Unveiling and Consulting Core Experts in Retrieval-Augmented MoE-based LLMs
Paper
•
2410.15438
•
Published
AI & ML interests
A one-year long research workshop on large language models: the Summer of Language Models 21 🌸
Recent Activity
pminervini
authored
9
papers
10 days ago
PosterSum: A Multimodal Benchmark for Scientific Poster Summarization
Paper
•
2502.17540
•
Published
•
3
Self-Training Large Language Models for Tool-Use Without Demonstrations
Paper
•
2502.05867
•
Published
Q-Filters: Leveraging QK Geometry for Efficient KV Cache Compression
Paper
•
2503.02812
•
Published
•
10
Parameter-Efficient Fine-Tuning of LLaMA for the Clinical Domain
Paper
•
2307.03042
•
Published
An Analysis of Decoding Methods for LLM-based Agents for Faithful Multi-Hop Question Answering
Paper
•
2503.23415
•
Published
•
1
MedDistant19: Towards an Accurate Benchmark for Broad-Coverage Biomedical Relation Extraction
Paper
•
2204.04779
•
Published
PiCSAR: Probabilistic Confidence Selection And Ranking
Paper
•
2508.21787
•
Published
•
4
Learning GUI Grounding with Spatial Reasoning from Visual Feedback
Paper
•
2509.21552
•
Published
•
11
Post
4353
🌎 AI ethics and sustainability are two sides of the same coin.
In our new blog post with Dr. Sasha Luccioni, we argue that separating them (as is too often the case) means missing the bigger picture of how AI systems impact both people and the planet.
Ethical and sustainable AI development can’t be pursued in isolation. The same choices that affect who benefits or is harmed by AI systems also determine how much energy and resources they consume.
We explore how two key concepts, evaluation and transparency, can serve as bridges between these domains:
📊 Evaluation, by moving beyond accuracy or performance metrics to include environmental and social costs, as we’ve done with tools like the AI Energy Score.
🔍 Transparency, by enabling reproducibility, accountability, and environmental reporting through open tools like the Environmental Transparency Space.
AI systems mirror our priorities. If we separate ethics from sustainability, we risk building technologies that are efficient but unjust, or fair but unsustainable.
Read our blog post here: https://huggingface.co/blog/sasha/ethics-sustainability
AIEnergyScore/Leaderboard
sasha/environmental-transparency
In our new blog post with Dr. Sasha Luccioni, we argue that separating them (as is too often the case) means missing the bigger picture of how AI systems impact both people and the planet.
Ethical and sustainable AI development can’t be pursued in isolation. The same choices that affect who benefits or is harmed by AI systems also determine how much energy and resources they consume.
We explore how two key concepts, evaluation and transparency, can serve as bridges between these domains:
📊 Evaluation, by moving beyond accuracy or performance metrics to include environmental and social costs, as we’ve done with tools like the AI Energy Score.
🔍 Transparency, by enabling reproducibility, accountability, and environmental reporting through open tools like the Environmental Transparency Space.
AI systems mirror our priorities. If we separate ethics from sustainability, we risk building technologies that are efficient but unjust, or fair but unsustainable.
Read our blog post here: https://huggingface.co/blog/sasha/ethics-sustainability
AIEnergyScore/Leaderboard
sasha/environmental-transparency
- 1 reply
Post
10821
One of the hardest challenges in AI safety is finding the right balance: how do we protect people from harm without undermining their agency? This tension is especially visible in conversational systems, where safeguards can sometimes feel more paternalistic than supportive.
In my latest piece for Hugging Face, I argue that open source and community-driven approaches offer a promising (though not exclusive) way forward.
✨ Transparency can make safety mechanisms into learning opportunities.
✨ Collaboration with diverse communities makes safeguards more relevant across contexts.
✨ Iteration in the open lets protections evolve rather than freeze into rigid, one-size-fits-all rules.
Of course, this isn’t a silver bullet. Top-down safety measures will still be necessary in some cases. But if we only rely on corporate control, we risk building systems that are safe at the expense of trust and autonomy.
