← Search

Boxun Xu

2 accepted papers

2026

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

AAAI 2026technical

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) has been extensively studied, next-scale prediction presents unique challenges, and KV caching design for next-scale ba

Cited by 0SourcePDFScholar
2026

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

AAAI 2026technical

Graph contrastive learning (GCL) has demonstrated great promise for learning generalizable graph representations from unlabeled data. However, conventional GCL approaches face two critical limitations: (1) the restricted expressive capacity of multilayer perceptron (MLP) based encoders, and (2) subo

Cited by 0SourcePDFScholar