Technicals and practicals on training and finetuning LLMs

Introduction talk for learning JAX and Flax as Deep Learning framework

I presented our work BISCUIT, on making CRL viable on realistic, temporal interactive environments.

I gave a tutorial on distributed training strategies for large-scale models.

I presented our work BISCUIT, on making CRL viable on realistic, temporal interactive environments.

I presented an overview of our efforts on scaling Causal Representation Learning towards real-world settings.

I presented our recent paper on modeling accurate long rollouts with neural PDE solvers.

I presented our UAI spotlight paper on learning causal representation learning from low-level actions.

I presented our ICML workshop paper on how to achieve accurate long rollouts with neural PDE solvers.

I shared my experience of being a PhD student at UvA.

I was invited to the Rising Stars in AI Symposium to give a talk on our work in Causal Representation Learning.

I shared my experience of the Master AI program with prospective students for the 2023-2025 program.

I joined a panel for discussing the newest trends in AI, and our predictions for 2023.

Introduction talk for learning JAX and Flax as Deep Learning framework

I gave an short introduction into causal representation learning and our ICML work “CITRIS”.

I gave an overview on recent advances in causal representation learning and possible relations to causal incentives analysis in AGI safety at the Causal Incentive Working Group.

I shared my experience of the Master AI program with new students of the 2022-2024 program.

I gave an invited talk on our vision for causal representation learning from temporal observations at the First Workshop on Causal Representation Learning at UAI 2022.

I presented our ICML paper on causal representation learning from temporal observations.

I gave a contributed talk at the 2022 SIGIR Workshop on eCommerce on our paper “Simultaneously Improving Utility and User Experience in Task-oriented Dialogue Systems”.

I gave an short introduction into causal discovery and our ICLR work “ENCO”.

I gave a contributed talk on our paper “Efficient Neural Causal Discovery”.

I gave a contributed talk at the 2020 NeurIPS Competition Workshop on the Hateful Memes Challenge on our 4th place winning solution.