ND
Nan Duan
cs.CVcs.AIcs.CLcs.LGcs.GRcs.MMcs.RO
On Valency
published · living versionsW_u6cz4v4d·v1 · currentpublished
SearchMaster: Grounded and Regulated Self-Play for Search Agents
with Wentao Tan, Qiong Cao, Jiaqi Wang
1 version
Preprints & journals
41 papers in the corpus · 2022–2026Learning from the Near Future: Temporal Self-Distillation for RLVR2604.20733v2 · Chuanyu Qin, Chenxu Yang, Qingyi Si et al.2026 · 0 citationsarXiv
Building Pretraining Data for World Models: An Unreal Engine-Based Pipeline for Action-Conditioned Video Generation2609.03557v1 · Haoyu Wang, Songchun Zhang, Haoran Li et al.2026 · 0 citationsarXiv
Unfold The World: Factorize 4D Properties in Reinforcing Spatial Reasoning2609.03729v1 · Yijun Yang, Shenghe Zheng, Wenbo Li et al.2026 · 0 citationsarXiv
ZimaBlue: Evolving Generalizable World Action Models through Scalable Video Pre-training2609.00188v1 · Xionghao Wu, Yijun Yang, Shiyang Zhou et al.2026 · 0 citationsarXiv
Long-Horizon Audio-Visual Generation for Persistent Stories and Interactive Worlds2608.23383v2 · Nan Duan, Haoyang Huang, Weiyang Jin et al.2026 · 0 citationsarXiv
EchoWM: Open and Enterable Omnimodal World Models2608.23189v1 · Songchun Zhang, Yaowei Li, Junhao Zhuang et al.2026 · 0 citationsarXiv
Teacher-Feature Drifting: One-Step Diffusion Distillation with Pretrained Diffusion Representations2605.07327v2 · Yuan Zhang, Chenyi Li, Haodong Yu et al.2026 · 0 citationsarXiv
SearchAuditor: Auditing and Attributing Failures in Long-Horizon Search Agents2608.05212v1 · Zhixiang Liang, Yifei Liu, Yidan Huang et al.2026 · 0 citationsarXiv
JoyAI-Video-Edit: Real-Time Open-Ended Video Editing with Autoregressive Diffusion2608.03974v1 · Yicheng Xiao, Wenxun Dai, Xinran Qin et al.2026 · 0 citationsarXiv
SearchMaster: Grounded and Regulated Self-Play for Search Agents2608.01822v1 · Wentao Tan, Qiong Cao, Jiaqi Wang et al.2026 · 0 citationsarXivon Valency
Role-Break in Attention Heads: Understanding and Detecting Hallucinations in VLMs2607.29412v1 · Mingyu Wang, Weilin Jin, Wenbo Li et al.2026 · 0 citationsarXiv
Perceptual Flow Matching for Few-Step Generative Modeling2607.03524v1 · Chuyang Zhao, Yifei Song, Hongfa Wang et al.2026 · 0 citationsarXiv
DiT-Reward: Generative Representations for Text-to-Image Reward Modeling2606.23626v1 · Yuanming Yang, Guoqing Ma, Bo Wang et al.2026 · 0 citationsarXiv
Flash-GRPO: Efficient Alignment for Video Diffusion via One-Step Policy Optimization2605.15980v3 · Xiaoxuan He, Siming Fu, Zeyue Xue et al.2026 · 0 citationsarXiv
SpatialWorld: Benchmarking Interactive Spatial Reasoning of Multimodal Agents in Real-World Tasks2606.09669v2 · Hongcheng Gao, Hailong Qu, Jingyi Tang et al.2026 · 0 citationsarXiv
AnchorEdit: Maintaining Temporal Consistency in Multi-turn Image Editing via Causal Memory2606.11751v2 · Hang Xu, Xiaoxiao Ma, Guohui Zhang et al.2026 · 0 citationsarXiv
Harnessing Streaming Video in the Wild2606.08615v1 · Dingyu Yao, Shuhuan Gu, Qingyi Si et al.2026 · 0 citationsarXiv
Echo-Memory: A Controlled Study of Memory in Action World Models2606.09803v1 · Wayne King, Zeyue Xue, Yuxuan Bian et al.2026 · 0 citationsarXiv
Leveraging Error Diversity in Group Rollouts for Reinforcement Learning2605.17333v2 · Wenpu Liu, Yuqi Xu, Weichu Xie et al.2026 · 0 citationsarXiv
