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 1–50 of 4891 papers

TitleStatusHype
TinyLlama: An Open-Source Small Language ModelCode11
LivePortrait: Efficient Portrait Animation with Stitching and Retargeting ControlCode11
PromptWizard: Task-Aware Prompt Optimization FrameworkCode7
Revisiting PCA for time series reduction in temporal dimensionCode7
Enhancing Fourier Neural Operators with Local Spatial FeaturesCode7
Muon is Scalable for LLM TrainingCode7
VMamba: Visual State Space ModelCode7
Mamba: Linear-Time Sequence Modeling with Selective State SpacesCode6
U-Net v2: Rethinking the Skip Connections of U-Net for Medical Image SegmentationCode6
RWKV: Reinventing RNNs for the Transformer EraCode6
MambaIRv2: Attentive State Space RestorationCode5
Comet: Fine-grained Computation-communication Overlapping for Mixture-of-ExpertsCode5
YOLOv13: Real-Time Object Detection with Hypergraph-Enhanced Adaptive Visual PerceptionCode5
CogView3: Finer and Faster Text-to-Image Generation via Relay DiffusionCode5
Exploring GLU Expansion Ratios: A Study of Structured Pruning in LLaMA-3.2 ModelsCode5
FireRedASR: Open-Source Industrial-Grade Mandarin Speech Recognition Models from Encoder-Decoder to LLM IntegrationCode5
Continuous Thought MachinesCode5
Video Depth Anything: Consistent Depth Estimation for Super-Long VideosCode5
A Convergent Single-Loop Algorithm for Relaxation of Gromov-Wasserstein in Graph DataCode4
T-MAC: CPU Renaissance via Table Lookup for Low-Bit LLM Deployment on EdgeCode4
RaDe-GS: Rasterizing Depth in Gaussian SplattingCode4
LLMC: Benchmarking Large Language Model Quantization with a Versatile Compression ToolkitCode4
AudioLDM: Text-to-Audio Generation with Latent Diffusion ModelsCode4
Mamba-UNet: UNet-Like Pure Visual Mamba for Medical Image SegmentationCode4
Vocos: Closing the gap between time-domain and Fourier-based neural vocoders for high-quality audio synthesisCode4
Universal and Extensible Language-Vision Models for Organ Segmentation and Tumor Detection from Abdominal Computed TomographyCode4
High-performance training and inference for deep equivariant interatomic potentialsCode4
Hierarchically Coherent Multivariate Mixture NetworksCode4
Partition Generative Modeling: Masked Modeling Without MasksCode4
On the limits of agency in agent-based modelsCode4
TorchRL: A data-driven decision-making library for PyTorchCode4
Time-MoE: Billion-Scale Time Series Foundation Models with Mixture of ExpertsCode4
TRIPS: Trilinear Point Splatting for Real-Time Radiance Field RenderingCode4
An Image is Worth 1/2 Tokens After Layer 2: Plug-and-Play Inference Acceleration for Large Vision-Language ModelsCode4
RL4CO: an Extensive Reinforcement Learning for Combinatorial Optimization BenchmarkCode4
On the Efficiency of NLP-Inspired Methods for Tabular Deep LearningCode3
Effects of charging and discharging capabilities on trade-offs between model accuracy and computational efficiency in pumped thermal electricity storageCode3
EMCAD: Efficient Multi-scale Convolutional Attention Decoding for Medical Image SegmentationCode3
NeuralOM: Neural Ocean Model for Subseasonal-to-Seasonal SimulationCode3
MoC: Mixtures of Text Chunking Learners for Retrieval-Augmented Generation SystemCode3
DUFOMap: Efficient Dynamic Awareness MappingCode3
MAPE-PPI: Towards Effective and Efficient Protein-Protein Interaction Prediction via Microenvironment-Aware Protein EmbeddingCode3
MetaDE: Evolving Differential Evolution by Differential EvolutionCode3
Nd-BiMamba2: A Unified Bidirectional Architecture for Multi-Dimensional Data ProcessingCode3
CoverM: Read alignment statistics for metagenomicsCode3
HyperSIGMA: Hyperspectral Intelligence Comprehension Foundation ModelCode3
Consistency Models Made EasyCode3
Human-like Episodic Memory for Infinite Context LLMsCode3
Is Mamba Effective for Time Series Forecasting?Code3
GSFusion: Online RGB-D Mapping Where Gaussian Splatting Meets TSDF FusionCode3
Show:102550
← PrevPage 1 of 98Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ViTaLHamming Loss0.05—Unverified