SOTAVerified

GPU

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 351–400 of 5629 papers

TitleStatusHype
Discovering the Gems in Early Layers: Accelerating Long-Context LLMs with 1000x Input Token ReductionCode2
Occupancy-Based Dual ContouringCode2
Scaling Smart: Accelerating Large Language Model Pre-training with Small Model InitializationCode2
RetrievalAttention: Accelerating Long-Context LLM Inference via Vector RetrievalCode2
Super Monotonic Alignment SearchCode2
Enhancing Privacy in Federated Learning: Secure Aggregation for Real-World Healthcare ApplicationsCode2
Follow-Your-Canvas: Higher-Resolution Video Outpainting with Extensive Content GenerationCode2
LongRecipe: Recipe for Efficient Long Context Generalization in Large Language ModelsCode2
MemLong: Memory-Augmented Retrieval for Long Text ModelingCode2
deepmriprep: Voxel-based Morphometry (VBM) Preprocessing via Deep Neural NetworksCode2
Tree Attention: Topology-aware Decoding for Long-Context Attention on GPU clustersCode2
Palu: Compressing KV-Cache with Low-Rank ProjectionCode2
HybridDepth: Robust Metric Depth Fusion by Leveraging Depth from Focus and Single-Image PriorsCode2
ESOD: Efficient Small Object Detection on High-Resolution ImagesCode2
Forecasting GPU Performance for Deep Learning Training and InferenceCode2
Spectra: Surprising Effectiveness of Pretraining Ternary Language Models at ScaleCode2
Differentiable Voxelization and Mesh MorphingCode2
From GaLore to WeLore: How Low-Rank Weights Non-uniformly Emerge from Low-Rank GradientsCode2
Gradient Boosting Reinforcement LearningCode2
MARS: Mixture of Auto-Regressive Models for Fine-grained Text-to-image SynthesisCode2
P2P: Part-to-Part Motion Cues Guide a Strong Tracking Framework for LiDAR Point CloudsCode2
MoA: Mixture of Sparse Attention for Automatic Large Language Model CompressionCode2
GeoLRM: Geometry-Aware Large Reconstruction Model for High-Quality 3D Gaussian GenerationCode2
Duoduo CLIP: Efficient 3D Understanding with Multi-View ImagesCode2
GradeADreamer: Enhanced Text-to-3D Generation Using Gaussian Splatting and Multi-View DiffusionCode2
Bag of Tricks: Benchmarking of Jailbreak Attacks on LLMsCode2
Is One GPU Enough? Pushing Image Generation at Higher-Resolutions with Foundation ModelsCode2
Low-Rank Quantization-Aware Training for LLMsCode2
Spectrum: Targeted Training on Signal to Noise RatioCode2
Latent Neural Operator for Solving Forward and Inverse PDE ProblemsCode2
Multi-Stage Speech Bandwidth Extension with Flexible Sampling Rate ControlCode2
SUBLLM: A Novel Efficient Architecture with Token Sequence Subsampling for LLMCode2
ZeroSmooth: Training-free Diffuser Adaptation for High Frame Rate Video GenerationCode2
Helix: Serving Large Language Models over Heterogeneous GPUs and Network via Max-FlowCode2
Scaling Laws and Compute-Optimal Training Beyond Fixed Training DurationsCode2
ViG: Linear-complexity Visual Sequence Learning with Gated Linear AttentionCode2
Hardware-Aware Parallel Prompt Decoding for Memory-Efficient Acceleration of LLM InferenceCode2
DiG: Scalable and Efficient Diffusion Models with Gated Linear AttentionCode2
LoQT: Low-Rank Adapters for Quantized PretrainingCode2
What is Your Data Worth to GPT? LLM-Scale Data Valuation with Influence FunctionsCode2
SSAMBA: Self-Supervised Audio Representation Learning with Mamba State Space ModelCode2
Advancing 6-DoF Instrument Pose Estimation in Variable X-Ray Imaging GeometriesCode2
MAMCA -- Optimal on Accuracy and Efficiency for Automatic Modulation Classification with Extended Signal LengthCode2
Xmodel-VLM: A Simple Baseline for Multimodal Vision Language ModelCode2
Preble: Efficient Distributed Prompt Scheduling for LLM ServingCode2
FeNNol: an Efficient and Flexible Library for Building Force-field-enhanced Neural Network PotentialsCode2
MiniGPT-3D: Efficiently Aligning 3D Point Clouds with Large Language Models using 2D PriorsCode2
MicroDreamer: Efficient 3D Generation in 20 Seconds by Score-based Iterative ReconstructionCode2
HLSTransform: Energy-Efficient Llama 2 Inference on FPGAs Via High Level SynthesisCode2
Partial Large Kernel CNNs for Efficient Super-ResolutionCode2
Show:102550
← PrevPage 8 of 113Next →

No leaderboard results yet.