Echo-Infinity: Learning Evolving Memory for Real-Time Infinite Video Generation2606.04527v1 · Yuxuan Bian, Zeyue Xue, Songchun Zhang et al.2026 · 0 citationsarXiv
Right Makes Might: Aligning Verified Hidden States Empowers RL Reasoning2606.03234v1 · Ziyue Wang, Aomufei Yuan, Yongfu Zhu et al.2026 · 0 citationsarXiv
AdaCodec: A Predictive Visual Code for Video MLLMs2606.02569v1 · Haowen Hou, Zhen Huang, Zheming Liang et al.2026 · 0 citationsarXiv
Embodied3DBench: Benchmarking Low-Level Embodied Spatial Intelligence of Vision Language Models2605.29074v1 · Jiyao Zhang, Mingxu Zhang, Yitong Peng et al.2026 · 0 citationsarXiv
JoyAI-Image: Awaking Spatial Intelligence in Unified Multimodal Understanding and Generation2605.04128v2 · Lin Song, Wenbo Li, Guoqing Ma et al.2026 · 0 citationsarXiv
Step-wise Rubric Rewards for LLM Reasoning2605.17291v1 · Weichu Xie, Haozhe Zhao, Wenpu Liu et al.2026 · 0 citationsarXiv
OmniNFT: Modality-wise Omni Diffusion Reinforcement for Joint Audio-Video Generation2605.12480v1 · Guohui Zhang, XiaoXiao Ma, Jie Huang et al.2026 · 0 citationsarXiv
Thinking with Novel Views: A Systematic Analysis of Generative-Augmented Spatial Intelligence2605.10588v1 · Yanbing Zhang, Bo Wang, Jianhui Liu et al.2026 · 0 citationsarXiv
TextLDM: Language Modeling with Continuous Latent Diffusion2605.07748v1 · Jiaxiu Jiang, Jingjing Ren, Wenbo Li et al.2026 · 0 citationsarXiv
Co-Evolving Policy Distillation2604.27083v1 · Naibin Gu, Chenxu Yang, Qingyi Si et al.2026 · 0 citationsarXiv
A Systematic Post-Train Framework for Video Generation2604.25427v1 · Zeyue Xue, Siming Fu, Jie Huang et al.2026 · 0 citationsarXiv
EasyVideoR1: Easier RL for Video Understanding2604.16893v1 · Chuanyu Qin, Chenxu Yang, Qingyi Si et al.2026 · 0 citationsarXiv
OpenSpatial: A Principled Data Engine for Empowering Spatial Intelligence2604.07296v2 · Jianhui Liu, Haoze Sun, Wenbo Li et al.2026 · 0 citationsarXiv
Self-Distilled RLVR2604.03128v2 · Chenxu Yang, Chuanyu Qin, Qingyi Si et al.2026 · 0 citationsarXiv
SpatialEdit: Benchmarking Fine-Grained Image Spatial Editing2604.04911v2 · Yicheng Xiao, Wenhu Zhang, Lin Song et al.2026 · 0 citationsarXiv
RAE-AR: Taming Autoregressive Models with Representation Autoencoders2604.01545v1 · Hu Yu, Hang Xu, Jie Huang et al.2026 · 0 citationsarXiv
Astrolabe: Steering Forward-Process Reinforcement Learning for Distilled Autoregressive Video Models2603.17051v1 · Songchun Zhang, Zeyue Xue, Siming Fu et al.2026 · 0 citationsarXiv
SetPO: Set-Level Policy Optimization for Diversity-Preserving LLM Reasoning2602.01062v1 · Chenyi Li, Yuan Zhang, Bo Wang et al.2026 · 0 citationsarXiv
Alchemy: Amplifying Theorem-Proving Capability through Symbolic Mutation2410.15748v2 · Shaonan Wu, Shuai Lu, Yeyun Gong et al.2024 · 0 citationsarXiv
Rho-1: Not All Tokens Are What You Need2404.07965v4 · Zhenghao Lin, Zhibin Gou, Yeyun Gong et al.2024 · 1 citationarXiv
PROM: A Phrase-level Copying Mechanism with Pre-training for Abstractive Summarization2305.06647v2 · Xinbei Ma, Yeyun Gong, Pengcheng He et al.2023 · 1 citationarXiv
LogiGAN: Learning Logical Reasoning via Adversarial Pre-training2205.08794v2 · Xinyu Pi, Wanjun Zhong, Yan Gao et al.2022 · 7 citationsarXiv
Career total: 52 works. 41 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.