Search Results for author:
Found 12 papers, 4 papers with code
AstroMLab 4: Benchmark-Topping Performance in Astronomy Q&A with a 70B-Parameter Domain-Specialized Reasoning Model
General-purpose large language models, despite their broad capabilities, often struggle with specialized domain knowledge, a limitation particularly pronounced in more accessible, lower-parameter versions.
Empirically evaluating commonsense intelligence in large language models with large-scale human judgments
Commonsense intelligence in machines is often assessed by static benchmarks that compare a model's output against human-prescribed correct labels.
AstroMLab 2: AstroLLaMA-2-70B Model and Benchmarking Specialised LLMs for Astronomy
We find that the previously released AstroLLaMA series, based on LLaMA-2-7B, underperforms compared to the base model.
AstroMLab 1: Who Wins Astronomy Jeopardy!?
This dataset comprises 4, 425 multiple-choice questions curated from the Annual Review of Astronomy and Astrophysics, covering a broad range of astrophysical topics.
Federated PCA on Grassmann Manifold for IoT Anomaly Detection
Experimental results on the UNSW-NB15 and TON-IoT datasets show that our proposed methods offer performance in anomaly detection comparable to nonlinear baselines, while providing significant improvements in communication and memory efficiency, underscoring their potential for securing IoT networks.
AstroLLaMA-Chat: Scaling AstroLLaMA with Conversational and Diverse Datasets
We explore the potential of enhancing LLM performance in astronomy-focused question-answering through targeted, continual pre-training.
On Partial Optimal Transport: Revising the Infeasibility of Sinkhorn and Efficient Gradient Methods
This paper studies the Partial Optimal Transport (POT) problem between two unbalanced measures with at most $n$ supports and its applications in various AI tasks such as color transfer or domain adaptation.
Federated Deep Equilibrium Learning: Harnessing Compact Global Representations to Enhance Personalization
Federated Learning (FL) has emerged as a groundbreaking distributed learning paradigm enabling clients to train a global model collaboratively without exchanging data.
AstroLLaMA: Towards Specialized Foundation Models in Astronomy
Large language models excel in many human-language tasks but often falter in highly specialized domains like scholarly astronomy.
On the Generalization of Wasserstein Robust Federated Learning
We show that the robustness of WAFL is more general than related approaches, and the generalization bound is robust to all adversarial distributions inside the Wasserstein ball (ambiguity set).
DONE: Distributed Approximate Newton-type Method for Federated Edge Learning
In this work, we propose DONE, a distributed approximate Newton-type algorithm with fast convergence rate for communication-efficient federated edge learning.
Personalized Federated Learning with Moreau Envelopes
Federated learning (FL) is a decentralized and privacy-preserving machine learning technique in which a group of clients collaborate with a server to learn a global model without sharing clients' data.
