Nan Duan

papers

950

total citations

papers (17)

NUWA-Infinity: Autoregressive over Autoregressive Generation for Infinite Visual Synthesis

NEURIPS 2022arXiv

citations

Key-Point-Driven Data Synthesis with Its Enhancement on Mathematical Reasoning

AAAI 2025arXiv

citations

VL-InterpreT: An Interactive Visualization Tool for Interpreting Vision-Language Transformers

CVPR 2022arXiv

citations

Taming Teacher Forcing for Masked Autoregressive Video Generation

CVPR 2025arXiv

citations

LogiGAN: Learning Logical Reasoning via Adversarial Pre-training

NEURIPS 2022arXiv

citations

Using Left and Right Brains Together: Towards Vision and Language Planning

ICML 2024arXiv

citations

Machine-Created Universal Language for Cross-Lingual Transfer

AAAI 2024arXiv

citations

M3P: Learning Universal Representations via Multitask Multilingual Multimodal Pre-Training

CVPR 2021arXiv

citations

HORIZON: High-Resolution Semantically Controlled Panorama Synthesis

AAAI 2024arXiv

citations

Alchemy: Amplifying Theorem-Proving Capability Through Symbolic Mutation

ICLR 2025arXiv

citations

Learning from Inside: Self-driven Siamese Sampling and Reasoning for Video Question Answering

NEURIPS 2021

citations

Less-forgetting Multi-lingual Fine-tuning

NEURIPS 2022

citations

Trace Controlled Text to Image Generation

ECCV 2022

citations

StrokeNUWA—Tokenizing Strokes for Vector Graphic Synthesis

ICML 2024

citations

Nan Duan

papers (17)

NÜWA: Visual Synthesis Pre-training for Neural visUal World creAtion

ReCo: Region-Controlled Text-to-Image Generation

AR-Diffusion: Auto-Regressive Diffusion Model for Text Generation

NUWA-Infinity: Autoregressive over Autoregressive Generation for Infinite Visual Synthesis

Key-Point-Driven Data Synthesis with Its Enhancement on Mathematical Reasoning

VL-InterpreT: An Interactive Visualization Tool for Interpreting Vision-Language Transformers

Taming Teacher Forcing for Masked Autoregressive Video Generation

LogiGAN: Learning Logical Reasoning via Adversarial Pre-training

Using Left and Right Brains Together: Towards Vision and Language Planning

Machine-Created Universal Language for Cross-Lingual Transfer

M3P: Learning Universal Representations via Multitask Multilingual Multimodal Pre-Training

HORIZON: High-Resolution Semantically Controlled Panorama Synthesis

Alchemy: Amplifying Theorem-Proving Capability Through Symbolic Mutation

Learning from Inside: Self-driven Siamese Sampling and Reasoning for Video Question Answering

Less-forgetting Multi-lingual Fine-tuning

Trace Controlled Text to Image Generation

StrokeNUWA—Tokenizing Strokes for Vector Graphic Synthesis

papers (17)

NÜWA: Visual Synthesis Pre-training for Neural visUal World creAtion

ReCo: Region-Controlled Text-to-Image Generation

AR-Diffusion: Auto-Regressive Diffusion Model for Text Generation

NUWA-Infinity: Autoregressive over Autoregressive Generation for Infinite Visual Synthesis

Key-Point-Driven Data Synthesis with Its Enhancement on Mathematical Reasoning

VL-InterpreT: An Interactive Visualization Tool for Interpreting Vision-Language Transformers

Taming Teacher Forcing for Masked Autoregressive Video Generation

LogiGAN: Learning Logical Reasoning via Adversarial Pre-training

Using Left and Right Brains Together: Towards Vision and Language Planning

Machine-Created Universal Language for Cross-Lingual Transfer

M3P: Learning Universal Representations via Multitask Multilingual Multimodal Pre-Training

HORIZON: High-Resolution Semantically Controlled Panorama Synthesis

Alchemy: Amplifying Theorem-Proving Capability Through Symbolic Mutation

Learning from Inside: Self-driven Siamese Sampling and Reasoning for Video Question Answering

Less-forgetting Multi-lingual Fine-tuning

Trace Controlled Text to Image Generation

StrokeNUWA—Tokenizing Strokes for Vector Graphic Synthesis