Africa
Mitigating Biases in Blackbox Feature Extractors for Image Classification Tasks
In image classification, it is common to utilize a pretrained model to extract meaningful features of the input images, and then to train a classifier on top of it to make predictions for any downstream task.
Mixed Dynamics In Linear Networks: Unifying the Lazy and Active Regimes
The mixed regime is the'best of both worlds': it converges
Large Language Model Unlearning
We study how to perform unlearning, i.e. forgetting undesirable (mis)behaviors, on large language models (LLMs).
The PRISM Alignment Dataset: What Participatory, Representative and Individualised Human Feedback Reveals About the Subjective and Multicultural Alignment of Large Language Models Hannah Rose Kirk 1
Human feedback is central to the alignment of Large Language Models (LLMs).
LCM: Locally Constrained Compact Point Cloud Model for Masked Point Modeling
The pre-trained point cloud model based on Masked Point Modeling (MPM) has exhibited substantial improvements across various tasks.
M3LEO: A Multi-Modal, Multi-Label Earth Observation Dataset Integrating Interferometric SAR and Multispectral Data
Satellite-based remote sensing has revolutionised the way we address global challenges in a rapidly evolving world. Huge quantities of Earth Observation (EO) data are generated by satellite sensors daily, but processing these large datasets for use in ML pipelines is technically and computationally challenging. Specifically, different types of EO data are often hosted on a variety of platforms, with differing degrees of availability for Python preprocessing tools. In addition, spatial alignment across data sources and data tiling for easier handling can present significant technical hurdles for novice users.
Logical Characterizations of Recurrent Graph Neural Networks with Reals and Floats
In pioneering work from 2019, Barceló and coauthors identified logics that precisely match the expressive power of constant iteration-depth graph neural networks (GNNs) relative to properties definable in first-order logic. In this article, we give exact logical characterizations of recurrent GNNs in two scenarios: (1) in the setting with floating-point numbers and (2) with reals. For floats, the formalism matching recurrent GNNs is a rule-based modal logic with counting, while for reals we use a suitable infinitary modal logic, also with counting. These results give exact matches between logics and GNNs in the recurrent setting without rel-ativising to a background logic in either case, but using some natural assumptions about floating-point arithmetic. Applying our characterizations, we also prove that, relative to graph properties definable in monadic second-order logic (MSO), our infinitary and rule-based logics are equally expressive. This implies that recurrent GNNs with reals and floats have the same expressive power over MSO-definable properties and shows that, for such properties, also recurrent GNNs with reals are characterized by a (finitary!)
SF-V: Single Forward Video Generation Model
Work done during an internship at Snap Inc.