SOTAVerified

GPU

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 151–200 of 5629 papers

TitleStatusHype
SceneSplat: Gaussian Splatting-based Scene Understanding with Vision-Language PretrainingCode3
ZO2: Scalable Zeroth-Order Fine-Tuning for Extremely Large Language Models with Limited GPU MemoryCode3
LiteGS: A High-Performance Modular Framework for Gaussian Splatting TrainingCode3
SelaVPR++: Towards Seamless Adaptation of Foundation Models for Efficient Place RecognitionCode3
Slamming: Training a Speech Language Model on One GPU in a DayCode3
MetaDE: Evolving Differential Evolution by Differential EvolutionCode3
Long-VITA: Scaling Large Multi-modal Models to 1 Million Tokens with Leading Short-Context AccurayCode3
Transolver++: An Accurate Neural Solver for PDEs on Million-Scale GeometriesCode3
M+: Extending MemoryLLM with Scalable Long-Term MemoryCode3
How Well Do Supervised 3D Models Transfer to Medical Imaging Tasks?Code3
Dataset Distillation with Neural Characteristic Function: A Minmax PerspectiveCode3
CLEAR: Conv-Like Linearization Revs Pre-Trained Diffusion Transformers UpCode3
PanSplat: 4K Panorama Synthesis with Feed-Forward Gaussian SplattingCode3
HadaCore: Tensor Core Accelerated Hadamard Transform KernelCode3
GraphNeuralNetworks.jl: Deep Learning on Graphs with JuliaCode3
APOLLO: SGD-like Memory, AdamW-level PerformanceCode3
Pushing the Limits of Large Language Model Quantization via the Linearity TheoremCode3
MobileMamba: Lightweight Multi-Receptive Visual Mamba NetworkCode3
Nd-BiMamba2: A Unified Bidirectional Architecture for Multi-Dimensional Data ProcessingCode3
REDUCIO! Generating 10241024 Video within 16 Seconds using Extremely Compressed Motion LatentsCode3
Video-RAG: Visually-aligned Retrieval-Augmented Long Video ComprehensionCode3
Data Generation for Hardware-Friendly Post-Training QuantizationCode3
ShadowKV: KV Cache in Shadows for High-Throughput Long-Context LLM InferenceCode3
Modular Duality in Deep LearningCode3
Breaking the Memory Barrier: Near Infinite Batch Size Scaling for Contrastive LossCode3
MagicPIG: LSH Sampling for Efficient LLM GenerationCode3
CtrLoRA: An Extensible and Efficient Framework for Controllable Image GenerationCode3
High-Speed Stereo Visual SLAM for Low-Powered Computing DevicesCode3
SwiftKV: Fast Prefill-Optimized Inference with Knowledge-Preserving Model TransformationCode3
LayerKV: Optimizing Large Language Model Serving with Layer-wise KV Cache ManagementCode3
Simple and Fast Distillation of Diffusion ModelsCode3
3DGS-LM: Faster Gaussian-Splatting Optimization with Levenberg-MarquardtCode3
LongLLaVA: Scaling Multi-modal LLMs to 1000 Images Efficiently via a Hybrid ArchitectureCode3
LinFusion: 1 GPU, 1 Minute, 16K ImageCode3
InstanSeg: an embedding-based instance segmentation algorithm optimized for accurate, efficient and portable cell segmentationCode3
The Mamba in the Llama: Distilling and Accelerating Hybrid ModelsCode3
OctFusion: Octree-based Diffusion Models for 3D Shape GenerationCode3
Accelerating Goal-Conditioned RL Algorithms and ResearchCode3
ABQ-LLM: Arbitrary-Bit Quantized Inference Acceleration for Large Language ModelsCode3
LLMServingSim: A HW/SW Co-Simulation Infrastructure for LLM Inference Serving at ScaleCode3
UniBench: Visual Reasoning Requires Rethinking Vision-Language Beyond ScalingCode3
Practical Video Object Detection via Feature Selection and AggregationCode3
vTensor: Flexible Virtual Tensor Management for Efficient LLM ServingCode3
Inference Performance Optimization for Large Language Models on CPUsCode3
EfficientQAT: Efficient Quantization-Aware Training for Large Language ModelsCode3
Consistency Models Made EasyCode3
VisualRWKV: Exploring Recurrent Neural Networks for Visual Language ModelsCode3
IMDL-BenCo: A Comprehensive Benchmark and Codebase for Image Manipulation Detection & LocalizationCode3
AdaRevD: Adaptive Patch Exiting Reversible Decoder Pushes the Limit of Image DeblurringCode3
Merlin: A Vision Language Foundation Model for 3D Computed TomographyCode3
Show:102550
← PrevPage 4 of 113Next →

No leaderboard results yet.