Jianfei Chen

papers

2,514

total citations

papers (12)

DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps

NEURIPS 2022arXiv

2,036

citations

Jetfire: Efficient and Accurate Transformer Pretraining with INT8 Data Flow and Per-Block Quantization

ICML 2024arXiv

citations

ReMoE: Fully Differentiable Mixture-of-Experts with ReLU Routing

ICLR 2025arXiv

citations

Pruning Large Language Models with Semi-Structural Adaptive Sparse Training

AAAI 2025arXiv

citations

Accelerating Transformer Pre-training with 2:4 Sparsity

ICML 2024arXiv

citations

Visual Generation Without Guidance

ICML 2025arXiv

citations

On the Optimization and Generalization of Two-layer Transformers with Sign Gradient Descent

ICLR 2025arXiv

citations

Task-Specific Zero-shot Quantization-Aware Training for Object Detection

ICCV 2025arXiv

citations

Jianfei Chen

papers (12)

DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps

DPM-Solver-v3: Improved Diffusion ODE Solver with Empirical Model Statistics

Training Transformers with 4-bit Integers

A Statistical Framework for Low-bitwidth Training of Deep Neural Networks

Memory Efficient Optimizers with 4-bit States

Jetfire: Efficient and Accurate Transformer Pretraining with INT8 Data Flow and Per-Block Quantization

ReMoE: Fully Differentiable Mixture-of-Experts with ReLU Routing

Pruning Large Language Models with Semi-Structural Adaptive Sparse Training

Accelerating Transformer Pre-training with 2:4 Sparsity

Visual Generation Without Guidance

On the Optimization and Generalization of Two-layer Transformers with Sign Gradient Descent

Task-Specific Zero-shot Quantization-Aware Training for Object Detection

papers (12)

DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps

DPM-Solver-v3: Improved Diffusion ODE Solver with Empirical Model Statistics

Training Transformers with 4-bit Integers

A Statistical Framework for Low-bitwidth Training of Deep Neural Networks

Memory Efficient Optimizers with 4-bit States

Jetfire: Efficient and Accurate Transformer Pretraining with INT8 Data Flow and Per-Block Quantization

ReMoE: Fully Differentiable Mixture-of-Experts with ReLU Routing

Pruning Large Language Models with Semi-Structural Adaptive Sparse Training

Accelerating Transformer Pre-training with 2:4 Sparsity

Visual Generation Without Guidance

On the Optimization and Generalization of Two-layer Transformers with Sign Gradient Descent

Task-Specific Zero-shot Quantization-Aware Training for Object Detection