Efficient Computing

FFN-SkipLLM: A Hidden Gem for Autoregressive Decoding with Adaptive Feed Forward Skipping EMNLP 2024 FilterNet: Harnessing Frequency Filters for Time Series Forecasting NeurIPS 2024 FITS: Modeling Time Series with $10k$ Parameters ICLR 2024 FlashAttention-3: Fast and Accurate Attention with Asynchrony and Low-precision NeurIPS 2024 FlexiBO: A Decoupled Cost-Aware Multi-objective Optimization Approach for Deep Neural Networks (Abstract Reprint) AAAI 2024 GAIA: Rethinking Action Quality Assessment for AI-Generated Videos NeurIPS 2024 Gated Attention Coding for Training High-Performance and Efficient Spiking Neural Networks AAAI 2024 Generalizing Weather Forecast to Fine-grained Temporal Scales via Physics-AI Hybrid Modeling NeurIPS 2024 Generation Meets Verification: Accelerating Large Language Model Inference with Smart Parallel Auto-Correct Decoding ACL 2024 Graph-Structured Speculative Decoding ACL 2024 GSO-Net: Grid Surface Optimization via Learning Geometric Constraints AAAI 2024 Harder Task Needs More Experts: Dynamic Routing in MoE Models ACL 2024 HiFT: A Hierarchical Full Parameter Fine-Tuning Strategy EMNLP 2024 Homology Consistency Constrained Efficient Tuning for Vision-Language Models NeurIPS 2024 How Does Quantization Affect Multilingual LLMs? EMNLP 2024 HW-GPT-Bench: Hardware-Aware Architecture Benchmark for Language Models NeurIPS 2024 HybridNeRF: Efficient Neural Rendering via Adaptive Volumetric Surfaces CVPR 2024 IAPT: Instance-Aware Prompt Tuning for Large Language Models ACL 2024 IceFormer: Accelerated Inference with Long-Sequence Transformers on CPUs ICLR 2024 Improving the Adversarial Transferability of Vision Transformers with Virtual Dense Connection AAAI 2024 Improving Training Efficiency of Diffusion Models via Multi-Stage Framework and Tailored Multi-Decoder Architecture CVPR 2024 In2Core: Leveraging Influence Functions for Coreset Selection in Instruction Finetuning of Large Language Models EMNLP 2024 In-Context Former: Lightning-fast Compressing Context for Large Language Model EMNLP 2024 In Defense of Structural Sparse Adapters for Concurrent LLM Serving EMNLP 2024 InfiniPot: Infinite Context Processing on Memory-Constrained LLMs EMNLP 2024