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 1541–1550 of 4891 papers

TitleStatusHype
DSMoE: Matrix-Partitioned Experts with Dynamic Routing for Computation-Efficient Dense LLMs—0
Revisiting Privacy, Utility, and Efficiency Trade-offs when Fine-Tuning Large Language Models—0
Minimal Ranks, Maximum Confidence: Parameter-efficient Uncertainty Quantification for LoRACode0
iMOVE: Instance-Motion-Aware Video Understanding—0
Symmetric Rank-One Quasi-Newton Methods for Deep Learning Using Cubic Regularization—0
IMTS-Mixer: Mixer-Networks for Irregular Multivariate Time Series Forecasting—0
Model-free system identification of surface ships in waves via Hankel dynamic mode decomposition with control—0
On the Query Complexity of Verifier-Assisted Language Generation—0
Collaborative Deterministic-Probabilistic Forecasting for Real-World Spatiotemporal Systems—0
Practical Topics in Optimization—0
Show:102550
← PrevPage 155 of 490Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ViTaLHamming Loss0.05—Unverified