SOTAVerified

GPU

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 776–800 of 5629 papers

TitleStatusHype
MCP-MedSAM: A Powerful Lightweight Medical Segment Anything Model Trained with a Single GPU in Just One DayCode1
Batch-Max: Higher LLM Throughput using Larger Batch Sizes and KV Cache Compression—0
Code generation and runtime techniques for enabling data-efficient deep learning training on GPUs—0
APOLLO: SGD-like Memory, AdamW-level PerformanceCode3
Flash Communication: Reducing Tensor Parallelization Bottleneck for Fast Large Language Model Inference—0
Momentum-GS: Momentum Gaussian Self-Distillation for High-Quality Large Scene ReconstructionCode2
DHIL-GT: Scalable Graph Transformer with Decoupled Hierarchy Labeling—0
Beyond Boxes: Mask-Guided Spatio-Temporal Feature Aggregation for Video Object Detection—0
GUIDE: A Global Unified Inference Engine for Deploying Large Language Models in Heterogeneous Environments—0
Transformers Can Navigate Mazes With Multi-Step PredictionCode1
DEIM: DETR with Improved Matching for Fast ConvergenceCode5
SKIM: Any-bit Quantization Pushing The Limits of Post-Training Quantization—0
Assessing and Learning Alignment of Unimodal Vision and Language Models—0
p-MoD: Building Mixture-of-Depths MLLMs via Progressive Ratio DecayCode1
Beyond [cls]: Exploring the true potential of Masked Image Modeling representationsCode1
FlashAttention on a Napkin: A Diagrammatic Approach to Deep Learning IO-Awareness—0
Diffusion-VLA: Generalizable and Interpretable Robot Foundation Model via Self-Generated Reasoning—0
Unifying KV Cache Compression for Large Language Models with LeanKV—0
CLAP: Unsupervised 3D Representation Learning for Fusion 3D Perception via Curvature Sampling and Prototype Learning—0
SJTU:Spatial judgments in multimodal models towards unified segmentation through coordinate detectionCode0
Can't Slow me Down: Learning Robust and Hardware-Adaptive Object Detectors against Latency Attacks for Edge Devices—0
Improving feature interactions at Pinterest under industry constraints—0
Quantization-Aware Imitation-Learning for Resource-Efficient Robotic Control—0
MamKPD: A Simple Mamba Baseline for Real-Time 2D Keypoint Detection—0
Memory-Efficient Training for Deep Speaker Embedding Learning in Speaker Verification—0
Show:102550
← PrevPage 32 of 226Next →

No leaderboard results yet.