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 451–500 of 4891 papers

TitleStatusHype
AMD-Hummingbird: Towards an Efficient Text-to-Video ModelCode1
Discriminative Co-Saliency and Background Mining Transformer for Co-Salient Object DetectionCode1
CalibQuant: 1-Bit KV Cache Quantization for Multimodal LLMsCode1
Fully Attentional Network for Semantic SegmentationCode1
BUFFER: Balancing Accuracy, Efficiency, and Generalizability in Point Cloud RegistrationCode1
From continuous-time formulations to discretization schemes: tensor trains and robust regression for BSDEs and parabolic PDEsCode1
Calibrating LLMs with Information-Theoretic Evidential Deep LearningCode1
Adapting LLaMA Decoder to Vision TransformerCode1
From NeRFLiX to NeRFLiX++: A General NeRF-Agnostic Restorer ParadigmCode1
DnS: Distill-and-Select for Efficient and Accurate Video Indexing and RetrievalCode1
MatIR: A Hybrid Mamba-Transformer Image Restoration ModelCode1
MATS: An Interpretable Trajectory Forecasting Representation for Planning and ControlCode1
DQO-MAP: Dual Quadrics Multi-Object mapping with Gaussian SplattingCode1
Anytime Sampling for Autoregressive Models via Ordered AutoencodingCode1
A machine learning-based viscoelastic-viscoplastic model for epoxy nanocomposites with moisture contentCode1
DragLoRA: Online Optimization of LoRA Adapters for Drag-based Image Editing in Diffusion ModelCode1
FM2S: Towards Spatially-Correlated Noise Modeling in Zero-Shot Fluorescence Microscopy Image DenoisingCode1
Dual Prototype Evolving for Test-Time Generalization of Vision-Language ModelsCode1
M3-Jepa: Multimodal Alignment via Multi-directional MoE based on the JEPA frameworkCode1
MetaSeg: MetaFormer-based Global Contexts-aware Network for Efficient Semantic SegmentationCode1
Boosting Light-Weight Depth Estimation Via Knowledge DistillationCode1
Focus on Local: Finding Reliable Discriminative Regions for Visual Place RecognitionCode1
FlexDiT: Dynamic Token Density Control for Diffusion TransformerCode1
A Pose-only Solution to Visual Reconstruction and NavigationCode1
A Non-autoregressive Multi-Horizon Flight Trajectory Prediction Framework with Gray Code RepresentationCode1
Dynamic Clustering and Cluster Contrastive Learning for Unsupervised Person Re-identificationCode1
Dynamic Group Convolution for Accelerating Convolutional Neural NetworksCode1
Dynamic Implicit Image Function for Efficient Arbitrary-Scale Image RepresentationCode1
CAMP: Collaborative Attention Model with Profiles for Vehicle Routing ProblemsCode1
FocusTrack: A Self-Adaptive Local Sampling Algorithm for Efficient Anti-UAV TrackingCode1
Model Editing by Standard Fine-TuningCode1
Model Predictive Control for Signal Temporal Logic Specifications with Time Interval DecompositionCode1
FViT: A Focal Vision Transformer with Gabor FilterCode1
Improved Protein-ligand Binding Affinity Prediction with Structure-Based Deep Fusion InferenceCode1
Fine-tuning a Large Language Model for Automating Computational Fluid Dynamics SimulationsCode1
Fine-Grained Pillar Feature Encoding Via Spatio-Temporal Virtual Grid for 3D Object DetectionCode1
Efficient and Information-Preserving Future Frame Prediction and BeyondCode1
MotionBEV: Attention-Aware Online LiDAR Moving Object Segmentation with Bird's Eye View based Appearance and Motion FeaturesCode1
Efficient and Accurate Pneumonia Detection Using a Novel Multi-Scale Transformer ApproachCode1
Efficient and Compact Convolutional Neural Network Architectures for Non-temporal Real-time Fire DetectionCode1
FilterTS: Comprehensive Frequency Filtering for Multivariate Time Series ForecastingCode1
MRI super-resolution reconstruction using efficient diffusion probabilistic model with residual shiftingCode1
MSFMamba: Multi-Scale Feature Fusion State Space Model for Multi-Source Remote Sensing Image ClassificationCode1
MT-TransUNet: Mediating Multi-Task Tokens in Transformers for Skin Lesion Segmentation and ClassificationCode1
Finer-CAM: Spotting the Difference Reveals Finer Details for Visual ExplanationCode1
Efficient Multi-agent Reinforcement Learning by PlanningCode1
A prediction and behavioural analysis of machine learning methods for modelling travel mode choiceCode1
FedPop: Federated Population-based Hyperparameter TuningCode1
FedSSA: Semantic Similarity-based Aggregation for Efficient Model-Heterogeneous Personalized Federated LearningCode1
A new computationally efficient algorithm to solve Feature Selection for Functional Data Classification in high-dimensional spacesCode1
Show:102550
← PrevPage 10 of 98Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ViTaLHamming Loss0.05—Unverified