Shengyi Qian

@JasonQSY

Research Scientist at Meta FAIR | Coding & Computer use agents | CS PhD @UMich

Seattle, WA

jasonqsy.github.io

Replies Reposts Media

Pinned
Shengyi Qian
@JasonQSY
Aug 10
Excited to share our work on Muse Glimmer!🚀 One thing I’m particularly excited about is the combination of coding + multimodal agentic capabilities in a 30B open model: → SWE-Bench Pro: 51.2 → CharXiv Reasoning: 78.8 → OSWorld-Verified: 65.9 → ScreenSpot Pro: 75.4
AI at Meta
@AIatMeta
Aug 10
Introducing Muse Glimmer, an open-weight 30B-parameter model optimized for local, always-on agent workflows. Muse Glimmer delivers strong performance on key agentic use cases and benchmarks compared with leading models in its size category, and is designed to run entirely on
3
Shengyi Qian
@JasonQSY
Aug 10
This demo is especially meaningful to me. I’ve been building toward this at Meta for ~2 years: starting with 8B mobile agents in DigiData, then making CUA actually useful with Muse Spark, and now distill it down to Muse Glimmer — running fully locally, even offline.
Francesco
@francedot
Aug 10
1/ Today was the first time offline computer use felt real to us. We ran Muse Glimmer 30B from @AIatMeta locally and watched it operate Notes and Reminders on macOS through Cua Driver We didn’t expect a 30B local model to get this far 🧵
00:00
3
Shengyi Qian
@JasonQSY
Mar 4
Vision isn't an "add-on"—and we have the data to prove it. 👁️⚡️ Thrilled to share our new work on Transfusion-style models. We explored treating visual data as a first-class citizen from day one, from architecture to scaling behavior. Check it out: 🔗 beyond-llms.github.io
David Fan
@DavidJFan
Mar 4
[1/9] What happens when you treat vision as a first-class citizen during multimodal pretraining? To find out, we studied the design space of training Transfusion-style models that input and output all modalities, from scratch. Here is what we learned about visual representations,
1
Shengyi Qian
@JasonQSY
Feb 19
Excited to share our latest work from Meta Superintelligence Labs! 🚀 We’re moving beyond static AI to agents that actually evolve with you. Our PAHF framework solves "Alignment Drift" through a continuous feedback loop. Check out the paper!
Kaiqu Liang
@kaiqu_liang
Feb 19
New Meta Research 🚀 AI agents are powerful, but don’t stay aligned with you over time. When preferences shift, they don’t adapt. You correct them once…they repeat the mistake. 🤦 Introducing PAHF: continual personalization where agents learn from feedback to stay in sync.
Shengyi Qian
@JasonQSY
Feb 3
We are excited to host the 2nd 3D-LLM / VLA Workshop at CVPR this June! If your research explores the synergy between spatial intelligence, robotics, and language grounding, we invite you to submit your work. We also have an incredible lineup of speakers. Join us!
Yining Hong
@yining_hong
Feb 3
LLMs are now learning space, geometry, and how to move. 🤖📐 The 2nd CVPR 3D-LLM VLA Workshop brings together language, 3D perception, and action for embodied intelligence. 📢 Call for Papers is OPEN: openreview.net/group?id=thecv… 🌐 Website: 3d-llm-vla.github.io If your