3 papers
cs.CL2026
Temporal Guidance for Large Language Models
Hong-Kai Zheng, Piji Li
Contrastive Decoding (CD) enhances the generation quality of large language models (LLMs) but incurs significant additional computational overhead due to the need for an auxiliary…
cs.CV2025
LSRS: Latent Scale Rejection Sampling for Visual Autoregressive Modeling
Hong-Kai Zheng, Piji Li
Visual Autoregressive (VAR) modeling approach for image generation proposes autoregressive processing across hierarchical scales, decoding multiple tokens per scale in parallel. Th…
cs.CV2025
Group-Wise Optimization for Self-Extensible Codebooks in Vector Quantized Models
Hong-Kai Zheng, Piji Li
Vector Quantized Variational Autoencoders (VQ-VAEs) leverage self-supervised learning through reconstruction tasks to represent continuous vectors using the closest vectors in a co…