Researcher — paper.dinq.me

2026 顶会论文

作者位次 #7/7NeurIPS 2026Poster

VideoMLA: Low-Rank Latent KV Cache for Minute-Scale Autoregressive Video Diffusion

Hidir Yesiltepe · Jiazhen Hu · Tuna Han Salih Meral · Adil K Akan · Kaan Oktay · Hoda Eldardiry · Pinar Yanardag

效率与系统多模态OpenReview

作者位次 #5/5NeurIPS 2026Poster

HiPhy: Hierarchical Alignment for Physically-Plausible Multi-Principle Video Generation

Tahira Kazimi · Shubhankar Borse · Munawar Hayat · Fatih Porikli · Pinar Yanardag

对齐与偏好多模态OpenReview

作者位次 #2/2NeurIPS 2026Poster

AdaState: Self-Evolving Anchors for Streaming Video Generation

Yusuf Dalva · Pinar Yanardag

多模态OpenReview

作者位次 #4/4NeurIPS 2026Poster· Computer Vision / Image and Video Generation

RAVEL: Rare Concept Generation and Editing via Graph-driven Relational Guidance

Kavana Venkatesh · Yusuf Dalva · Ismini Lourentzou · Pinar Yanardag

多模态OpenReview

作者位次 #2/2NeurIPS 2026Poster

From Zero to Hero: Training-Free Custom Concept Spawning in World Models

Kiymet Akdemir · Pinar Yanardag

OpenReview

作者位次 #5/5CVPR 2026Poster· Computer Vision & Pattern Recognition

Infinity-RoPE: Action-Controllable Infinite Video Generation Emerges From Autoregressive Self-Rollout

Hidir Yesiltepe · Tuna Meral · Adil Kaan Akan · Kaan Oktay · Pinar Yanardag

多模态OpenReview 项目页

作者位次 #3/3CVPR 2026Poster· Computer Vision & Pattern Recognition

Diverse Video Generation with Determinantal Point Process-Guided Policy Optimization

Tahira Kazimi · Connor Dunlop · Pinar Yanardag

多模态强化学习与后训练OpenReview 项目页

作者位次 #6/7CVPR 2026Poster· Computer Vision & Pattern Recognition

DTG-Restore: Training-Free Diffusion Refinement for Generative Video Super-Resolution

Hidir Yesiltepe · Koutilya PNVR · Gaurav Pathak · Navaneeth Bodla · Bharat Singh · Pinar Yanardag · Jinrong Xie

多模态OpenReview 项目页

作者位次 #7/8SIGGRAPH 2026Oral· Computer Graphics (Conference Track)

Canvas-to-Image: Compositional Image Generation with Multimodal Controls

Yusuf Dalva · Guocheng Gordon Qian · Maya Goldenberg · Tsai-Shien Chen · Kfir Aberman · Sergey Tulyakov · Pinar Yanardag · Kuan-Chieh Jackson Wang

多模态长上下文与架构OpenReview

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

Plot'n Polish: Zero-Shot Story Visualization and Disentangled Editing with Text-to-Image Diffusion Models

Kiymet Akdemir · Jing Shi · Kushal Kafle · Brian L. Price · Pinar Yanardag

多模态OpenReview

作者位次 #4/4AAAI 2026Poster· Artificial Intelligence

MotionFlow: Attention-Driven Motion Transfer in Video Diffusion Models

Tuna Han Salih Meral · Hidir Yesiltepe · Connor Dunlop · Pinar Yanardag

多模态OpenReview

Pinar Yanardag

获取完整研究档案

联系方式

2026 顶会论文

VideoMLA: Low-Rank Latent KV Cache for Minute-Scale Autoregressive Video Diffusion

HiPhy: Hierarchical Alignment for Physically-Plausible Multi-Principle Video Generation

AdaState: Self-Evolving Anchors for Streaming Video Generation

RAVEL: Rare Concept Generation and Editing via Graph-driven Relational Guidance

From Zero to Hero: Training-Free Custom Concept Spawning in World Models

Infinity-RoPE: Action-Controllable Infinite Video Generation Emerges From Autoregressive Self-Rollout

Diverse Video Generation with Determinantal Point Process-Guided Policy Optimization

DTG-Restore: Training-Free Diffusion Refinement for Generative Video Super-Resolution

Canvas-to-Image: Compositional Image Generation with Multimodal Controls

Plot'n Polish: Zero-Shot Story Visualization and Disentangled Editing with Text-to-Image Diffusion Models

MotionFlow: Attention-Driven Motion Transfer in Video Diffusion Models

常见合作者