SOTAVerified

CPU

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 51–75 of 2231 papers

TitleStatusHype
A GPU-specialized Inference Parameter Server for Large-Scale Deep Recommendation ModelsCode3
Fast-MD: Fast Multi-Decoder End-to-End Speech Translation with Non-Autoregressive Hidden IntermediatesCode3
Observation-Centric SORT: Rethinking SORT for Robust Multi-Object TrackingCode3
Performance Analysis of Open Source Machine Learning Frameworks for Various Parameters in Single-Threaded and Multi-Threaded ModesCode3
ShadowKV: KV Cache in Shadows for High-Throughput Long-Context LLM InferenceCode3
Musika! Fast Infinite Waveform Music GenerationCode2
Multi-Stage Speech Bandwidth Extension with Flexible Sampling Rate ControlCode2
Neural Network Compression Framework for fast model inferenceCode2
MathOptAI.jl: Embed trained machine learning predictors into JuMP modelsCode2
Low-latency Real-time Voice Conversion on CPUCode2
MixFormerV2: Efficient Fully Transformer TrackingCode2
NAVIX: Scaling MiniGrid Environments with JAXCode2
Iterative Corresponding Geometry: Fusing Region and Depth for Highly Efficient 3D Tracking of Textureless ObjectsCode2
JaxMARL: Multi-Agent RL Environments and Algorithms in JAXCode2
Isaac Gym: High Performance GPU-Based Physics Simulation For Robot LearningCode2
JaxUED: A simple and useable UED library in JaxCode2
CAGRA: Highly Parallel Graph Construction and Approximate Nearest Neighbor Search for GPUsCode2
HLSTransform: Energy-Efficient Llama 2 Inference on FPGAs Via High Level SynthesisCode2
HybriMoE: Hybrid CPU-GPU Scheduling and Cache Management for Efficient MoE InferenceCode2
Breaking of brightness consistency in optical flow with a lightweight CNN networkCode2
ImMesh: An Immediate LiDAR Localization and Meshing FrameworkCode2
Lightweight and High-Fidelity End-to-End Text-to-Speech with Multi-Band Generation and Inverse Short-Time Fourier TransformCode2
Nix-TTS: Lightweight and End-to-End Text-to-Speech via Module-wise DistillationCode2
HeadInfer: Memory-Efficient LLM Inference by Head-wise OffloadingCode2
Ghost in the Minecraft: Generally Capable Agents for Open-World Environments via Large Language Models with Text-based Knowledge and MemoryCode2
Show:102550
← PrevPage 3 of 90Next →

No leaderboard results yet.