Meta AI

297 results for "robustness"

Publication

December 18, 2025

Computer Vision

We Can Hide More Bits: The Unused Watermarking Capacity in Theory and Practice

Aleksandar Petrov, Hady Elsahar, Pierre Fernandez, Tomáš Souček

December 18, 2025

Read the Paper

Publication

December 18, 2025

Computer Vision

Learning to Watermark in the Latent Space of Generative Models

Alexandre Mourachko, Hady Elsahar, Pierre Fernandez, Sylvestre Rebuffi, Tom Sander, Tomáš Souček, Tuan Tran, Valeriu Lacatusu

December 18, 2025

Read the Paper

Publication

December 18, 2025

Computer Vision

Pixel Seal: Adversarial-only training for invisible image and video watermarking

Alexandre Mourachko, Hady Elsahar, Pierre Fernandez, Sylvestre Rebuffi, Tom Sander, Tomáš Souček, Tuan Tran, Valeriu Lacatusu

December 18, 2025

Read the Paper

Publication

November 18, 2025

Core Machine Learning

Souper-Model: How Simple Arithmetic Unlocks State-of-the-Art LLM Performance

Roberta Raileanu, * Equal authorship, Alexis Audran-Reiss, Amar Budhiraja *, Anton Protopopov, Bhavul Gauri, Despoina Magka, Gaurav Chaurasia, Michael Slater, Shalini Maiti *, Tatiana Shavrina, Yoram Bachrach

November 18, 2025

Read the Paper

Publication

March 25, 2025

Integrity

Speech & Audio

Targeted Data Poisoning for Black-Box Audio Datasets Ownership Verification

El Mahdi El Mhamdi, Nicolas Usunier, Wassim (Wes) Bouaziz

March 25, 2025

Read the Paper

Publication

March 24, 2025

Integrity

Data Taggants: Dataset Ownership Verification Via Harmless Targeted Data Poisoning

Nicolas Usunier, El Mahdi El Mhamdi, Wassim (Wes) Bouaziz

March 24, 2025

Read the Paper

Publication

March 17, 2025

NLP

reWordBench: Benchmarking and Improving the Robustness of Reward Models with Transformed Inputs

Zhaofeng Wu, Yoon Kim, Andrew Cohen, Asli Celikyilmaz, Marjan Ghazvininejad, Michihiro Yasunaga

March 17, 2025

Read the Paper

Publication

January 02, 2025

Core Machine Learning

A Structure-Aware Framework for Learning Device Placements on Computation Graphs

Shukai Duan, Heng Ping, Nikos Kanakaris, Xiongye Xiao, Nesreen K. Ahmed, Peiyu Zhang, Guixiang Ma, Mihai Capota, Shahin Nazarian, Theodore L. Willke, Paul Bogdan, Panagiotis Kyriakis

January 02, 2025

Read the Paper

Publication

December 12, 2024

NLP

Byte Latent Transformer: Patches Scale Better Than Tokens

Margaret Li, Chunting Zhou, Ari Holtzman, Srini Iyer, Artidoro Pagnoni, Benjamin Muller, Gargi Ghosh, Jason Weston, John Nguyen, Lili Yu, Luke Zettlemoyer, Mike Lewis, Pedro Rodriguez, Ram Pasunuru

December 12, 2024

Read the Paper

Publication

December 12, 2024

Computer Vision

EvalGIM: A Library for Evaluating Generative Image Models

Melissa Hall, Abhishek Charnalia, Adriana Romero Soriano, Candace Ross, Carolina Braga, Jakob Verbeek, Karen Ullrich, Maeve Ryan, Mark Ibrahim, Marton Havasi, Michal Drozdzal, Mike Rabbat, Oscar Mañas, Pietro Astolfi, Reyhane Askari, Tariq Berrada Ifriqi, Yohann Benchetrit

December 12, 2024

Read the Paper

Publication

December 11, 2024

Computer Vision

Video Seal: Open and Efficient Video Watermarking

Alexandre Mourachko, Hady Elsahar, Pierre Fernandez, Zeki Yalniz

December 11, 2024

Read the Paper

Publication

November 20, 2024

Conversational AI

Computer Vision

Llama Guard 3 Vision: Safeguarding Human-AI Image Understanding Conversations

Javier Rando, Jianfeng Chi, Eric Smith, Hongyuan Zhan, Kartikeya Upasani, Kate Plawiak, Mahesh Pasupuleti, Ujjwal Karn, Yiming Zhang, Zacharie Delpierre Coudert

November 20, 2024

Read the Paper

Person

Abhimanyu Dubey

Menlo Park, United States

Abhimanyu is a Research Scientist at Facebook AI Research working on problems in machine learning. He received his Ph.D. in 2021 from the Massachusetts ...