Read the blog post here: https://huggingface.co/blog/giadap/preserving-agency
In my latest piece for Hugging Face, I argue that open source and community-driven approaches offer a promising (though not exclusive) way forward.
✨ Transparency can make safety mechanisms into learning opportunities.
✨ Collaboration with diverse communities makes safeguards more relevant across contexts.
✨ Iteration in the open lets protections evolve rather than freeze into rigid, one-size-fits-all rules.
Of course, this isn’t a silver bullet. Top-down safety measures will still be necessary in some cases. But if we only rely on corporate control, we risk building systems that are safe at the expense of trust and autonomy.
Read the blog post here: https://huggingface.co/blog/giadap/preserving-agency
- 7 replies
monsoon-nlp
posted
an
update
30 days ago
Post
433
Bio LLMs train on many genomes, but can we encode differences within a species? TomatoTomato adds pangenome tokens to represent a domestic tomato and a wild tomato in one sequence 🍅 🧬
monsoon-nlp/tomatotomato-gLM2-150M-v0.1
monsoon-nlp/tomatotomato-gLM2-150M-v0.1
HugoLaurencon
authored
a
paper
about 1 month ago
Post
2842
🤖 As AI-generated content is shared in movies/TV/across the web, there's one simple low-hanging fruit 🍇 to help know what's real: Visible watermarks. With the Gradio team, I've made sure it's trivially easy to add this disclosure to images, video, chatbot text. See how: https://huggingface.co/blog/watermarking-with-gradio
Thanks to the code collab in particular from @abidlabs and Yuvraj Sharma.
Thanks to the code collab in particular from @abidlabs and Yuvraj Sharma.
jaketae
authored
4
papers
about 2 months ago
What Language Model to Train if You Have One Million GPU Hours?
Paper
•
2210.15424
•
Published
•
2
BLOOM: A 176B-Parameter Open-Access Multilingual Language Model
Paper
•
2211.05100
•
Published
•
34
Enhancing Few-shot Text-to-SQL Capabilities of Large Language Models: A Study on Prompt Design Strategies
Paper
•
2305.12586
•
Published
TESS 2: A Large-Scale Generalist Diffusion Language Model
Paper
•
2502.13917
•
Published
•
6
davanstrien
posted
an
update
about 2 months ago
Post
949
I fine-tuned a smol VLM to generate specialized art history metadata!
https://huggingface.co/davanstrien/iconclass-vlm: Qwen2.5-VL-3B trained using SFT to generate ICONCLASS codes (think Dewey Decimal for art!)
Trained with TRL + HF Jobs - single UV script, no GPU needed!
Space to explore predictions on a test set: davanstrien/iconclass-predictions
Blog soon!
https://huggingface.co/davanstrien/iconclass-vlm: Qwen2.5-VL-3B trained using SFT to generate ICONCLASS codes (think Dewey Decimal for art!)
Trained with TRL + HF Jobs - single UV script, no GPU needed!
Space to explore predictions on a test set: davanstrien/iconclass-predictions
Blog soon!
Post
411
I've noticed something. While we're careful about what we post on social media, we're sharing our deepest and most intimate thoughts with AI chatbots -- health concerns, financial worries, relationship issues, business ideas...
With OpenAI hinting at ChatGPT advertising, this matters more than ever. Unlike banner ads, AI advertising happens within the conversation itself. Sponsors could subtly influence that relationship advice or financial guidance.
The good news? We have options.
🤝 Open source AI models let us keep conversations private, avoid surveillance-based business models, and build systems that actually serve users first.
Read more about it in our latest blog post, co-written with
@frimelle
https://huggingface.co/blog/giadap/privacy-conversational-ai
With OpenAI hinting at ChatGPT advertising, this matters more than ever. Unlike banner ads, AI advertising happens within the conversation itself. Sponsors could subtly influence that relationship advice or financial guidance.
The good news? We have options.
🤝 Open source AI models let us keep conversations private, avoid surveillance-based business models, and build systems that actually serve users first.
Read more about it in our latest blog post, co-written with
@frimelle
https://huggingface.co/blog/giadap/privacy-conversational-ai