← Authors

Jianfei Chen

40 papers · 2013–2025 · 5 conferences · across top CS/AI conferences

Achievements

πŸƒ Academic Marathon (12) 🐣 Hot Topic Early Bird 🌍 Conference Polyglot (5) 🌈 Renaissance Researcher (5) πŸŒ‰ Interdisciplinary Bridge 🐝 Cross-Pollinator (15) πŸ—ΊοΈ Taxonomy Completionist (10) 🧭 Keyword Pioneer πŸ† Grand Slam πŸ‘‘ Triple Crown 🀝 Dynamic Duo (34) πŸ”¬ Deep Specialist (11) πŸ† Keyword Champion (2) πŸ“ˆ Trend Setter πŸ—ƒοΈ Keyword Collector (121) ⚑ Prolific Year (7) πŸ’Ž Century Club (40) πŸ”₯ Unstoppable (6)

Conferences

ICML (18) NIPS (11) ICLR (9) AAAI (1) ICCV (1)

Top co-authors

Jun Zhu (34) Kaiwen Zheng (7) Cheng Lu (7) Haocheng Xi (6) Chongxuan Li (6) Fan Bao (5) Jintao Zhang (4) Guande He (4) Jia wei (3) Huayu Chen (3)

Keywords

diffusion model (5) model compression (4) generative model (4) ode solver (3) data augmentation (3) gradient quantization (2) training stability (2) integer arithmetic (2) model quantization (2) likelihood estimation (2) image generation (2) control theory (2) sparse training (2) gibbs sampling (2) knowledge distillation (2) variance reduction (2) bayesian inference (2) maximum likelihood (2) normalizing flow (2) memory efficient training (2)

Papers

SpargeAttention: Accurate and Training-free Sparse Attention Accelerating Any Model Inference ICML 2025
Pruning Large Language Models with Semi-Structural Adaptive Sparse Training AAAI 2025
Task-Specific Zero-shot Quantization-Aware Training for Object Detection ICCV 2025
SageAttention: Accurate 8-Bit Attention for Plug-and-play Inference Acceleration ICLR 2025
ReMoE: Fully Differentiable Mixture-of-Experts with ReLU Routing ICLR 2025
On the Optimization and Generalization of Two-layer Transformers with Sign Gradient Descent ICLR 2025
COAT: Compressing Optimizer states and Activations for Memory-Efficient FP8 Training ICLR 2025
Elucidating the Preconditioning in Consistency Distillation ICLR 2025
Diffusion Bridge Implicit Models ICLR 2025
Visual Generation Without Guidance ICML 2025
Oscillation-Reduced MXFP4 Training for Vision Transformers ICML 2025
FrameBridge: Improving Image-to-Video Generation with Bridge Models ICML 2025
Sparse Video-Gen: Accelerating Video Diffusion Transformers with Spatial-Temporal Sparsity ICML 2025
SageAttention2: Efficient Attention with Thorough Outlier Smoothing and Per-thread INT4 Quantization ICML 2025
C-GAIL: Stabilizing Generative Adversarial Imitation Learning with Control Theory NIPS 2024
Consistency Diffusion Bridge Models NIPS 2024
Accelerating Transformer Pre-training with 2:4 Sparsity ICML 2024
Jetfire: Efficient and Accurate Transformer Pretraining with INT8 Data Flow and Per-Block Quantization ICML 2024
S-STE: Continuous Pruning Function for Efficient 2:4 Sparse Pre-training NIPS 2024
Efficient Backpropagation with Variance Controlled Adaptive Sampling ICLR 2024
Stabilizing GANs’ Training with Brownian Motion Controller ICML 2023
Preserving Pre-trained Features Helps Calibrate Fine-tuned Language Models ICLR 2023
Training Transformers with 4-bit Integers NIPS 2023
DPM-Solver-v3: Improved Diffusion ODE Solver with Empirical Model Statistics NIPS 2023
Memory Efficient Optimizers with 4-bit States NIPS 2023
Improved Techniques for Maximum Likelihood Estimation for Diffusion ODEs ICML 2023
Contrastive Energy Prediction for Exact Energy-Guided Diffusion Sampling in Offline Reinforcement Learning ICML 2023
DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps NIPS 2022
Fast Lossless Neural Compression with Integer-Only Discrete Flows ICML 2022
Maximum Likelihood Training for Score-based Diffusion ODEs by High Order Denoising Score Matching ICML 2022
GACT: Activation Compressed Training for Generic Network Architectures ICML 2022
Implicit Normalizing Flows ICLR 2021
ActNN: Reducing Training Memory Footprint via 2-Bit Activation Compressed Training ICML 2021
VFlow: More Expressive Generative Flows with Variational Data Augmentation ICML 2020
A Statistical Framework for Low-bitwidth Training of Deep Neural Networks NIPS 2020
Stochastic Training of Graph Convolutional Networks with Variance Reduction ICML 2018
Stochastic Expectation Maximization with Variance Reduction NIPS 2018
Population Matching Discrepancy and Applications in Deep Learning NIPS 2017
Bayesian Max-margin Multi-Task Learning with Data Augmentation ICML 2014
Scalable Inference for Logistic-Normal Topic Models NIPS 2013