conftrace_

activation caching

3 papers

Explore in graph

Co-occurring keywords · papers mentioning both

embedding recycling (1) bitrate optimization (1) large language model (1) neural image compression (1) contextualized embedding (1) gradient checkpointing (1) bidirectional transformer (1) masked token prediction (1) training acceleration (1) inference acceleration (1)

Papers

Forward Knows Efficient Backward Path: Saliency-Guided Memory-Efficient Fine-tuning of Large Language Models ACL 2025 Embedding Recycling for Language Models EACL 2023 M2T: Masking Transformers Twice for Faster Decoding ICCV 2023