conftrace_

low-rank projection

9 papers

Explore in graph

Also known as

LORP

Co-occurring keywords · papers mentioning both

model compression (3) error feedback (2) inference efficiency (2) memory efficiency (2) key-value memory (1) interactive retrieval (1) optimizer state (1) cascaded projection (1) latent space transformation (1) matryoshka learning (1)

Papers

CAST: Context-Aware Dynamic Latent Space Transformation for Interactive Text-to-Image Retrieval CVPR 2026 Gradient Weight-normalized Low-rank Projection for Efficient LLM Training AAAI 2025 LDAdam: Adaptive Optimization from Low-Dimensional Gradient Statistics ICLR 2025 MatryoshkaKV: Adaptive KV Compression via Trainable Orthogonal Projection ICLR 2025 Palu: KV-Cache Compression with Low-Rank Projection ICLR 2025 SEPARATE: A Simple Low-rank Projection for Gradient Compression in Modern Large-scale Model Training Process ICLR 2025 GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection ICML 2024 Linearizing Transformer with Key-Value Memory EMNLP 2022 Cascaded Projection: End-To-End Network Compression and Acceleration CVPR 2019