SOTAVerified

GPU

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1976–2000 of 5629 papers

TitleStatusHype
ClusComp: A Simple Paradigm for Model Compression and Efficient Finetuning—0
Long-VMNet: Accelerating Long-Form Video Understanding via Fixed Memory—0
MagicDistillation: Weak-to-Strong Video Distillation for Large-Scale Few-Step Synthesis—0
AccelGen: Heterogeneous SLO-Guaranteed High-Throughput LLM Inference Serving for Diverse Applications—0
Changing Base Without Losing Pace: A GPU-Efficient Alternative to MatMul in DNNs—0
PIPO: Pipelined Offloading for Efficient Inference on Consumer Devices—0
Characterizing GPU Resilience and Impact on AI/HPC Systems—0
Vamba: Understanding Hour-Long Videos with Hybrid Mamba-Transformers—0
Distance-Based Tree-Sliced Wasserstein DistanceCode0
X-EcoMLA: Upcycling Pre-Trained Attention into MLA for Efficient and Extreme KV Compression—0
LLMPerf: GPU Performance Modeling meets Large Language ModelsCode0
Cost-effective Deep Learning Infrastructure with NVIDIA GPUCode0
OuroMamba: A Data-Free Quantization Framework for Vision Mamba Models—0
KV-Distill: Nearly Lossless Learnable Context Compression for LLMs—0
Speedy MASt3R—0
MoE-Gen: High-Throughput MoE Inference on a Single GPU with Module-Based BatchingCode0
Priority-Aware Preemptive Scheduling for Mixed-Priority Workloads in MoE Inference—0
Sometimes Painful but Certainly Promising: Feasibility and Trade-offs of Language Model Inference at the Edge—0
VideoScan: Enabling Efficient Streaming Video Understanding via Frame-level Semantic Carriers—0
MarineGym: A High-Performance Reinforcement Learning Platform for Underwater Robotics—0
Mind the Memory Gap: Unveiling GPU Bottlenecks in Large-Batch LLM InferenceCode0
Accelerating MoE Model Inference with Expert Sharding—0
TT-GaussOcc: Test-Time Compute for Self-Supervised Occupancy Prediction via Spatio-Temporal Gaussian Splatting—0
AdaptSR: Low-Rank Adaptation for Efficient and Scalable Real-World Super-Resolution—0
Global Context Is All You Need for Parallel Efficient Tractography Parcellation—0
Show:102550
← PrevPage 80 of 226Next →

No leaderboard results yet.