SOTAVerified

GPU

Papers

Showing 20762100 of 5629 papers

TitleStatusHype
Ultra-Long Sequence Distributed Transformer0
Augmentation is AUtO-Net: Augmentation-Driven Contrastive Multiview Learning for Medical Image Segmentation0
Performance Optimization of Deep Learning Sparse Matrix Kernels on Intel Max Series GPU0
Zero Coordinate Shift: Whetted Automatic Differentiation for Physics-informed Operator LearningCode0
A Two-Step Framework for Multi-Material Decomposition of Dual Energy Computed Tomography from Projection Domain0
LoRA Fine-tuning Efficiently Undoes Safety Training in Llama 2-Chat 70B0
In Search of Lost Online Test-time Adaptation: A SurveyCode1
StairNet: Visual Recognition of Stairs for Human-Robot Locomotion0
Network Contention-Aware Cluster Scheduling with Reinforcement LearningCode1
DiffusionVID: Denoising Object Boxes with Spatio-temporal Conditioning for Video Object DetectionCode1
Learning to love diligent trolls: Accounting for rater effects in the dialogue safety taskCode0
FetusMapV2: Enhanced Fetal Pose Estimation in 3D Ultrasound0
Prediction of Effective Elastic Moduli of Rocks using Graph Neural NetworksCode1
PolyThrottle: Energy-efficient Neural Network Inference on Edge Devices0
Bespoke Solvers for Generative Flow Models0
SiDA-MoE: Sparsity-Inspired Data-Aware Serving for Efficient and Scalable Large Mixture-of-Experts ModelsCode1
Atom: Low-bit Quantization for Efficient and Accurate LLM ServingCode2
The Synergy of Speculative Decoding and Batching in Serving Large Language Models0
Punica: Multi-Tenant LoRA ServingCode3
OpenDMC: An Open-Source Library and Performance Evaluation for Deep-learning-based Multi-frame CompressionCode0
FP8-LM: Training FP8 Large Language ModelsCode2
LLMSTEP: LLM proofstep suggestions in LeanCode1
Real-Time Neural Materials using Block-Compressed Features0
PockEngine: Sparse and Efficient Fine-tuning in a Pocket0
TorchSparse++: Efficient Training and Inference Framework for Sparse Convolution on GPUsCode3
Show:102550
← PrevPage 84 of 226Next →

No leaderboard results yet.