Junlin Han

@han_junlin

Multimodal pre-training/post-training. Meta FAIR. PhD Oxford

London, England

junlinhan.github.io

Replies Reposts Media

Pinned
Junlin Han
@han_junlin
Aug 6
We live in a multimodal world. We see, talk, act, and dream. Yet most LLMs still start with language pretraining. Why not train them natively with multimodal I/O from scratch? Because it’s SUPER HARD, adding modalities triggers training instability, design complexity, and
29
Junlin Han
@han_junlin
Sep 10
Computer vision is officially 3D only. 7 out of the 10 candidates are 3D. Multimodal foundation models, generative scaling, representation learning? Irrelevant to intelligence. The universe is made of point clouds, meshes, and Gaussians. (Nothing against the authors btw)
8
Junlin Han
@han_junlin
Aug 6
Thanks for posting our work! Hope this can be helpful for multimodal intelligence!
AK
@_akhaliq
Aug 6
Towards Physics of Multimodal Pretraining Knowledge Flow, Modality Synergy, Early Unification, and Recipes paper: huggingface.co/papers/2608.05…
Junlin Han
@han_junlin
Jul 7
Don’t miss Beyond Language Modeling with two amazing main authors @DavidJFan and @__JohnNguyen__ !!!!!
David Fan
@DavidJFan
Jul 7
@__JohnNguyen__ and I are presenting the Beyond Language Modeling paper as an ICML spotlight in 30 minutes at the 10:30 AM poster session! I’ll also be at the AMI Mixer on Thursday and hanging around in Seoul until early next week :)
Junlin Han
@han_junlin
Jul 3
best lecture/tutorial in native mllms!!!
Victoria X Lin
@VictoriaLinML
Jul 3
The video of my Stanford CS25 guest lecture, From Language Models to Native Multimodal Intelligence, is now online. I discussed how the core ideas behind LLMs has shaped multimodal AI, from architectures to training paradigms and scaling, and where the next challenges may lie.