SmolVLM2 📺 Smallest video LM ever 🤏🏻
Collection
11 items
•
Updated
•
29
Adina Yakefu
AdinaY
AI & ML interests
None yet
Recent Activity
upvoted
a
collection
about 10 hours ago
SmolVLM2 📺 Smallest video LM ever 🤏🏻
upvoted
an
article
about 10 hours ago
SigLIP 2: A better multilingual vision language encoder
upvoted
an
article
about 11 hours ago
SmolVLM2: Bringing Video Understanding to Every Device
Organizations
AdinaY's activity
upvoted
a
collection
about 10 hours ago
upvoted
an
article
about 10 hours ago
Article
SigLIP 2: A better multilingual vision language encoder
•
50
upvoted
an
article
about 11 hours ago
Article
SmolVLM2: Bringing Video Understanding to Every Device
•
116
upvoted
a
paper
about 16 hours ago
updated
a
collection
1 day ago
liked
a
Space
1 day ago
posted
an
update
1 day ago
Post
569
VLM-R1🔥bringing DeepSeek’s R1 method to vision language models!
GitHub: https://github.com/om-ai-lab/VLM-R1
Demo: omlab/VLM-R1-Referral-Expression
GitHub: https://github.com/om-ai-lab/VLM-R1
Demo: omlab/VLM-R1-Referral-Expression
liked
a
Space
1 day ago
upvoted
a
paper
1 day ago
liked
a
Space
2 days ago
upvoted
a
paper
2 days ago
reacted to
clem's
post with ❤️🔥
2 days ago
Post
3269
We crossed 1B+ tokens routed to inference providers partners on HF, that we released just a few days ago.
Just getting started of course but early users seem to like it & always happy to be able to partner with cool startups in the ecosystem.
Have you been using any integration and how can we make it better?
https://huggingface.co/blog/inference-providers
Just getting started of course but early users seem to like it & always happy to be able to partner with cool startups in the ecosystem.
Have you been using any integration and how can we make it better?
https://huggingface.co/blog/inference-providers
reacted to
ginipick's
post with 🚀🔥
2 days ago
Post
5618
🚀 FLUX Workflow Canvas
Welcome to Workflow Canvas, your ultimate AI-driven platform for crafting stunning design concepts and intricate workflow diagrams that empower your business! 🤖✨
ginigen/Workflow-Canvas
Features
Product Design 🛠️
Transform your ideas into reality with sleek, industrial product designs that blend modern aesthetics with advanced technology.
Mindmap 🧠
Generate vibrant, educational mind maps that outline your strategies and processes in a clear, visually engaging layout.
Mockup 📱
Quickly prototype intuitive app interfaces and web designs using clean, hand-drawn wireframes that capture your vision.
Infographic 📊
Build polished, data-rich infographics that communicate complex corporate metrics and trends with style and clarity.
Diagram 📈
Illustrate comprehensive, end-to-end business workflows—from market analysis to implementation—with detailed and organized diagrams.
Flowchart 🔄
Design easy-to-follow, hand-drawn style flowcharts that map out your operational processes using vibrant colors and minimalistic icons.
How It Works
Set Your Parameters:
Customize your creative process by adjusting the seed, dimensions, inference steps, and guidance scale through the intuitive sidebar.
Choose Your Visual Style:
Explore our diverse range of tabs—from Product Design and Mindmap to Flowchart—each tailored to a unique creative output.
Get Inspired:
Dive into our rich library of example prompts featuring detailed lists and tree structures to instantly populate your design ideas.
Generate Your Masterpiece:
Click the “Generate” button and watch as your ideas come to life in beautifully rendered images! 🎨
Experience the fusion of art and technology with Workflow Canvas – where your business ideas transform into dynamic, visual masterpieces. Get started today and revolutionize the way you design! 🚀
Welcome to Workflow Canvas, your ultimate AI-driven platform for crafting stunning design concepts and intricate workflow diagrams that empower your business! 🤖✨
ginigen/Workflow-Canvas
Features
Product Design 🛠️
Transform your ideas into reality with sleek, industrial product designs that blend modern aesthetics with advanced technology.
Mindmap 🧠
Generate vibrant, educational mind maps that outline your strategies and processes in a clear, visually engaging layout.
Mockup 📱
Quickly prototype intuitive app interfaces and web designs using clean, hand-drawn wireframes that capture your vision.
Infographic 📊
Build polished, data-rich infographics that communicate complex corporate metrics and trends with style and clarity.
Diagram 📈
Illustrate comprehensive, end-to-end business workflows—from market analysis to implementation—with detailed and organized diagrams.
Flowchart 🔄
Design easy-to-follow, hand-drawn style flowcharts that map out your operational processes using vibrant colors and minimalistic icons.
