Researcher — paper.dinq.me

2026 顶会论文

作者位次 #8/9ICML 2026Poster· Deep Learning / Generative Models and Autoencoders

LaTtE-Flow: Layerwise Timestep-Expert Flow-based Transformer

Ying Shen · Zhiyang Xu · Jiuhai Chen · Shizhe Diao · Jiaxin Zhang · Yuguang Yao · Joy Rimchala · Ismini Lourentzou · Lifu Huang

OpenReview

作者位次 #11/11ICML 2026Poster· Deep Learning / Generative Models and Autoencoders

Best of Both Worlds: Multimodal Reasoning and Generation via Unified Discrete Flow Matching

Onkar Susladkar · Tushar Prakash · Gayatri Deshmukh · Kiet Nguyen · Jiaxun Zhang · Adheesh Juvekar · Tianshu Bao · Lin Chai · Sparsh Mittal · Inderjit Dhillon · Ismini Lourentzou

推理多模态OpenReview

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

PyraTok: Language-Aligned Pyramidal Tokenizer for Video Understanding and Generation

Onkar Susladkar · Tushar Prakash · Adheesh Juvekar · Kiet A. Nguyen · Dong-Hwan Jang · Inderjit S Dhillon · Ismini Lourentzou

多模态对齐与偏好数据与预训练OpenReview 项目页

作者位次 #10/10CVPR 2026Poster· Computer Vision & Pattern Recognition

RewardFlow: Generate Images by Optimizing What You Reward

Onkar Susladkar · Dong-Hwan Jang · Tushar Prakash · Adheesh Juvekar · Vedant Shah · Ayush Barik · Nabeel Bashir · Muntasir Wahed · Ritish Shrirao · Ismini Lourentzou

多模态OpenReview 项目页

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

Part$^{2}$GS: Part-aware Modeling of Articulated Objects using 3D Gaussian Splatting

Tianjiao Yu · Vedant Shah · Muntasir Wahed · Ying Shen · Kiet A. Nguyen · Ismini Lourentzou

多模态OpenReview 项目页

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

PALM: Progress-Aware Policy Learning via Affordance Reasoning for Long-Horizon Robotic Manipulation

Yuanzhe Liu · Jingyuan Zhu · Yuchen Mo · Gen Li · Xu Cao · Jin Jin · Yifan Shen · Zhengyuan Li · Tianjiao Yu · Wenzhen Yuan · Fangqiang Ding · Ismini Lourentzou

推理多模态OpenReview 项目页

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

3D-VCD: Hallucination Mitigation in 3D-LLM Embodied Agents through Visual Contrastive Decoding

Makanjuola Adekunmi Ogunleye · Eman Abdelrahman · Ismini Lourentzou

多模态智能体与工具安全OpenReview 项目页

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

PHANTOM: Physics-Infused Video Generation via Joint Modeling of Visual and Latent Physical Dynamics

Ying Shen · Jerry Xiong · Tianjiao Yu · Ismini Lourentzou

多模态OpenReview 项目页

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

Hierarchical Dataset Selection for High-Quality Data Sharing

Xiaona Zhou · Yingyan Zeng · Ran Jin · Ismini Lourentzou

数据与预训练OpenReview

Ismini Lourentzou

获取完整研究档案

联系方式

2026 顶会论文

LaTtE-Flow: Layerwise Timestep-Expert Flow-based Transformer

Best of Both Worlds: Multimodal Reasoning and Generation via Unified Discrete Flow Matching

PyraTok: Language-Aligned Pyramidal Tokenizer for Video Understanding and Generation

RewardFlow: Generate Images by Optimizing What You Reward

Part$^{2}$GS: Part-aware Modeling of Articulated Objects using 3D Gaussian Splatting

PALM: Progress-Aware Policy Learning via Affordance Reasoning for Long-Horizon Robotic Manipulation

3D-VCD: Hallucination Mitigation in 3D-LLM Embodied Agents through Visual Contrastive Decoding

PHANTOM: Physics-Infused Video Generation via Joint Modeling of Visual and Latent Physical Dynamics

Hierarchical Dataset Selection for High-Quality Data Sharing

常见合作者