Albert Villanova del Moral

albertvillanova

AI & ML interests

ML Engineer @ Hugging Face: Evaluations (Science)

Recent Activity

Organizations

Language Technology Research Group at the University of Helsinki's profile picture Hugging Face's profile picture AI4Bharat's profile picture WMT: Workshop on Statistical Machine Translation's profile picture DAIR.AI's profile picture BigScience Workshop's profile picture Neuropark's profile picture Hugging Face Internal Testing Organization's profile picture superb's profile picture OSCAR's profile picture GEM benchmark's profile picture Tmp Test's profile picture Col·lectivaT's profile picture Wikimedia's profile picture BigScience Catalogue Data's profile picture tmp avm 1's profile picture Softcatalà's profile picture PubMed Central's profile picture Speech Recognition Community Event Version 2's profile picture BIG-bench's profile picture I Hackathon Somos NLP: PLN en Español's profile picture BigScience Biomedical Datasets's profile picture OpenSLR's profile picture BigScience Data's profile picture The UIT Natural Language Processing Group's profile picture Evaluation datasets's profile picture WebNLG's profile picture SomosNLP's profile picture Data's profile picture Datasets Maintainers's profile picture Open-Source AI Meetup's profile picture EuroPython 2022's profile picture FEVER's profile picture BigLAM: BigScience Libraries, Archives and Museums's profile picture BigCode's profile picture Hugging Face H4's profile picture Center for AI Safety's profile picture Hugging Face OSS Metrics's profile picture BigBang's profile picture OPUS's profile picture Aiinnova's profile picture Research Computing Center of Lomonosov Moscow State University's profile picture Open LLM Leaderboard's profile picture University of Edinburgh - Institute for Language, Cognition and Computation's profile picture EdinburghNLP - Natural Language Processing Group at the University of Edinburgh's profile picture Datasets examples's profile picture Demo leaderboard with an integrated backend's profile picture La Leaderboard's profile picture Paris AI Running Club's profile picture HuggingFaceEval's profile picture Legacy Datasets's profile picture Department of Cognitive Science @ JHU's profile picture Google Research Datasets's profile picture Defunct Datasets's profile picture ADE Benchmark Corpus's profile picture Natural Language Processing Group - Athens University of Economics and Business's profile picture OMILab, The Open University of Israel's profile picture hotpotqa's profile picture Universidad de Sevilla - Departamento de Lenguajes y Sistemas Informáticos's profile picture AILAB-VNUHCM's profile picture tweets-hate-speech-detection's profile picture Software Evolution and Architecture Lab's profile picture GRIT ID's profile picture National Center for Sign Language and Gesture Resources's profile picture ParaPat's profile picture Center for SuperIntelligence's profile picture cornell_movie_dialog's profile picture Abuelkhair Corpus's profile picture dataset-org's profile picture Consumer Financial Protection Bureau's profile picture Project Ben-Yehuda - פרויקט בן-יהודה's profile picture Maluuba's profile picture ParaCrawl's profile picture boschresearch's profile picture uestc-swahili's profile picture Language Technology Group, TU Darmstadt) 's profile picture ufldl-stanford's profile picture Statistical and Neural Machine Translation's profile picture Linguateca's profile picture sonos-nlu-benchmark's profile picture Department of Computer Science and Technology (University of Cambridge)'s profile picture Jeopardy Datasets's profile picture ptb-text-only's profile picture BnL Open Data's profile picture china-ai-law-challenge's profile picture hover-nlp's profile picture WHUIR's profile picture cornell-movie-review-data's profile picture Centre for Speech Technology Research - University of Edinburgh's profile picture webnlg-challenge's profile picture Building Educational Applications 2019 Shared Task's profile picture bookcorpus's profile picture convai-challenge's profile picture Large Text Compression Benchmark's profile picture GermanEval's profile picture PKU-TANGENT's profile picture Narodowego Korpusu Języka Polskiego's profile picture Arabic Language Technologies - Qatar Computing Research Institute's profile picture ubuntu-dialogs-corpus's profile picture Korea Maritime and Ocean University's profile picture scan-tasks's profile picture TruthfulQA's profile picture conceptnet5's profile picture li2017dailydialog's profile picture zalando-datasets's profile picture hirupert's profile picture Tokyo Metropolitan University Natural Language Processing Group's profile picture Machine Reading for Question Answering Workshop's profile picture Clinc: Conversational AI Technology's profile picture CMU Festvox Project's profile picture corona-tweet's profile picture SemEval's profile picture quora-competitions's profile picture Electricity Transformer Dataset (ETDataset)'s profile picture ParlAI's profile picture emotone-ar-cicling2017's profile picture SpellOnYou's profile picture Shanasai LLC's profile picture hate-speech-filipino's profile picture code-search-net's profile picture esnli's profile picture dravidianlangtech's profile picture kmi-linguistics's profile picture jnlpba's profile picture Read The Web - Carnegie Mellon University's profile picture Iowa State University's profile picture HDLTex's profile picture peoples-daily-ner's profile picture timit-asr's profile picture ArXiv Community's profile picture UCSD-AI4H's profile picture Ixa - HiTZ's profile picture Large Scale Visual Recognition Challenge's profile picture SNOW - Natural Language Processing Laboratory, Nagaoka University of Technology's profile picture KorQuAD's profile picture LSDSem's profile picture nfL6's profile picture Community Datasets's profile picture ontonotes's profile picture factckbr's profile picture QAngaroo's profile picture Centre for Text Technology - Humanities - NWU's profile picture halabi2016's profile picture dki-lab's profile picture billion-word-benchmark's profile picture Universal Morphology's profile picture hate-speech-portuguese's profile picture senti-lex's profile picture universal-dependencies's profile picture achrafothman's profile picture lince-benchmark's profile picture eraser-benchmark's profile picture Turkic Interlingua - TIL's profile picture Center for Language Technologies - De La Salle University's profile picture Wongnai's profile picture open-llm-leaderboard-react's profile picture Prompt Leaderboard's profile picture smolagents's profile picture smolagents Tools's profile picture

albertvillanova's activity

posted an update 9 days ago
view post
Post
3554
🚀 New smolagents update: Safer Local Python Execution! 🦾🐍

