Lujun Li

15

Papers

103

Total Citations

Papers (15)

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

EMQ: Evolving Training-free Proxies for Automated Mixed Precision Quantization

Automated Knowledge Distillation via Monte Carlo Tree Search

Self-Regulated Feature Learning via Teacher-Free Feature Distillation

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

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

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

DetKDS: Knowledge Distillation Search for Object Detectors

DisWOT: Student Architecture Search for Distillation WithOut Training

Shadow Knowledge Distillation: Bridging Offline and Online Knowledge Transfer

KD-Zero: Evolving Knowledge Distiller for Any Teacher-Student Pairs