SOTAVerified

GPU

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 451–500 of 5629 papers

TitleStatusHype
HLSTransform: Energy-Efficient Llama 2 Inference on FPGAs Via High Level SynthesisCode2
QMoE: Practical Sub-1-Bit Compression of Trillion-Parameter ModelsCode2
HybriMoE: Hybrid CPU-GPU Scheduling and Cache Management for Efficient MoE InferenceCode2
Quantized Neural Networks: Training Neural Networks with Low Precision Weights and ActivationsCode2
Habitat: A Platform for Embodied AI ResearchCode2
RAGViz: Diagnose and Visualize Retrieval-Augmented GenerationCode2
Hardware-Aware Parallel Prompt Decoding for Memory-Efficient Acceleration of LLM InferenceCode2
Habitat 2.0: Training Home Assistants to Rearrange their HabitatCode2
HeadInfer: Memory-Efficient LLM Inference by Head-wise OffloadingCode2
Accelerating Sparse Deep Neural NetworksCode2
CoMoSVC: Consistency Model-based Singing Voice ConversionCode2
CoMoSpeech: One-Step Speech and Singing Voice Synthesis via Consistency ModelCode2
Bag of Tricks: Benchmarking of Jailbreak Attacks on LLMsCode2
DEYO: DETR with YOLO for End-to-End Object DetectionCode2
H_2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language ModelsCode2
Helix: Serving Large Language Models over Heterogeneous GPUs and Network via Max-FlowCode2
I-BERT: Integer-only BERT QuantizationCode2
Rethinking Visual Geo-localization for Large-Scale ApplicationsCode2
LAMP: Learn A Motion Pattern for Few-Shot-Based Video GenerationCode2
ManiSkill-HAB: A Benchmark for Low-Level Manipulation in Home Rearrangement TasksCode2
DeeR-VLA: Dynamic Inference of Multimodal Large Language Models for Efficient Robot ExecutionCode2
3DGen: Triplane Latent Diffusion for Textured Mesh GenerationCode2
GradeADreamer: Enhanced Text-to-3D Generation Using Gaussian Splatting and Multi-View DiffusionCode2
Gradient Boosting Reinforcement LearningCode2
Saving 77% of the Parameters in Large Language Models Technical ReportCode2
AutoTriton: Automatic Triton Programming with Reinforcement Learning in LLMsCode2
Enhancing Detail Preservation for Customized Text-to-Image Generation: A Regularization-Free ApproachCode2
Scaling Down Text Encoders of Text-to-Image Diffusion ModelsCode2
Deep Snake for Real-Time Instance SegmentationCode2
GPU Performance Portability needs AutotuningCode2
GPTAQ: Efficient Finetuning-Free Quantization for Asymmetric CalibrationCode2
geomstats: a Python Package for Riemannian Geometry in Machine LearningCode2
DeepLIIF: An Online Platform for Quantification of Clinical Pathology SlidesCode2
Geomstats: A Python Package for Riemannian Geometry in Machine LearningCode2
deepmriprep: Voxel-based Morphometry (VBM) Preprocessing via Deep Neural NetworksCode2
GeoLRM: Geometry-Aware Large Reconstruction Model for High-Quality 3D Gaussian GenerationCode2
Ghost in the Minecraft: Generally Capable Agents for Open-World Environments via Large Language Models with Text-based Knowledge and MemoryCode2
AutoFocus: Efficient Multi-Scale InferenceCode2
4D-Rotor Gaussian Splatting: Towards Efficient Novel View Synthesis for Dynamic ScenesCode2
SimpleNet: A Simple Network for Image Anomaly Detection and LocalizationCode2
A User's Guide to KSig: GPU-Accelerated Computation of the Signature KernelCode2
GPflow: A Gaussian process library using TensorFlowCode2
GaussianPretrain: A Simple Unified 3D Gaussian Representation for Visual Pre-training in Autonomous DrivingCode2
Gamba: Marry Gaussian Splatting with Mamba for single view 3D reconstructionCode2
GaussianDreamer: Fast Generation from Text to 3D Gaussians by Bridging 2D and 3D Diffusion ModelsCode2
gCastle: A Python Toolbox for Causal DiscoveryCode2
Fully-fused Multi-Layer Perceptrons on Intel Data Center GPUsCode2
Full Parameter Fine-tuning for Large Language Models with Limited ResourcesCode2
Machine-learned molecular mechanics force field for the simulation of protein-ligand systems and beyondCode2
AudioDec: An Open-source Streaming High-fidelity Neural Audio CodecCode2
Show:102550
← PrevPage 10 of 113Next →

No leaderboard results yet.