Artemis Panagopoulou (@artemispng)

A

Artemis Panagopoulou@artemispng · Jun 15

Come learn about our #CVPR2025 work! Poster 346!

AArtemis Panagopoulou@artemispng · Jun 15

🚨 Are visual programs actually reasoning correctly? Spoiler: 40% of the time, they get the right answer for the wrong reason. Come check out our #CVPR2025 poster (#346) tomorrow — Sunday, June 15th from 10:30am–12:30pm CDT!

0

2

0

147

Artemis Panagopoulou Retweeted

J

Jack (in SF) Langerman@jacklangerman · Jun 13

@ir0armeni getting hands on at the @CVPR art gallery

1

5

18

0

2.0K

A

Artemis Panagopoulou@artemispng · Apr 21

Take a look at @jcniebles blog post about our upcoming @CVPR #CVPR2025 paper! The blog post highlights the key contribution of our work on improving visual program quality with automatically generated test cases!👇

JJuan Carlos Niebles@jcniebles · Apr 18

New blog post: "Are your Visual Programs Right for the Wrong Reasons?" 🤔 Dive into the motivation behind our upcoming @CVPR #CVPR2025 paper! 📰 Blog: niebles.net/blog/2025/viun… ➡️ Project: artemisp.github.io/viunit/ 📄 Paper: arxiv.org/abs/2412.08859 w/ @artemispng & @zhou_honglu

0

1

2

0

403

A

Artemis Panagopoulou@artemispng · Apr 18

New blog post: "Are your Visual Programs Right for the Wrong Reasons?" 🤔 Dive into the motivation behind our upcoming @CVPR #CVPR2025 paper! 📰 Blog: niebles.net/blog/2025/viun… ➡️ Project: artemisp.github.io/viunit/ 📄 Paper: arxiv.org/abs/2412.08859 w/ @artemispng & @zhou_honglu

SSalesforce AI Research@SFResearch · Mar 4

🎉Just Announced: "ViUniT: Visual Unit Tests for More Robust Visual Programming" has been accepted at #CVPR2025! Paper Link: arxiv.org/pdf/2412.08859 Project Page: artemisp.github.io/viunit/ Researcher’s walk-through 👇 In collaboration with @UPenn, we introduce ViUniT, a framework…

0

1

10

5

3.0K

A

Artemis Panagopoulou@artemispng · Mar 4

Exciting news! 🎉 Our paper “ViUniT: Visual Unit Tests for More Robust Visual Programming” got accepted at #CVPR2025

SSalesforce AI Research@SFResearch · Mar 4

🎉Just Announced: "ViUniT: Visual Unit Tests for More Robust Visual Programming" has been accepted at #CVPR2025! Paper Link: arxiv.org/pdf/2412.08859 Project Page: artemisp.github.io/viunit/ Researcher’s walk-through 👇 In collaboration with @UPenn, we introduce ViUniT, a framework…

0

2

17

3

1.0K

Artemis Panagopoulou Retweeted

P

Penn Engineering AI@PennEngAI · Feb 24

@artemispng (SEAS’20, SAS’20), doctoral student in @CIS_Penn, led a workshop on vision-language models as part of the Sixth Women in Data Science Conference at Amy Gutmann Hall. Thanks to everyone who joined and participated in the workshop. #AIVision #AIImaging #WIDS

0

2

4

0

250

Artemis Panagopoulou Retweeted

Y

Yue Yang@YueYangAI · Feb 24

We share Code-Guided Synthetic Data Generation: using LLM-generated code to create multimodal datasets for text-rich images, such as charts📊, documents📄, etc., to enhance Vision-Language Models. Website: yueyang1996.github.io/cosyn/ Dataset: huggingface.co/datasets/allen… Paper:…

6

46

196

133

23.0K

Artemis Panagopoulou Retweeted

W

Wharton AI & Analytics Initiative@WhartonAIAI · Feb 21

Thanks to @artemispng, PhD student at @PennEngineers, for providing a workshop on vision-language models as part of our Women in Data Science @ @Penn programming. Stay tuned for more updates on WiDS @ Penn offerings in the coming days!

