3 papers
cs.AI2025
Surfer-H Meets Holo1: Cost-Efficient Web Agent Powered by Open Weights
Mathieu Andreux, Breno Baldas Skuk, Hamza Benchekroun +41
We present Surfer-H, a cost-efficient web agent that integrates Vision-Language Models (VLM) to perform user-defined tasks on the web. We pair it with Holo1, a new open-weight coll…
cs.LG2025
This Time is Different: An Observability Perspective on Time Series Foundation Models
Ben Cohen, Emaad Khwaja, Youssef Doubli +16
We introduce Toto, a time series forecasting foundation model with 151 million parameters. Toto uses a modern decoder-only architecture coupled with architectural innovations desig…
cs.LG2024
Toto: Time Series Optimized Transformer for Observability
Ben Cohen, Emaad Khwaja, Kan Wang +4
This technical report describes the Time Series Optimized Transformer for Observability (Toto), a new state of the art foundation model for time series forecasting developed by Dat…