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 21–30 of 4891 papers

TitleStatusHype
TorchRL: A data-driven decision-making library for PyTorchCode4
RL4CO: an Extensive Reinforcement Learning for Combinatorial Optimization BenchmarkCode4
A Convergent Single-Loop Algorithm for Relaxation of Gromov-Wasserstein in Graph DataCode4
AudioLDM: Text-to-Audio Generation with Latent Diffusion ModelsCode4
Hierarchically Coherent Multivariate Mixture NetworksCode4
TRIPS: Trilinear Point Splatting for Real-Time Radiance Field RenderingCode4
On the limits of agency in agent-based modelsCode4
High-performance training and inference for deep equivariant interatomic potentialsCode4
An Image is Worth 1/2 Tokens After Layer 2: Plug-and-Play Inference Acceleration for Large Vision-Language ModelsCode4
Partition Generative Modeling: Masked Modeling Without MasksCode4
Show:102550
← PrevPage 3 of 490Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ViTaLHamming Loss0.05—Unverified