Orr Zohar
@orr_zohar
Followers
385
Following
185
Media
18
Statuses
93
PhD Student @Stanford • Researching large multimodal models • @KnightHennessy scholar • Advised by @yeung_levy
Joined May 2023
Excited to present Apollo at #CVPR2025's poster session today! .📽️Apollo explores the video understanding design space. 📷 Visit Poster 296, Today at 5-7pm.
1
10
66
RT @lusxvr: Today, we are open-sourcing our pipeline to deduplicate large-scale image datasets. On one GPU, we can deduplicate 10k images….
0
99
0
RT @_fracapuano: Robotics models are increasingly bulky and difficult to run directly on robots. With @RemiCadene and the team @LeRobotHF a….
0
35
0
RT @micuelll: WE ARE COOKING!! . I’m looking for a creative engineer to join the ride 🤩 .If that’s you, send me a message 🚀. You should be….
0
2
0
RT @Thom_Wolf: New open-source drop from the HF team - nanoVLM. A super tight codebase to learn/train VLM with good performances - inspired….
0
25
0
RT @lusxvr: Today, we are open-sourcing nanoVLM, a pure pytorch library to train a Vision-Language Model from scratch in 750 lines of code.….
0
149
0
RT @andimarafioti: Alert alert, we got our first external contribution to the nanoVLM project! Thank you, @not_so_lain ! .
0
3
0
Excited to present Video-STaR at #ICLR2025’s poster session tomorrow!.🗓️ Visit me at Poster 91, 10:00 AM–12:30 PM.🚀 Dive into our work on advancing video reasoning using self-training:
🚀 Can self-training improve general LVLM performance?.🏎️ How can you adapt your LVLMs to new and diverse applications?.📢 Happy to announce Video-STaR, a self-training approach to utilize any supervision for video instruction tuning!.🧵👇
0
5
18
🚀 Excited to present Video-STaR at #ICLR2025 this week!. Our latest work, recently featured by @StanfordHAI, introduces an AI method that teaches itself to reason about video without costly human labels - opening doors for visually aware AI in sports coaching, education, and.
1
0
5
RT @andimarafioti: @leeeric0 @vikhyatk The values we report can be corroborated with the open-source evaluation from Open Compass. The mode….
0
1
0
RT @andimarafioti: We are taking the most popular open-source reproducible evaluation (OpenCompass). I actually reached out to moondream an….
0
1
0
RT @mervenoyann: SmolVLM paper is out 🔥. It's one of my favorite papers since it contains a ton of findings on training a good smol model 🤯….
0
35
0
RT @andimarafioti: Today, we share the tech report for SmolVLM: Redefining small and efficient multimodal models. 🔥 Explaining how to desig….
0
112
0
🤗The SmolVLM report is out, with all the experiments, findings, and insights that led to high performance at tiny sizes🤏. 📱These models can run on most mobile/edge devices. 📖Give it a look!
Today, we share the tech report for SmolVLM: Redefining small and efficient multimodal models. 🔥 Explaining how to design a tiny 256M VLM that uses less than 1GB of RAM and outperforms our 80B models from 18 months ago!. Here are the coolest insights from our experiments:.✨
0
9
52
RT @TongPetersb: Vision models have been smaller than language models; what if we scale them up?. Introducing Web-SSL: A family of billion-….
0
85
0
RT @andimarafioti: We are so back with Hugging Face’s Smol models 🚀.Usage doubled 🔥 and we’re now at 110k+ MAU 📈.SmolLM, SmolVLM, SmolDocli….
0
4
0