With the latest release, we've added security checks to the local Python interpreter: every evaluation is now analyzed for dangerous builtins, modules, and functions. 🔒

Here's why this matters & what you need to know! 🧵👇

1️⃣ Why is local execution risky? ⚠️
AI agents that run arbitrary Python code can unintentionally (or maliciously) access system files, run unsafe commands, or exfiltrate data.

2️⃣ New Safety Layer in smolagents 🛡️
We now inspect every return value during execution:
✅ Allowed: Safe built-in types (e.g., numbers, strings, lists)
⛔ Blocked: Dangerous functions/modules (e.g., os.system, subprocess, exec, shutil)

3️⃣ Immediate Benefits 💡
- Prevent agents from accessing unsafe builtins
- Block unauthorized file or network access
- Reduce accidental security vulnerabilities

4️⃣ Security Disclaimer ⚠️
🚨 Despite these improvements, local Python execution is NEVER 100% safe. 🚨
If you need true isolation, use a remote sandboxed executor like Docker or E2B.

5️⃣ The Best Practice: Use Sandboxed Execution 🔐
For production-grade AI agents, we strongly recommend running code in a Docker or E2B sandbox to ensure complete isolation.

6️⃣ Upgrade Now & Stay Safe! 🚀
Check out the latest smolagents release and start building safer AI agents today.

🔗 https://github.com/huggingface/smolagents

What security measures do you take when running AI-generated code? Let’s discuss! 👇

#AI #smolagents #Python #Security
  • 2 replies
·
posted an update 10 days ago
view post
Post
3784
🚀 Big news for AI agents! With the latest release of smolagents, you can now securely execute Python code in sandboxed Docker or E2B environments. 🦾🔒

Here's why this is a game-changer for agent-based systems: 🧵👇

1️⃣ Security First 🔐
Running AI agents in unrestricted Python environments is risky! With sandboxing, your agents are isolated, preventing unintended file access, network abuse, or system modifications.

2️⃣ Deterministic & Reproducible Runs 📦
By running agents in containerized environments, you ensure that every execution happens in a controlled and predictable setting—no more environment mismatches or dependency issues!

3️⃣ Resource Control & Limits 🚦
Docker and E2B allow you to enforce CPU, memory, and execution time limits, so rogue or inefficient agents don’t spiral out of control.

4️⃣ Safer Code Execution in Production 🏭
Deploy AI agents confidently, knowing that any generated code runs in an ephemeral, isolated environment, protecting your host machine and infrastructure.

5️⃣ Easy to Integrate 🛠️
With smolagents, you can simply configure your agent to use Docker or E2B as its execution backend—no need for complex security setups!

6️⃣ Perfect for Autonomous AI Agents 🤖
If your AI agents generate and execute code dynamically, this is a must-have to avoid security pitfalls while enabling advanced automation.

⚡ Get started now: https://github.com/huggingface/smolagents

What will you build with smolagents? Let us know! 🚀💡
updated a Space 25 days ago
reacted to m-ric's post with 🚀 about 1 month ago
view post
Post
9786
Introducing 𝗼𝗽𝗲𝗻 𝗗𝗲𝗲𝗽-𝗥𝗲𝘀𝗲𝗮𝗿𝗰𝗵 by Hugging Face! 💥

OpenAI's latest agentic app Deep Research seems really good... But it's closed, as usual.

⏱️ So with a team of cracked colleagues, we set ourselves a 24hours deadline to replicate and open-source Deep Research! ⏱️

➡️ We built open-Deep-Research, an entirely open agent that can: navigate the web autonomously, scroll and search through pages, download and manipulate files, run calculation on data...

We aimed for the best performance: are the agent's answers really rigorous?

On GAIA benchmark, Deep Research had 67% accuracy on the validation set.
➡️ open Deep Research is at 55% (powered by o1), it is:
- the best pass@1 solution submitted
- the best open solution 💪💪

And it's only getting started ! Please jump in, drop PRs, and let's bring it to the top !

Read the blog post 👉 https://huggingface.co/blog/open-deep-research
upvoted an article about 1 month ago
view article
Article

DABStep: Data Agent Benchmark for Multi-step Reasoning

63
posted an update about 1 month ago
view post
Post
3790
🚀 Introducing @huggingface Open Deep-Research💥

In just 24 hours, we built an open-source agent that:
✅ Autonomously browse the web
✅ Search, scroll & extract info
✅ Download & manipulate files
✅ Run calculations on data

55% on GAIA validation set! Help us improve it!💡
https://huggingface.co/blog/open-deep-research
  • 3 replies
·
upvoted 2 articles about 1 month ago
view article
Article

Open-source DeepResearch – Freeing our search agents

1.17k
published an article about 1 month ago
view article
Article

Open-source DeepResearch – Freeing our search agents

1.17k