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 681–690 of 4891 papers

TitleStatusHype
HDFlow: Enhancing LLM Complex Problem-Solving with Hybrid Thinking and Dynamic WorkflowsCode1
DnS: Distill-and-Select for Efficient and Accurate Video Indexing and RetrievalCode1
DragLoRA: Online Optimization of LoRA Adapters for Drag-based Image Editing in Diffusion ModelCode1
Contextualizing MLP-Mixers Spatiotemporally for Urban Data Forecast at ScaleCode1
DQO-MAP: Dual Quadrics Multi-Object mapping with Gaussian SplattingCode1
Not All Heads Matter: A Head-Level KV Cache Compression Method with Integrated Retrieval and ReasoningCode1
HADAS: Hardware-Aware Dynamic Neural Architecture Search for Edge Performance ScalingCode1
BUFFER: Balancing Accuracy, Efficiency, and Generalizability in Point Cloud RegistrationCode1
Dynamic Cardiac MRI Reconstruction Using Combined Tensor Nuclear Norm and Casorati Matrix Nuclear Norm RegularizationsCode1
HAAQI-Net: A Non-intrusive Neural Music Audio Quality Assessment Model for Hearing AidsCode1
Show:102550
← PrevPage 69 of 490Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ViTaLHamming Loss0.05—Unverified