collaborators

5 papers

cs.LG2025

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…

cs.LG2025

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…

cs.LG2025

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…

cs.SD2024

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…

cs.CV2024

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…