3 48 53

Brigitte Tousignant

BrigitteTousi

AI & ML interests

None yet

Recent Activity

upvoted an article 20 days ago

Highlights from the First ICLR 2025 Watermarking Workshop

upvoted an article 26 days ago

NVIDIA's GTC 2025 Announcement for Physical AI Developers: New Open Models and Datasets

reacted to giadap's post with 🤗 27 days ago

Ever notice how some AI assistants feel like tools while others feel like companions? Turns out, it's not always about fancy tech upgrades, because sometimes it's just clever design. Our latest blog post at Hugging Face dives into how minimal design choices can completely transform how users experience AI. We've seen our community turn the same base models into everything from swimming coaches to interview prep specialists with surprisingly small tweaks. The most fascinating part? When we tested identical models with different "personalities" in our Inference Playground, the results were mind-blowing. Want to experiment yourself? Our Inference Playground lets anyone (yes, even non-coders!) test these differences in real-time. You can: - Compare multiple models side-by-side - Customize system prompts - Adjust parameters like temperature - Test multi-turn conversations It's fascinating how a few lines of instruction text can transform the same AI from strictly professional to seemingly caring and personal, without changing a single line of code in the model itself. Read more here: https://huggingface.co/blog/giadap/ai-personas

View all activity

Organizations

BrigitteTousi's activity

reacted to giadap's post with 🤗❤️ 27 days ago

Post

4204

Ever notice how some AI assistants feel like tools while others feel like companions? Turns out, it's not always about fancy tech upgrades, because sometimes it's just clever design.

Our latest blog post at Hugging Face dives into how minimal design choices can completely transform how users experience AI. We've seen our community turn the same base models into everything from swimming coaches to interview prep specialists with surprisingly small tweaks.

The most fascinating part? When we tested identical models with different "personalities" in our Inference Playground, the results were mind-blowing.

Want to experiment yourself? Our Inference Playground lets anyone (yes, even non-coders!) test these differences in real-time. You can:

- Compare multiple models side-by-side
- Customize system prompts
- Adjust parameters like temperature
- Test multi-turn conversations

It's fascinating how a few lines of instruction text can transform the same AI from strictly professional to seemingly caring and personal, without changing a single line of code in the model itself.

Read more here: https://huggingface.co/blog/giadap/ai-personas

reacted to DawnC's post with 🔥 27 days ago

Post

5338

VisionScout — Now with Video Analysis! 🚀

I’m excited to announce a major update to VisionScout, my interactive vision tool that now supports VIDEO PROCESSING, in addition to powerful object detection and scene understanding!

⭐️ NEW: Video Analysis Is Here!
🎬 Upload any video file to detect and track objects using YOLOv8.
⏱️ Customize processing intervals to balance speed and thoroughness.
📊 Get comprehensive statistics and summaries showing object appearances across the entire video.

What else can VisionScout do?

🖼️ Analyze any image and detect 80 object types with YOLOv8.
🔄 Switch between Nano, Medium, and XLarge models for speed or accuracy.
🎯 Filter by object classes (people, vehicles, animals, etc.) to focus on what matters.
📊 View detailed stats on detections, confidence levels, and distributions.
🧠 Understand scenes — interpreting environments and potential activities.
⚠️ Automatically identify possible safety concerns based on detected objects.

What’s coming next?
🔎 Expanding YOLO’s object categories.
⚡ Faster real-time performance.
📱 Improved mobile responsiveness.

My goal:
To bridge the gap between raw detection and meaningful interpretation.
I’m constantly exploring ways to help machines not just "see" but truly understand context — and to make these advanced tools accessible to everyone, regardless of technical background.

Try it now! 🖼️👉 DawnC/VisionScout

If you enjoy VisionScout, a ❤️ Like for this project or feedback would mean a lot and keeps me motivated to keep building and improving!

