Picture for Olivier Bachem

Olivier Bachem

Google Research

Diversity-Rewarded CFG Distillation

Add code
Oct 08, 2024
Viaarxiv icon

Imitating Language via Scalable Inverse Reinforcement Learning

Add code
Sep 02, 2024
Figure 1 for Imitating Language via Scalable Inverse Reinforcement Learning
Figure 2 for Imitating Language via Scalable Inverse Reinforcement Learning
Figure 3 for Imitating Language via Scalable Inverse Reinforcement Learning
Figure 4 for Imitating Language via Scalable Inverse Reinforcement Learning
Viaarxiv icon

Gemma 2: Improving Open Language Models at a Practical Size

Add code
Aug 02, 2024
Figure 1 for Gemma 2: Improving Open Language Models at a Practical Size
Figure 2 for Gemma 2: Improving Open Language Models at a Practical Size
Figure 3 for Gemma 2: Improving Open Language Models at a Practical Size
Figure 4 for Gemma 2: Improving Open Language Models at a Practical Size
Viaarxiv icon

Conditioned Language Policy: A General Framework for Steerable Multi-Objective Finetuning

Add code
Jul 22, 2024
Figure 1 for Conditioned Language Policy: A General Framework for Steerable Multi-Objective Finetuning
Figure 2 for Conditioned Language Policy: A General Framework for Steerable Multi-Objective Finetuning
Figure 3 for Conditioned Language Policy: A General Framework for Steerable Multi-Objective Finetuning
Figure 4 for Conditioned Language Policy: A General Framework for Steerable Multi-Objective Finetuning
Viaarxiv icon

BOND: Aligning LLMs with Best-of-N Distillation

Add code
Jul 19, 2024
Figure 1 for BOND: Aligning LLMs with Best-of-N Distillation
Figure 2 for BOND: Aligning LLMs with Best-of-N Distillation
Figure 3 for BOND: Aligning LLMs with Best-of-N Distillation
Figure 4 for BOND: Aligning LLMs with Best-of-N Distillation
Viaarxiv icon

WARP: On the Benefits of Weight Averaged Rewarded Policies

Add code
Jun 24, 2024
Figure 1 for WARP: On the Benefits of Weight Averaged Rewarded Policies
Figure 2 for WARP: On the Benefits of Weight Averaged Rewarded Policies
Figure 3 for WARP: On the Benefits of Weight Averaged Rewarded Policies
Figure 4 for WARP: On the Benefits of Weight Averaged Rewarded Policies
Viaarxiv icon

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

MusicRL: Aligning Music Generation to Human Preferences

Add code
Feb 06, 2024
Viaarxiv icon

WARM: On the Benefits of Weight Averaged Reward Models

Add code
Jan 22, 2024
Viaarxiv icon