Lujun Li

9

Papers

103

Total Citations

Papers (9)

STBLLM: Breaking the 1-Bit Barrier with Structured Binary LLMs

Auto-Prox: Training-Free Vision Transformer Architecture Search via Automatic Proxy Discovery

Delta Decompression for MoE-based LLMs Compression

Auto-GAS: Automated Proxy Discovery for Training-free Generative Architecture Search

ParZC: Parametric Zero-Cost Proxies for Efficient NAS

DetKDS: Knowledge Distillation Search for Object Detectors

AIRA: Activation-Informed Low-Rank Adaptation for Large Models

Pruner-Zero: Evolving Symbolic Pruning Metric From Scratch for Large Language Models

Efficient Fine-Tuning of Large Models via Nested Low-Rank Adaptation