Meta Research

This repository contains the code to train and evaluate TRIBE v2, a multimodal model for brain response prediction

[CVPR 2026 Oral] VGGT Omega

Official implementation of Tuna-2: Pixel Embeddings Beat Vision Encoders for Unified Understanding and Generation

Can Language Models Rebuild Programs From Scratch?

Python suite for neuroscience research across all modalities.

MultiModal Audio Generation in Raw Waveform Space.

Superintelligent Retrieval Agent (SIRA)

WybeCoder Verified Generation of Imperative Code with LLMs

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.

Procedural Knowledge at Scale Improves ReasoningThis repository contains the minimal, end-to-end pipeline for reproducing the paper results generate a procedural knowledge datastore, build retrieval indices, run retrieval, perform model rollouts with retrieved subroutines, and filter the samples to output the final metrics.

[CVPR 26'] Code for the LAMP research paper.

Official Code Repository for the paper "LILO Bayesian Optimization with Natural Language Feedback".

Official Code Repository for the paper FRESCO Benchmarking and Optimizing Re-rankers for Evolving Semantic Conflict in Retrieval-Augmented Generation

Repository for the EgoBabyVLM Challenge

Grounded Integration Measure

Unified LLM-agent skill for code review covering both security (CWE) and privacy (GDPR) through one detector-validator methodology. Ships the SKILL.md, a 128-case Python benchmark across 30 canonical categories with a held-out true-negative subset, and the evaluation harness from the SecPriv paper.

Brittlebench

Official implementation of "Strand-accurate Multi-view Hair Capture" (CVPR 2019)

This repository contains replication materials for the paper "Unbiased Prevalence Estimation with Multicalibrated LLMs"

This repo contains the source code for Sondos shell as well as example designs demonstrating RTL interfaces, hardware abstraction layer (HAL) and example SW applications

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

Models for the work in Fully Self-Supervised Pretraining with Transformers for Recommendation

This repository contains the code for generating the benchmark results in the paper "How Surrogate Fidelity and Dataset Size Shape Benchmarking Conclusions A Case Study in Ads Ranking", to be submitted to AutoML Conference, 2026

Code implements analysis for SCRuB (Social Concept Reasoning under Rubric-Based Evaluation) framework for assessing model reasoning capabilities within the domain of social concepts abstract ideas and categories that shape human social life, relationships, and institutions.

This is a research project for robustly estimating underlying effect size distributions when there is measurement noise.

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

The repository contains raw data results and code for scaling laws fitting and visualization used in "Compute Optimal Tokenization" paper.

Supporting code material to the paper "Estimate Level Adjustment For Inference With Proxies Under Random Distribution Shifts".

Efficient Calculation of Shapley Values in Critical Path Method (CPM) Networks for Concurrent Delay Analysis

Official Claude Code marketplace for Project Aria — install ARK plugins for Aria SDK development, VRS data processing, MPS workflows, and device operations.