Sponsor of the Day:
Jerkmate
https://allenai.org/blog/olmohybrid
Introducing Olmo Hybrid: Combining transformers and linear RNNs for superior scaling | Ai2
Ai2, a non-profit research institute founded by Paul Allen, is committed to breakthrough AI to solve the world’s biggest problems.
linear rnnsintroducingolmohybridcombining
https://openreview.net/forum?id=UvTo3tVBk2
Unlocking State-Tracking in Linear RNNs Through Negative Eigenvalues | OpenReview
Linear Recurrent Neural Networks (LRNNs) such as Mamba, RWKV, GLA, mLSTM, and DeltaNet have emerged as efficient alternatives to Transformers for long...
unlocking statelinear rnnstrackingnegativeeigenvalues
https://openreview.net/forum?id=Iqex1gfnvc
TempoPFN: Towards Synthetic Pre-training of Linear RNNs for Zero-shot Time Series Forecasting |...
Foundation models for zero-shot time series forecasting face challenges in efficient long-horizon prediction and reproducibility, with existing synthetic-only...
time series forecastingpre traininglinear rnnszero shottowards
https://openreview.net/forum?id=EXGAodFkQX
Unlocking State-Tracking in Linear RNNs Through Negative Eigenvalues | OpenReview
Linear Recurrent Neural Networks (LRNNs) such as Mamba, RWKV, GLA, mLSTM, and DeltaNet have emerged as efficient alternatives to Transformers in large language...
unlocking statelinear rnnstrackingnegativeeigenvalues