AI at Meta

company

Verified

https://ai.facebook.com/

facebookresearch

AI & ML interests

None defined yet.

Recent Activity

taesiri submitted a paper about 12 hours ago

Skaling: Chinchilla's Exponents Meet Kaplan's Coupling

htranx new activity 1 day ago

facebook/wearable-ai-leaderboard:drop every count from the invited tab

htranx new activity 1 day ago

facebook/wearable-ai-leaderboard:lay the invited tab out as the boards' 3x2 grid, tinted blue

View all activity

Papers

Skaling: Chinchilla's Exponents Meet Kaplan's Coupling

Towards Physics of Multimodal Pretraining: Knowledge Flow, Modality Synergy, Early Unification, and Recipes

View all Papers

facebook 's papers 71

Submitted by

taesiri

Skaling: Chinchilla's Exponents Meet Kaplan's Coupling

Submitted by

Junlin Han

Towards Physics of Multimodal Pretraining: Knowledge Flow, Modality Synergy, Early Unification, and Recipes

Submitted by

Pierre Chambon

Reinforcement Learning for Code Optimization

Submitted by

Xilun Chen

Two-Level Meta-Rubrics for Evaluating Open-Ended Generation: GAMUT, a Benchmark for Factual Completeness

Submitted by

Niels Rogge

Sparse Delta Memory: Scaling the State of Linear RNNs through Sparsity

Submitted by

taesiri

TUA-Bench: A Benchmark for General-Purpose Terminal-Use Agents

Submitted by

taesiri

Autodata: An agentic data scientist to create high quality synthetic data

Submitted by

Vijay Viswanathan

Discretizing Reward Models

Submitted by

Nicolas Beltran-Velez

The Reward Was in Your Data All Along: Correcting Flow Matching with Discriminator-Guided RL

2

Submitted by

Xichen Pan

RepFusion: Leveraging Multimodal Priors for Denoising in Representation Space

2

Submitted by

Jiasenlu

MobileMoE: Scaling On-Device Mixture of Experts

Submitted by

Rawal Khirodkar

Sapiens2