paper.dinq.meAI 与前沿科学顶会 · 学术新星雷达

更新于

返回新星榜

SM

Shah Mubarak

ECCV 2026×8多模态安全可解释性评测与基准社会与人本

新星分资深

25

一作贡献0

核心/参与10

方向广度10

合作网络9

0 一作 · 8 篇 · ECCV 2026

获取完整研究档案

首次获取该候选人的完整档案及 StartLux 评估共 20 积分；每位用户单独解锁，之后查看免费。主动刷新 20 积分。

联系方式

实时查找电子邮箱，费用不超过20积分；未找到邮箱不扣费。

2026 顶会论文

8

作者位次 #5/5ECCV 2026Poster

The Illusion of High Utility in Safety Alignment of Text-to-Image Diffusion Models

Adeel Yousaf · Soumik Ghosh · James Beetham · Amrit Singh Bedi · Shah Mubarak

多模态对齐与偏好安全Multimodal, Video & Document UnderstandingOpenReview

作者位次 #4/4ECCV 2026Poster

Pixel-wise Geo-registration of Drone and Satellite Images

Qingyang Liu · David G Shatwell · Parth Parag Kulkarni · Shah Mubarak

多模态3D Reconstruction, Registration and Scene ModelingOpenReview

作者位次 #8/8ECCV 2026Poster

ReasonCLIP-58M: Visually Grounded Commonsense Reasoning Supervision for CLIP

Sicheng Zhang · Muhammad Muzammal Naseer · Binzhu Xie · Naufal Suryanto · Shi Qiu · Jamal Bentahar · NAVEED AKHTAR · Shah Mubarak

多模态推理可解释性Vision Foundation Models: Interpretability and ReasoningOpenReview

作者位次 #5/5ECCV 2026Poster

BBQ-V: Benchmarking Visual Stereotype Bias in Large Multimodal Models

Vishal Narnaware · Ashmal Vayani · Rohit Gupta · Swetha Sirnam · Shah Mubarak

多模态评测与基准社会与人本Multimodal, Video & Document UnderstandingOpenReview

作者位次 #5/5ECCV 2026Poster

Seeing to Ground: Visual Attention for Hallucination-Resilient MDLLMs

Vishal Narnaware · Animesh Gupta · Kevin Zhai · Zhenyi Wang · Shah Mubarak

多模态安全Image Generation, Editing & DiffusionOpenReview

作者位次 #4/5ECCV 2026Poster

Controlling Embedding Spaces with Text-Conditioned Transformations

Joseph Fioresi · Fabian Caba · Pankaj Nathani · Shah Mubarak · Kushal Kafle

可解释性3D Graphics and Geometric RepresentationsOpenReview

作者位次 #6/6ECCV 2026Poster

The Telephone Game: Evaluating Semantic Drift in Unified Models

Sabbir Mollah · Rohit Gupta · Swetha Sirnam · Qingyang Liu · Ahnaf Munir · Shah Mubarak

多模态评测与基准Multimodal, Video & Document UnderstandingOpenReview

作者位次 #4/5ECCV 2026Poster

CLARITY: Medical World Model for Guiding Treatment Decisions by Simulating Context-Aware Disease Trajectories in Latent Space

Tianxingjian Ding · Yuanhao Zou · Chen Chen · Shah Mubarak · Yu Tian

社会与人本多模态Computational Imaging, Medical & Scientific VisionOpenReview

常见合作者

QLQingyang Liu×2 VNVishal Narnaware×2 RGRohit Gupta×2 SSSwetha Sirnam×2 AYAdeel Yousaf SGSoumik Ghosh JBJames Beetham ABAmrit Singh Bedi DSDavid G Shatwell PKParth Parag Kulkarni SZSicheng Zhang MNMuhammad Muzammal Naseer