Papersby GlyphToto: Time Series Optimized Transformer for Observability research paper by Datadog, 2024
Datadog · Architectures · Jul 10, 2024 · 47 citations · 33 upvotes · unverified
What it shows
Toto, a Time Series Optimized Transformer for Observability, achieves state-of-the-art performance in observability and general-purpose forecasting using a vast dataset of time series data.
By Ben Cohen, Emaad Khwaja, Kan Wang and 4 more · arXiv 2407.07874 · PDF
UnverifiedHugging Face's summary; not yet checked by hand.
More from Datadog
All 3Toto 2.0: Time Series Forecasting Enters the Scaling EraTime series foundation models demonstrate scalable forecasting performance across parameter sizes, with Toto 2.0 achieving state-of-the-art results on multiple benchmarks through a unified training approach.
Datadog39 citations39 upvotesRead →This Time is Different: An Observability Perspective on Time Series Foundation ModelsToto is a time series forecasting foundation model using a decoder-only architecture, demonstrating state-of-the-art performance on large-scale benchmarks with multivariate observability data.Datadog79 citations40 upvotesRead →
Other architectures papers
TopicAttention Is All You NeedIntroduced the Transformer, the attention-only architecture behind nearly every large language model since.
Google201k citations142 upvotesRead →Mamba: Linear-Time Sequence Modeling with Selective State SpacesA selective state space model that scales linearly with sequence length and matches Transformers on language.
Carnegie Mellon University10.2k citations152 upvotesRead →CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and GenerationCodeT5, a unified encoder-decoder Transformer model, improves code understanding and generation by leveraging semantic information from identifiers and user comments.
Salesforce2,633 citations3 upvotesRead →VGGT: Visual Geometry Grounded TransformerVGGT, a feed-forward neural network, efficiently infers multiple 3D attributes from single or multiple views, outperforming alternatives and enhancing downstream tasks without post-processing.
Meta2,132 citations40 upvotesRead →DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language ModelsThe DeepSeekMoE architecture improves expert specialization in Mixture-of-Experts models by segmenting experts and isolating shared ones, achieving better performance and computational efficiency compared to GShard and other models.
DeepSeek1,268 citations65 upvotesRead →CodeT5+: Open Code Large Language Models for Code Understanding and GenerationCodeT5+, a family of flexible encoder-decoder LLMs initialized with frozen LLMs and trained with a mixture of pretraining objectives, achieves state-of-the-art performance across various code-related tasks.Salesforce836 citations7 upvotesRead →
About this paper
- Venue
- arXiv.org
- Citations
- 47, 10 influential · Semantic Scholar
- Upvotes
- 33 · Hugging Face
- Lab
- Datadog · on Companies · on Acquisitions · on advisories · on awards · on blogs · on calendar · on certifications · on Attested · on Quarterly · on Tier Zero · on Downtime · on Mainstage · on Leaders · on marketplaces · on openperks · on Allied · on Paydays · on problems · on quadrant · on Releases · on repos · on salaries · on Nines · on socials · on standards · on Stories · on TechConf · on terms · on Titlewave
Changes
Citations rose from 46 to 47.
Influential citations rose from 9 to 10.
Citations rose from 44 to 46.
Citations rose from 43 to 44.
A first count of 9 influential citations.
A first count of 43 citations.
Found by the weekly Hugging Face scan; not yet checked by hand.