SOTAVerified

GPU

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 451–500 of 5629 papers

TitleStatusHype
Atom: Low-bit Quantization for Efficient and Accurate LLM ServingCode2
FP8-LM: Training FP8 Large Language ModelsCode2
QMoE: Practical Sub-1-Bit Compression of Trillion-Parameter ModelsCode2
LAMP: Learn A Motion Pattern for Few-Shot-Based Video GenerationCode2
ReMax: A Simple, Effective, and Efficient Reinforcement Learning Method for Aligning Large Language ModelsCode2
GaussianDreamer: Fast Generation from Text to 3D Gaussians by Bridging 2D and 3D Diffusion ModelsCode2
Im4D: High-Fidelity and Real-Time Novel View Synthesis for Dynamic ScenesCode2
DISTFLASHATTN: Distributed Memory-efficient Attention for Long-context LLMs TrainingCode2
MEM: Multi-Modal Elevation Mapping for Robotics and LearningCode2
ModuLoRA: Finetuning 2-Bit LLMs on Consumer GPUs by Integrating with Modular QuantizersCode2
OmniDrones: An Efficient and Flexible Platform for Reinforcement Learning in Drone ControlCode2
Flash-LLM: Enabling Cost-Effective and Highly-Efficient Large Generative Model Inference with Unstructured SparsityCode2
CoLA: Exploiting Compositional Structure for Automatic and Efficient Numerical Linear AlgebraCode2
CAGRA: Highly Parallel Graph Construction and Approximate Nearest Neighbor Search for GPUsCode2
OmniQuant: Omnidirectionally Calibrated Quantization for Large Language ModelsCode2
FastSurfer-HypVINN: Automated sub-segmentation of the hypothalamus and adjacent structures on high-resolutional brain MRICode2
Platypus: Quick, Cheap, and Powerful Refinement of LLMsCode2
Machine-learned molecular mechanics force field for the simulation of protein-ligand systems and beyondCode2
Differentiable Forward Projector for X-ray Computed TomographyCode2
InPars Toolkit: A Unified and Reproducible Synthetic Data Generation Pipeline for Neural Information RetrievalCode2
cuSLINK: Single-linkage Agglomerative Clustering on the GPUCode2
LeanDojo: Theorem Proving with Retrieval-Augmented Language ModelsCode2
DNABERT-2: Efficient Foundation Model and Benchmark For Multi-Species GenomeCode2
H_2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language ModelsCode2
RoMe: Towards Large Scale Road Surface Reconstruction via Mesh RepresentationCode2
Full Parameter Fine-tuning for Large Language Models with Limited ResourcesCode2
Datasets and Benchmarks for Offline Safe Reinforcement LearningCode2
Efficient 3D Semantic Segmentation with Superpoint TransformerCode2
StreetSurf: Extending Multi-view Implicit Surface Reconstruction to Street ViewsCode2
SpQR: A Sparse-Quantized Representation for Near-Lossless LLM Weight CompressionCode2
Wuerstchen: An Efficient Architecture for Large-Scale Text-to-Image Diffusion ModelsCode2
Accelerating Text-to-Image Editing via Cache-Enabled Sparse Diffusion InferenceCode2
AudioDec: An Open-source Streaming High-fidelity Neural Audio CodecCode2
MixFormerV2: Efficient Fully Transformer TrackingCode2
Ghost in the Minecraft: Generally Capable Agents for Open-World Environments via Large Language Models with Text-based Knowledge and MemoryCode2
Enhancing Detail Preservation for Customized Text-to-Image Generation: A Regularization-Free ApproachCode2
Quiver: Supporting GPUs for Low-Latency, High-Throughput GNN Serving with Workload AwarenessCode2
CoMoSpeech: One-Step Speech and Singing Voice Synthesis via Consistency ModelCode2
OctFormer: Octree-based Transformers for 3D Point CloudsCode2
VPGTrans: Transfer Visual Prompt Generator across LLMsCode2
Domain Adaptive and Generalizable Network Architectures and Training Strategies for Semantic Image SegmentationCode2
Scaling the leading accuracy of deep equivariant models to biomolecular simulations of realistic sizeCode2
Pgx: Hardware-Accelerated Parallel Game Simulators for Reinforcement LearningCode2
SimpleNet: A Simple Network for Image Anomaly Detection and LocalizationCode2
EfficientAD: Accurate Visual Anomaly Detection at Millisecond-Level LatenciesCode2
BiFormer: Vision Transformer with Bi-Level Routing AttentionCode2
3DGen: Triplane Latent Diffusion for Textured Mesh GenerationCode2
Run, Don't Walk: Chasing Higher FLOPS for Faster Neural NetworksCode2
FluidLab: A Differentiable Environment for Benchmarking Complex Fluid ManipulationCode2
POPGym: Benchmarking Partially Observable Reinforcement LearningCode2
Show:102550
← PrevPage 10 of 113Next →

No leaderboard results yet.