0

3

8

0

376

Artemis Panagopoulou Retweeted

K

Karan Wanchoo@WanchooKaran · Dec 25

Introducing NAVCON: A large-scale #vln corpus with 236k+ cognitively inspired, linguistically grounded annotations! Enables interpretable, robust navigation models and unlocks new research in embodied AI. Groundbreaking for #NLProc and #robotics. 🚀 arxiv.org/abs/2412.13026

0

2

1

0

217

A

Artemis Panagopoulou@artemispng · Oct 2

It’s happening now! X-InstructBLIP is poster 92 #ECCV2024 @artemispng @eccvconf

AArtemis Panagopoulou@artemispng · Oct 2

We are presenting X-InstructBLIP at #ECCV2024 4:30pm CET (poster 92). Thank you to the amazing team: @Le_Xue01, @realNingYu, @LiJunnan0409, @dongxuli_, @JotyShafiq, @stanleyran, @silviocinguetta, @CaimingXiong, @jcniebles #AIResearch #MultimodalAI #llm #multimodalai #multimodal

2

1

17

2

4.0K

A

Artemis Panagopoulou@artemispng · Oct 2

We are presenting X-InstructBLIP at #ECCV2024 4:30pm CET (poster 92). Thank you to the amazing team: @Le_Xue01, @realNingYu, @LiJunnan0409, @dongxuli_, @JotyShafiq, @stanleyran, @silviocinguetta, @CaimingXiong, @jcniebles #AIResearch #MultimodalAI #llm #multimodalai #multimodal

artemispng's tweet image. We are presenting X-InstructBLIP at #ECCV2024 4:30pm CET (poster 92). Thank you to the amazing team: @Le_Xue01, @realNingYu, @LiJunnan0409, @dongxuli_, @JotyShafiq, @stanleyran, @silviocinguetta, @CaimingXiong, @jcniebles
#AIResearch #MultimodalAI #llm #multimodalai #multimodal

0

3

17

3

3.0K

A

Artemis Panagopoulou@artemispng · Oct 2

Happening in 3h! We are presenting 🚀X-InstructBLIP🚀 in #ECCV2024 #Milano poster session 4 ID 92 starting 4:30pm CET. X-InstructBLIP unifies texts, images, videos, sounds, and 3D into LLMs for general-purpose cross-modality question-answering. Kudos to the team @artemispng,…

SSalesforce AI Research@SFResearch · Oct 1

🎉 #ECCV2024 attendees: Don't miss our revolutionary X-InstructBLIP poster tomorrow 2 Oct at 4pm CEST. Tackling text, images, videos, sound, and 3D tasks with unprecedented flexibility, our novel framework equips LLMs to juggle 5 modalities using single modality-to-text alone!…

0

1

2

0

273

A

Artemis Panagopoulou@artemispng · Oct 1

Exciting work from @artemispng !

SSilvio Savarese@silviocinguetta · Oct 1

X-InstructBLIP is a remarkable framework for efficient multimodal learning. By aligning modalities independently to language, we've created a scalable approach that doesn't require joint training data. #ECCV colleagues: come learn how it could advance your multimodal research!

0

1

8

0

233

A

Artemis Panagopoulou@artemispng · Jun 20, 2024

It was great to be a #CVPR2024 panelist about what’s next in multimodal foundation models! One of the most exciting areas in this space is cross-modal interactions. I’ve posted an outline of my opening statement here for those who couldn’t make it: niebles.net/blog/2024/mult…

##3 MMFM Workshop@MMFMWorkshop · Jun 18, 2024

Panel starts now 🥳 @jcniebles @YejinChoinka Alexie A.Efros Antonio Torralba

0

2

13

3

2.0K

Artemis Panagopoulou Retweeted

S

Sebastian Angel@sebsgangel · Dec 7, 2023

Excited that our paper "MuCache: A General Framework for Caching in Microservice Graphs" was accepted at NSDI'24. This work builds a system that caches requests/responses across microservices to avoid duplicating work. MuCache does it automatically, fast, and correctly. 1\2

1

9

38

3

7.0K

Artemis Panagopoulou Retweeted

C

Caiming Xiong@CaimingXiong · Dec 8, 2023

We introduce 🔥X-InstructBLIP🔥, a simple and effective scalable cross-modal framework to empower LLMs to handle tasks across modalities such as text, image, video, sound, and 3D. Web: tinyurl.com/yc32ntfs ArXiv: arxiv.org/pdf/2311.18799… Code: github.com/salesforce/LAV…

3

43

180

80

37.0K