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 876–900 of 4891 papers

TitleStatusHype
Symmetric Rank-One Quasi-Newton Methods for Deep Learning Using Cubic Regularization—0
Table-Critic: A Multi-Agent Framework for Collaborative Criticism and Refinement in Table ReasoningCode1
Without Paired Labeled Data: An End-to-End Self-Supervised Paradigm for UAV-View Geo-LocalizationCode2
On the Query Complexity of Verifier-Assisted Language Generation—0
IMTS-Mixer: Mixer-Networks for Irregular Multivariate Time Series Forecasting—0
iMOVE: Instance-Motion-Aware Video Understanding—0
Minimal Ranks, Maximum Confidence: Parameter-efficient Uncertainty Quantification for LoRACode0
Practical Topics in Optimization—0
Collaborative Deterministic-Probabilistic Forecasting for Real-World Spatiotemporal Systems—0
Don't Get Lost in the Trees: Streamlining LLM Reasoning by Overcoming Tree Search Exploration PitfallsCode0
Emergent functions of noise-driven spontaneous activity: Homeostatic maintenance of criticality and memory consolidation—0
CalibQuant: 1-Bit KV Cache Quantization for Multimodal LLMsCode1
RemInD: Remembering Anatomical Variations for Interpretable Domain Adaptive Medical Image Segmentation—0
Reduced Order Modeling with Shallow Recurrent Decoder NetworksCode1
Probabilistic Lexical Manifold Construction in Large Language Models via Hierarchical Vector Field Interpolation—0
HADL Framework for Noise Resilient Long-Term Time Series ForecastingCode0
GoRA: Gradient-driven Adaptive Low Rank Adaptation—0
Long-Range LiDAR Vehicle Detection Through Clustering and Classification for Autonomous Racing—0
MetaDE: Evolving Differential Evolution by Differential EvolutionCode3
E-MD3C: Taming Masked Diffusion Transformers for Efficient Zero-Shot Object Customization—0
Medicine on the Edge: Comparative Performance Analysis of On-Device LLMs for Clinical ReasoningCode1
Structured Convergence in Large Language Model Representations via Hierarchical Latent Space Folding—0
PTZ-Calib: Robust Pan-Tilt-Zoom Camera CalibrationCode1
Criteria-Aware Graph Filtering: Extremely Fast Yet Accurate Multi-Criteria RecommendationCode0
Data-Enabled Predictive Control for Flexible Spacecraft—0
Show:102550
← PrevPage 36 of 196Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ViTaLHamming Loss0.05—Unverified