Nicholas Donald Lane

13 papers · 2021–2025 · 2 conferences · across top CS/AI conferences

Achievements

🌍 Conference Polyglot (2) ❓ The Questioner 💎 Century Club (13)

Conferences

ICLR (10) ICML (3)

Top co-authors

Łukasz Dudziak (4) Abhinav Mehrotra (4) Mohamed S Abdelfattah (3) Yan Gao (3) Javier Fernández-Marqués (3) Xinchi Qiu (3) Lorenzo Sani (2) Sourav Bhattacharya (2) Alex Iacob (2) Shyam A. Tailor (2)

Classification in progress for this author's papers.

Papers

DEPT: Decoupled Embeddings for Pre-training Language Models ICLR 2025

SparsyFed: Sparse Adaptive Federated Learning ICLR 2025

TinyTrain: Resource-Aware Task-Adaptive Sparse Training of DNNs at the Data-Scarce Edge ICML 2024

Breaking Physical and Linguistic Borders: Multilingual Federated Prompt Tuning for Low-Resource Languages ICLR 2024

Recurrent Early Exits for Federated Learning with Heterogeneous Clients ICML 2024

Towards Neural Architecture Search through Hierarchical Generative Modeling ICML 2024

Do We Need Anisotropic Graph Neural Networks? ICLR 2022

Conditioning Sequence-to-sequence Networks with Learned Activations ICLR 2022

Prospect Pruning: Finding Trainable Weights at Initialization using Meta-Gradients ICLR 2022

ZeroFL: Efficient On-Device Training for Federated Learning with Local Sparsity ICLR 2022

NAS-Bench-ASR: Reproducible Neural Architecture Search for Speech Recognition ICLR 2021

Zero-Cost Proxies for Lightweight NAS ICLR 2021

Degree-Quant: Quantization-Aware Training for Graph Neural Networks ICLR 2021