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 311–320 of 4891 papers

TitleStatusHype
SelfElicit: Your Language Model Secretly Knows Where is the Relevant EvidenceCode1
Calibrating LLMs with Information-Theoretic Evidential Deep LearningCode1
Cached Multi-Lora Composition for Multi-Concept Image GenerationCode1
Activation-Informed Merging of Large Language ModelsCode1
FastKV: KV Cache Compression for Fast Long-Context Processing with Token-Selective PropagationCode1
MatIR: A Hybrid Mamba-Transformer Image Restoration ModelCode1
Return of the Encoder: Maximizing Parameter Efficiency for SLMsCode1
CFT-RAG: An Entity Tree Based Retrieval Augmented Generation Algorithm With Cuckoo FilterCode1
A Survey of World Models for Autonomous DrivingCode1
Finer-CAM: Spotting the Difference Reveals Finer Details for Visual ExplanationCode1
Show:102550
← PrevPage 32 of 490Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ViTaLHamming Loss0.05—Unverified