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 251–300 of 4891 papers

TitleStatusHype
Fast Point TransformerCode1
Calibrating LLMs with Information-Theoretic Evidential Deep LearningCode1
CAMP: Collaborative Attention Model with Profiles for Vehicle Routing ProblemsCode1
FM2S: Towards Spatially-Correlated Noise Modeling in Zero-Shot Fluorescence Microscopy Image DenoisingCode1
Fast Sequence Based Embedding with Diffusion GraphsCode1
Cached Multi-Lora Composition for Multi-Concept Image GenerationCode1
Fast Kernel Scene FlowCode1
CalibQuant: 1-Bit KV Cache Quantization for Multimodal LLMsCode1
3D Gaussian Splatting against Moving Objects for High-Fidelity Street Scene ReconstructionCode1
Complex Neural Network based Joint AoA and AoD Estimation for Bistatic ISACCode1
FastKV: KV Cache Compression for Fast Long-Context Processing with Token-Selective PropagationCode1
Fast Sequence-Based Embedding with Diffusion GraphsCode1
Fine-Grained Pillar Feature Encoding Via Spatio-Temporal Virtual Grid for 3D Object DetectionCode1
From continuous-time formulations to discretization schemes: tensor trains and robust regression for BSDEs and parabolic PDEsCode1
α-DPO: Adaptive Reward Margin is What Direct Preference Optimization NeedsCode1
Fast and Low-Cost Genomic Foundation Models via Outlier RemovalCode1
Fast and Interpretable 2D Homography Decomposition: Similarity-Kernel-Similarity and Affine-Core-Affine TransformationsCode1
Fast, Expressive SE(n) Equivariant Networks through Weight-Sharing in Position-Orientation SpaceCode1
Boosting Light-Weight Depth Estimation Via Knowledge DistillationCode1
Fast ABC-Boost: A Unified Framework for Selecting the Base Class in Multi-Class ClassificationCode1
FAMO: Fast Adaptive Multitask OptimizationCode1
Fast and Accurate Entity Recognition with Iterated Dilated ConvolutionsCode1
Fast Fishing: Approximating BAIT for Efficient and Scalable Deep Active Image ClassificationCode1
Efficient Learning of Mesh-Based Physical Simulation with BSMS-GNNCode1
A Deep Reinforcement Learning Approach for Solving the Traveling Salesman Problem with DroneCode1
Facial Emotion Recognition: State of the Art Performance on FER2013Code1
ACEnet: Anatomical Context-Encoding Network for Neuroanatomy SegmentationCode1
A practical PINN framework for multi-scale problems with multi-magnitude loss termsCode1
Birdie: Advancing State Space Models with Reward-Driven Objectives and CurriculaCode1
FADRM: Fast and Accurate Data Residual Matching for Dataset DistillationCode1
Exploring Quality and Generalizability in Parameterized Neural Audio EffectsCode1
ExpoMamba: Exploiting Frequency SSM Blocks for Efficient and Effective Image EnhancementCode1
BUFFER: Balancing Accuracy, Efficiency, and Generalizability in Point Cloud RegistrationCode1
Exploring _0 Sparsification for Inference-free Sparse RetrieversCode1
EXTENDING CONDITIONAL CONVOLUTION STRUCTURES FOR ENHANCING MULTITASKING CONTINUAL LEARNINGCode1
Faith-Shap: The Faithful Shapley Interaction IndexCode1
Towards Reliable Medical Image Segmentation by utilizing Evidential Calibrated UncertaintyCode1
Beyond The Rainbow: High Performance Deep Reinforcement Learning on a Desktop PCCode1
Evidential Deep Learning: Enhancing Predictive Uncertainty Estimation for Earth System Science ApplicationsCode1
Bidirectional Recurrence for Cardiac Motion Tracking with Gaussian Process Latent CodingCode1
Structured Multi-Track Accompaniment Arrangement via Style Prior ModellingCode1
Event-based Video Reconstruction via Potential-assisted Spiking Neural NetworkCode1
EViT: An Eagle Vision Transformer with Bi-Fovea Self-AttentionCode1
BetterNet: An Efficient CNN Architecture with Residual Learning and Attention for Precision Polyp SegmentationCode1
Accel-GCN: High-Performance GPU Accelerator Design for Graph Convolution NetworksCode1
Estimating Koopman operators with sketching to provably learn large scale dynamical systemsCode1
Benchmarking the Robustness of Spatial-Temporal Models Against CorruptionsCode1
2D-TPE: Two-Dimensional Positional Encoding Enhances Table Understanding for Large Language ModelsCode1
Estimating the Optimal Covariance with Imperfect Mean in Diffusion Probabilistic ModelsCode1
Exploiting Deblurring Networks for Radiance FieldsCode1
Show:102550
← PrevPage 6 of 98Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ViTaLHamming Loss0.05—Unverified