← Search

Yuanyuan Xi

2 accepted papers

2026

Rethinking 1-bit Optimization Leveraging Pre-trained Large Language Models

ICML 2026poster

1-bit LLM quantization offers significant advantages in reducing storage and computational costs. However, existing methods typically train 1-bit LLMs from scratch, failing to fully leverage pre-trained models. This results in high training costs and notable accuracy degradation. We identify that th…

Cited by 0SourceScholar
2024

PQ-SAM: Post-training Quantization for Segment Anything Model

ECCV 2024poster

"Segment anything model (SAM) is a promising prompt-guided vision foundation model to segment objects of interest. However, the extensive computational requirements of SAM have limited its applicability in resource-constraint edge devices. Post-training quantization (PTQ) is an effective potential f…

Cited by 5SourcePDFScholar