activity
20242026
collaborators
Showing cs.LGShow all

6 papers · 1 filter

cs.LG2026

Multi-Token Residual Prediction

Yufeng Xu, Zishuo Bao, Qian Wang +6

Diffusion Language Models (DLMs) generate text by iteratively denoising masked token sequences, offering a tradeoff between parallelism and quality compared to autoregressive model…

cs.LG2026

Capacity-Aware Inference: Mitigating the Straggler Effect in Mixture of Experts

Shwai He, Weilin Cai, Jiayi Huang +1

The Mixture of Experts (MoE) is an effective architecture for scaling large language models by leveraging sparse expert activation to balance performance and efficiency. However, u…

cs.LG2026

Beyond the Birkhoff Polytope: Spectral-Sphere-Constrained Hyper-Connections

Zhaoyi Liu, Haichuan Zhang, Ang Li

Hyper-Connections (HC) generalize residual connections into multiple streams, employing residual matrices for cross-stream feature mixing to enrich model expressivity. However, unc…

cs.LG2025

DualSparse-MoE: Coordinating Tensor/Neuron-Level Sparsity with Expert Partition and Reconstruction

Weilin Cai, Le Qin, Shwai He +3

Mixture of Experts (MoE) has become a mainstream architecture for building Large Language Models (LLMs) by reducing per-token computation while enabling model scaling. It can be vi…

cs.LG2025

Towards Efficient Mixture of Experts: A Holistic Study of Compression Techniques

Shwai He, Daize Dong, Liang Ding +1

Scaling large language models has driven remarkable advancements across various domains, yet the continual increase in model size presents significant challenges for real-world dep…

cs.LG2024

What Matters in Transformers? Not All Attention is Needed

Shwai He, Guoheng Sun, Zheyu Shen +1

While scaling Transformer-based large language models (LLMs) has demonstrated promising performance across various tasks, it also introduces redundant architectures, posing efficie…