Unlocking State-Tracking in Linear RNNs Through Negative Eigenvalues
35:19
Vanilla Bayesian Optimization Performs Great in High Dimensions
42:54
Chronos: Time series forecasting in the age of pretrained models
51:36
The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery
22:43
How might LLMs store facts | DL7
46:31
Surrogate model-based algorithms for expensive black-box optimization
40:01
Scaling Exponents Across Parameterizations and Optimizers
48:45
Xingyou (Richard) Song - OmniPred: Towards Universal Regressors with Language Models
23:19