Researcher — paper.dinq.me

2026 顶会论文

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

DeFlowCritic: Dense Latent Reward Alignment for Text-to-Image Flow Matching Models

Zeeshan Khan · Xin Yu · Shizhe Chen · Cordelia Schmid

多模态对齐与偏好OpenReview

作者位次 #3/4NeurIPS 2026Poster· Applications / Robotics

Unbiased First-Order Randomized Smoothing for Differentiable Simulation

Mathis SCHEFFLER · Wilson Jallet · Cordelia Schmid · Justin Carpentier

社会与人本OpenReview

作者位次 #2/2NeurIPS 2026Poster

BrickFlow: Connectivity-Guided Brick Reconstruction

Peter Kulits · Cordelia Schmid

OpenReview

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

CaptionFormer: Unified Segmentation, Tracking, and Captioning for Spatio-Temporal Objects

Gabriel Fiastre · Antoine Yang · Cordelia Schmid

多模态OpenReview 项目页

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

VOLD: Reasoning Transfer from LLMs to Vision-Language Models via On-Policy Distillation

Walid Bousselham · Hilde Kuehne · Cordelia Schmid

推理多模态强化学习与后训练OpenReview 项目页

作者位次 #2/2CVPR 2026Poster· Computer Vision & Pattern Recognition

BrickNet: Graph-Backed Generative Brick Assembly

Peter Kulits · Cordelia Schmid

多模态OpenReview 项目页

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

What Are You Doing? A Closer Look at Controllable Human Video Generation

Emanuele Bugliarello · Anurag Arnab · Roni Paiss · Christy Koh · Pieter-Jan Kindermans · Cordelia Schmid

多模态社会与人本OpenReview 项目页

作者位次 #7/9CVPR 2026Spotlight· Computer Vision & Pattern Recognition

CURVE: A Benchmark for Cultural and Multilingual Long Video Reasoning

Darshan Singh · Arsha Nagrani · Kawshik Manikantan · Harman Singh · Dinesh Tewari · Tobias Weyand · Cordelia Schmid · Anelia Angelova · Shachi Dave

多模态推理评测与基准OpenReview 项目页

作者位次 #9/9CVPR 2026Poster· Computer Vision & Pattern Recognition

Minerva-Ego: Spatiotemporal Hints for Egocentric Video Understanding

Arsha Nagrani · Jasper Uijlings · Shyamal Buch · Tobias Weyand · Sudheendra Vijayanarasimhan · Bo Hu · Ramin Mehran · David A Ross · Cordelia Schmid

多模态OpenReview 项目页

作者位次 #4/4IROS 2026Oral· Planning Manipulation Under Uncertainty and Constraints

Gondola: Grounded Vision Language Planning for Robotic Manipulation

Shizhe Chen · Ricardo Garcia-Pinel · Paul Pacaud · Cordelia Schmid

推理多模态Manipulation PlanningDeep Learning in Grasping and ManipulationImitation LearningOpenReview

Cordelia Schmid

获取完整研究档案

联系方式

2026 顶会论文

DeFlowCritic: Dense Latent Reward Alignment for Text-to-Image Flow Matching Models

Unbiased First-Order Randomized Smoothing for Differentiable Simulation

BrickFlow: Connectivity-Guided Brick Reconstruction

CaptionFormer: Unified Segmentation, Tracking, and Captioning for Spatio-Temporal Objects

VOLD: Reasoning Transfer from LLMs to Vision-Language Models via On-Policy Distillation

BrickNet: Graph-Backed Generative Brick Assembly

What Are You Doing? A Closer Look at Controllable Human Video Generation

CURVE: A Benchmark for Cultural and Multilingual Long Video Reasoning

Minerva-Ego: Spatiotemporal Hints for Egocentric Video Understanding

Gondola: Grounded Vision Language Planning for Robotic Manipulation

常见合作者