Skip to content
conftrace_

activation compression

7 papers

Explore in graph

Co-occurring keywords · papers mentioning both

memory efficiency (3) memory-efficient training (2) memory optimization (2) transformer model (1) graph neural network (1) stochastic gradient descent convergence (1) deep neural network training (1) rank-1 projection (1) lossy compression (1) key-value cache (1)

Papers

Long Context Compression with Activation Beacon ICLR 2025 ALAM: Averaged Low-Precision Activation for Memory-Efficient Training of Transformer Models ICLR 2024 VeLoRA: Memory Efficient Training using Rank-1 Sub-Token Projections NeurIPS 2024 DIVISION: Memory Efficient Training via Dual Activation Precision ICML 2023 EXACT: Scalable Graph Neural Networks Training via Extreme Activation Compression ICLR 2022 GACT: Activation Compressed Training for Generic Network Architectures ICML 2022 AC-GC: Lossy Activation Compression with Guaranteed Convergence NeurIPS 2021