SOTAVerified

Inference Optimization

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–25 of 56 papers

TitleStatusHype
The 1st Solution for 4th PVUW MeViS Challenge: Unleashing the Potential of Large Multimodal Models for Referring Video SegmentationCode5
Optimizing LLM Inference: Fluid-Guided Online Scheduling with Memory ConstraintsCode4
SimpleAR: Pushing the Frontier of Autoregressive Visual Generation through Pretraining, SFT, and RLCode3
A Survey on Inference Optimization Techniques for Mixture of Experts ModelsCode3
Inference Performance Optimization for Large Language Models on CPUsCode3
CycleBNN: Cyclic Precision Training in Binary Neural NetworksCode2
Painterly Image Harmonization using Diffusion ModelCode1
Adaptive Deep Neural Network Inference Optimization with EENetCode1
ADJUST: A Dictionary-Based Joint Reconstruction and Unmixing Method for Spectral TomographyCode1
A Novel 1D State Space for Efficient Music Rhythmic AnalysisCode1
Easy and Efficient Transformer : Scalable Inference Solution For large NLP modelCode1
Sub-MoE: Efficient Mixture-of-Expert LLMs Compression via Subspace Expert MergingCode0
The Foundation Cracks: A Comprehensive Study on Bugs and Testing Practices in LLM Libraries—0
Brevity is the soul of sustainability: Characterizing LLM response lengthsCode0
DSMentor: Enhancing Data Science Agents with Curriculum Learning and Online Knowledge Accumulation—0
Faster MoE LLM Inference for Extremely Large Models—0
Energy-Efficient Transformer Inference: Optimization Strategies for Time Series Classification—0
Hybrid Offline-online Scheduling Method for Large Language Model Inference Optimization—0
DVFS-Aware DNN Inference on GPUs: Latency Modeling and Performance Analysis—0
Hellinger-Kantorovich Gradient Flows: Global Exponential Decay of Entropy Functionals—0
FluidML: Fast and Memory Efficient Inference Optimization—0
A Temporal Linear Network for Time Series ForecastingCode0
LLM-Rank: A Graph Theoretical Approach to Pruning Large Language ModelsCode0
EdgeRL: Reinforcement Learning-driven Deep Learning Model Inference Optimization at Edge—0
Revisiting SMoE Language Models by Evaluating Inefficiencies with Task Specific Expert Pruning—0
Show:102550
← PrevPage 1 of 3Next →

No leaderboard results yet.