Cheng Li

papers

274

total citations

papers (12)

Exploring Post-training Quantization in LLMs from Comprehensive Study to Low Rank Compensation

AAAI 2024arXiv

citations

Efficient Multi-Stage Video Denoising With Recurrent Spatio-Temporal Fusion

CVPR 2021arXiv

citations

VIL-100: A New Dataset and a Baseline Model for Video Instance Lane Detection

ICCV 2021arXiv

citations

DeepSpeed Data Efficiency: Improving Deep Learning Model Quality and Training Efficiency via Efficient Data Sampling and Routing

AAAI 2024arXiv

citations

Self-Distillation Regularized Connectionist Temporal Classification Loss for Text Recognition: A Simple Yet Effective Approach

AAAI 2024arXiv

citations

World Knowledge-Enhanced Reasoning Using Instruction-Guided Interactor in Autonomous Driving

AAAI 2025arXiv

citations

BigMac: A Communication-Efficient Mixture-of-Experts Model Structure for Fast Training and Inference

AAAI 2025arXiv

citations

Cheng Li

papers (12)

Exploring Post-training Quantization in LLMs from Comprehensive Study to Low Rank Compensation

Efficient Multi-Stage Video Denoising With Recurrent Spatio-Temporal Fusion

VIL-100: A New Dataset and a Baseline Model for Video Instance Lane Detection

DeepSpeed Data Efficiency: Improving Deep Learning Model Quality and Training Efficiency via Efficient Data Sampling and Routing

Self-Distillation Regularized Connectionist Temporal Classification Loss for Text Recognition: A Simple Yet Effective Approach

World Knowledge-Enhanced Reasoning Using Instruction-Guided Interactor in Autonomous Driving

BigMac: A Communication-Efficient Mixture-of-Experts Model Structure for Fast Training and Inference

Autonomous Sparse Mean-CVaR Portfolio Optimization

De-singularity Subgradient for the q-th-Powered lₚ-Norm Weber Location Problem

Toward RAW Object Detection: A New Benchmark and a New Model

Style Projected Clustering for Domain Generalized Semantic Segmentation

Hyperspectral Image Denoising With Realistic Data

papers (12)

Exploring Post-training Quantization in LLMs from Comprehensive Study to Low Rank Compensation

Efficient Multi-Stage Video Denoising With Recurrent Spatio-Temporal Fusion

VIL-100: A New Dataset and a Baseline Model for Video Instance Lane Detection

DeepSpeed Data Efficiency: Improving Deep Learning Model Quality and Training Efficiency via Efficient Data Sampling and Routing

Self-Distillation Regularized Connectionist Temporal Classification Loss for Text Recognition: A Simple Yet Effective Approach

World Knowledge-Enhanced Reasoning Using Instruction-Guided Interactor in Autonomous Driving

BigMac: A Communication-Efficient Mixture-of-Experts Model Structure for Fast Training and Inference

Autonomous Sparse Mean-CVaR Portfolio Optimization

De-singularity Subgradient for the q-th-Powered lₚ-Norm Weber Location Problem

Toward RAW Object Detection: A New Benchmark and a New Model

Style Projected Clustering for Domain Generalized Semantic Segmentation

Hyperspectral Image Denoising With Realistic Data