conftrace_

once-for-all training

3 papers

Explore in graph

Also known as

OFA

Co-occurring keywords · papers mentioning both

low-rank adapter (1) large language model quantization (1) large language model (1) deployment efficiency (1) switchable output layer (1) flops (1) epsilon-shrinking (1) gpu hours (1) weight-shared shrinking (1) model efficiency (1)

Papers

SOLAR: Switchable Output Layer for Accuracy and Robustness in Once-for-All Training WACV 2026 One QuantLLM for ALL: Fine-tuning Quantized LLMs Once for Efficient Deployments ACL 2025 DεpS: Delayed ε-Shrinking for Faster Once-For-All Training ECCV 2024