SOTAVerified

GPU

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 351–375 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
Follow-Your-Canvas: Higher-Resolution Video Outpainting with Extensive Content GenerationCode2
Enhancing Privacy in Federated Learning: Secure Aggregation for Real-World Healthcare ApplicationsCode2
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
From GaLore to WeLore: How Low-Rank Weights Non-uniformly Emerge from Low-Rank GradientsCode2
Differentiable Voxelization and Mesh MorphingCode2
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
Show:102550
← PrevPage 15 of 226Next →

No leaderboard results yet.