collaborators

13 papers

cs.CL2025

SelecTKD: Selective Token-Weighted Knowledge Distillation for LLMs

Haiduo Huang, Jiangcheng Song, Yadong Zhang +1

Knowledge distillation (KD) is a standard route to compress Large Language Models (LLMs) into compact students, yet most pipelines uniformly apply token-wise loss regardless of tea…

cs.LG2025

FastEagle: Cascaded Drafting for Accelerating Speculative Decoding

Haiduo Huang, Jiangcheng Song, Wenzhe Zhao +1

Speculative decoding accelerates generation by drafting candidates and verifying them in parallel, yet state-of-the-art drafters (e.g., EAGLE) still require N sequential passes to…

cs.CV2025

SpecVLM: Fast Speculative Decoding in Vision-Language Models

Haiduo Huang, Fuwei Yang, Zhenhua Liu +4

Speculative decoding is a powerful way to accelerate autoregressive large language models (LLMs), but directly porting it to vision-language models (VLMs) faces unique systems cons…

cs.DC2025

IsoSched: Preemptive Tile Cascaded Scheduling of Multi-DNN via Subgraph Isomorphism

Boran Zhao, Zihang Yuan, Yanbin Hu +5

Deploying deep neural network (DNN) accelerators with Layer Temporal Scheduling (LTS) often incurs significant overheads (e.g., energy and latency), as intermediate activations mus…

cs.LG2025

AdapSNE: Adaptive Fireworks-Optimized and Entropy-Guided Dataset Sampling for Edge DNN Training

Boran Zhao, Hetian Liu, Zihang Yuan +5

Training deep neural networks (DNNs) directly on edge devices has attracted increasing attention, as it offers promising solutions to challenges such as domain adaptation and priva…

cs.LG2025

SparseMap: A Sparse Tensor Accelerator Framework Based on Evolution Strategy

Boran Zhao, Haiming Zhai, Zihang Yuan +4

The growing demand for sparse tensor algebra (SpTA) in machine learning and big data has driven the development of various sparse tensor accelerators. However, most existing manual…