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 1601–1610 of 4891 papers

TitleStatusHype
Self-Data Distillation for Recovering Quality in Pruned Large Language Models—0
Generalized Group Data Attribution—0
SimBa: Simplicity Bias for Scaling Up Parameters in Deep Reinforcement LearningCode2
WGFormer: An SE(3)-Transformer Driven by Wasserstein Gradient Flows for Molecular Ground-State Conformation Prediction—0
Dualformer: Controllable Fast and Slow Thinking by Learning with Randomized Reasoning Traces—0
Retrieval Instead of Fine-tuning: A Retrieval-based Parameter Ensemble for Zero-shot Learning—0
Prompt Tuning for Audio Deepfake Detection: Computationally Efficient Test-time Domain Adaptation with Limited Target DatasetCode1
COrAL: Order-Agnostic Language Modeling for Efficient Iterative RefinementCode0
POPoS: Improving Efficient and Robust Facial Landmark Detection with Parallel Optimal Position SearchCode0
pLDDT-Predictor: High-speed Protein Screening Using Transformer and ESM2Code0
Show:102550
← PrevPage 161 of 490Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ViTaLHamming Loss0.05—Unverified