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 1021–1030 of 4891 papers

TitleStatusHype
Semantic Layered Embedding Diffusion in Large Language Models for Multi-Contextual Consistency—0
AI-Driven Secure Data Sharing: A Trustworthy and Privacy-Preserving Approach—0
RotateKV: Accurate and Robust 2-Bit KV Cache Quantization for LLMs via Outlier-Aware Adaptive Rotations—0
DER Hosting capacity for distribution networks: definitions, attributes, use-cases and challenges—0
Split-Merge: A Difference-based Approach for Dominant Eigenvalue Problem—0
Efficient and Interpretable Neural Networks Using Complex Lehmer Transform—0
Uni-Sign: Toward Unified Sign Language Understanding at ScaleCode2
CFT-RAG: An Entity Tree Based Retrieval Augmented Generation Algorithm With Cuckoo FilterCode1
ReInc: Scaling Training of Dynamic Graph Neural Networks—0
UDiTQC: U-Net-Style Diffusion Transformer for Quantum Circuit Synthesis—0
Show:102550
← PrevPage 103 of 490Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ViTaLHamming Loss0.05—Unverified