EdinburghNLP - Natural Language Processing Group at the University of Edinburgh

university

https://edinburghnlp.inf.ed.ac.uk/

Activity Feed Request to join this org

AI & ML interests

We do research in all core areas of natural language processing, including morphology, parsing, semantics, discourse, language generation, and machine translation. EdinburghNLP also has a strong track record of work at the interface of NLP with other areas, including speech technology, machine learning, computer vision, cognitive modeling, social media, information retrieval, robotics, bioinformatics, and educational technology.

Recent Activity

ducdauge authored a paper 14 days ago

Model Merging by Uncertainty-Based Gradient Matching

ducdauge authored a paper 14 days ago

XCOPA: A Multilingual Dataset for Causal Commonsense Reasoning

ducdauge authored a paper 14 days ago

Are Large Language Models Temporally Grounded?

View all activity

EdinburghNLP's activity

ducdauge

authored 19 papers 14 days ago

Model Merging by Uncertainty-Based Gradient Matching

Paper • 2310.12808 • Published Oct 19, 2023 • 6

XCOPA: A Multilingual Dataset for Causal Commonsense Reasoning

Paper • 2005.00333 • Published May 1, 2020

Are Large Language Models Temporally Grounded?

Paper • 2311.08398 • Published Nov 14, 2023 • 1

Distilling Efficient Language-Specific Models for Cross-Lingual Transfer

Paper • 2306.01709 • Published Jun 2, 2023 • 1

Scaling Sparse Fine-Tuning to Large Language Models

Paper • 2401.16405 • Published Jan 29, 2024

Composable Sparse Fine-Tuning for Cross-Lingual Transfer

Paper • 2110.07560 • Published Oct 14, 2021 • 1

Combining Modular Skills in Multitask Learning

Paper • 2202.13914 • Published Feb 28, 2022 • 4

Image Retrieval from Contextual Descriptions

Paper • 2203.15867 • Published Mar 29, 2022 • 1

FaithDial: A Faithful Benchmark for Information-Seeking Dialogue

Paper • 2204.10757 • Published Apr 22, 2022 • 1

UniMorph 4.0: Universal Morphology

Paper • 2205.03608 • Published May 7, 2022

Fine-tuning Large Language Models with Sequential Instructions

Paper • 2403.07794 • Published Mar 12, 2024

Dynamic Memory Compression: Retrofitting LLMs for Accelerated Inference

Paper • 2403.09636 • Published Mar 14, 2024 • 3

Multi-Head Adapter Routing for Cross-Task Generalization

Paper • 2211.03831 • Published Nov 7, 2022 • 2

Efficient Transformers with Dynamic Token Pooling

Paper • 2211.09761 • Published Nov 17, 2022

Zero-Shot Tokenizer Transfer

Paper • 2405.07883 • Published May 13, 2024 • 5

Mixtures of In-Context Learners

Paper • 2411.02830 • Published Nov 5, 2024 • 2

Modular Deep Learning

Paper • 2302.11529 • Published Feb 22, 2023

Cross-Tokenizer Distillation via Approximate Likelihood Matching

Paper • 2503.20083 • Published Mar 25 • 1

The Sparse Frontier: Sparse Attention Trade-offs in Transformer LLMs

Paper • 2504.17768 • Published 18 days ago • 13

albertvillanova

posted an update 20 days ago

Post

2546

smolagents v1.14.0 is out! 🚀
🔌 MCPClient: A sleek new client for connecting to remote MCP servers, making integrations more flexible and scalable.
🪨 Amazon Bedrock: Native support for Bedrock-hosted models.
SmolAgents is now more powerful, flexible, and enterprise-ready. 💼

Full release 👉 https://github.com/huggingface/smolagents/releases/tag/v1.14.0
#smolagents #LLM #AgenticAI