Research Area:

Computer Vision

Human & Machine Intelligence

Person

Arman Zharmagambetov

Menlo Park, United States

Arman Zharmagambetov is a Research Scientist in the Fundamental AI Research (FAIR) team at Meta. His research primarily focuses on machine learning and ...

Research Area:

Reinforcement Learni9ng

NLP

Person

Chuan Guo

Menlo Park, United States

Chuan is a research scientist at Facebook AI Research. His research focuses on machine learning safety, working towards a principled resolution of the r...

Research Area:

Responsible AI

Computer Vision

Person

Mark Ibrahim

New York City, United States

How do we encode our intuitive ability to recognize the same dog while it's jumping during the day or hiding behind a tree at night? Mark is interested ...

Research Area:

Computer Vision

Core Machine Learning

Person

Vítor Albiero

Menlo Park, United States

Vítor is a Research Scientist in the Trust team at GenAI. He received his Ph.D. from the University of Notre Dame. His research interests lie in the fi...

Research Area:

Responsible AI

Computer Vision

Blog

April 08, 2026

Introducing Muse Spark: Scaling Towards Personal Superintelligence

April 08, 2026

Learn More

Blog

March 10, 2026

Open Source

Mapping the World's Forests with Greater Precision: Introducing Canopy Height Maps v2

In partnership with the World Resources Institute, today we’re announcing Canopy Height Maps v2 (CHMv2), an open source model, along with world-scale maps generated with the model.

March 10, 2026

Learn More

Blog

March 27, 2026

Computer Vision

SAM 3.1: Faster and More Accessible Real-Time Video Detection and Tracking With Multiplexing and Global Reasoning

March 27, 2026

Learn More

Blog

February 09, 2026

Computer Vision

Open Source

Reducing Government Costs and Increasing Access to Greenspaces in the United Kingdom with DINO

Meta's DINOv2 model is enhancing reforestation efforts around the world. Learn how the UK government is using DINO to help reduce costs and increase access to greenspaces.

February 09, 2026

Learn More

Blog

December 16, 2025

Computer Vision

Introducing SAM Audio: The First Unified Multimodal Model for Audio Separation

SAM Audio transforms audio processing by making it easy to isolate any sound from complex audio mixtures using natural, multimodal prompts — whether through text, visual cues, or marking time segments.

December 16, 2025

Learn More

Blog

November 19, 2025

Computer Vision

Introducing SAM 3D: Powerful 3D Reconstruction for Physical World Images

This release introduces two new state-of-the-art models: SAM 3D Objects for object and scene reconstruction, and SAM 3D Body for human body and shape estimation.

November 19, 2025

Learn More

Blog

October 31, 2025

Agents Rule of Two: A Practical Approach to AI Agent Security

We've developed the Agents Rule of Two. When this framework is followed, the severity of security risks is deterministically reduced.

October 31, 2025

Learn More

Blog

May 01, 2019

Developer Tools

Open-sourcing new AI tools for adaptive experimentation

We are open-sourcing BoTorch and Ax, two new tools that leverage adaptive experimentation to efficiently tackle optimization challenges in tuning software configurations, machine learning hyperparameters, ranking systems, and more.

May 01, 2019

Learn More

Blog

October 24, 2025

Open Source

The Building Blocks of Agentic AI: From Kernels to Clusters

At PyTorch Conference 2025 in San Francisco, we unveiled five new projects spanning kernel languages, distributed systems, reinforcement learning, agentic frameworks, and edge AI deployment.

October 24, 2025

Learn More

Blog

April 29, 2025

Developer Tools

Open Source

Sharing new open source protection tools and advancements in AI privacy and security

Today, we’re releasing new Llama protection tools for the open source AI community.

April 29, 2025

Learn More

Blog

August 14, 2025

Open Source

DINOv3: Self-supervised learning for vision at unprecedented scale

DINOv3 scales self-supervised learning for images to create universal vision backbones that achieve absolute state-of-the-art performance across diverse domains, including web and satellite imagery.