SOTAVerified

GPU

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 2651–2700 of 5629 papers

TitleStatusHype
UpDLRM: Accelerating Personalized Recommendation using Real-World PIM Architecture—0
Sparse High Rank Adapters—0
GPU-Accelerated DCOPF using Gradient-Based OptimizationCode0
Under the Hood of Tabular Data Generation Models: Benchmarks with Extensive Tuning—0
Contraction rates for conjugate gradient and Lanczos approximate posteriors in Gaussian process regression—0
MCSD: An Efficient Language Model with Diverse Fusion—0
Multispectral Snapshot Image Registration Using Learned Cross Spectral Disparity Estimation and a Deep Guided Occlusion Reconstruction NetworkCode0
Endor: Hardware-Friendly Sparse Format for Offloaded LLM Inference—0
What Operations can be Performed Directly on Compressed Arrays, and with What Error?—0
VideoLLM-online: Online Video Large Language Model for Streaming Video—0
Compress then Serve: Serving Thousands of LoRA Adapters with Little Overhead—0
Optimized Speculative Sampling for GPU Hardware AcceleratorsCode0
CancerLLM: A Large Language Model in Cancer Domain—0
Bypass Back-propagation: Optimization-based Structural Pruning for Large Language Models via Policy Gradient—0
A Training-free Sub-quadratic Cost Transformer Model Serving Framework With Hierarchically Pruned Attention—0
Deep Symbolic Optimization for Combinatorial Optimization: Accelerating Node Selection by Discovering Potential HeuristicsCode0
Practical offloading for fine-tuning LLM on commodity GPU via learned sparse projectorsCode0
PixRO: Pixel-Distributed Rotational Odometry with Gaussian Belief Propagation—0
Modeling Ambient Scene Dynamics for Free-view Synthesis—0
Cognitively Inspired Energy-Based World Models—0
Toffee: Efficient Million-Scale Dataset Construction for Subject-Driven Text-to-Image Generation—0
LASER: Learning by Aligning Self-supervised Representations of Speech for Improving Content-related TasksCode0
ME-Switch: A Memory-Efficient Expert Switching Framework for Large Language Models—0
WonderWorld: Interactive 3D Scene Generation from a Single Image—0
XLand-100B: A Large-Scale Multi-Task Dataset for In-Context Reinforcement LearningCode0
ProTrain: Efficient LLM Training via Memory-Aware Techniques—0
ALPS: Improved Optimization for Highly Sparse One-Shot Pruning for Large Language Models—0
GraphFM: A Comprehensive Benchmark for Graph Foundation ModelCode0
VoxNeuS: Enhancing Voxel-Based Neural Surface Reconstruction via Gradient Interpolation—0
PreSto: An In-Storage Data Preprocessing System for Training Recommendation Models—0
Benchmarking and Boosting Radiology Report Generation for 3D High-Resolution Medical Images—0
Sustainable self-supervised learning for speech representations—0
Label-Looping: Highly Efficient Decoding for Transducers—0
Enhancing Large-Scale AI Training Efficiency: The C4 Solution for Real-Time Anomaly Detection and Communication Optimization—0
Speed of Light Exact Greedy Decoding for RNN-T Speech Recognition Models on GPU—0
ReDistill: Residual Encoded Distillation for Peak Memory Reduction—0
Quality-Diversity with Limited ResourcesCode0
Global Parameterization-based Texture Space Optimization—0
Zeroth-Order Fine-Tuning of LLMs with Extreme Sparsity—0
Searching Priors Makes Text-to-Video Synthesis Better—0
A Flexible Recursive Network for Video Stereo Matching Based on Residual EstimationCode0
A Comprehensive Library for Benchmarking Multi-class Visual Anomaly Detection—0
A Study of Optimizations for Fine-tuning Large Language Models—0
Speeding up Policy Simulation in Supply Chain RL—0
CE-NAS: An End-to-End Carbon-Efficient Neural Architecture Search Framework—0
GPU-Accelerated Rule Evaluation and Evolution—0
D-CPT Law: Domain-specific Continual Pre-Training Scaling Law for Large Language Models—0
OLoRA: Orthonormal Low-Rank Adaptation of Large Language Models—0
Advancing Supervised Local Learning Beyond Classification with Long-term Feature Bank—0
Multi-Objective Neural Architecture Search by Learning Search Space Partitions—0
Show:102550
← PrevPage 54 of 113Next →

No leaderboard results yet.