SOTAVerified

GPU

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 551–575 of 5629 papers

TitleStatusHype
MetaDE: Evolving Differential Evolution by Differential EvolutionCode3
InfiniteHiP: Extending Language Model Context Up to 3 Million Tokens on a Single GPU—0
On LLM-generated Logic Programs and their Inference Execution Methods—0
E-MD3C: Taming Masked Diffusion Transformers for Efficient Zero-Shot Object Customization—0
CopySpec: Accelerating LLMs with Speculative Copy-and-Paste Without Compromising QualityCode0
Latents of latents to delineate pixels: hybrid Matryoshka autoencoder-to-U-Net pairing for segmenting large medical images in GPU-poor and low-data regimes—0
Neuromorphic Principles for Efficient Large Language Models on Intel Loihi 2—0
Inference-time sparse attention with asymmetric indexing—0
High-Throughput SAT SamplingCode0
Democratizing AI: Open-source Scalable LLM Training on GPU-based Supercomputers—0
Numerical Schemes for Signature KernelsCode0
Bag of Tricks for Inference-time Computation of LLM ReasoningCode1
Memory Analysis on the Training Course of DeepSeek Models—0
Fast-COS: A Fast One-Stage Object Detector Based on Reparameterized Attention Vision Transformer for Autonomous Driving—0
Small Language Model Makes an Effective Long Text ExtractorCode1
Memory Is Not the Bottleneck: Cost-Efficient Continual Learning via Weight Space Consolidation—0
Exploiting Sparsity for Long Context Inference: Million Token Contexts on Commodity GPUsCode0
Accelerating Outlier-robust Rotation Estimation by Stereographic Projection—0
MoETuner: Optimized Mixture of Expert Serving with Balanced Expert Placement and Token Routing—0
MERGE^3: Efficient Evolutionary Merging on Consumer-grade GPUsCode1
Crypto Miner Attack: GPU Remote Code Execution Attacks—0
Klotski: Efficient Mixture-of-Expert Inference via Expert-Aware Multi-Batch PipelineCode0
Saving 77% of the Parameters in Large Language Models Technical ReportCode2
fMoE: Fine-Grained Expert Offloading for Large Mixture-of-Experts Serving—0
Long-VITA: Scaling Large Multi-modal Models to 1 Million Tokens with Leading Short-Context AccurayCode3
Show:102550
← PrevPage 23 of 226Next →

No leaderboard results yet.