AI at Meta

company

Verified

https://ai.facebook.com/

facebookresearch

AI & ML interests

None defined yet.

Recent Activity

cointegrated updated a Space about 5 hours ago

facebook/bouquet

marksibrahim updated a dataset about 20 hours ago

facebook/Common-O

zcai authored a paper 24 days ago

Metric3D v2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimation

View all activity

Papers

CRAG-MM: Multi-modal Multi-turn Comprehensive RAG Benchmark

SPICE: Self-Play In Corpus Environments Improves Reasoning

View all Papers

Articles

LayerSkip：使用自推测解码加速大模型推理

Faster Text Generation with Self-Speculative Decoding

facebook 's Papers 15

Submitted by

taesiri

CRAG-MM: Multi-modal Multi-turn Comprehensive RAG Benchmark

Submitted by

Jason Weston

SPICE: Self-Play In Corpus Environments Improves Reasoning

Submitted by

Deren Lei

Beyond Reasoning Gains: Mitigating General Capabilities Forgetting in Large Reasoning Models

1

Submitted by

Niels Rogge

The Art of Scaling Reinforcement Learning Compute for LLMs

Submitted by

Hritik Bansal

HoneyBee: Data Recipes for Vision-Language Reasoners

Submitted by

Jack Zhang

The Alignment Waltz: Jointly Training Agents to Collaborate for Safety

Submitted by

Lin Long

Hybrid Reinforcement: When Reward Is Sparse, It's Better to Be Dense

4

Submitted by

Niels Rogge

OneFlow: Concurrent Mixed-Modal and Interleaved Generation with Edit Flows

4

Submitted by

Jacob Kahn

CWM: An Open-Weights LLM for Research on Code Generation with World Models

Submitted by

Zhepei Wei

TruthRL: Incentivizing Truthful LLMs via Reinforcement Learning

Submitted by

zhipeng cai

DepthLM: Metric Depth From Vision Language Models

Submitted by

Chuanyang Jin

The Era of Real-World Human Interaction: RL from User Conversations

3

Submitted by

Niels Rogge

DINOv3

Submitted by

Jianyuan Wang

VGGT: Visual Geometry Grounded Transformer

Submitted by

Niels Rogge

Cluster and Predict Latents Patches for Improved Masked Image Modeling