SOTAVerified

GPU

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 376–400 of 5629 papers

TitleStatusHype
LoongServe: Efficiently Serving Long-Context Large Language Models with Elastic Sequence ParallelismCode2
ImMesh: An Immediate LiDAR Localization and Meshing FrameworkCode2
I-BERT: Integer-only BERT QuantizationCode2
Cross-domain Neural Pitch and Periodicity EstimationCode2
Im4D: High-Fidelity and Real-Time Novel View Synthesis for Dynamic ScenesCode2
ALBERT: A Lite BERT for Self-supervised Learning of Language RepresentationsCode2
HybridDepth: Robust Metric Depth Fusion by Leveraging Depth from Focus and Single-Image PriorsCode2
AutoFocus: Efficient Multi-Scale InferenceCode2
Cross-Scale MAE: A Tale of Multi-Scale Exploitation in Remote SensingCode2
HybriMoE: Hybrid CPU-GPU Scheduling and Cache Management for Efficient MoE InferenceCode2
InPars Toolkit: A Unified and Reproducible Synthetic Data Generation Pipeline for Neural Information RetrievalCode2
Accelerating Transformer Pre-training with 2:4 SparsityCode2
A User's Guide to KSig: GPU-Accelerated Computation of the Signature KernelCode2
HRDA: Context-Aware High-Resolution Domain-Adaptive Semantic SegmentationCode2
CPPO: Accelerating the Training of Group Relative Policy Optimization-Based Reasoning ModelsCode2
HLSTransform: Energy-Efficient Llama 2 Inference on FPGAs Via High Level SynthesisCode2
CrypTen: Secure Multi-Party Computation Meets Machine LearningCode2
Holistically-Attracted Wireframe Parsing: From Supervised to Self-Supervised LearningCode2
HTS-AT: A Hierarchical Token-Semantic Audio Transformer for Sound Classification and DetectionCode2
HeadInfer: Memory-Efficient LLM Inference by Head-wise OffloadingCode2
Hardware-Aware Parallel Prompt Decoding for Memory-Efficient Acceleration of LLM InferenceCode2
Helix: Serving Large Language Models over Heterogeneous GPUs and Network via Max-FlowCode2
MARS: Mixture of Auto-Regressive Models for Fine-grained Text-to-image SynthesisCode2
Habitat: A Platform for Embodied AI ResearchCode2
HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech SynthesisCode2
Show:102550
← PrevPage 16 of 226Next →

No leaderboard results yet.