Hi HN, current frontier models (e.g., Claude, GPT, etc.) show incredible results across text, video, and audio. However, when looking at real world scenarios like production lines, trading, drilling operations, or demand supply forecasting these models are not capable of comprehending this data, especially given a limited context.
That’s why it needs models that are able to understand temporal information natively: temporal foundation models (TFMs). However, there is a data problem.
Anthropic, OpenAI and the likes know that we are already squeezing every available public information on the internet around text, video, and audio. Temporal information though is still scattered across organizations without a unified way to access it.
That’s why we built TimeNet, the ImageNet for temporal data.
Key facts:
- One uniform data layer for either our repository or your own data
- Define tasks on top temporal data around classification, question answering, scalar prediction, temporal localization, forecasting, generation, editing, and correspondence (more to come)
- Simple and performant API to integrate into ML frameworks.
- First experimental results: training on multiple temporal datasets increased F1 performance on each dataset respectively by an average of 14% and 22% for OpenTSLM and SLIP respectively.
- Install via ‘uv add timenet’
TimeNet is the result of a growing open and global collaboration between researchers from Aionic Labs, Stanford, ETH Zurich, UNSW Sydney, Sun Yat-sen University, Griffith University, Google, UCLA, TimeCopilot, Dartmouth, Harvard, Cambridge, Eindhoven University of Technology and KAIST.
There is currently an online hackathon ongoing on TimeNet with up to $50k in cloud credit prizes, this should fuel your first model training. Happy to see what you are building on top of it and to hear your thoughts.
Huge potential for healthcare, where patient data is longitudinal but often fragmented across systems. Curious how TimeNet approaches standardizing clinical time-series data without losing important context?
13 comments
[ 49.2 ms ] story [ 298 ms ] threadPaper: https://arxiv.org/abs/2610.04407
Quickstart: https://docs.timenet.ai/get-started.html
Hackathon Challenge: https://challenge.timenet.ai/
TimeNet Registry: https://registry.timenet.ai/
Hi HN, current frontier models (e.g., Claude, GPT, etc.) show incredible results across text, video, and audio. However, when looking at real world scenarios like production lines, trading, drilling operations, or demand supply forecasting these models are not capable of comprehending this data, especially given a limited context.
That’s why it needs models that are able to understand temporal information natively: temporal foundation models (TFMs). However, there is a data problem.
Anthropic, OpenAI and the likes know that we are already squeezing every available public information on the internet around text, video, and audio. Temporal information though is still scattered across organizations without a unified way to access it.
That’s why we built TimeNet, the ImageNet for temporal data.
Key facts:
- One uniform data layer for either our repository or your own data
- Define tasks on top temporal data around classification, question answering, scalar prediction, temporal localization, forecasting, generation, editing, and correspondence (more to come)
- Simple and performant API to integrate into ML frameworks.
- First experimental results: training on multiple temporal datasets increased F1 performance on each dataset respectively by an average of 14% and 22% for OpenTSLM and SLIP respectively.
- Install via ‘uv add timenet’
TimeNet is the result of a growing open and global collaboration between researchers from Aionic Labs, Stanford, ETH Zurich, UNSW Sydney, Sun Yat-sen University, Griffith University, Google, UCLA, TimeCopilot, Dartmouth, Harvard, Cambridge, Eindhoven University of Technology and KAIST.
There is currently an online hackathon ongoing on TimeNet with up to $50k in cloud credit prizes, this should fuel your first model training. Happy to see what you are building on top of it and to hear your thoughts.