Meta Research

SuperDex brings together a purpose-built physics engine, robotics authoring tools, and a scalable reinforcement learning interface in a unified simulation platform, with VR-based teleoperation and additional capabilities planned for future releases.

Official repository for "Context Language Models"

How many bugs can LMs find & fix in large codebases?

Residual emotion steering for emotional TTS generation. EmoRES-TTS decomposes a mixed-emotion steering vector into a shared axis and an emotion-carrying residual and weight the two independently.

Official code release for "MoE-ViE Mixture of Experts Vision Encoder for Efficient Image and Video Understanding" (ECCV 2026)

WearableQA A Benchmark for Health Reasoningover Real-World Wearable Data

Generative Reconstruction with Test-Time Input Alignment

Diagnose and correct proxy metrics against a primary outcome across four levels (representativity, unit, estimate, domain). It diagnoses failures, then apply adequate corrections when needed. Supporting code for the paper "proxymate: Diagnosing and Correcting Proxy Metrics for Reliable Inference."

Training and evaluation code for our paper "MJEPA: A Simple and Scalable Joint-Embedding Predictive Architecture for Audio-Visual Learning"

Official implementation of the paper UnStep Training-Free Acceleration of Causal Video Diffusion with Fewer Steps Than Distillation

Code for our paper: "Knowledge Distillation During Mid-Training Favors Reasoning over Factual Recall"

OSS of roboJEPA

A benchmark for evaluating Computer Use Agents (CUAs) on 15 sandboxed Android apps. DigiWorld has 3.2M+ unique configurations across data, themes, and UI states.

E2E-SWE Benchmarking LLMs on Building Working Codebases from Scratch

Reference firmware and 3D-printable enclosure for a SubGHz LTC beacon (STEVAL-FKI868V2) that time-aligns Project Aria Gen2 captures with any SMPTE LTC source.

HEAR (Human-recorded Evaluation of Audio-LLM bias by Real speakers), a large-scale, ecologically valid benchmark comprising real human audio samples from demographically diverse participants.

Repo for 'ADeptS-Bench Measuring the Trustworthiness of Computer Use Agents across Devices'

schlepp is the Python package for the Schlepp synthetic dataset, which features multi-camera, multi-actor, multi-modal object manipulation sequences. It provides dense ground-truth optical flow, depth, segmentation, point tracks, oriented bounding boxes, object animation, and MHR body parameters.

Statistical evaluation for PRISM-compliant Computer-Using Agent (CUA) benchmarks.

GAMUT a Two-Level Meta-Rubric Benchmark for Long-Form Factuality

Source for Logbook: Extremely Long-form Audio Event Understanding

Python API for the SHOW3D dataset (CVPR 2026) https://huggingface.co/datasets/facebook/show3d-dataset

Official source code for "Tabula Rasa Monte Carlo estimation of unit-variance noise with controlled spatio-temporal correlation"

This repo contains the code supporting the paper "Sharp Linear-Minimax Constants for Causal Smoothing" submitted to IEEE TSP

This is the source implementation for SaliMory Orchestrating Cognitive Memory forConversational Agents.

Code for the paper "Selecting or Solving? What Best-of-$N$ Verification Delivers in Video Reasoning"

Hardening Agentic Systems via a Shared Log Design

Code for the paper "A/B testing with opportunity costs: Trading off reward and error control" by Ben Chugg, Artem Vorozhtsov, and Houssam Nassif

Artifact for REAP paper "REAP Automatic Curation of Coding Agent Benchmarks from Interactive Production Usage"

A repository supporting the paper "Learning Regularization Structure for Biosignal Template Estimation".