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 301–350 of 4891 papers

TitleStatusHype
TabMixer: advancing tabular data analysis with an enhanced MLP-mixer approachCode1
H3DE-Net: Efficient and Accurate 3D Landmark Detection in Medical ImagingCode1
Exploiting Deblurring Networks for Radiance FieldsCode1
Table-Critic: A Multi-Agent Framework for Collaborative Criticism and Refinement in Table ReasoningCode1
Reduced Order Modeling with Shallow Recurrent Decoder NetworksCode1
CalibQuant: 1-Bit KV Cache Quantization for Multimodal LLMsCode1
Medicine on the Edge: Comparative Performance Analysis of On-Device LLMs for Clinical ReasoningCode1
PTZ-Calib: Robust Pan-Tilt-Zoom Camera CalibrationCode1
InTAR: Inter-Task Auto-Reconfigurable Accelerator Design for High Data Volume Variation in DNNsCode1
Hi-End-MAE: Hierarchical encoder-driven masked autoencoders are stronger vision learners for medical image segmentationCode1
SelfElicit: Your Language Model Secretly Knows Where is the Relevant EvidenceCode1
Calibrating LLMs with Information-Theoretic Evidential Deep LearningCode1
Cached Multi-Lora Composition for Multi-Concept Image GenerationCode1
Activation-Informed Merging of Large Language ModelsCode1
FastKV: KV Cache Compression for Fast Long-Context Processing with Token-Selective PropagationCode1
MatIR: A Hybrid Mamba-Transformer Image Restoration ModelCode1
Return of the Encoder: Maximizing Parameter Efficiency for SLMsCode1
CFT-RAG: An Entity Tree Based Retrieval Augmented Generation Algorithm With Cuckoo FilterCode1
Finer-CAM: Spotting the Difference Reveals Finer Details for Visual ExplanationCode1
A Survey of World Models for Autonomous DrivingCode1
DualOpt: A Dual Divide-and-Optimize Algorithm for the Large-scale Traveling Salesman ProblemCode1
Poseidon: A ViT-based Architecture for Multi-Frame Pose Estimation with Adaptive Frame Weighting and Multi-Scale Feature FusionCode1
Flash Window Attention: speedup the attention computation for Swin TransformerCode1
DispFormer: Pretrained Transformer for Flexible Dispersion Curve Inversion from Global Synthesis to Regional ApplicationsCode1
CAMP: Collaborative Attention Model with Profiles for Vehicle Routing ProblemsCode1
KM-UNet KAN Mamba UNet for medical image segmentationCode1
Robust Self-Paced Hashing for Cross-Modal Retrieval with Noisy LabelsCode1
HCMA-UNet: A Hybrid CNN-Mamba UNet with Axial Self-Attention for Efficient Breast Cancer SegmentationCode1
TeLU Activation Function for Fast and Stable Deep LearningCode1
Underwater Image Restoration via Polymorphic Large Kernel CNNsCode1
LiRCDepth: Lightweight Radar-Camera Depth Estimation via Knowledge Distillation and Uncertainty GuidanceCode1
GaraMoSt: Parallel Multi-Granularity Motion and Structural Modeling for Efficient Multi-Frame Interpolation in DSA ImagesCode1
Rethinking Chain-of-Thought from the Perspective of Self-TrainingCode1
FM2S: Towards Spatially-Correlated Noise Modeling in Zero-Shot Fluorescence Microscopy Image DenoisingCode1
Dynamic-VLM: Simple Dynamic Visual Token Compression for VideoLLMCode1
ProtoOcc: Accurate, Efficient 3D Occupancy Prediction Using Dual Branch Encoder-Prototype Query DecoderCode1
Enhancing Scene Coordinate Regression with Efficient Keypoint Detection and Sequential InformationCode1
Multi-Behavior Recommendation with Personalized Directed Acyclic Behavior GraphsCode1
FlexDiT: Dynamic Token Density Control for Diffusion TransformerCode1
Neural Representation for Wireless Radiation Field Reconstruction: A 3D Gaussian Splatting ApproachCode1
NeRF and Gaussian Splatting SLAM in the WildCode1
Gracefully Filtering Backdoor Samples for Generative Large Language Models without RetrainingCode1
How Much Can Time-related Features Enhance Time Series Forecasting?Code1
Fréchet Radiomic Distance (FRD): A Versatile Metric for Comparing Medical Imaging DatasetsCode1
VICON: Vision In-Context Operator Networks for Multi-Physics Fluid Dynamics PredictionCode1
LDM-Morph: Latent diffusion model guided deformable image registrationCode1
Recursive Gaussian Process State Space ModelCode1
Local-Global Attention: An Adaptive Mechanism for Multi-Scale Feature IntegrationCode1
Large-scale moral machine experiment on large language modelsCode1
LSSInst: Improving Geometric Modeling in LSS-Based BEV Perception with Instance RepresentationCode1
Show:102550
← PrevPage 7 of 98Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ViTaLHamming Loss0.05—Unverified