Olivier Bachem

16

Papers

50

Total Citations

Papers (16)

BOND: Aligning LLMs with Best-of-N Distillation

WARM: On the Benefits of Weight Averaged Reward Models

MusicRL: Aligning Music Generation to Human Preferences

Nash Learning from Human Feedback

Fast and Provably Good Seedings for k-Means

Assessing Generative Models via Precision and Recall

On the Fairness of Disentangled Representations

Are Disentangled Representations Helpful for Abstract Visual Reasoning?

On the Transfer of Inductive Bias from Simulation to the Real World: a New Disentanglement Dataset

What Matters for Adversarial Imitation Learning?

Coresets for Nonparametric Estimation - the Case of DP-Means

Horizontally Scalable Submodular Maximization

Uniform Deviation Bounds for k-Means Clustering

Distributed and Provably Good Seedings for k-Means in Constant Rounds

Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations

High-Fidelity Image Generation With Fewer Labels