2 papers
cs.CV2025
SPEED-Q: Staged Processing with Enhanced Distillation towards Efficient Low-bit On-device VLM Quantization
Tianyu Guo, Shanwei Zhao, Shiai Zhu +1
Deploying Vision-Language Models (VLMs) on edge devices (e.g., smartphones and robots) is crucial for enabling low-latency and privacy-preserving intelligent applications. Given th…
cs.LG2025
LoRASuite: Efficient LoRA Adaptation Across Large Language Model Upgrades
Yanan Li, Fanxu Meng, Muhan Zhang +3
As Large Language Models (LLMs) are frequently updated, LoRA weights trained on earlier versions quickly become obsolete. The conventional practice of retraining LoRA weights from…