Mustafa Shukor

Rewarded soups: towards Pareto-optimal alignment by interpolating weights fine-tuned on diverse rewards

2023 · arXiv (Cornell University)

Foundation models are first pre-trained on vast unsupervised datasets and then fine-tuned on labeled data. Reinforcement learning, notably from human feedback (RLHF), can further align the network with the intended usage. Yet the imperfections in …

A Concept-Based Explainability Framework for Large Multimodal Models

2024 · arXiv (Cornell University)

Large multimodal models (LMMs) combine unimodal encoders and large language models (LLMs) to perform multimodal tasks. Despite recent advancements towards the interpretability of these models, understanding internal representations of LMMs remains largely a mystery. In …

Multimodal Autoregressive Pre-training of Large Vision Encoders

2024 · arXiv (Cornell University)

We introduce a novel method for pre-training of large-scale vision encoders. Building on recent advancements in autoregressive pre-training of vision models, we extend this framework to a multimodal setting, i.e., images and text. In this …