Efficient Computing

Speech Boosting: Low-Latency Live Speech Enhancement for TWS Earbuds Interspeech 2024 Speech Prefix-Tuning with RNNT Loss for Improving LLM Predictions Interspeech 2024 SPEED: Experimental Design for Policy Evaluation in Linear Heteroscedastic Bandits AISTATS 2024 Speeding up NAS with Adaptive Subset Selection AutoML 2024 SpeedLoader: An I/O efficient scheme for heterogeneous and distributed LLM operation NeurIPS 2024 Spherical Pseudo-Cylindrical Representation for Omnidirectional Image Super-resolution AAAI 2024 SpikedAttention: Training-Free and Fully Spike-Driven Transformer-to-SNN Conversion with Winner-Oriented Spike Shift for Softmax Operation NeurIPS 2024 Spike-driven Transformer V2: Meta Spiking Neural Network Architecture Inspiring the Design of Next-generation Neuromorphic Chips ICLR 2024 SpikeLM: Towards General Spike-Driven Language Modeling via Elastic Bi-Spiking Mechanisms ICML 2024 SpikePoint: An Efficient Point-based Spiking Neural Network for Event Cameras Action Recognition ICLR 2024 SpikeZIP-TF: Conversion is All You Need for Transformer-based SNN ICML 2024 Spiking Transformer with Experts Mixture NeurIPS 2024 Split-Ensemble: Efficient OOD-aware Ensemble via Task and Model Splitting ICML 2024 SPP: Sparsity-Preserved Parameter-Efficient Fine-Tuning for Large Language Models ICML 2024 SpQR: A Sparse-Quantized Representation for Near-Lossless LLM Weight Compression ICLR 2024 Sprout: Green Generative AI with Carbon-Efficient LLM Inference EMNLP 2024 SqueezeLLM: Dense-and-Sparse Quantization ICML 2024 SS1: Accelerating Inference with Fast and Expressive Sketch Structured Transform NeurIPS 2024 S-STE: Continuous Pruning Function for Efficient 2:4 Sparse Pre-training NeurIPS 2024 StablePrompt : Automatic Prompt Tuning using Reinforcement Learning for Large Language Model EMNLP 2024 StableToolBench: Towards Stable Large-Scale Benchmarking on Tool Learning of Large Language Models ACL 2024 Stacking Your Transformers: A Closer Look at Model Growth for Efficient LLM Pre-Training NeurIPS 2024 StackSight: Unveiling WebAssembly through Large Language Models and Neurosymbolic Chain-of-Thought Decompilation ICML 2024 START: A Generalized State Space Model with Saliency-Driven Token-Aware Transformation NeurIPS 2024 State-Free Inference of State-Space Models: The *Transfer Function* Approach ICML 2024