Victoria X Lin (@VictoriaLinML) / X

Victoria X Lin

1,473 posts

Victoria X Lin

@VictoriaLinML

MTS @thinkymachines | Native Multimodal Intelligence Prev: @AIatMeta @SFResearch • PhD @uwcse

San Francisco Bay Area

Joined December 2010

Pinned
Victoria X Lin
@VictoriaLinML
Jul 16
Inkling is a 975B-41B(A) MoE model that natively reasons across modalities (text, images and audio). It is intelligent and versatile🌱. I’ve had so much fun building it alongside an incredible team over the past few months and proud to openly share this work.
Thinking Machines
@thinkymachines
Jul 15
Today, we are introducing Inkling. Inkling reasons efficiently across text, image, and audio modalities. We are making the full weights available. thinkingmachines.ai/news/introduci… Available today for fine-tuning on Tinker. Play with it in the Inkling Playground. 🧵
Made with AI
Victoria X Lin
@VictoriaLinML
Jul 7
If you're excited about efficient parallel reasoning 🧠⚡ in LLMs, don't miss the ThreadWeaver paper presentation at #ICML2026. 🗓️Oral: Thu, Jul 9, 2026 • 10:15 AM – 10:30 AM KST 🗓️Poster: Thu, Jul 9, 2026 • 2:30 PM – 4:15 PM KST 📎 threadweaver-parallel.github.io Feel free to reach
Long Lian
@LongTonyLian
Jul 6
ThreadWeaver 🧵⚡️ is accepted for an oral presentation at #ICML2026 🎉 ThreadWeaver achieves faster reasoning end-to-end though multiple reasoning agents efficiently working together. Come to our talk at Thursday, Jul 9, 10 AM and poster at 2:30 PM!
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.
Stanford CS25: Transformers United V6 I From Language Models to Native Multimodal Intelligence
From youtube.com
Victoria X Lin
@VictoriaLinML
Jun 3
Excited to see 🌟 Mixture-of-Transformers (MoT) ideas continue to scale in native multimodal systems. nvidia.com/en-gb/glossary… In our MoT work, we explored modality-specialized transformer parameters as a path toward building more efficient multimodal foundation models with
NVIDIA AI
@NVIDIAAI
Jun 1
Replying to @NVIDIAAI
Cosmos 3 ties everything together. Previous releases separated world generation, physical understanding, and controlled scene generation. Cosmos 3’s MoT architecture unifies these capabilities by pairing an autoregressive reasoner tower with a diffusion-based generator tower.
Victoria X Lin
@VictoriaLinML
May 11
✨We are showing some experiments with interaction models @thinkymachines: models that could see and hear continuously while processing tasks in the background and generating responses in real-time. Interaction models offer a glimpse into a future where people collaborate with
Thinking Machines
@thinkymachines
May 11
People talk, listen, watch, think, and collaborate at the same time, in real time. We've designed an AI that works with people the same way. We share our approach, early results, and a quick look at our model in action. thinkingmachines.ai/blog/interacti…
00:00
See @VictoriaLinML's full profile
Sign up
Log in

See @VictoriaLinML's full profile