Max Schwarzer
Mila - Quebec Artificial Intelligence Institute · 23 works · 371 citations · h-index 8
Top works
- Learning to fail: Predicting fracture evolution in brittle material models using recurrent graph convolutional neural networks
- MM1: Methods, Analysis and Insights from Multimodal LLM Pre-training
- Data-Efficient Reinforcement Learning with Self-Predictive Representations
- OpenAI o1 System Card
- Deep Reinforcement Learning at the Edge of the Statistical Precipice
- Pretraining Representations for Data-Efficient Reinforcement Learning
- MM1: Methods, Analysis & Insights from Multimodal LLM Pre-training
- OpenAI GPT-5 System Card
- The Primacy Bias in Deep Reinforcement Learning
- Reincarnating Reinforcement Learning: Reusing Prior Computation to Accelerate Progress
- Competitive Programming with Large Reasoning Models
- Bigger, Better, Faster: Human-level Atari with human-level efficiency
- Large Language Models as Generalizable Policies for Embodied Tasks
- Simplicial Embeddings in Self-Supervised Learning and Downstream Classification
- Improving Human Text Simplification with Sentence Fusion
- GAIT: A Geometric Approach to Information Theory
- Iterated learning for emergent systematicity in VQA
- Improving Human Text Simplification with Sentence Fusion
- Discovering the Electron Beam Induced Transition Rates for Silicon Dopants in Graphene with Deep Neural Networks in the STEM
- The Position Dependence of Electron Beam Induced Effects in 2D Materials with Deep Neural Networks