Efficient Computing

Preparing Lessons for Progressive Training on Language Models AAAI 2024 PRoLoRA: Partial Rotation Empowers More Parameter-Efficient LoRA ACL 2024 Provable Tempered Overfitting of Minimal Nets and Typical Nets NeurIPS 2024 PyramidInfer: Pyramid KV Cache Compression for High-throughput LLM Inference ACL 2024 QKFormer: Hierarchical Spiking Transformer using Q-K Attention NeurIPS 2024 QTIP: Quantization with Trellises and Incoherence Processing NeurIPS 2024 Real-time Core-Periphery Guided ViT with Smart Data Layout Selection on Mobile Devices NeurIPS 2024 Reparameterized Multi-Resolution Convolutions for Long Sequence Modelling NeurIPS 2024 Retaining Key Information under High Compression Ratios: Query-Guided Compressor for LLMs ACL 2024 Rethinking Memory and Communication Costs for Efficient Data Parallel Training of Large Language Models NeurIPS 2024 RevMUX: Data Multiplexing with Reversible Adapters for Efficient LLM Batch Inference EMNLP 2024 RL-SeqISP: Reinforcement Learning-Based Sequential Optimization for Image Signal Processing AAAI 2024 Satformer: Accurate and Robust Traffic Data Estimation for Satellite Networks NeurIPS 2024 Searching for Efficient Linear Layers over a Continuous Space of Structured Matrices NeurIPS 2024 SEA: Sparse Linear Attention with Estimated Attention Mask ICLR 2024 SeTAR: Out-of-Distribution Detection with Selective Low-Rank Approximation NeurIPS 2024 SGLang: Efficient Execution of Structured Language Model Programs NeurIPS 2024 SIRIUS : Contexual Sparisty with Correction for Efficient LLMs NeurIPS 2024 Slack-Free Spiking Neural Network Formulation for Hypergraph Minimum Vertex Cover NeurIPS 2024 SnapKV: LLM Knows What You are Looking for Before Generation NeurIPS 2024 Speculative Decoding with CTC-based Draft Model for LLM Inference Acceleration NeurIPS 2024 SpikedAttention: Training-Free and Fully Spike-Driven Transformer-to-SNN Conversion with Winner-Oriented Spike Shift for Softmax Operation NeurIPS 2024 Spiking Token Mixer: An event-driven friendly Former structure for spiking neural networks NeurIPS 2024 Stepping Forward on the Last Mile NeurIPS 2024 StreamingDialogue: Prolonged Dialogue Learning via Long Context Compression with Minimal Losses NeurIPS 2024