Talks

Causal Representation Learning across Multiple Environments

Reviewing our ongoing works on generalizing CRL for multiple causal models.

Training LLMs at Scale

Technicals and practicals on training and finetuning LLMs

An Introduction to JAX

Introduction talk for learning JAX and Flax as Deep Learning framework

OCIS: BISCUIT - Causal Representation Learning from Binary Interactions

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

Training Models at Scale

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

CARE: BISCUIT - Causal Representation Learning from Binary Interactions

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

On Practical Challenges of Scaling Causal Representation Learning

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

AI4Science Talks: PDE-Refiner - Achieving Accurate Long Rollouts with Neural PDE Solvers

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

UAI Spotlight Talk: BISCUIT - Causal Representation Learning from Binary Interactions

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

ICML F4LCD Contributed Talk: Modeling Accurate Long Rollouts with Neural PDE Solvers

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