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 2141–2150 of 4891 papers

TitleStatusHype
Consistency Calibration: Improving Uncertainty Calibration via Consistency among Perturbed Neighbors—0
Expected Sliced Transport Plans—0
EPS-MoE: Expert Pipeline Scheduler for Cost-Efficient MoE Inference—0
The Best of Both Worlds: Bridging Quality and Diversity in Data Selection with Bipartite Graph—0
The Moral Case for Using Language Model Agents for Recommendation—0
Holistic Physics Solver: Learning PDEs in a Unified Spectral-Physical Space—0
Rethinking Graph Transformer Architecture Design for Node Classification—0
Improving Bias in Facial Attribute Classification: A Combined Impact of KL Divergence induced Loss Function and Dual Attention—0
OMCAT: Omni Context Aware Transformer—0
Beyond Sequence: Impact of Geometric Context for RNA Property Prediction—0
Show:102550
← PrevPage 215 of 490Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ViTaLHamming Loss0.05—Unverified