SOTAVerified

GPU

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1201–1250 of 5629 papers

TitleStatusHype
Attention as an RNNCode1
CycleNet: Rethinking Cycle Consistency in Text-Guided Diffusion for Image ManipulationCode1
Asynchronous Methods for Deep Reinforcement LearningCode1
LinkNet: Exploiting Encoder Representations for Efficient Semantic SegmentationCode1
Attention in SRAM on Tenstorrent GrayskullCode1
LIPT: Latency-aware Image Processing TransformerCode1
Accelerating Neural Architecture Search via Proxy DataCode1
DAAIN: Detection of Anomalous and Adversarial Input using Normalizing FlowsCode1
EEEA-Net: An Early Exit Evolutionary Neural Architecture SearchCode1
Lightweight Real-time Semantic Segmentation Network with Efficient Transformer and CNNCode1
Efficient Quantized Sparse Matrix Operations on Tensor CoresCode1
Effective Batching for Recurrent Neural Network GrammarsCode1
Efficient Self-Supervised Adaptation for Medical Image AnalysisCode1
DAGER: Exact Gradient Inversion for Large Language ModelsCode1
Lightweight Neural Architecture Search for Temporal Convolutional Networks at the EdgeCode1
Lightweight Vision Transformer with Bidirectional InteractionCode1
Efficient Video Compression via Content-Adaptive Super-ResolutionCode1
Cross-Camera Convolutional Color ConstancyCode1
DARER: Dual-task Temporal Relational Recurrent Reasoning Network for Joint Dialog Sentiment Classification and Act RecognitionCode1
Efficient Training of Audio Transformers with PatchoutCode1
EPE-NAS: Efficient Performance Estimation Without Training for Neural Architecture SearchCode1
Cross-Batch Memory for Embedding LearningCode1
Edge and Identity Preserving Network for Face Super-ResolutionCode1
Edge-MoE: Memory-Efficient Multi-Task Vision Transformer Architecture with Task-level Sparsity via Mixture-of-ExpertsCode1
Differentiable Neural Architecture Search for Extremely Lightweight Image Super-ResolutionCode1
CritiPrefill: A Segment-wise Criticality-based Approach for Prefilling Acceleration in LLMsCode1
Data-efficient LLM Fine-tuning for Code GenerationCode1
Data-Efficient Multimodal Fusion on a Single GPUCode1
Easy and Efficient Transformer : Scalable Inference Solution For large NLP modelCode1
EAGAN: Efficient Two-stage Evolutionary Architecture Search for GANsCode1
Transformer TrackingCode1
EdgeNAT: Transformer for Efficient Edge DetectionCode1
Efficient Expert Pruning for Sparse Mixture-of-Experts Language Models: Enhancing Performance and Reducing Inference CostsCode1
Lightweight LiDAR-Camera 3D Dynamic Object Detection and Multi-Class Trajectory PredictionCode1
LLMThinkBench: Towards Basic Math Reasoning and Overthinking in Large Language ModelsCode1
MEFT: Memory-Efficient Fine-Tuning through Sparse AdapterCode1
CrAM: A Compression-Aware MinimizerCode1
Embedding a Differentiable Mel-cepstral Synthesis Filter to a Neural Speech Synthesis SystemCode1
Crabs: Consuming Resource via Auto-generation for LLM-DoS Attack under Black-box SettingsCode1
CPU- and GPU-based Distributed Sampling in Dirichlet Process Mixtures for Large-scale AnalysisCode1
A Unified Framework for Implicit Sinkhorn DifferentiationCode1
MGG: Accelerating Graph Neural Networks with Fine-grained intra-kernel Communication-Computation Pipelining on Multi-GPU PlatformsCode1
Dynamic Pooling Improves Nanopore Base Calling AccuracyCode1
Decentralized Training of Foundation Models in Heterogeneous EnvironmentsCode1
CPM-2: Large-scale Cost-effective Pre-trained Language ModelsCode1
MariusGNN: Resource-Efficient Out-of-Core Training of Graph Neural NetworksCode1
Aerial Single-View Depth Completion with Image-Guided Uncertainty EstimationCode1
DeAR: Accelerating Distributed Deep Learning with Fine-Grained All-Reduce PipeliningCode1
Dynamic Perceiver for Efficient Visual RecognitionCode1
Dynamic Sparse Training with Structured SparsityCode1
Show:102550
← PrevPage 25 of 113Next →

No leaderboard results yet.