倪赞林 · 清华大学

我是清华大学自动化系博士研究生，导师为黄高副教授；目前在 DeepSeek 预训练团队实习。

我的研究关注大语言模型，尤其是模型架构与高效解码，包括扩散语言模型。我的工作 The Flexibility Trap 获 ICML 2026 杰出论文奖。此前，我主要研究图像生成中的并行解码。

动态

2026.10
Co-GRPO 与 UNO 被 NeurIPS 2026 接收；InsightTok 获 LoViF @ ECCV 2026 Workshop 杰出论文奖（Oral）。
2026.10
连续第二年获博士研究生国家奖学金（2025、2026）。
2026.07
The Flexibility Trap 获 ICML 2026 杰出论文奖。
2026.01
The Flexibility Trap 预印本发布，见项目主页。
2025.10
AdaGen 被 TPAMI 接收。

论文

* 表示共同第一作者。

The Flexibility Trap: Rethinking the Value of Arbitrary Order in Diffusion Language Models

Zanlin Ni, Shenzhi Wang, Yang Yue, Tianyu Yu, Weilin Zhao, Yeguo Hua, Tianyi Chen, Jun Song, Cheng Yu, Bo Zheng, Gao Huang

ICML 2026杰出论文奖 2 / 23,918Oral论文 arXiv 代码项目主页模型

Co-GRPO: Co-Optimized Group Relative Policy Optimization for Masked Image Generation

Renping Zhou*, Zanlin Ni*, Tianyi Chen, Zeyu Liu, Yang Yue, Yulin Wang, Yuxuan Wang, Jingshu Liu, Gao Huang

NeurIPS 2026论文

AdaGen: Learning Adaptive Policy for Image Synthesis

Zanlin Ni*, Yulin Wang*, Yeguo Hua, Renping Zhou, Jiayi Guo, Jun Song, Bo Zheng, Gao Huang

TPAMI 20262025 年在线发表论文 arXiv

What Makes World Action Models Generalize? An Empirical Study of Test-Time Future Modeling

Renping Zhou*, Zanlin Ni*, Zihao Fan, Guohao Fu, Zeyu Liu, Hao Shi, Jie Zhang, Chi Bene Chen, Yang Yue, Xueyang Fu, Gao Huang

arXiv 预印本 2026arXiv

DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression

DeepSeek-AI

技术报告 2026论文

Steering Visual Generation in Unified Multimodal Models with Understanding Supervision

Zeyu Liu, Zanlin Ni, Yang Yue, Cheng Da, Huan Yang, Di Zhang, Kun Gai, Gao Huang

NeurIPS 2026arXiv 项目主页

InsightTok: Improving Text and Face Fidelity in Discrete Tokenization for Autoregressive Image Generation

Yang Yue, Fangyun Wei, Tianyu He, Jinjing Zhao, Zanlin Ni, Zeyu Liu, Jiayi Guo, Lei Shi, Yue Dong, Li Chen, Ji Li, Gao Huang, Dong Chen

LoViF Workshop @ ECCV 2026杰出论文奖OralarXiv 代码

OmniTTT: Linear Complexity Multimodal Visual Generation with Test-Time Training

Zeyu Liu, Dongchen Han, Zanlin Ni, Yining Li, Yuanzheng Ci, Yuan Gao, Xin Tao, Pengfei Wan, Gao Huang

在审 2026

CODA: Repurposing Continuous VAEs for Discrete Tokenization

Zeyu Liu*, Zanlin Ni*, Yeguo Hua, Xin Deng, Xiao Ma, Cheng Zhong, Gao Huang

ICCV 2025arXiv 代码

InfoPro: Locally Supervised Deep Learning by Maximizing Information Propagation

Yulin Wang*, Zanlin Ni*, Yifan Pu, Cai Zhou, Jixuan Ying, Shiji Song, Gao Huang

IJCV 2025论文代码

Emulating Human-like Adaptive Vision for Efficient and Flexible Machine Visual Perception

Yulin Wang*, Yang Yue* (乐洋), Yang Yue* (乐阳), Huanqian Wang, Haojun Jiang, Yizeng Han, Zanlin Ni, Yifan Pu, Minglei Shi, Rui Lu, Qisen Yang, Andrew Zhao, Zhuofan Xia, Shiji Song, Gao Huang

Nature Machine Intelligence 2025论文代码

Everything to the Synthetic: Diffusion-driven Test-time Adaptation via Synthetic-Domain Alignment

Jiayi Guo, Junhao Zhao, Chaoqun Du, Yulin Wang, Chunjiang Ge, Zanlin Ni, Shiji Song, Humphrey Shi, Gao Huang

CVPR 2025arXiv 代码

Cross-modal Adapter for Vision-Language Retrieval

Haojun Jiang, Jianke Zhang, Rui Huang, Chunjiang Ge, Zanlin Ni, Shiji Song, Gao Huang

Pattern Recognition 2025arXiv 代码

AdaNAT: Exploring Adaptive Policy for Token-Based Image Generation

Zanlin Ni*, Yulin Wang*, Renping Zhou, Rui Lu, Jiayi Guo, Jinyi Hu, Zhiyuan Liu, Yuan Yao, Gao Huang

ECCV 2024arXiv 代码

AutoNAT: Revisiting Non-Autoregressive Transformers for Efficient Image Synthesis

Zanlin Ni*, Yulin Wang*, Renping Zhou, Jiayi Guo, Jinyi Hu, Zhiyuan Liu, Shiji Song, Yuan Yao, Gao Huang

CVPR 2024论文代码

ENAT: Rethinking Spatial-temporal Interactions in Token-based Image Synthesis

Zanlin Ni*, Yulin Wang*, Renping Zhou, Yizeng Han, Jiayi Guo, Zhiyuan Liu, Yuan Yao, Gao Huang

NeurIPS 2024论文代码

Smooth Diffusion: Crafting Smooth Latent Spaces in Diffusion Models

Jiayi Guo*, Xingqian Xu*, Yifan Pu, Zanlin Ni, Chaofei Wang, Manushree Vasu, Shiji Song, Gao Huang, Humphrey Shi

CVPR 2024论文代码

LLaVA-UHD: An LMM Perceiving Any Aspect Ratio and High-Resolution Images

Zonghao Guo, Ruyi Xu, Yuan Yao, Junbo Cui, Zanlin Ni, Chunjiang Ge, Tat-Seng Chua, Zhiyuan Liu, Gao Huang

ECCV 2024论文代码

Deep Incubation: Training Large Models by Divide-and-Conquering

Zanlin Ni*, Yulin Wang*, Jiangwei Yu, Haojun Jiang, Yue Cao, Gao Huang

ICCV 2023论文代码

Revisiting Locally Supervised Learning: An Alternative to End-to-end Training

Yulin Wang, Zanlin Ni, Shiji Song, Le Yang, Gao Huang

ICLR 2021arXiv 代码

Uncertainty-Aware Score Distribution Learning for Action Quality Assessment

Yansong Tang*, Zanlin Ni*, Jiahuan Zhou, Danyang Zhang, Jiwen Lu, Ying Wu, Jie Zhou

CVPR 2020Oral论文代码