#ComputerVision #ObjectDetection #VideoAnalysis #YOLO #SceneUnderstanding #MachineLearning #TechForLife

2 replies

reacted to abidlabs's post with 🔥❤️ 27 days ago

Post

4904

HOW TO ADD MCP SUPPORT TO ANY 🤗 SPACE

Gradio now supports MCP! If you want to convert an existing Space, like this one hexgrad/Kokoro-TTS, so that you can use it with Claude Desktop / Cursor / Cline / TinyAgents / or any LLM that supports MCP, here's all you need to do:

1. Duplicate the Space (in the Settings Tab)
2. Upgrade the Gradio sdk_version to 5.28 (in the README.md)
3. Set mcp_server=True in launch()
4. (Optionally) add docstrings to the function so that the LLM knows how to use it, like this:

def generate(text, speed=1):
    """
    Convert text to speech audio.

    Parameters:
        text (str): The input text to be converted to speech.
        speed (float, optional): Playback speed of the generated speech.

That's it! Now your LLM will be able to talk to you 🤯

reacted to fdaudens's post with 🔥 27 days ago

Post

3182

Forget everything you know about transcription models - NVIDIA's parakeet-tdt-0.6b-v2 changed the game for me!

Just tested it with Steve Jobs' Stanford speech and was speechless (pun intended). The video isn’t sped up.

3 things that floored me:
- Transcription took just 10 seconds for a 15-min file
- Got a CSV with perfect timestamps, punctuation & capitalization
- Stunning accuracy (correctly captured "Reed College" and other specifics)

NVIDIA also released a demo where you can click any transcribed segment to play it instantly.

The improvement is significant: number 1 on the ASR Leaderboard, 6% error rate (best in class) with complete commercial freedom (cc-by-4.0 license).

Time to update those Whisper pipelines! H/t @Steveeeeeeen for the finding!

Model: nvidia/parakeet-tdt-0.6b-v2
Demo: nvidia/parakeet-tdt-0.6b-v2
ASR Leaderboard: hf-audio/open_asr_leaderboard

1 reply

reacted to linoyts's post with ❤️ 27 days ago

Post

3184

FramePack is hands down one of the best OS releases in video generation 🙇🏻‍♀️🤯
✅ fully open sourced + amazing quality + reduced memory + improved speed
but more even - its gonna facilitate *soooo* many downstream applications
like this version adapted for landscape rotation 👇https://huggingface.co/spaces/tori29umai/FramePack_rotate_landscape

2 replies

reacted to jeffboudier's post with 🚀👀 27 days ago

Post

3012

So many orgs on HF would really benefit from security and governance built into Enterprise Hub - I wrote a guide on why and how upgrade: jeffboudier/how-to-upgrade-to-enterprise

For instance, did you know about Resource Groups?

reacted to Jaward's post with 👀 about 1 month ago

Post

2252

New reasoning algo just dropped: Adaptive Parallel Reasoning
“we propose Adaptive Parallel Reasoning (APR), a novel reasoning framework that enables language models to orchestrate both serialized and parallel computations end-to-end. APR generalizes existing reasoning methods by enabling adaptive multi-threaded inference using spawn() and join() operations.”
Paper: https://arxiv.org/pdf/2504.15466
Code: https://github.com/Parallel-Reasoning/APR

reacted to hannayukhymenko's post with 🔥 about 1 month ago

Post

3446

🚀 We are delighted to announce MamayLM, a new state-of-the-art efficient Ukrainian LLM!

📈 MamayLM surpasses similar-sized models in both English and Ukrainian, while matching or overtaking up to 10x larger models.

📊 MamayLM is a 9B model that can run on a single GPU, enabling cost-efficient AI autonomy and adoption across sectors in Ukraine such as education, legal, healthcare, public services and others (e.g., by specializing it to particular use cases). MalayLM is also attractive for organizations wishing to preserve data privacy as it s efficiency allows it to run on a local machine.

🧠 MamayLM is trained on high-quality Ukrainian data and understands Ukrainian language, culture, and history. It is built on top of Google’s Gemma 2 9B model, but uses a number of new advances stemming from INSAIT’s experience in creating BgGPT, a Bulgarian LLM we released last year, now adopted nationwide and profiled several times by Google as a worldwide success case.

🤝 MamayLM is developed in a collaboration between researchers at INSAIT and ETH Zürich and is trained entirely via donations to INSAIT for AI compute resources.

