SOTAVerified

CPU

Papers

Showing 101150 of 2231 papers

TitleStatusHype
Deep Differentiable Logic Gate NetworksCode2
An efficient encoder-decoder architecture with top-down attention for speech separationCode2
On Efficient Reinforcement Learning for Full-length Game of StarCraft IICode2
Musika! Fast Infinite Waveform Music GenerationCode2
Delivering Document Conversion as a Cloud Service with High Throughput and ResponsivenessCode2
BMInf: An Efficient Toolkit for Big Model Inference and TuningCode2
Nix-TTS: Lightweight and End-to-End Text-to-Speech via Module-wise DistillationCode2
TGL: A General Framework for Temporal GNN Training on Billion-Scale GraphsCode2
Iterative Corresponding Geometry: Fusing Region and Depth for Highly Efficient 3D Tracking of Textureless ObjectsCode2
EvoJAX: Hardware-Accelerated NeuroevolutionCode2
Godot Reinforcement Learning AgentsCode2
RAVE: A variational autoencoder for fast and high-quality neural audio synthesisCode2
Isaac Gym: High Performance GPU-Based Physics Simulation For Robot LearningCode2
High-performance symbolic-numerics via multiple dispatchCode2
HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech SynthesisCode2
A Tensor Compiler for Unified Machine Learning Prediction ServingCode2
Efficient One-Pass End-to-End Entity Linking for QuestionsCode2
Towards Fast, Accurate and Stable 3D Dense Face AlignmentCode2
VoiceFilter-Lite: Streaming Targeted Voice Separation for On-Device Speech RecognitionCode2
Real Time Speech Enhancement in the Waveform DomainCode2
Neural Network Compression Framework for fast model inferenceCode2
Efficient Neural Audio SynthesisCode2
LIGHTHOUSE: Fast and precise distance to shoreline calculations from anywhere on earthCode1
ConsumerBench: Benchmarking Generative AI Applications on End-User DevicesCode1
TailorKV: A Hybrid Framework for Long-Context Inference via Tailored KV Cache OptimizationCode1
Why Not Replace? Sustaining Long-Term Visual Localization via Handcrafted-Learned Feature Collaboration on CPUCode1
SpecOffload: Unlocking Latent GPU Capacity for LLM Inference on Resource-Constrained DevicesCode1
Fast Differentiable Modal Simulation of Non-linear Strings, Membranes, and PlatesCode1
Morello: Compiling Fast Neural Networks with Dynamic Programming and Spatial CompressionCode1
Mesh-Learner: Texturing Mesh with Spherical HarmonicsCode1
Design and Implementation of an FPGA-Based Hardware Accelerator for TransformerCode1
DQO-MAP: Dual Quadrics Multi-Object mapping with Gaussian SplattingCode1
DuoDecoding: Hardware-aware Heterogeneous Speculative Decoding with Dynamic Multi-Sequence DraftingCode1
Two-stream Beats One-stream: Asymmetric Siamese Network for Efficient Visual TrackingCode1
LightFC-X: Lightweight Convolutional Tracker for RGB-X TrackingCode1
Dynamic Low-Rank Sparse Adaptation for Large Language ModelsCode1
Habitizing Diffusion Planning for Efficient and Effective Decision MakingCode1
Return of the Encoder: Maximizing Parameter Efficiency for SLMsCode1
Glinthawk: A Two-Tiered Architecture for Offline LLM InferenceCode1
NITRO: LLM Inference on Intel Laptop NPUsCode1
Real-time Identity Defenses against Malicious Personalization of Diffusion ModelsCode1
Expert-guided protein language models enable accurate and blazingly fast fitness predictionCode1
PKF: Probabilistic Data Association Kalman Filter for Multi-Object TrackingCode1
syren-new: Precise formulae for the linear and nonlinear matter power spectra with massive neutrinos and dynamical dark energyCode1
Octopus Inspired Optimization Algorithm: Multi-Level Structures and Parallel Computing StrategiesCode1
Large Language Model Inference Acceleration: A Comprehensive Hardware PerspectiveCode1
OATS: Outlier-Aware Pruning Through Sparse and Low Rank DecompositionCode1
LowFormer: Hardware Efficient Design for Convolutional Transformer BackbonesCode1
The Compressor-Retriever Architecture for Language Model OSCode1
Efficient Camera Exposure Control for Visual Odometry via Deep Reinforcement LearningCode1
Show:102550
← PrevPage 3 of 45Next →

No leaderboard results yet.