Artificial Intelligence Research Group Talks

Abstract not available

There is a curious trend in machine learning (ML): researchers developing the most capable large language models (LLMs) increasingly evaluate them using manual methods such as red teaming. In red teaming, researchers hire workers to manually try to break the LLM in some form by interacting with it. Similarly, some users...

Technological advances in medical data collection such as high-resolution histopathology and high-throughput genomic sequencing have contributed to the rising requirement for multi-modal biomedical modelling, specifically for image, tabular, and graph data. Most multi-modal deep learning approaches use modality-specific...

In this talk, we will discuss how multi-agent simulation and learning can be performed in the TorchRL library. In particular, we will focus on showcasing TorchRL's MARL API through a series of examples and demos from the multi-robot systems domain. The talk will begin by introducing the VectorizedMultiAgentSimulator (VMAS...

We will discuss AbDiffuser, our latest equivariant and physics-informed diffusion model for the joint generation of antibody 3D structures and sequences. AbDiffuser is built on top of a new representation of protein structure, and utilizes strong diffusion priors to improve the denoising process. Our approach improves...

This presentation will center around the implementation challenges associated with generative AI on emerging spatial computing hardware. A comprehensive examination of the Tensix core architecture, integrated within the flagship Wormhole chips provided by Tenstorrent Inc., will be undertaken. Subsequently, we will assess...

We consider a weakly supervised learning scenario where the supervision signal is generated by a transition function σ of labels associated with multiple input instances. We formulate this problem as multi-instance Partial Label Learning (multi-instance PLL), which is an extension to the standard PLL problem. Our problem...