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 276–300 of 4891 papers

TitleStatusHype
InternVL-X: Advancing and Accelerating InternVL Series with Efficient Visual Token CompressionCode1
VADMamba: Exploring State Space Models for Fast Video Anomaly DetectionCode1
Siformer: Feature-isolated Transformer for Efficient Skeleton-based Sign Language RecognitionCode1
Language Model Uncertainty Quantification with Attention ChainCode1
AMD-Hummingbird: Towards an Efficient Text-to-Video ModelCode1
EdgeRegNet: Edge Feature-based Multimodal Registration Network between Images and LiDAR Point CloudsCode1
TriLiteNet: Lightweight Model for Multi-Task Visual PerceptionCode1
GS-I^3: Gaussian Splatting for Surface Reconstruction from Illumination-Inconsistent ImagesCode1
3D Gaussian Splatting against Moving Objects for High-Fidelity Street Scene ReconstructionCode1
MMS-LLaMA: Efficient LLM-based Audio-Visual Speech Recognition with Minimal Multimodal Speech TokensCode1
CoLLMLight: Cooperative Large Language Model Agents for Network-Wide Traffic Signal ControlCode1
STEAD: Spatio-Temporal Efficient Anomaly Detection for Time and Compute Sensitive ApplicationsCode1
SEAP: Training-free Sparse Expert Activation Pruning Unlock the Brainpower of Large Language ModelsCode1
M^3amba: CLIP-driven Mamba Model for Multi-modal Remote Sensing ClassificationCode1
FastMap: Fast Queries Initialization Based Vectorized HD Map Reconstruction FrameworkCode1
DiRe-JAX: A JAX based Dimensionality Reduction Algorithm for Large-scale DataCode1
Small but Mighty: Enhancing Time Series Forecasting with Lightweight LLMsCode1
DQO-MAP: Dual Quadrics Multi-Object mapping with Gaussian SplattingCode1
From Claims to Evidence: A Unified Framework and Critical Analysis of CNN vs. Transformer vs. Mamba in Medical Image SegmentationCode1
MRI super-resolution reconstruction using efficient diffusion probabilistic model with residual shiftingCode1
TAET: Two-Stage Adversarial Equalization Training on Long-Tailed DistributionsCode1
Long-Context Inference with Retrieval-Augmented Speculative DecodingCode1
PrimeK-Net: Multi-scale Spectral Learning via Group Prime-Kernel Convolutional Neural Networks for Single Channel Speech EnhancementCode1
VesselSAM: Leveraging SAM for Aortic Vessel Segmentation with AtrousLoRACode1
A Reverse Mamba Attention Network for Pathological Liver SegmentationCode1
Show:102550
← PrevPage 12 of 196Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ViTaLHamming Loss0.05—Unverified