Mark Ibrahim
@markibrahim.bsky.social
Researching the dark arts of deep learning at Meta's FAIR (Fundamental AI Research) Lab https://markibrahim.me/
We introduce, Common-O, a new multimodal benchmark for hallucination when reasoning across scenes.
We find leading multimodal LLMs can reliably identify objects, yet hallucinate when reasoning across scenes.
🧵1/3
We find leading multimodal LLMs can reliably identify objects, yet hallucinate when reasoning across scenes.
🧵1/3
November 7, 2025 at 8:55 PM
We introduce, Common-O, a new multimodal benchmark for hallucination when reasoning across scenes.
We find leading multimodal LLMs can reliably identify objects, yet hallucinate when reasoning across scenes.
🧵1/3
We find leading multimodal LLMs can reliably identify objects, yet hallucinate when reasoning across scenes.
🧵1/3
If you’re an NYU student, come learn about this wonderful opportunity to collaborate with us at FAIR events.atmeta.com/metanyuaimen... Panel is tomorrow 10am at NYU Center for Data Science.
events.atmeta.com
October 16, 2025 at 2:45 PM
If you’re an NYU student, come learn about this wonderful opportunity to collaborate with us at FAIR events.atmeta.com/metanyuaimen... Panel is tomorrow 10am at NYU Center for Data Science.
One can manipulate LLM rankings to put any model in the lead—only by modifying the single character separating demonstration examples. Learn more in our new paper arxiv.org/abs/2510.05152
w/ Jingtong Su, Jianyu Zhang, @karen-ullrich.bsky.social , and Léon Bottou.
🧵
w/ Jingtong Su, Jianyu Zhang, @karen-ullrich.bsky.social , and Léon Bottou.
🧵
October 9, 2025 at 2:32 PM
One can manipulate LLM rankings to put any model in the lead—only by modifying the single character separating demonstration examples. Learn more in our new paper arxiv.org/abs/2510.05152
w/ Jingtong Su, Jianyu Zhang, @karen-ullrich.bsky.social , and Léon Bottou.
🧵
w/ Jingtong Su, Jianyu Zhang, @karen-ullrich.bsky.social , and Léon Bottou.
🧵
Open-weights for our Llip multimodal vision-language model led by @lavoiems.bsky.social are public!
LLIP proposes new pre-training objective to capture the many ways to describe an image leading to strong performance across a suite of 22-zero shot benchmarks.
bsky.app/profile/lavo...
LLIP proposes new pre-training objective to capture the many ways to describe an image leading to strong performance across a suite of 22-zero shot benchmarks.
bsky.app/profile/lavo...
The code and model weights for Llip are finally out! I hope you will find this model useful!
Paper: arxiv.org/abs/2405.00740
Code: github.com/facebookrese...
Models:
- ViT-G: huggingface.co/lavoies/llip...
- ViT-B: huggingface.co/lavoies/llip...
Paper: arxiv.org/abs/2405.00740
Code: github.com/facebookrese...
Models:
- ViT-G: huggingface.co/lavoies/llip...
- ViT-B: huggingface.co/lavoies/llip...
Modeling Caption Diversity in Contrastive Vision-Language Pretraining
There are a thousand ways to caption an image. Contrastive Language Pretraining (CLIP) on the other hand, works by mapping an image and its caption to a single vector -- limiting how well CLIP-like mo...
arxiv.org
July 21, 2025 at 6:57 PM
Open-weights for our Llip multimodal vision-language model led by @lavoiems.bsky.social are public!
LLIP proposes new pre-training objective to capture the many ways to describe an image leading to strong performance across a suite of 22-zero shot benchmarks.
bsky.app/profile/lavo...
LLIP proposes new pre-training objective to capture the many ways to describe an image leading to strong performance across a suite of 22-zero shot benchmarks.
bsky.app/profile/lavo...
A good language model should say “I don’t know” by reasoning about the limits of its knowledge. Our new work AbstentionBench carefully measures this overlooked skill in an open-codebase others can build on!
We find frontier reasoning degrades models’ ability to know when NOT to answer.
🧵1/2
We find frontier reasoning degrades models’ ability to know when NOT to answer.
🧵1/2
June 17, 2025 at 6:32 PM
A good language model should say “I don’t know” by reasoning about the limits of its knowledge. Our new work AbstentionBench carefully measures this overlooked skill in an open-codebase others can build on!
We find frontier reasoning degrades models’ ability to know when NOT to answer.
🧵1/2
We find frontier reasoning degrades models’ ability to know when NOT to answer.
🧵1/2
Join us as a PhD research intern at FAIR w/ @polkirichenko.bsky.social and Kamalika Chaudhuri
to start this summer or fall with a focus on open science into multimodal models, agents and beyond! Email polkirichenko@meta.com with the title [Prospective Intern 2025] and attach your CV if interested!
to start this summer or fall with a focus on open science into multimodal models, agents and beyond! Email polkirichenko@meta.com with the title [Prospective Intern 2025] and attach your CV if interested!
May 2, 2025 at 7:29 PM
Join us as a PhD research intern at FAIR w/ @polkirichenko.bsky.social and Kamalika Chaudhuri
to start this summer or fall with a focus on open science into multimodal models, agents and beyond! Email polkirichenko@meta.com with the title [Prospective Intern 2025] and attach your CV if interested!
to start this summer or fall with a focus on open science into multimodal models, agents and beyond! Email polkirichenko@meta.com with the title [Prospective Intern 2025] and attach your CV if interested!
Can we boost transformers’ ability to retrieve knowledge and plan in maze navigation by only tweaking the learning objective?
We emphatically say YES in our #NeurIPS 2024 study! 🧵
w/ Ouail Kitouni, Niklas Nolte, Diane Bouchacourt, Adina Williams, and Mike Rabbat
Paper arxiv.org/abs/2406.05183
We emphatically say YES in our #NeurIPS 2024 study! 🧵
w/ Ouail Kitouni, Niklas Nolte, Diane Bouchacourt, Adina Williams, and Mike Rabbat
Paper arxiv.org/abs/2406.05183
December 11, 2024 at 6:32 PM
Can we boost transformers’ ability to retrieve knowledge and plan in maze navigation by only tweaking the learning objective?
We emphatically say YES in our #NeurIPS 2024 study! 🧵
w/ Ouail Kitouni, Niklas Nolte, Diane Bouchacourt, Adina Williams, and Mike Rabbat
Paper arxiv.org/abs/2406.05183
We emphatically say YES in our #NeurIPS 2024 study! 🧵
w/ Ouail Kitouni, Niklas Nolte, Diane Bouchacourt, Adina Williams, and Mike Rabbat
Paper arxiv.org/abs/2406.05183