Machine LearningAI Research5 min reading time

IBM Releases Granite PatchTST-FM-R2 Zero-Shot Time Series Model

Unite.AI
Read the full article
IBM launched Granite PatchTST-FM-r2, a 385M-parameter zero-shot time-series forecasting model with improved architecture and features, ranking second on the GIFT-Eval benchmark among replicable zero-shot models. The model is open-sourced under Apache 2.0 and Linux Foundation licenses, supporting probabilistic forecasting and missing data imputation without fine-tuning.

More on this story


More in Machine Learning

Machine Learning5 min read

Researchers from Stanford and UC Berkeley Introduce TokenGate: Token-Gated Attention Makes Long-Context Prefill Up to 11.3x Faster

MarkTechPost
Machine Learning2 min read

Jack Dorsey’s Block made an AI model that talks to you like an awkward new friend

Covered by 5 sources
Machine Learning6 min read

AI21 Labs Releases LIFT-Bench to Curb Reward Hacking in RL Training

Unite.AI