How It Works
Set Your Parameters:
Customize your creative process by adjusting the seed, dimensions, inference steps, and guidance scale through the intuitive sidebar.
Choose Your Visual Style:
Explore our diverse range of tabs—from Product Design and Mindmap to Flowchart—each tailored to a unique creative output.
Get Inspired:
Dive into our rich library of example prompts featuring detailed lists and tree structures to instantly populate your design ideas.
Generate Your Masterpiece:
Click the “Generate” button and watch as your ideas come to life in beautifully rendered images! 🎨
Experience the fusion of art and technology with Workflow Canvas – where your business ideas transform into dynamic, visual masterpieces. Get started today and revolutionize the way you design! 🚀
- 1 reply
reacted to
m-ric's
post with 👍🚀
2 days ago
Post
2401
Less is More for Reasoning (LIMO): a 32B model fine-tuned with 817 examples can beat o1-preview on math reasoning! 🤯
Do we really need o1's huge RL procedure to see reasoning emerge? It seems not.
Researchers from Shanghai Jiaotong University just demonstrated that carefully selected examples can boost math performance in large language models using SFT —no huge datasets or RL procedures needed.
Their procedure allows Qwen2.5-32B-Instruct to jump from 6.5% to 57% on AIME and from 59% to 95% on MATH, while using only 1% of the data in previous approaches.
⚡ The Less-is-More Reasoning Hypothesis:
‣ Minimal but precise examples that showcase optimal reasoning patterns matter more than sheer quantity
‣ Pre-training knowledge plus sufficient computational resources at inference levels up math skills
➡️ Core techniques:
‣ High-quality reasoning chains with self-verification steps
‣ 817 handpicked problems that encourage deeper reasoning
‣ Enough inference-time computation to allow extended reasoning
💪 Efficiency gains:
‣ Only 817 examples instead of 100k+
‣ 40.5% absolute improvement across 10 diverse benchmarks, outperforming models trained on 100x more data
This really challenges the notion that SFT leads to memorization rather than generalization! And opens up reasoning to GPU-poor researchers 🚀
Read the full paper here 👉 LIMO: Less is More for Reasoning (2502.03387)
Do we really need o1's huge RL procedure to see reasoning emerge? It seems not.
Researchers from Shanghai Jiaotong University just demonstrated that carefully selected examples can boost math performance in large language models using SFT —no huge datasets or RL procedures needed.
Their procedure allows Qwen2.5-32B-Instruct to jump from 6.5% to 57% on AIME and from 59% to 95% on MATH, while using only 1% of the data in previous approaches.
⚡ The Less-is-More Reasoning Hypothesis:
‣ Minimal but precise examples that showcase optimal reasoning patterns matter more than sheer quantity
‣ Pre-training knowledge plus sufficient computational resources at inference levels up math skills
➡️ Core techniques:
‣ High-quality reasoning chains with self-verification steps
‣ 817 handpicked problems that encourage deeper reasoning
‣ Enough inference-time computation to allow extended reasoning
💪 Efficiency gains:
‣ Only 817 examples instead of 100k+
‣ 40.5% absolute improvement across 10 diverse benchmarks, outperforming models trained on 100x more data
This really challenges the notion that SFT leads to memorization rather than generalization! And opens up reasoning to GPU-poor researchers 🚀
Read the full paper here 👉 LIMO: Less is More for Reasoning (2502.03387)
upvoted
2
papers
3 days ago
posted
an
update
3 days ago
Post
4084
🚀 StepFun阶跃星辰 is making BIG open moves!
Last year, their GOT-OCR 2.0 took the community by storm 🔥but many didn’t know they were also building some amazing models. Now, they’ve just dropped something huge on the hub!
📺 Step-Video-T2V: a 30B bilingual open video model that generates 204 frames (8-10s) at 540P resolution with high information density & consistency.
stepfun-ai/stepvideo-t2v
🔊 Step-Audio-TTS-3B : a TTS trained with the LLM-Chat paradigm on a large synthetic dataset, capable of generating RAP & Humming
stepfun-ai/step-audio-67b33accf45735bb21131b0b
Last year, their GOT-OCR 2.0 took the community by storm 🔥but many didn’t know they were also building some amazing models. Now, they’ve just dropped something huge on the hub!
📺 Step-Video-T2V: a 30B bilingual open video model that generates 204 frames (8-10s) at 540P resolution with high information density & consistency.
stepfun-ai/stepvideo-t2v
🔊 Step-Audio-TTS-3B : a TTS trained with the LLM-Chat paradigm on a large synthetic dataset, capable of generating RAP & Humming
stepfun-ai/step-audio-67b33accf45735bb21131b0b
- 3 replies