: Kim, Jaeyung, et al.
Pubblicazione: (2026)

Baguan-TS: A Sequence-Native In-Context Learning Model for Time Series Forecasting with Covariates
di: Yang, Linxiao, et al.
Pubblicazione: (2026)

VARMA-Enhanced Transformer for Time Series Forecasting
di: Song, Jiajun, et al.
Pubblicazione: (2025)

LATST: Are Transformers Necessarily Complex for Time-Series Forecasting
di: Liang, Dizhen
Pubblicazione: (2024)

SST: Multi-Scale Hybrid Mamba-Transformer Experts for Time Series Forecasting
di: Xu, Xiongxiao, et al.
Pubblicazione: (2024)

VQ-DeepISC: Vector Quantized-Enabled Digital Semantic Communication with Channel Adaptive Image Transmission
di: Chen, Jianqiao, et al.
Pubblicazione: (2025)

VQ-Map: Bird's-Eye-View Map Layout Estimation in Tokenized Discrete Space via Vector Quantization
di: Zhang, Yiwei, et al.
Pubblicazione: (2024)

Enhancing Time Series Forecasting via Multi-Level Text Alignment with LLMs
di: Zhao, Taibiao, et al.
Pubblicazione: (2025)

Less is more: Embracing sparsity and interpolation with Esiformer for time series forecasting
di: Guo, Yangyang, et al.
Pubblicazione: (2024)

FAF: A Feature-Adaptive Framework for Few-Shot Time Series Forecasting
di: Ouyang, Pengpeng, et al.
Pubblicazione: (2025)

MergeVQ: A Unified Framework for Visual Generation and Representation with Disentangled Token Merging and Quantization
di: Li, Siyuan, et al.
Pubblicazione: (2025)

Analytical Provisioning for Attention-FFN Disaggregated LLM Serving under Stochastic Workloads
di: Song, Chendong, et al.
Pubblicazione: (2026)

Accurate and Efficient Multi-Channel Time Series Forecasting via Sparse Attention Mechanism
di: Gao, Lei, et al.
Pubblicazione: (2026)

SEDformer: Event-Synchronous Spiking Transformers for Irregular Telemetry Time Series Forecasting
di: Zhou, Ziyu, et al.
Pubblicazione: (2026)

Breaking the Context Bottleneck on Long Time Series Forecasting
di: Ma, Chao, et al.
Pubblicazione: (2024)

Amplify Adjacent Token Differences: Enhancing Long Chain-of-Thought Reasoning with Shift-FFN
di: Xu, Yao, et al.
Pubblicazione: (2025)

SDMixer: Sparse Dual-Mixer for Time Series Forecasting
di: Ao, Xiang
Pubblicazione: (2026)

Understanding the Role of Textual Prompts in LLM for Time Series Forecasting: an Adapter View
di: Niu, Peisong, et al.
Pubblicazione: (2023)

Towards Expressive Spectral-Temporal Graph Neural Networks for Time Series Forecasting
di: Jin, Ming, et al.
Pubblicazione: (2023)

FreEformer: Frequency Enhanced Transformer for Multivariate Time Series Forecasting
di: Yue, Wenzhen, et al.
Pubblicazione: (2025)

Enhancing Large Language Models for Time-Series Forecasting via Vector-Injected In-Context Learning
di: Zhang, Jianqi, et al.
Pubblicazione: (2026)

UniBias: Unveiling and Mitigating LLM Bias through Internal Attention and FFN Manipulation
di: Zhou, Hanzhang, et al.
Pubblicazione: (2024)

Fredformer: Frequency Debiased Transformer for Time Series Forecasting
di: Piao, Xihao, et al.
Pubblicazione: (2024)

Why Do Transformers Fail to Forecast Time Series In-Context?
di: Zhou, Yufa, et al.
Pubblicazione: (2025)

CATS: Enhancing Multivariate Time Series Forecasting by Constructing Auxiliary Time Series as Exogenous Variables
di: Lu, Jiecheng, et al.
Pubblicazione: (2024)

HAS-VQ: Hessian-Adaptive Sparse Vector Quantization for High-Fidelity LLM Compression
di: Khasia, Vladimer
Pubblicazione: (2026)

HDT: Hierarchical Discrete Transformer for Multivariate Time Series Forecasting
di: Feng, Shibo, et al.
Pubblicazione: (2025)

Nexus : An Agentic Framework for Time Series Forecasting
di: Das, Sarkar Snigdha Sarathi, et al.
Pubblicazione: (2026)