←
Fabio Pardo97 posts
Fabio Pardo avatar

Fabio Pardo

@PardoFab

Senior Research Scientist at @GoogleDeepMind. Previously at @ImperialCollege, @Sorbonne_Univ_ and @ENS_ULM.

◷ Joined February 2016▧ 26 Photos and videos
Anian Ruoss avatar
⟳ Fabio Pardo retweeted
Anian Ruoss@anianruoss·15 Jul 2025

Our LMAct benchmark evaluates LMs in dynamic environments (Atari, chess, DM Control) in the zero-to-many-shot regime (up to 1M tokens) With @PardoFab, @SirrahChan, @bonniesjli, Volodymyr Mnih, and Tim Genewein 📅 Tue 15 July ⏰ 11:00 – 13:30 📍East Exhibition Hall A-B #e-1804

Post attachment
Fabio Pardo avatar
Fabio Pardo@PardoFab·10 Dec 2024

Thrilled to be at #neurips this week! Excited to reconnect with friends and colleagues I haven’t seen in a while. If you’d like to meet up, don’t hesitate to reach out, I’ll be stopping by the @GoogleDeepMind booth occasionally.

Post attachment
Fabio Pardo avatar
Fabio Pardo@PardoFab·5 Dec 2024

Genie 2 🧞‍♂️ is a very impressive model and the perspective of generating endless, unique worlds is incredibly exciting! Collaborating with the team has been a truly fun and inspiring experience 😁

Introducing 🧞Genie 2 🧞 - our most capable large-scale foundation world model, which can generate a diverse array of consistent worlds, playable for up to a minute. We believe Genie 2 could unlock the next wave of capabilities for embodied agents 🧠.

0:35
Fabio Pardo avatar
Fabio Pardo@PardoFab·3 Dec 2024

We explored how LLMs tackle low-level control tasks across diverse domains. While there's room to grow, in-context learning and existing image/text tokens can handle diverse observation and action spaces. No special tokens or adapters are needed to play games or control robots!

Ever wonder how well frontier models (Claude 3.5 Sonnet, Gemini 1.5 Flash & Pro, GPT-4o, o1-mini & o1-preview) play Atari, chess, or tic-tac-toe? We present LMAct, an in-context imitation learning benchmark with long multimodal demonstrations (arxiv.org/abs/2412.01441). 🧵 1/N

Post attachment
AK avatar
⟳ Fabio Pardo retweeted
AK@_akhaliq·15 Dec 2023

Google DeepMind announces Vision-Language Models as a Source of Rewards paper page: huggingface.co/papers/2312.0… Building generalist agents that can accomplish many goals in rich open-ended environments is one of the research frontiers for reinforcement learning. A key limiting factor for building generalist agents with RL has been the need for a large number of reward functions for achieving different goals. We investigate the feasibility of using off-the-shelf vision-language models, or VLMs, as sources of rewards for reinforcement learning agents. We show how rewards for visual achievement of a variety of language goals can be derived from the CLIP family of models, and used to train RL agents that can achieve a variety of language goals. We showcase this approach in two distinct visual domains and present a scaling trend showing how larger VLMs lead to more accurate rewards for visual goal achievement, which in turn produces more capable RL agents.

Post attachment
Fabio Pardo avatar
Fabio Pardo@PardoFab·7 Dec 2023

Gemini is a suite of incredibly powerful and general models that push the limits of artificial intelligence. Participating in this massive effort made me feel like I was part of history in the making and I can't wait to see what lies ahead! #geminiai blog.google/technology/ai/go…

Demis Hassabis avatar
⟳ Fabio Pardo retweeted
Demis Hassabis@demishassabis·6 Dec 2023

The Gemini era is here. Thrilled to launch Gemini 1.0, our most capable & general AI model. Built to be natively multimodal, it can understand many types of info. Efficient & flexible, it comes in 3 sizes each best-in-class & optimized for different uses blog.google/technology/ai/go…

Post attachment
Jeff Dean avatar
⟳ Fabio Pardo retweeted
Jeff Dean@JeffDean·6 Dec 2023

I’m very excited to share our work on Gemini today! Gemini is a family of multimodal models that demonstrate really strong capabilities across the image, audio, video, and text domains. Our most-capable model, Gemini Ultra, advances the state of the art in 30 of 32 benchmarks, including 10 of 12 popular text and reasoning benchmarks, 9 of 9 image understanding benchmarks, 6 of 6 video understanding benchmarks, and 5 of 5 speech recognition and speech translation benchmarks. Gemini Ultra is the first model to achieve human-expert performance on MMLU across 57 subjects with a score above 90%. It also achieves a new state-of-the-art score of 62.4% on the new MMMU multimodal reasoning benchmark, outperforming the previous best model by more than 5 percentage points. Gemini was built by an awesome team of people from @GoogleDeepMind, @GoogleResearch, and elsewhere at @Google, and is one of the largest science and engineering efforts we’ve ever undertaken. As one of the two overall technical leads of the Gemini effort, along with my colleague @OriolVinyalsML, I am incredibly proud of the whole team, and we’re so excited to be sharing our work with you today! There’s quite a lot of different material about Gemini available, starting with: Main blog post: blog.google/technology/ai/go… 60-page technical report authored by th Gemini Team: deepmind.google/gemini/gemin… In this thread, I’ll walk you through some of the highlights.

Post attachmentPost attachment
Fabio Pardo avatar
Fabio Pardo@PardoFab·10 Oct 2022

I am incredibly happy to announce that I am joining DeepMind Toronto as a Research Scientist 🎉🇨🇦 Working at @DeepMind on the team led by @VladMnih is a great honor for me. I can't wait to get started!

Post attachment
Fabio Pardo avatar
Fabio Pardo@PardoFab·15 Dec 2021

While a naive “run forward” reward does not provide a strong signal for learning an efficient gait, we found that applying motion capture tracking gave great results. Our dataset contains 35 clips of various behaviours that were also adapted for a Cassie robot model.

Fabio Pardo avatar
Fabio Pardo@PardoFab·15 Dec 2021

Ostriches are very fast bipeds that can sprint at speeds of up to 70 km/h (45 mph). They are therefore ideal to study bio-mechanical locomotion. Our model is based on CT scans and dissections of real ostriches. It contains 50 joints and 120 muscles 🔥