collaborators

9 papers

cs.CV2025

VEGAS: Mitigating Hallucinations in Large Vision-Language Models via Vision-Encoder Attention Guided Adaptive Steering

Zihu Wang, Boxun Xu, Yuxuan Xia +1

Large vision-language models (LVLMs) exhibit impressive ability to jointly reason over visual and textual inputs. However, they often produce outputs that are linguistically fluent…

cs.CV2025

AMS-KV: Adaptive KV Caching in Multi-Scale Visual Autoregressive Transformers

Boxun Xu, Yu Wang, Zihu Wang +1

Visual autoregressive modeling (VAR) via next-scale prediction has emerged as a scalable image generation paradigm. While Key and Value (KV) caching in large language models (LLMs)…

cs.NE2025

SpikeX: Exploring Accelerator Architecture and Network-Hardware Co-Optimization for Sparse Spiking Neural Networks

Boxun Xu, Richard Boone, Peng Li

Spiking Neural Networks (SNNs) are promising biologically plausible models of computation which utilize a spiking binary activation function similar to that of biological neurons.…

cs.NE2025

Bishop: Sparsified Bundling Spiking Transformers on Heterogeneous Cores with Error-Constrained Pruning

Boxun Xu, Yuxuan Yin, Vikram Iyer +1

We present Bishop, the first dedicated hardware accelerator architecture and HW/SW co-design framework for spiking transformers that optimally represents, manages, and processes sp…

cs.LG2025

Khan-GCL: Kolmogorov-Arnold Network Based Graph Contrastive Learning with Hard Negatives

Zihu Wang, Boxun Xu, Hejia Geng +1

Graph contrastive learning (GCL) has demonstrated great promise for learning generalizable graph representations from unlabeled data. However, conventional GCL approaches face two…

cs.NE2024

Towards 3D Acceleration for low-power Mixture-of-Experts and Multi-Head Attention Spiking Transformers

Boxun Xu, Junyoung Hwang, Pruek Vanna-iampikul +3

Spiking Neural Networks(SNNs) provide a brain-inspired and event-driven mechanism that is believed to be critical to unlock energy-efficient deep learning. The mixture-of-experts a…