SOTAVerified

Computational Efficiency

Methods and optimizations to reduce the computational resources (e.g., time, memory, or power) needed for training and inference in models. This involves techniques that streamline processing, optimize algorithms, or leverage hardware to enhance performance without compromising accuracy.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 376–400 of 4891 papers

TitleStatusHype
Fast ground penetrating radar dual-parameter full waveform inversion method accelerated by hybrid compilation of CUDA kernel function and PyTorchCode1
Anchor-based Large Language ModelsCode1
FastKV: KV Cache Compression for Fast Long-Context Processing with Token-Selective PropagationCode1
Efficient and Information-Preserving Future Frame Prediction and BeyondCode1
Fast Sequence-Based Embedding with Diffusion GraphsCode1
Fast TreeSHAP: Accelerating SHAP Value Computation for TreesCode1
featsel: A framework for benchmarking of feature selection algorithms and cost functionsCode1
Dynamic Multimodal FusionCode1
Dynamic Implicit Image Function for Efficient Arbitrary-Scale Image RepresentationCode1
Dynamic-VLM: Simple Dynamic Visual Token Compression for VideoLLMCode1
DynamicDet: A Unified Dynamic Architecture for Object DetectionCode1
Dynamic Clustering and Cluster Contrastive Learning for Unsupervised Person Re-identificationCode1
Dynamic Group Convolution for Accelerating Convolutional Neural NetworksCode1
EdgeRegNet: Edge Feature-based Multimodal Registration Network between Images and LiDAR Point CloudsCode1
A Non-autoregressive Multi-Horizon Flight Trajectory Prediction Framework with Gray Code RepresentationCode1
Embedding-Free Transformer with Inference Spatial Reduction for Efficient Semantic SegmentationCode1
DualOpt: A Dual Divide-and-Optimize Algorithm for the Large-scale Traveling Salesman ProblemCode1
Adaptive wavelet distillation from neural networks through interpretationsCode1
Focus on Local: Finding Reliable Discriminative Regions for Visual Place RecognitionCode1
AdaRank: Adaptive Rank Pruning for Enhanced Model MergingCode1
Dropout Q-Functions for Doubly Efficient Reinforcement LearningCode1
Enhancing Scene Coordinate Regression with Efficient Keypoint Detection and Sequential InformationCode1
Prompt Tuned Embedding Classification for Multi-Label Industry Sector AllocationCode1
Dual Prototype Evolving for Test-Time Generalization of Vision-Language ModelsCode1
AMD-Hummingbird: Towards an Efficient Text-to-Video ModelCode1
Show:102550
← PrevPage 16 of 196Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ViTaLHamming Loss0.05—Unverified