schneiderkamplab/SDU-Daisy
Viewer
• Updated
• 592 • 68
Schneider-Kamp Lab
university
AI & ML interests
- Ressource constrained language modelling - Evaluation - Low-Bandwidth Distributed Training - Quantization - Medical Language Modelling - AI x Human
Recent Activity
Papers
FlexMoRE: A Flexible Mixture of Rank-heterogeneous Experts for Efficient Federatedly-trained Large Language Models
DeToNATION: Decoupled Torch Network-Aware Training on Interlinked Online Nodes
JacobBITLABS
updated a dataset 9 days ago
JacobBITLABS
authored a paper 15 days ago
JacobBITLABS
submitted a paper to Daily Papers 15 days ago
JacobBITLABS
published a dataset 15 days ago
Kuchenpferd
authored a paper about 2 months ago
JacobBITLABS
authored 2 papers 2 months ago
lgalke
authored a paper 4 months ago
lgalke
authored 6 papers 7 months ago
Continual Quantization-Aware Pre-Training: When to transition from 16-bit to 1.58-bit pre-training for BitNet language models?
Paper
• 2502.11895 • Published
• 3
What makes a language easy to deep-learn? Deep neural networks and humans similarly benefit from compositional structure
Paper
• 2302.12239 • Published
• 1
Dynaword: From One-shot to Continuously Developed Datasets
Paper
• 2508.02271 • Published
• 15
GenCodeSearchNet: A Benchmark Test Suite for Evaluating Generalization in Programming Language Understanding
Paper
• 2311.09707 • Published
When are 1.58 bits enough? A Bottom-up Exploration of BitNet Quantization
Paper
• 2411.05882 • Published
• 1
CBOW Is Not All You Need: Combining CBOW with the Compositional Matrix Space Model
Paper
• 1902.06423 • Published
JacobBITLABS
authored a paper 7 months ago
giannor
authored a paper 7 months ago
JacobBITLABS
authored 3 papers over 1 year ago
Multiview Aerial Visual Recognition (MAVREC): Can Multi-view Improve Aerial Visual Perception?
Paper
• 2312.04548 • Published
• 1
BitNet b1.58 Reloaded: State-of-the-art Performance Also on Smaller Networks
Paper
• 2407.09527 • Published
When are 1.58 bits enough? A Bottom-up Exploration of BitNet Quantization
Paper
• 2411.05882 • Published
• 1