andito/faster-qwen3-tts-usage
20.5 kB
Andres Marafioti
andito
AI & ML interests
Multimodal models, VLM and TTS
Recent Activity
new activity 32 minutes ago
vlmbook/notebooks:Missing code updated a dataset about 1 hour ago
vlmbook/notebooks published a bucket about 23 hours ago
smolagents/demo-s2s-dashboardOrganizations
Posts 9
Post
2836
Finally, our new paper is out! "𝗙𝗶𝗻𝗲𝗩𝗶𝘀𝗶𝗼𝗻: 𝗢𝗽𝗲𝗻 𝗗𝗮𝘁𝗮 𝗜𝘀 𝗔𝗹𝗹 𝗬𝗼𝘂 𝗡𝗲𝗲𝗱"! 🥳
FineVision: Open Data Is All You Need (2510.17269)
If you've ever trained a VLM, you know this problem: nobody shares their data mixtures. It's a black box, making replicating SOTA work impossible.
We wanted to change that.
FineVision unifies 200 sources into 24 million samples. With 17.3 million images and 9.5 billion answer tokens, it's the largest open resource of its kind.
In the paper, we share how we built it:
🔍 finding and cleaning data at scale
🧹 removing excessive duplicates across sources
🤗 decontaminating against 66 public benchmarks
My favorite part is Figure 6 (in the video!). It's our visual diversity analysis. It shows that FineVision isn't just bigger; it's more balanced and conceptually richer than other open datasets.
NVIDIA's Eagle 2 paper highlighted just how critical this visual diversity is, and our results confirm it: models trained on FineVision consistently outperform those trained on any other open dataset on 11 benchmarks!
🎉 To celebrate the paper, I’m also releasing a concatenated and shuffled version of the full dataset! 👉
It’s ready to stream, so you can start training your own models right away:
from datasets import load_dataset
d = load_dataset("HuggingFaceM4/FineVision_full_shuffled", split="train", streaming=True)
print(next(iter(d)))
A big shoutout to the first authors: Luis Wiedmann and Orr Zohar. They are rockstars!
FineVision: Open Data Is All You Need (2510.17269)
If you've ever trained a VLM, you know this problem: nobody shares their data mixtures. It's a black box, making replicating SOTA work impossible.
We wanted to change that.
FineVision unifies 200 sources into 24 million samples. With 17.3 million images and 9.5 billion answer tokens, it's the largest open resource of its kind.
In the paper, we share how we built it:
🔍 finding and cleaning data at scale
🧹 removing excessive duplicates across sources
🤗 decontaminating against 66 public benchmarks
My favorite part is Figure 6 (in the video!). It's our visual diversity analysis. It shows that FineVision isn't just bigger; it's more balanced and conceptually richer than other open datasets.
NVIDIA's Eagle 2 paper highlighted just how critical this visual diversity is, and our results confirm it: models trained on FineVision consistently outperform those trained on any other open dataset on 11 benchmarks!
🎉 To celebrate the paper, I’m also releasing a concatenated and shuffled version of the full dataset! 👉
HuggingFaceM4/FineVision_full_shuffled It’s ready to stream, so you can start training your own models right away:
from datasets import load_dataset
d = load_dataset("HuggingFaceM4/FineVision_full_shuffled", split="train", streaming=True)
print(next(iter(d)))
A big shoutout to the first authors: Luis Wiedmann and Orr Zohar. They are rockstars!
Articles 19
Article
20
Hugging Face and Cerebras bring Gemma 4 to real-time voice AI
papers about VLM reasoning
-
VL-Rethinker: Incentivizing Self-Reflection of Vision-Language Models with Reinforcement Learning
Paper • 2504.08837 • Published • 45 -
OpenVLThinker: An Early Exploration to Complex Vision-Language Reasoning via Iterative Self-Improvement
Paper • 2503.17352 • Published • 24 -
Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling
Paper • 2412.05271 • Published • 162 -
R1-Omni: Explainable Omni-Multimodal Emotion Recognition with Reinforcing Learning
Paper • 2503.05379 • Published • 38
papers about VLM reasoning
-
VL-Rethinker: Incentivizing Self-Reflection of Vision-Language Models with Reinforcement Learning
Paper • 2504.08837 • Published • 45 -
OpenVLThinker: An Early Exploration to Complex Vision-Language Reasoning via Iterative Self-Improvement
Paper • 2503.17352 • Published • 24 -
Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling
Paper • 2412.05271 • Published • 162 -
R1-Omni: Explainable Omni-Multimodal Emotion Recognition with Reinforcing Learning
Paper • 2503.05379 • Published • 38
Papers that I've read or want to read
spaces 13
Sleeping
Agents
Ml Intern Someid
🎯
Display an interactive tracking dashboard
Running
Reachy
Reachy Mini Conversation App
🎤
Talk with Reachy Mini!
Sleeping
Agents
Mlintern Convfillq
🎯
Show an interactive tracking dashboard
Running
Reachy
1
Standby
🌙
Ambient standby motion for Reachy Mini.
Running
Featured
93
Parakeet STT Progressive Transcription
🎤
Transcribe speech to text instantly with WebGPU acceleration
Running
Reachy
4
Reachy Pocket TTS Demo
🗣
Text-to-speech with head wobble using pocket-tts
models 13
andito/smolvlm-encoder-free-finevisionmax
0.1B • Updated • 234
andito/convfill-qwen35-4b-repro
Updated
andito/convfill-qwen35-4b-test
Updated
andito/s2s-endpoint
Updated
andito/nanoVLM
Image-Text-to-Text • 0.2B • Updated • 5 • 2
andito/nanoVLM-500M
Image-Text-to-Text • 0.5B • Updated • 5 • 1
andito/moondream05
Updated
andito/SmolVLM-Base-vqav2
Updated
andito/mlx_summarization
Text Generation • 2B • Updated • 13 • 1
andito/SmolLM2-1.7B-Instruct-F16-GGUF
2B • Updated • 32 • 2
datasets 12
andito/qwentts-cpp-python-wheels
Updated • 146
andito/convfill-qwen35-synthetic
Viewer • Updated • 223 • 57
andito/transformers-pr-triage
Viewer • Updated • 50 • 16 • 1
andito/blog-images
Viewer • Updated • 9 • 197
andito/test_olmocr_documents_qa
Viewer • Updated • 92 • 13
andito/google-landmarks
Viewer • Updated • 1.26M • 416 • 1
andito/Objects365_test
Viewer • Updated • 100 • 18
andito/clevr-math-deduplicated
Viewer • Updated • 70k • 76 • 1
andito/ai2d-merged
Viewer • Updated • 4.86k • 42
andito/mathwriting-google
Viewer • Updated • 656k • 543 • 8