📥 MamayLM is now freely available to download on INSAIT’s HuggingFace in both full and quantized versions. We also publicly release all Ukrainian benchmarks we evaluated on.

📝 Further, we release blog posts in both English and Ukrainian, sharing our approach to creating MamayLM, hoping to drive further improvements by the community.

🌎 The release of LLMs for various languages is part of INSAIT’s mission in ensuring countries can achieve AI autonomy in a cost-efficient, controlled, safe and predictable manner.

MamayLM model and benchmarks:

INSAIT-Institute
Blog (EN): https://huggingface.co/blog/INSAIT-Institute/mamaylm
Blog (UKR): https://huggingface.co/blog/INSAIT-Institute/mamaylm-ukr

1 reply

reacted to davanstrien's post with 🔥❤️ about 1 month ago

Post

2203

Came across a very nice submission from @marcodsn for the reasoning datasets competition (https://huggingface.co/blog/bespokelabs/reasoning-datasets-competition).

The dataset distils reasoning chains from arXiv research papers in biology and economics. Some nice features of the dataset:

- Extracts both the logical structure AND researcher intuition from academic papers
- Adopts the persona of researchers "before experiments" to capture exploratory thinking
- Provides multi-short and single-long reasoning formats with token budgets - Shows 7.2% improvement on MMLU-Pro Economics when fine-tuning a 3B model

It's created using the Curator framework with plans to scale across more scientific domains and incorporate multi-modal reasoning with charts and mathematics.

I personally am very excited about datasets like this, which involve creativity in their creation and don't just rely on $$$ to produce a big dataset with little novelty.

Dataset can be found here: marcodsn/academic-chains (give it a like!)

reacted to merve's post with 🔥 about 1 month ago

Post

3425

New foundation model on image and video captioning just dropped by NVIDIA AI 🔥

Describe Anything Model (DAM) is a 3B vision language model to generate detailed captions with localized references 😮

The team released the models, the dataset, a new benchmark and a demo 🤩 nvidia/describe-anything-680825bb8f5e41ff0785834c

Most of the vision LMs focus on image as a whole, lacking localized references in captions, and not taking in visual prompts (points, boxes, drawings around objects)

DAM addresses this on two levels: new vision backbone that takes in focal crops and the image itself, and a large scale dataset 👀

They generate a dataset by extending existing segmentation and referring expression generation datasets like REFCOCO, by passing in the images and classes to VLMs and generating captions.

Lastly, they also release a new benchmark again with self-supervision, they use an LLM to evaluate the detailed captions focusing on localization 👏

reacted to davidberenstein1957's post with 🚀 about 1 month ago

Post

2192

🔥 Announcing FLUX-Juiced: The Fastest Image Generation Endpoint (2.6x faster)!

Optimisations are widely applied and can reduce inference time, but their impact on quality often remains unclear, so we decided to challenge the status quo and create our own optimised version of FLUX.1[dev] called FLUX-juiced.

Blog: https://huggingface.co/blog/PrunaAI/flux-fastest-image-generation-endpoint

reacted to AdinaY's post with 🔥 about 1 month ago

Post

3512

MAGI-1 🪄 the autoregressive diffusion video model, released by Sand AI

sand-ai/MAGI-1

✨ 24B with Apache 2.0
✨ Strong temporal consistency
✨ Benchmark-topping performance

1 reply

reacted to clem's post with ❤️🔥 about 1 month ago

Post

4026

Energy is a massive constraint for AI but do you even know what energy your chatGPT convos are using?

We're trying to change this by releasing ChatUI-energy, the first interface where you see in real-time what energy your AI conversations consume. Great work from @jdelavande powered by spaces & TGI, available for a dozen of open-source models like Llama, Mistral, Qwen, Gemma and more.

jdelavande/chat-ui-energy

Should all chat interfaces have this? Just like ingredients have to be shown on products you buy, we need more transparency in AI for users!

3 replies

reacted to meg's post with ❤️🔥 about 1 month ago

Post

2552

New launch: See the energy use of chatbot conversations, in real time. =)
jdelavande/chat-ui-energy
Great work from @JulienDelavande !