Meta Research

Non-invasive decoding of typed sentences from MEG and EEG brain recordings using a convolutional encoder, transformer, and character-level language model.

Repository for the CVPR 2026 paper MeshFlow Efficient Artistic Mesh Generation via MeshVAE and Flow-based Diffusion Transformer by Weiyu Li, Antoine Toisoul, Tom Monnier, Roman Shapovalov, Rakesh Ranjan, Ping Tan and Andrea Vedaldi.

ATLAS Autoformalized Textbook Library At Scale

Autoform Bot

FlowWM stochastic world modeling via flow matching in DINOv3 feature space, with the FuturePerception (Waymo) benchmark.

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.

[NeurIPS 2025] AutoPartGen: Autoregressive 3D Part Generation and Discovery. This is a re-implementation of original model.

A benchmark for general-purpose terminal-use agents.

Dance is an end-to-end framework that detects and classifies events in EEG signals. In a single forward pass, it extracts a set of events directly from the raw, unaligned recording.

This repositories contains the reference implementation for the Sparse Delta Memory paper.More precisely, it contains the model definition as well as triton and cuda kernels for the Sparse Delta Memory layer.

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

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."

Welcome to KernelBench-Verified. This repository provides a robust, realistic evaluation framework for assessing custom CUDA kernels generated by Large Language Models (LLMs).

Official source code release for R3D Quantitative 3D Spatial Reasoning for Egocentric Wearables

Code for “Speculative Sampling For Faster Molecular Dynamics”.

Official codebase for S-EMBER A Large-Scale Benchmark for Streaming Egocentric Memory Retrieval

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

Companion repository to the paper "Multicalibration yields better matchings".https//arxiv.org/abs/2511.11413

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.

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

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

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.

HST-Bench evaluation dataset contains 753 agentic tasks along with the time taken by human annotators to solve each task. This dataset was collected as part of our ICML 2026 paper on Scaling Small Agents Through Strategy Auctions https//arxiv.org/pdf/2602.02751

Unity toolkit for interacting with Aria devices.

This is for a research project on detecting outliers by their impact

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

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"

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

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