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 391–400 of 4891 papers

TitleStatusHype
Cached Multi-Lora Composition for Multi-Concept Image GenerationCode1
An Efficient Memory-Augmented Transformer for Knowledge-Intensive NLP TasksCode1
Adaptive wavelet distillation from neural networks through interpretationsCode1
Consistent Accelerated Inference via Confident Adaptive TransformersCode1
FastKV: KV Cache Compression for Fast Long-Context Processing with Token-Selective PropagationCode1
Context is Gold to find the Gold Passage: Evaluating and Training Contextual Document EmbeddingsCode1
Fast Sequence-Based Embedding with Diffusion GraphsCode1
Prompt Tuned Embedding Classification for Multi-Label Industry Sector AllocationCode1
Federated Bayesian Optimization via Thompson SamplingCode1
Five A^+ Network: You Only Need 9K Parameters for Underwater Image EnhancementCode1
Show:102550
← PrevPage 40 of 490Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ViTaLHamming Loss0.05—Unverified