SOTAVerified

GPU

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1551–1600 of 5629 papers

TitleStatusHype
MiniGPT-3D: Efficiently Aligning 3D Point Clouds with Large Language Models using 2D PriorsCode2
Clover: Regressive Lightweight Speculative Decoding with Sequential KnowledgeCode0
A Comprehensive Survey of Dynamic Graph Neural Networks: Models, Frameworks, Benchmarks, Experiments and Challenges—0
Streamlining Image Editing with Layered Diffusion Brushes—0
Extending Llama-3's Context Ten-Fold Overnight—0
Bypassing Skip-Gram Negative Sampling: Dimension Regularization as a More Efficient Alternative for Graph Embeddings—0
GS-LRM: Large Reconstruction Model for 3D Gaussian Splatting—0
MicroDreamer: Efficient 3D Generation in 20 Seconds by Score-based Iterative ReconstructionCode2
LoRA Land: 310 Fine-tuned LLMs that Rival GPT-4, A Technical ReportCode1
HLSTransform: Energy-Efficient Llama 2 Inference on FPGAs Via High Level SynthesisCode2
Multi-Page Document Visual Question Answering using Self-Attention Scoring MechanismCode0
CoSense3D: an Agent-based Efficient Learning Framework for Collective PerceptionCode1
Mamba-FETrack: Frame-Event Tracking via State Space ModelCode4
Deep Learning for Low-Latency, Quantum-Ready RF Sensing—0
Child Speech Recognition in Human-Robot Interaction: Problem Solved?—0
Exploring Pre-trained General-purpose Audio Representations for Heart Murmur Detection—0
Andes: Defining and Enhancing Quality-of-Experience in LLM-Based Text Streaming ServicesCode3
NeRF-XL: Scaling NeRFs with Multiple GPUs—0
BASS: Batched Attention-optimized Speculative Sampling—0
CORM: Cache Optimization with Recent Message for Large Language Model Inference—0
GPU-RANC: A CUDA Accelerated Simulation Framework for Neuromorphic Architectures—0
CutDiffusion: A Simple, Fast, Cheap, and Strong Diffusion Extrapolation MethodCode1
CNN-Based Equalization for Communications: Achieving Gigabit Throughput with a Flexible FPGA Hardware Architecture—0
Mélange: Cost Efficient Large Language Model Serving by Exploiting GPU HeterogeneityCode1
SnapKV: LLM Knows What You are Looking for Before GenerationCode3
Apodotiko: Enabling Efficient Serverless Federated Learning in Heterogeneous Environments—0
MixLoRA: Enhancing Large Language Models Fine-Tuning with LoRA-based Mixture of ExpertsCode3
STROOBnet Optimization via GPU-Accelerated Proximal Recurrence Strategies—0
GaussianTalker: Speaker-specific Talking Head Synthesis via 3D Gaussian Splatting—0
Accelerating Image Generation with Sub-path Linear Approximation Model—0
Turbo-CF: Matrix Decomposition-Free Graph Filtering for Fast RecommendationCode0
Evaluating Retrieval Quality in Retrieval-Augmented GenerationCode1
On-board classification of underwater images using hybrid classical-quantum CNN based method—0
Towards Universal Performance Modeling for Machine Learning Training on Multi-GPU Platforms—0
Scalable Data Assimilation with Message PassingCode0
RAGCache: Efficient Knowledge Caching for Retrieval-Augmented Generation—0
Warped Time Series Anomaly Detection—0
Partial Large Kernel CNNs for Efficient Super-ResolutionCode2
TriForce: Lossless Acceleration of Long Sequence Generation with Hierarchical Speculative DecodingCode3
FastFace: Fast-converging Scheduler for Large-scale Face Recognition Training with One GPUCode0
LLMem: Estimating GPU Memory Usage for Fine-Tuning Pre-Trained LLMsCode1
Shears: Unstructured Sparsity with Neural Low-rank Adapter Search—0
SparseDM: Toward Sparse Efficient Diffusion Models—0
Interpolating neural network: A novel unification of machine learning and interpolation theoryCode1
Label merge-and-split: A graph-colouring approach for memory-efficient brain parcellation—0
Insight Gained from Migrating a Machine Learning Model to Intelligence Processing Units—0
Optimal Kernel Tuning Parameter Prediction using Deep Sequence Models—0
Post-Training Network Compression for 3D Medical Image Segmentation: Reducing Computational Efforts via Tucker DecompositionCode0
LoongServe: Efficiently Serving Long-Context Large Language Models with Elastic Sequence ParallelismCode2
Ctrl-Adapter: An Efficient and Versatile Framework for Adapting Diverse Controls to Any Diffusion Model—0
Show:102550
← PrevPage 32 of 113Next →

No leaderboard results yet.