SOTAVerified

CPU

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 101–125 of 2231 papers

TitleStatusHype
HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech SynthesisCode2
High-performance symbolic-numerics via multiple dispatchCode2
HeadInfer: Memory-Efficient LLM Inference by Head-wise OffloadingCode2
RAVE: A variational autoencoder for fast and high-quality neural audio synthesisCode2
AdFlush: A Real-World Deployable Machine Learning Solution for Effective Advertisement and Web Tracker PreventionCode2
Real-time and Continuous Turn-taking Prediction Using Voice Activity ProjectionCode2
Run, Don't Walk: Chasing Higher FLOPS for Faster Neural NetworksCode2
SCNet: Sparse Compression Network for Music Source SeparationCode2
Ghost in the Minecraft: Generally Capable Agents for Open-World Environments via Large Language Models with Text-based Knowledge and MemoryCode2
FireANTs: Adaptive Riemannian Optimization for Multi-Scale Diffeomorphic MatchingCode2
Godot Reinforcement Learning AgentsCode2
HLSTransform: Energy-Efficient Llama 2 Inference on FPGAs Via High Level SynthesisCode2
Exponentially Faster Language ModellingCode2
EvoJAX: Hardware-Accelerated NeuroevolutionCode2
Enhancing Privacy in Federated Learning: Secure Aggregation for Real-World Healthcare ApplicationsCode2
Towards Fast, Accurate and Stable 3D Dense Face AlignmentCode2
evosax: JAX-based Evolution StrategiesCode2
tsdownsample: high-performance time series downsampling for scalable visualizationCode2
CAGRA: Highly Parallel Graph Construction and Approximate Nearest Neighbor Search for GPUsCode2
An efficient encoder-decoder architecture with top-down attention for speech separationCode2
Fast-Poly: A Fast Polyhedral Framework For 3D Multi-Object TrackingCode2
HybriMoE: Hybrid CPU-GPU Scheduling and Cache Management for Efficient MoE InferenceCode2
Accelerating Translational Image Registration for HDR Images on GPUCode1
Efficient neural networks for real-time modeling of analog dynamic range compressionCode1
Efficient Hyperparameter Optimization in Deep Learning Using a Variable Length Genetic AlgorithmCode1
Show:102550
← PrevPage 5 of 90Next →

No leaderboard results yet.