1 citations · 1 across the 9 of their papers we have counts for
10 papers
Muse Glimmer 30B: An On-Device Agentic Model
Arash Ebrahim Abtahizadeh, Muna Aghamelu, Adil Ahmed +327
We introduce Muse Glimmer, an open-source 30B parameter causal language model with perception encoder, purpose-built for autonomous agentic tasks on consumer hardware. Muse Glimmer…
AI Research Preference Models
Thomas Simon Foster, Bassel Al Omari, Tingchen Fu +30
AI research agents (AIRA) can now carry machine learning experiments from proposal through implementation and evaluation. Yet progress on frontier tasks is throttled by the cost of…
Generalised Transportability via Causal Abstractions
Yorgos Felekis, Paris Giampouras, Fabio Massimo Zennaro +1
Transporting a causal conclusion from a source study population to a target one is a fundamental problem in causal inference. The theory of transportability provides a criterion fo…
Align & Invert: Solving Inverse Problems with Diffusion and Flow-based Models via Representation Alignment
Loukas Sfountouris, Giannis Daras, Paris Giampouras
Enforcing alignment between the internal representations of diffusion or flow-based generative models and those of pretrained self-supervised encoders has recently been shown to pr…
Distributionally Robust Causal Abstractions
Yorgos Felekis, Theodoros Damoulas, Paris Giampouras
Causal Abstraction (CA) theory provides a principled framework for relating causal models that describe the same system at different levels of granularity while ensuring interventi…
Rates of Convergence of Generalised Variational Inference Posteriors under Prior Misspecification
Terje Mildner, Paris Giampouras, Theodoros Damoulas
We prove rates of convergence and robustness to prior misspecification within a Generalised Variational Inference (GVI) framework with bounded divergences. This addresses a signifi…
DES-LOC: Desynced Low Communication Adaptive Optimizers for Training Foundation Models
Alex Iacob, Lorenzo Sani, Mher Safaryan +8
Scaling foundation model training with Distributed Data Parallel (DDP) methods is bandwidth-limited. Existing infrequent communication methods like Local SGD were designed to synch…
Federated Generalised Variational Inference: A Robust Probabilistic Federated Learning Framework
Terje Mildner, Oliver Hamelijnck, Paris Giampouras +1
We introduce FedGVI, a probabilistic Federated Learning (FL) framework that is robust to both prior and likelihood misspecification. FedGVI addresses limitations in both frequentis…
Guarantees of a Preconditioned Subgradient Algorithm for Overparameterized Asymmetric Low-rank Matrix Recovery
Paris Giampouras, HanQin Cai, Rene Vidal
In this paper, we focus on a matrix factorization-based approach to recover low-rank {\it asymmetric} matrices from corrupted measurements. We propose an {\it Overparameterized Pre…
Clustering-based Domain-Incremental Learning
Christiaan Lamers, Rene Vidal, Nabil Belbachir +3
We consider the problem of learning multiple tasks in a continual learning setting in which data from different tasks is presented to the learner in a streaming fashion. A key chal…