Researcher — paper.dinq.me

Recent advances in neural song generation have enabled high-quality synthesis from lyrics and global textual prompts. However, most systems fail to model temporally varying attributes of songs, severely limiting fine-grained control over musical structure and dynamics. To address this, we propose...

对齐与偏好评测与基准OpenReview 项目页

作者位次 #7/9SIGGRAPH 2026Oral· Computer Graphics (Conference Track)

CameraSquad: Achieving Content Consistency in Parallel Multi-Trajectory Camera-Controlled Video Generation

Zhufeng Xu · Xuan Gao · Bailin Deng · Yikang Ding · Xiaoqiang Liu · Haoxian Zhang · Pengfei Wan · Hongbo Fu · Lin Gao

多模态OpenReview

作者位次 #5/7AAAI 2026Poster· Artificial Intelligence

Boosting Resolution Generalization of Diffusion Transformers with Randomized Positional Encodings

Liang Hou · Cong Liu · Mingwu Zheng · Xin Tao · Pengfei Wan · Di Zhang · Kun Gai

代码理论与学习动力学长上下文与架构OpenReview

作者位次 #7/10AAAI 2026Poster· Artificial Intelligence

FilmWeaver: Weaving Consistent Multi-Shot Videos with Cache-Guided Autoregressive Diffusion

Xiangyang Luo · Qingyu Li · Xiaokun Liu · Wenyu Qin · Miao Yang · Meng Wang · Pengfei Wan · Di Zhang · Kun Gai · Shao-Lun Huang

多模态OpenReview

作者位次 #8/9AAAI 2026Poster· Artificial Intelligence

Bridging Cognitive Gap: Hierarchical Description Learning for Artistic Image Aesthetics Assessment

henglin liu · Nisha Huang · Chang Liu · Jiangpeng Yan · Huijuan Huang · Jixuan Ying · Tong-Yee Lee · Pengfei Wan · Xiangyang Ji

多模态OpenReview

Pengfei Wan

获取完整研究档案

联系方式

2026 顶会论文

Astra: General Interactive World Model with Autoregressive Denoising

UniVideo: Unified Understanding, Generation, and Editing for Videos

Mitigating Noise Shift in Denoising Generative Models with Noise Awareness Guidance

Easier Painting Than Thinking: Can Text-to-Image Models Set the Stage, but Not Direct the Play?

Latent Diffusion Model without Variational Autoencoder

AdaViewPlanner: Adapting Video Diffusion Models for Viewpoint Planning in 4D Scenes

AVoCaDO: An Audiovisual Video Captioner Driven by Temporal Orchestration

VidBridge-R1: Bridging QA and Captioning for RL-based Video Understanding Models with Intermediate Proxy Tasks

FilMaster: Bridging Cinematic Principles and Generative AI for Automated Film Generation

VMoBA: Mixture-of-Block Attention for Video Diffusion Models

Improving Autoregressive Video Modeling with History Understanding

SimpleGVR: A Simple Baseline for Latent-Cascaded Generative Video Super-Resolution

Unified In-Context Video Editing

Learning Video Generation for Robotic Manipulation with Collaborative Trajectory Control

MultiShotMaster: A Controllable Multi-Shot Video Generation Framework

Monet: Reasoning in Latent Visual Space Beyond Image and Language

RealUnify: Do Unified Models Truly Benefit from Unification? A Comprehensive Benchmark

UnityVideo: Unified Multi-Modal Multi-Task Learning for Enhancing World-Aware Video Generation

Visual-Aware CoT: Achieving High-Fidelity Visual Consistency in Unified Models

3D-Aware Implicit Motion Control for View-Adaptive Human Video Generation

GRPO-Guard: Mitigating Implicit Over-Optimization in Flow Matching via Regulated Clipping

S eg T une: Structured and Fine-Grained Control for Song Generation

CameraSquad: Achieving Content Consistency in Parallel Multi-Trajectory Camera-Controlled Video Generation

Boosting Resolution Generalization of Diffusion Transformers with Randomized Positional Encodings

FilmWeaver: Weaving Consistent Multi-Shot Videos with Cache-Guided Autoregressive Diffusion

Bridging Cognitive Gap: Hierarchical Description Learning for Artistic Image Aesthetics Assessment

常见合作者