Efficient Computing

BiDM: Pushing the Limit of Quantization for Diffusion Models NeurIPS 2024 Block Transformer: Global-to-Local Language Modeling for Fast Inference NeurIPS 2024 BOLD: Boolean Logic Deep Learning NeurIPS 2024 Boosting Generalization in Parametric PDE Neural Solvers through Adaptive Conditioning NeurIPS 2024 Boosting Spike Camera Image Reconstruction from a Perspective of Dealing with Spike Fluctuations CVPR 2024 C3: High-Performance and Low-Complexity Neural Compression from a Single Image or Video CVPR 2024 Cache Me if You Can: Accelerating Diffusion Models through Block Caching CVPR 2024 CALANet: Cheap All-Layer Aggregation for Human Activity Recognition NeurIPS 2024 CAMixerSR: Only Details Need More "Attention" CVPR 2024 Cascade Speculative Drafting for Even Faster LLM Inference NeurIPS 2024 CE-NAS: An End-to-End Carbon-Efficient Neural Architecture Search Framework NeurIPS 2024 CHESS: Optimizing LLM Inference via Channel-Wise Thresholding and Selective Sparsification EMNLP 2024 Chunk, Align, Select: A Simple Long-sequence Processing Method for Transformers ACL 2024 CItruS: Chunked Instruction-aware State Eviction for Long Sequence Modeling EMNLP 2024 Clockwork Diffusion: Efficient Generation With Model-Step Distillation CVPR 2024 CMA: A Chromaticity Map Adapter for Robust Detection of Screen-Recapture Document Images CVPR 2024 Codec Avatar Studio: Paired Human Captures for Complete, Driveable, and Generalizable Avatars NeurIPS 2024 Codec-SUPERB: An In-Depth Analysis of Sound Codec Models ACL 2024 CodeM: Less Data Yields More Versatility via Ability Matrix ACL 2024 CoMERA: Computing- and Memory-Efficient Training via Rank-Adaptive Tensor Optimization NeurIPS 2024 Communication-Efficient Collaborative Perception via Information Filling with Codebook CVPR 2024 ConsistentEE: A Consistent and Hardness-Guided Early Exiting Method for Accelerating Language Models Inference AAAI 2024 Context-Driven Index Trimming: A Data Quality Perspective to Enhancing Precision of RALMs EMNLP 2024 COSMIC: Compress Satellite Image Efficiently via Diffusion Compensation NeurIPS 2024 Cost-Performance Optimization for Processing Low-Resource Language Tasks Using Commercial LLMs EMNLP 2024