🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

Can visual SSL match CLIP on VQA? Yes! We show with controlled experiments that visual SSL can be competitive even on OCR/Chart VQA, as demonstrated by our new Web-SSL model family (1B-7B params) which is trained purely on web images – without any language supervision.

[7/8] This side project started in October when Peter Tong, Amir Bar, and I were thinking about the rise of CLIP as a popular vision encoder for MLLMs. The community often assumes that language supervision is the primary reason for CLIP's strong performance. However, we

FAIR is probably the only lab outside of academia where research projects can start like this.

In Cambrian-1, we found that vision SSL representations usually lagged behind language-supervised ones -- but once the data gap is closed and scaling kicks in, performance catches up. We’ve tried scaling SSL before, but this is the first time I’ve seen real signal: SSL adapts to

New paper from FAIR+NYU: Q: Is language supervision required to learn effective visual representations for multimodal tasks? A: No. ⬇️⬇️⬇️

Excited to release the training code for MetaMorph! MetaMorph offers a simple yet effective way to convert LLMs into a multimodal LLM that not only takes multimodal inputs, but also generates multimodal outputs via AR prediction. This confers the ability to “think visually”, and

Recently open-sourced projects from Peter Tong, David Fan, and the team at Meta FAIR. MetaMorph (training code and model weights): github.com/facebookresear… Web-SSL (model weights for Web-DINO and Web-MAE) github.com/facebookresear… FAIR's still leading the way in open research.

Web-SSL model weights are now available on GitHub and HuggingFace! You may use your favorite Transformers library API calls or load the model with native PyTorch - up to your preference. For more usage details, please see github.com/facebookresear… HuggingFace collection:

Introducing COMPACT: COMPositional Atomic-to-complex Visual Capability Tuning, a data-efficient approach to improve multimodal models on complex visual tasks without scaling data volume. 📦 arxiv.org/abs/2504.21850 1/10