Get started
Author

Nan Duan

LogiGAN: Learning Logical Reasoning Via Adversarial Pre-Training
2022 · Xinyu Pi, Wanjun Zhong, et al. · neural information processing systems · 9
PDF
Generative Pre-trained Autoregressive Diffusion Transformer
2025 · Yuan Zhang, Jiacheng Jiang, et al. · neural information processing systems · 2
PDF
Rho-1: Not All Tokens Are What You Need
2024 · Lin, Zhenghao, Gou, Zhibin, et al. · arXiv (Cornell University) · 2
PDF
PROM: A Phrase-level Copying Mechanism with Pre-training for Abstractive Summarization
2024 · Xinbei Ma, Yeyun Gong, et al. · Language Resources and Evaluation Conference (LREC) · 1
PDF
Tempo-Zero: Recursive Self-Play in Executable Worlds for Video Reasoning
2026 · Zhu, Jingmin, Zou, Yanyan, et al. · arXiv (Cornell University)
PDF
Decoupling Action from Egocentric Observation for World Simulation
2026 · Ma, Yue, Song, Pengjie, et al. · arXiv (Cornell University)
PDF
WorldStream: Streaming Interactive 3D Worlds with Hierarchical Planning and Persistent State
2026 · Ma, Xiaoxiao, Jin, Weiyang, et al. · arXiv (Cornell University)
PDF
When Non-Adversarial Noise Hurts Learning: Benchmarking Skill Self-Evolution in Agents
2026 · Yu, Tao, Luo, Zhongtian, et al. · arXiv (Cornell University)
PDF
VideoJev: System One Model for Video Understanding and Interaction
2026 · Zhu, Yuhan, Zeng, Xiangyu, et al. · arXiv (Cornell University)
PDF
Avoiding What Your Teacher Already Knows: Entity Familiarity for Deep-Search Distillation
2026 · Liu, Yifei, Liang, Zhixiang, et al. · arXiv (Cornell University)
PDF
REEL: Learning to Retrieve, Evaluate, and Evolve Visual Memory for Any Long-Horizon Multi-Shot Video Generation
2026 · Xu, Hang, Zhang, Guohui, et al. · arXiv (Cornell University)
PDF
Building Pretraining Data for World Models: An Unreal Engine-Based Pipeline for Action-Conditioned Video Generation
2026 · Wang, Haoyu, Zhang, Songchun, et al. · arXiv (Cornell University)
PDF
ZimaBlue: Evolving Generalizable World Action Models through Scalable Video Pre-training
2026 · Wu, Xionghao, Yang, Yijun, et al. · arXiv (Cornell University)
PDF
EchoWM: Open and Enterable Omnimodal World Models
2026 · Zhang, Songchun, Li, Yaowei, et al. · arXiv (Cornell University)
PDF
Long-Horizon Audio-Visual Generation for Persistent Stories and Interactive Worlds
2026 · Duan, Nan, Huang, Haoyang, et al. · arXiv (Cornell University)
PDF
SearchAuditor: Auditing and Attributing Failures in Long-Horizon Search Agents
2026 · Liang, Zhixiang, Liu, Yifei, et al. · arXiv (Cornell University)
PDF
JoyAI-Video-Edit: Real-Time Open-Ended Video Editing with Autoregressive Diffusion
2026 · Xiao, Yicheng, Dai, Wenxun, et al. · arXiv (Cornell University)
PDF
SearchMaster: Grounded and Regulated Self-Play for Search Agents
2026 · Tan, Wentao, Cao, Qiong, et al. · arXiv (Cornell University)
PDF
JoyAI-Talker: Full-Duplex Speech Interactive Large Model Built for Empathetic Voice Agents
2026 · Bai, Yinhao, Chen, Jinming, et al. · arXiv (Cornell University)
PDF
Role-Break in Attention Heads: Understanding and Detecting Hallucinations in VLMs
2026 · Wang, Mingyu, Jin, Weilin, et al. · arXiv (Cornell University)
PDF
Oxygen-TryOn: Fashion-Native Foundation Model for Any-item Virtual Try-On
2026 · Liu, Yong, Fu, Xiaolong, et al. · arXiv (Cornell University)
PDF
Self Gradient Forcing: Native Long Video Extrapolation
2026 · Zhuang, Junhao, Zhang, Shiyi, et al. · arXiv (Cornell University)
PDF
EchoStory: Slot-Paired Audio-Visual Memory for Multi-Shot Long Audio-Video Storytelling
2026 · Jie Huang, Yijun Liu, et al.
Perceptual Flow Matching for Few-Step Generative Modeling
2026 · Zhao, Chuyang, Song, Yifei, et al. · arXiv (Cornell University)
PDF
DiT-Reward: Generative Representations for Text-to-Image Reward Modeling
2026 · Yang, Yuanming, Ma, Guoqing, et al. · arXiv (Cornell University)
PDF
Works count: 59
Citation count: 14
H-index: 2
I10-index:
Year
Topic
Type