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 931–940 of 4891 papers

TitleStatusHype
Attention Is Not Always the Answer: Optimizing Voice Activity Detection with Simple Feature Fusion—0
FreqPolicy: Frequency Autoregressive Visuomotor Policy with Continuous Tokens—0
Quantization-based Bounds on the Wasserstein Metric—0
Fighting Fire with Fire (F3): A Training-free and Efficient Visual Adversarial Example Purification Method in LVLMs—0
Beyond Attention: Learning Spatio-Temporal Dynamics with Emergent Interpretable Topologies—0
LD-RPMNet: Near-Sensor Diagnosis for Railway Point Machines—0
Learning to Upsample and Upmix Audio in the Latent Domain—0
Label-shift robust federated feature screening for high-dimensional classification—0
Latent Wavelet Diffusion: Enabling 4K Image Synthesis for Free—0
Neural Network-based Information-Theoretic Transceivers for High-Order Modulation Schemes—0
Show:102550
← PrevPage 94 of 490Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ViTaLHamming Loss0.05—Unverified