activity
20202022
most citedFlow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow

82 citations · 106 across the 5 of their papers we have counts for

collaborators

6 papers

cs.CV2022

Fast Point Cloud Generation with Straight Flows

Lemeng Wu, Dilin Wang, Chengyue Gong +6

Diffusion models have emerged as a powerful tool for point cloud generation. A key component that drives the impressive performance for generating high-quality samples from noise i…

cs.CL2022

Passage-Mask: A Learnable Regularization Strategy for Retriever-Reader Models

Shujian Zhang, Chengyue Gong, Xingchao Liu

Retriever-reader models achieve competitive performance across many different NLP tasks such as open question answering and dialogue conversations. In this work, we notice these mo…

cs.CV20224 cited

Neural Volumetric Mesh Generator

Yan Zheng, Lemeng Wu, Xingchao Liu +3

Deep generative models have shown success in generating 3D shapes with different representations. In this work, we propose Neural Volumetric Mesh Generator(NVMG) which can generate…

cs.LG202282 cited

Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow

Xingchao Liu, Chengyue Gong, Qiang Liu

We present rectified flow, a surprisingly simple approach to learning (neural) ordinary differential equation (ODE) models to transport between two empirically observed distributio…

cs.LG202120 cited

Centroid Transformers: Learning to Abstract with Attention

Lemeng Wu, Xingchao Liu, Qiang Liu

Self-attention, as the key block of transformers, is a powerful mechanism for extracting features from the inputs. In essence, what self-attention does is to infer the pairwise rel…

cs.LG2020

Post-training Quantization with Multiple Points: Mixed Precision without Mixed Precision

Xingchao Liu, Mao Ye, Dengyong Zhou +1

We consider the post-training quantization problem, which discretizes the weights of pre-trained deep neural networks without re-training the model. We propose multipoint quantizat…