Picture for Zoubin Ghahramani

Zoubin Ghahramani

University of Cambridge

RecurrentGemma: Moving Past Transformers for Efficient Open Language Models

Add code
Apr 11, 2024
Figure 1 for RecurrentGemma: Moving Past Transformers for Efficient Open Language Models
Figure 2 for RecurrentGemma: Moving Past Transformers for Efficient Open Language Models
Figure 3 for RecurrentGemma: Moving Past Transformers for Efficient Open Language Models
Figure 4 for RecurrentGemma: Moving Past Transformers for Efficient Open Language Models
Viaarxiv icon

Gemma: Open Models Based on Gemini Research and Technology

Add code
Mar 13, 2024
Figure 1 for Gemma: Open Models Based on Gemini Research and Technology
Figure 2 for Gemma: Open Models Based on Gemini Research and Technology
Figure 3 for Gemma: Open Models Based on Gemini Research and Technology
Figure 4 for Gemma: Open Models Based on Gemini Research and Technology
Viaarxiv icon

Plex: Towards Reliability using Pretrained Large Model Extensions

Add code
Jul 15, 2022
Figure 1 for Plex: Towards Reliability using Pretrained Large Model Extensions
Figure 2 for Plex: Towards Reliability using Pretrained Large Model Extensions
Figure 3 for Plex: Towards Reliability using Pretrained Large Model Extensions
Figure 4 for Plex: Towards Reliability using Pretrained Large Model Extensions
Viaarxiv icon

Pre-training helps Bayesian optimization too

Add code
Jul 07, 2022
Figure 1 for Pre-training helps Bayesian optimization too
Figure 2 for Pre-training helps Bayesian optimization too
Figure 3 for Pre-training helps Bayesian optimization too
Figure 4 for Pre-training helps Bayesian optimization too
Viaarxiv icon

Neural Diffusion Processes

Add code
Jun 08, 2022
Figure 1 for Neural Diffusion Processes
Figure 2 for Neural Diffusion Processes
Figure 3 for Neural Diffusion Processes
Figure 4 for Neural Diffusion Processes
Viaarxiv icon

Automatic prior selection for meta Bayesian optimization with a case study on tuning deep neural network optimizers

Add code
Sep 16, 2021
Figure 1 for Automatic prior selection for meta Bayesian optimization with a case study on tuning deep neural network optimizers
Figure 2 for Automatic prior selection for meta Bayesian optimization with a case study on tuning deep neural network optimizers
Figure 3 for Automatic prior selection for meta Bayesian optimization with a case study on tuning deep neural network optimizers
Figure 4 for Automatic prior selection for meta Bayesian optimization with a case study on tuning deep neural network optimizers
Viaarxiv icon

Deep Neural Networks as Point Estimates for Deep Gaussian Processes

Add code
May 10, 2021
Figure 1 for Deep Neural Networks as Point Estimates for Deep Gaussian Processes
Figure 2 for Deep Neural Networks as Point Estimates for Deep Gaussian Processes
Figure 3 for Deep Neural Networks as Point Estimates for Deep Gaussian Processes
Figure 4 for Deep Neural Networks as Point Estimates for Deep Gaussian Processes
Viaarxiv icon

Learning Continuous Treatment Policy and Bipartite Embeddings for Matching with Heterogeneous Causal Effects

Add code
Apr 21, 2020
Figure 1 for Learning Continuous Treatment Policy and Bipartite Embeddings for Matching with Heterogeneous Causal Effects
Figure 2 for Learning Continuous Treatment Policy and Bipartite Embeddings for Matching with Heterogeneous Causal Effects
Figure 3 for Learning Continuous Treatment Policy and Bipartite Embeddings for Matching with Heterogeneous Causal Effects
Figure 4 for Learning Continuous Treatment Policy and Bipartite Embeddings for Matching with Heterogeneous Causal Effects
Viaarxiv icon

Einsum Networks: Fast and Scalable Learning of Tractable Probabilistic Circuits

Add code
Apr 13, 2020
Figure 1 for Einsum Networks: Fast and Scalable Learning of Tractable Probabilistic Circuits
Figure 2 for Einsum Networks: Fast and Scalable Learning of Tractable Probabilistic Circuits
Figure 3 for Einsum Networks: Fast and Scalable Learning of Tractable Probabilistic Circuits
Figure 4 for Einsum Networks: Fast and Scalable Learning of Tractable Probabilistic Circuits
Viaarxiv icon

DynamicPPL: Stan-like Speed for Dynamic Probabilistic Models

Add code
Feb 07, 2020
Figure 1 for DynamicPPL: Stan-like Speed for Dynamic Probabilistic Models
Viaarxiv icon