影响力指数

93.45/100

前 0.4%

全站排名 #234

发表论文32 篇

平均评分5.6

年均产出10.7 篇/年

Jianfei Chen

Associate Professor@Tsinghua University·中国·OpenReview

研究方向

Generative models · diffusion models · Large scale machine learning · Efficient machine learning · neural network quantization · Topic models

Achieving low-bit Muon through subspace preservation and grid quantization

ICLR 2026Poster

Large Scale Diffusion Distillation via Score-Regularized Continuous-Time Consistency

ICLR 2026Poster

SLA: Beyond Sparsity in Diffusion Transformers via Fine-Tunable Sparse–Linear Attention

ICLR 2026Poster

Efficient Hyperparameter Tuning via Trajectory Invariance Principle

ICLR 2026Rejected

LLaDA 1.5: Variance-Reduced Preference Optimization for Large Language Diffusion Models

ICLR 2026Withdrawn

Stabilizing Gradient Descent via Second-Order Control-Theoretic Dynamics

ICLR 2026Withdrawn

SageAttention2: Efficient Attention with Thorough Outlier Smoothing and Per-thread INT4 Quantization

ICML 2025Poster

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

ICLR 2025Spotlight

Sparse VideoGen2: Accelerate Video Generation with Sparse Attention via Semantic-Aware Permutation

NeurIPS 2025Spotlight

SageAttention: Accurate 8-Bit Attention for Plug-and-play Inference Acceleration

ICLR 2025Poster

SageAttention3: Microscaling FP4 Attention for Inference and An Exploration of 8-Bit Training

NeurIPS 2025Spotlight

Visual Generation Without Guidance

ICML 2025Poster

FrameBridge: Improving Image-to-Video Generation with Bridge Models

ICML 2025Poster

SpargeAttention: Accurate and Training-free Sparse Attention Accelerating Any Model Inference

ICML 2025Poster

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

ICLR 2025Poster

Oscillation-Reduced MXFP4 Training for Vision Transformers

ICML 2025Poster

Diffusion Bridge Implicit Models

ICLR 2025Poster

Sparse Video-Gen: Accelerating Video Diffusion Transformers with Spatial-Temporal Sparsity

ICML 2025Poster

Elucidating the Preconditioning in Consistency Distillation

ICLR 2025Poster

COAT: Compressing Optimizer states and Activations for Memory-Efficient FP8 Training

ICLR 2025Poster

Beyond 2:4: Exploring V:N:M Sparsity for Efficient Transformer Inference on GPUs

ICLR 2025Rejected

1-Bit FQT: Pushing the Limit of Fully Quantized Training to 1-bit

ICLR 2025Rejected

Zero-shot Quantization for Object Detection

ICLR 2025Rejected

When Bigger is Better: Revisiting Large-Batch Optimization in Language Model Pretraining

NeurIPS 2025Rejected

SparseDM: Toward Sparse Efficient Diffusion Models

ICLR 2025Withdrawn

FrameBridge: Improving Image-to-Video Generation with Bridge Models

ICLR 2025Rejected

合作者 (20)