10 papers
One LR Doesn't Fit All: Heavy-Tail Guided Layerwise Learning Rates for LLMs
Di He, Songjun Tu, Keyu Wang +2
Learning rate configuration is a fundamental aspect of modern deep learning. The prevailing practice of applying a uniform learning rate across all layers overlooks the structural…
MedFM-Robust: Benchmarking Robustness of Medical Foundation Models
Xiangxiang Cui, Tianjin Huang, Yifang Wang +2
Medical foundation models have achieved remarkable clinical performance, yet their robustness under real-world perturbations remains underexplored. We present a robustness benchmar…
Chain-of-Experts: Unlocking the Communication Power of Mixture-of-Experts Models
Zihan Wang, Rui Pan, Jiarui Yao +7
We propose Chain-of-Experts (CoE), a new Mixture-of-Experts (MoE) architecture that introduces sequential expert communication within each layer. Unlike traditional MoE models, whe…
LIFT the Veil for the Truth: Principal Weights Emerge after Rank Reduction for Reasoning-Focused Supervised Fine-Tuning
Zihang Liu, Tianyu Pang, Oleg Balabanov +5
Recent studies have shown that supervised fine-tuning of LLMs on a small number of high-quality datasets can yield strong reasoning capabilities. However, full fine-tuning (Full FT…
NeuroTrails: Training with Dynamic Sparse Heads as the Key to Effective Ensembling
Bram Grooten, Farid Hasanov, Chenxiang Zhang +9
Model ensembles have long been a cornerstone for improving generalization and robustness in deep learning. However, their effectiveness often comes at the cost of substantial compu…
Leave it to the Specialist: Repair Sparse LLMs with Sparse Fine-Tuning via Sparsity Evolution
Qiao Xiao, Alan Ansell, Boqian Wu +4
Sparse large language models (LLMs) offer an attractive direction toward efficient deployment, but adapting them to downstream tasks remains challenging. The central difficulty is…
Full-Rank No More: Low-Rank Weight Training for Modern Speech Recognition Models
Adriana Fernandez-Lopez, Shiwei Liu, Lu Yin +2
This paper investigates the under-explored area of low-rank weight training for large-scale Conformer-based speech recognition models from scratch. Our study demonstrates the viabi…
Are Sparse Neural Networks Better Hard Sample Learners?
Qiao Xiao, Boqian Wu, Lu Yin +4
While deep learning has demonstrated impressive progress, it remains a daunting challenge to learn from hard samples as these samples are usually noisy and intricate. These hard sa…
Dynamic Data Pruning for Automatic Speech Recognition
Qiao Xiao, Pingchuan Ma, Adriana Fernandez-Lopez +7
The recent success of Automatic Speech Recognition (ASR) is largely attributed to the ever-growing amount of training data. However, this trend has made model training prohibitivel…
MSRS: Training Multimodal Speech Recognition Models from Scratch with Sparse Mask Optimization
Adriana Fernandez-Lopez, Honglie Chen, Pingchuan Ma +5
Pre-trained models have been a foundational approach in speech recognition, albeit with associated additional costs. In this study, we propose a regularization technique that facil…