Jianfei Chen

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