Linjie (Lindsey) Li
@LINJIEFUN
Followers
2K
Following
817
Statuses
137
researching @Microsoft, @UW, contributing to https://t.co/a3zper7NJG
Seattle, WA
Joined August 2012
Sorry to leave out one important detail on this job posting. The research area is multimodal understanding and generation.
We are hiring full-time/part-time research interns all year round. If you are interested, please send your resume to linjli@microsoft.com.
7
3
86
RT @yining_hong: SlowFast-VGen has been accepted to ICLR as a spotlight paper with scores of 8-8-8-6 š
0
4
0
Our ShowUI has reached 100K+ downloads! Kudos to the team and especially our amazing intern @KevinQHLin. If you are interested in developing computer using agent, we encourage you to try ShowUI!
š Exciting milestone! Our ShowUI model on Hugging Face just surpassed 100K downloads! š Big thanks to everyone exploring GUI automation with our vision-language-action models.
0
3
25
RT @ManlingLi_: š¤Reasoning Agent: A General-Purpose Agent Learning Framework š«DeepSeek-R1 training approach for agents, no SFT, just RL trā¦
0
40
0
RT @KevinQHLin: The OpenAI Operator/CUA looks like an end-to-end Vision-Language Model (VLM) via RL training that takes an image as input,ā¦
0
4
0
RT @will_wang_whc: (5/8) We also try various test-time compute scaling strategies. While they tend to boost model performance, they are farā¦
0
1
0
RT @will_wang_whc: (1/8) Can your MLLM actually reason over text and images? āØIntroducing EMMA: An Enhanced MultiModal ReAsoning Benchmarkā¦
0
5
0
RT @XiyaoWang10: Our code and model is now available: Code Model Feel free to contact me ifā¦
0
24
0
RT @KevinQHLin: š I am honored that our work ShowUI is recognized as one of the Outstanding Paper Award at the NeurIPS Open-World Agent Worā¦
0
8
0
RT @drjingjing2026: 2/3 The speaker chose to specify that the perpetrator is Chinese. To me, this implies the speakerās assumption that beiā¦
0
16
0
RT @furongh: I saw a slide circulating on social media last night while working on a deadline. I didnāt comment immediately because I wanteā¦
0
185
0
RT @drjingjing2026: 1/3 Today, an anecdote shared by an invited speaker at #NeurIPS2024 left many Chinese scholars, myself included, feelinā¦
0
630
0
RT @xyz2maureen: š„Poster: Fri 13 Dec 4:30 pm - 7:30 pm PST (West) It is the first time for me try to sell a new concept that I believe butā¦
0
14
0
RT @furongh: š„ Test-time reasoning for LLMs is trending! GPT-O1 and follow-ups have shown the power of inference-time search. But what abouā¦
0
29
0
RT @oodgnas: We're thrilled to announce the _Workshop on Video-Language Models_ at #NeurIPS2024! Join us, along with leading researchers aā¦
0
6
0
RT @1jaskiratsingh: Prompt: Realistic, real life photo of person, ultra realistic facial details. Top: Flux-Dev Bottom: Flux-Dev + NegToMeā¦
0
2
0
RT @1jaskiratsingh: š„Negative Token Merging: Image-based Adversarial Feature Guidanceš„ NegToMe is training-free and leads to better: diverā¦
0
7
0
Check out our latest work on building a lightweight vision-language-action model for GUI agent control!
āInterested in developing a local multimodal model to control your screen (PC š„ļø or phone š±) like the Claude API? šIntroducing āShowUIāāan open-source, lightweight 2B vision-language-action model designed for GUI agent control š¤! š
1
1
16
RT @yuyangzhao_: ššExcited to introduce GenXD: Generating Any 3D and 4D Scenes! A joint framework for general 3D and 4D generation, supportā¦
0
20
0