SOTAVerified

GPU

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 801–850 of 5629 papers

TitleStatusHype
Towards a Comprehensive, Efficient and Promptable Anatomic Structure Segmentation Model using 3D Whole-body CT ScansCode1
DaCapo: Accelerating Continuous Learning in Autonomous Systems for Video AnalyticsCode1
On Pretraining Data Diversity for Self-Supervised LearningCode1
Binary Noise for Binary Tasks: Masked Bernoulli Diffusion for Unsupervised Anomaly DetectionCode1
JORA: JAX Tensor-Parallel LoRA Library for Retrieval Augmented Fine-TuningCode1
Optimistic Verifiable Training by Controlling Hardware NondeterminismCode1
FastSAM3D: An Efficient Segment Anything Model for 3D Volumetric Medical ImagesCode1
SM4Depth: Seamless Monocular Metric Depth Estimation across Multiple Cameras and Scenes by One ModelCode1
Augmenting Efficient Real-time Surgical Instrument Segmentation in Video with Point Tracking and Segment AnythingCode1
SSM Meets Video Diffusion Models: Efficient Long-Term Video Generation with Structured State SpacesCode1
LookupFFN: Making Transformers Compute-lite for CPU inferenceCode1
UniSparse: An Intermediate Language for General Sparse Format CustomizationCode1
LLM-PQ: Serving LLM on Heterogeneous Clusters with Phase-Aware Partition and Adaptive QuantizationCode1
Efficient Lifelong Model Evaluation in an Era of Rapid ProgressCode1
DropBP: Accelerating Fine-Tuning of Large Language Models by Dropping Backward PropagationCode1
Multimodal Learned Sparse Retrieval with Probabilistic Expansion ControlCode1
PyGim: An Efficient Graph Neural Network Library for Real Processing-In-Memory ArchitecturesCode1
Mechanistic Neural Networks for Scientific Machine LearningCode1
BESA: Pruning Large Language Models with Blockwise Parameter-Efficient Sparsity AllocationCode1
Rewards-in-Context: Multi-objective Alignment of Foundation Models with Dynamic Preference AdjustmentCode1
Anchor-based Large Language ModelsCode1
TASER: Temporal Adaptive Sampling for Fast and Accurate Dynamic Graph Representation LearningCode1
Everybody Prune Now: Structured Pruning of LLMs with only Forward PassesCode1
Improving Token-Based World Models with Parallel Observation PredictionCode1
ApiQ: Finetuning of 2-Bit Quantized Large Language ModelCode1
A Lightweight Inception Boosted U-Net Neural Network for Routability PredictionCode1
Pruner: A Speculative Exploration Mechanism to Accelerate Tensor Program TuningCode1
Structure-Aware E(3)-Invariant Molecular Conformer Aggregation NetworksCode1
InferCept: Efficient Intercept Support for Augmented Large Language Model InferenceCode1
HiFT: A Hierarchical Full Parameter Fine-Tuning StrategyCode1
InverseMatrixVT3D: An Efficient Projection Matrix-Based Approach for 3D Occupancy PredictionCode1
immrax: A Parallelizable and Differentiable Toolbox for Interval Analysis and Mixed Monotone Reachability in JAXCode1
Dynamic DNNs and Runtime Management for Efficient Inference on Mobile/Embedded DevicesCode1
Exploiting Inter-Layer Expert Affinity for Accelerating Mixture-of-Experts Model InferenceCode1
CAVIAR: Co-simulation of 6G Communications, 3D Scenarios and AI for Digital TwinsCode1
TinyPredNet: A Lightweight Framework for Satellite Image Sequence PredictionCode1
Resource-Efficient Transformer Pruning for Finetuning of Large ModelsCode1
City-on-Web: Real-time Neural Rendering of Large-scale Scenes on the WebCode1
ZO-AdaMU Optimizer: Adapting Perturbation by the Momentum and Uncertainty in Zeroth-order OptimizationCode1
Regulating Intermediate 3D Features for Vision-Centric Autonomous DrivingCode1
Enhancing predictive capabilities in fusion burning plasmas through surrogate-based optimization in core transport solversCode1
Lightning-Fast Image Inversion and Editing for Text-to-Image Diffusion ModelsCode1
Opara: Exploiting Operator Parallelism for Expediting DNN Inference on GPUsCode1
Binary Code Summarization: Benchmarking ChatGPT/GPT-4 and Other Large Language ModelsCode1
Data-Efficient Multimodal Fusion on a Single GPUCode1
MaxK-GNN: Extremely Fast GPU Kernel Design for Accelerating Graph Neural Networks TrainingCode1
Memory-Efficient Reversible Spiking Neural NetworksCode1
EZ-CLIP: Efficient Zeroshot Video Action RecognitionCode1
DTL: Disentangled Transfer Learning for Visual RecognitionCode1
Modality Plug-and-Play: Elastic Modality Adaptation in Multimodal LLMs for Embodied AICode1
Show:102550
← PrevPage 17 of 113Next →

No leaderboard results yet.