We presented  two papers at NeurIPS 2024 this year:

• Building on Efficient Foundations: Effectively Training LLMs with Structured Feedforward Layers

• No Representation, No Trust: Connecting Representation, Collapse, and Trust Issues in PPO​

I co-organized the Pluralistic Alignment workshop at NeurIPS 2024 with an amazing list of speakers and panelists. 

​​​​​I gave a keynote talk at Deep Learning Indaba in Senegal Dakar alongside other ​incredible speakers like Samy Bengio.

I was a panelist in Long Context Foundation Models (LCFM) workshop at ICML 2024.

Organizing the Next Generation of Sequence Models workshop at ICML 2024.

Our paper Building on Efficient Foundations: Effectively Training LLMs with Structured Feedforward Layers is on arxiv!​

Gave a lecture on transformers and foundation models at the Eastern European Machine Learning (EEML) 2024 summer school.

I was invited by Peter Dayan's group to give a talk on "Scaling up reinforcement learning" at Max Planck Institute (MPI) in Tubingen.

I gave an inaugural lecture at EPFL on "Bridging Generative AI and Reinforcement Learning Towards Safer and Reliable AI Systems."

You can find the YouTube video of the talk here.

We published our work on Griffin, which is an efficient, high-performant state space model architecture for foundation models.

Published our Reinforced Self-Training work as an efficient approach to the alignment of LLMs.

Gave a talk at the EPFL IC department on the evolution of LLM architecture. 

Gave a talk at ICRC in Geneva on the open-source State of Art Foundation models November 2023).​

• Gave a talk UN in Geneva workshop on foundation models about the risks and potentials of foundation models for humanitarian operations (October 2023.)

• Gave a talk at EEML 2023 in Albania on the History of Large Language models.

We developed a new sequence modeling paradigm called LRU (Linear Recurrent Units), and our paper was published at ICML 2023.

Our paper "On integrating a language model into neural machine translation" got the best research paper award at Interspeech 2022.

Our paper "An Empirical Study of Implicit Regularization in Deep Offline RL" is on arXiv.

We are organizing the ML Evaluation Standards workshop at ICLR 2022.

We presented our paper "StarCraft II Unplugged: Large Scale Offline Reinforcement Learning" at the Deep RL workshop at NeurIPS 2021.

Our paper, Active Offline Policy Selection, has been accepted to NeurIPS 2021.

I have presented Intro to RL (part 1 slides) and Offline RL lectures (part 2 slides) at DeepLearn 2021 Summer School.

We have released DeepMind Lab and Bsuite datasets for Offline RL Under RL Unplugged which is published in NeurIPS 2021.

Our paper On Instrumental Variable Regression for Deep Offline Policy Evaluation is on arXiv.

​

Our paper, Regularized behavior value estimation on a single-step policy improvement method, is on arXiv.

Our paper Addressing Extrapolation Error in Deep Offline Reinforcement Learning was Oral at the Offline RL Workshop at NeurIPS 2020.

We released the hard-eight task suite used in the "Making Efficient Use of Demonstrations" paper.