Researcher — paper.dinq.me

2026 顶会论文

作者位次 #4/5ICLR 2026Poster· Deep Learning / Generative Models and Autoencoders

Tracing the Principles Behind Modern Diffusion Models

Chieh-Hsin Lai · Yang Song · Dongjun Kim · Yuki Mitsufuji · Stefano Ermon

OpenReview

作者位次 #3/4ICLR 2026Poster· Computer Vision / Image and Video Generation

CMT: Mid-Training for Efficient Learning of Consistency, Mean Flow, and Flow-Map Models

Zheyuan Hu · Chieh-Hsin Lai · Yuki Mitsufuji · Stefano Ermon

多模态效率与系统OpenReview

作者位次 #5/5ICLR 2026Poster· General Machine Learning / Representation Learning

VIRTUE: Visual-Interactive Text-Image Universal Embedder

Wei-Yao Wang · Kazuya Tateishi · Qiyu Wu · Shusuke Takahashi · Yuki Mitsufuji

多模态可解释性OpenReview

作者位次 #8/9ICLR 2026Poster· Computer Vision / Image and Video Generation

3D Scene Prompting for Scene-Consistent Camera-Controllable Video Generation

JoungBin Lee · Jaewoo Jung · Jisang Han · Takuya Narihira · Kazumi Fukuda · Junyoung Seo · Sunghwan Hong · Yuki Mitsufuji · Seungryong Kim

多模态OpenReview

作者位次 #9/9ICLR 2026Poster

SONA: Learning Conditional, Unconditional, and Matching-Aware Discriminator

Yuhta Takida · Satoshi Hayakawa · Takashi Shibuya · Masaaki Imaizumi · Naoki Murata · Bac Nguyen · Toshimitsu Uesaka · Chieh-Hsin Lai · Yuki Mitsufuji

OpenReview

作者位次 #5/6ICLR 2026Poster· Deep Learning / Generative Models and Autoencoders

Improving Classifier-Free Guidance in Masked Diffusion: Low-Dim Theoretical Insights with High-Dim Impact

Kevin Rojas · Ye He · Chieh-Hsin Lai · Yuhta Takida · Yuki Mitsufuji · Molei Tao

理论与学习动力学OpenReview

作者位次 #7/7ICLR 2026Poster· Deep Learning / Generative Models and Autoencoders

Improved Object-Centric Diffusion Learning with Registers and Contrastive Alignment

Bac Nguyen · Yuhta Takida · Naoki Murata · Chieh-Hsin Lai · Toshimitsu Uesaka · Stefano Ermon · Yuki Mitsufuji

对齐与偏好OpenReview

作者位次 #10/10ICLR 2026Poster· Computer Vision / Image and Video Generation

Concept-TRAK: Understanding how diffusion models learn concepts through concept attribution

Yong-Hyun Park · Chieh-Hsin Lai · Satoshi Hayakawa · Yuhta Takida · Naoki Murata · WeiHsiang Liao · Woosung Choi · Kin Wai Cheuk · Junghyun (Tony) Koo · Yuki Mitsufuji

多模态OpenReview

作者位次 #8/8ICLR 2026Poster· Applications / Language, Speech and Dialog

LLM2Fx-Tools: Tool Calling for Music Post-Production

SeungHeon Doh · Junghyun (Tony) Koo · Marco Martínez-Ramírez · Woosung Choi · WeiHsiang Liao · Qiyu Wu · Juhan Nam · Yuki Mitsufuji

智能体与工具多模态OpenReview

作者位次 #4/5CVPR 2026Poster· Computer Vision & Pattern Recognition

MeanFlow Transformers with Representation Autoencoders

Zheyuan Hu · Chieh-Hsin Lai · Ge Wu · Yuki Mitsufuji · Stefano Ermon

可解释性多模态OpenReview 项目页

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

PAVAS: Physics-Aware Video-to-Audio Synthesis

Oh Hyun-Bin · Yuhta Takida · Toshimitsu Uesaka · Tae-Hyun Oh · Yuki Mitsufuji

多模态OpenReview 项目页

作者位次 #11/11CVPR 2026Poster· Computer Vision & Pattern Recognition

Echoes Over Time: Unlocking Length Generalization in Video-to-Audio Generation Models

christian simon · Masato Ishii · Wei-Yao Wang · Koichi Saito · Akio Hayakawa · Dongseok Shim · Zhi Zhong · Shuyang Cui · Takashi Shibuya · Shusuke Takahashi · Yuki Mitsufuji

多模态理论与学习动力学OpenReview 项目页

作者位次 #12/13CVPR 2026Poster· Computer Vision & Pattern Recognition

Learning Compact 3D Representations from Feed-Forward Novel View Synthesis

Honggyu An · Jaewoo Jung · Mungyeom Kim · Chaehyun Kim · Minkyeong Jeon · Jisang Han · Kazumi Fukuda · Takuya Narihira · Hyunah Ko · Junsu Kim · Sunghwan Hong · Yuki Mitsufuji · Seungryong Kim

可解释性多模态OpenReview 项目页

作者位次 #3/3CHI 2026Oral· Human-Computer Interaction

Emergent, not Immanent: A Baradian Reading of Explainable AI

Fabio Morreale · Joan Serrà · Yuki Mitsufuji

社会与人本理论与学习动力学OpenReview

作者位次 #11/11AAAI 2026Poster· Artificial Intelligence

SteerMusic: Enhanced Musical Consistency for Zero-shot Text-Guided and Personalized Music Editing

Xinlei Niu · Kin Wai Cheuk · Jing Zhang · Naoki Murata · Chieh-Hsin Lai · Michele Mancusi · Woosung Choi · Giorgio Fabbro · Wei-Hsiang Liao · Charles Patrick Martin · Yuki Mitsufuji

对齐与偏好OpenReview

作者位次 #12/12AAAI 2026Poster· Artificial Intelligence

Video Camera Trajectory Editing with Generative Rendering from Estimated Geometry

Junyoung Seo · Jisang Han · Jaewoo Jung · Siyoon Jin · JoungBin Lee · Takuya Narihira · Kazumi Fukuda · Takashi Shibuya · Donghoon Ahn · Shoukang Hu · Seungryong Kim · Yuki Mitsufuji

多模态OpenReview

Yuki Mitsufuji

获取完整研究档案

联系方式

2026 顶会论文

Tracing the Principles Behind Modern Diffusion Models

CMT: Mid-Training for Efficient Learning of Consistency, Mean Flow, and Flow-Map Models

VIRTUE: Visual-Interactive Text-Image Universal Embedder

3D Scene Prompting for Scene-Consistent Camera-Controllable Video Generation

SONA: Learning Conditional, Unconditional, and Matching-Aware Discriminator

Improving Classifier-Free Guidance in Masked Diffusion: Low-Dim Theoretical Insights with High-Dim Impact

Improved Object-Centric Diffusion Learning with Registers and Contrastive Alignment

Concept-TRAK: Understanding how diffusion models learn concepts through concept attribution

LLM2Fx-Tools: Tool Calling for Music Post-Production

MeanFlow Transformers with Representation Autoencoders

PAVAS: Physics-Aware Video-to-Audio Synthesis

Echoes Over Time: Unlocking Length Generalization in Video-to-Audio Generation Models

Learning Compact 3D Representations from Feed-Forward Novel View Synthesis

Emergent, not Immanent: A Baradian Reading of Explainable AI

SteerMusic: Enhanced Musical Consistency for Zero-shot Text-Guided and Personalized Music Editing

Video Camera Trajectory Editing with Generative Rendering from Estimated Geometry

常见合作者