Zhiteng Li

Quant-dLLM: Post-Training Extreme Low-Bit Quantization for Diffusion Large Language Models

DVD-Quant: Data-free Video Diffusion Transformers Quantization

PT$^2$-LLM: Post-Training Ternarization for Large Language Models

CondiQuant: Condition Number Based Low-Bit Quantization for Image Super-Resolution

Progressive Binarization with Semi-Structured Pruning for LLMs

ReCalKV: Low-Rank KV Cache Compression via Head Reordering and Offline Calibration

AdaSVD: Adaptive Singular Value Decomposition for Large Language Models

FlashEdit: Decoupling Speed, Structure, and Semantics for Precise Image Editing

ARB-LLM: Alternating Refined Binarizations for Large Language Models

GenDataAgent: On-the-fly Dataset Augmentation with Synthetic Data

BiDRN: Binarized 3D Whole-body Human Mesh Recovery

BiMaCoSR: Binary One-Step Diffusion Model Leveraging Flexible Matrix Compression for Real Super-Resolution