238 citations · 535 across the 27 of their papers we have counts for
27 papers
Gemma 4 Technical Report
Gemma Team, Sherif El Abd, Vaibhav Aggarwal +320
We introduce Gemma 4, a new generation of open-weight, natively multimodal language models in the Gemma model family. Designed to advance compute efficiency and reasoning, the Gemm…
Gemma 3 Technical Report
Gemma Team, Aishwarya Kamath, Johan Ferret +209
We introduce Gemma 3, a multimodal addition to the Gemma family of lightweight open models, ranging in scale from 1 to 27 billion parameters. This version introduces vision underst…
Gemma 2: Improving Open Language Models at a Practical Size
Gemma Team, Morgane Riviere, Shreya Pathak +195
In this work, we introduce Gemma 2, a new addition to the Gemma family of lightweight, state-of-the-art open models, ranging in scale from 2 billion to 27 billion parameters. In th…
Optimistic Games for Combinatorial Bayesian Optimization with Application to Protein Design
Melis Ilayda Bal, Pier Giuseppe Sessa, Mojmir Mutny +1
Bayesian optimization (BO) is a powerful framework to optimize black-box expensive-to-evaluate functions via sequential interactions. In several important problems (e.g. drug disco…
BOND: Aligning LLMs with Best-of-N Distillation
Pier Giuseppe Sessa, Robert Dadashi, Léonard Hussenot +17
Reinforcement learning from human feedback (RLHF) is a key driver of quality and safety in state-of-the-art large language models. Yet, a surprisingly simple and strong inference-t…
WARP: On the Benefits of Weight Averaged Rewarded Policies
Alexandre Ramé, Johan Ferret, Nino Vieillard +7
Reinforcement learning from human feedback (RLHF) aligns large language models (LLMs) by encouraging their generations to have high rewards, using a reward model trained on human p…
Group Robust Preference Optimization in Reward-free RLHF
Shyam Sundhar Ramesh, Yifan Hu, Iason Chaimalas +4
Adapting large language models (LLMs) for specific tasks usually involves fine-tuning through reinforcement learning with human feedback (RLHF) on preference data. While these data…
Gemma: Open Models Based on Gemini Research and Technology
Gemma Team, Thomas Mesnard, Cassidy Hardin +105
This work introduces Gemma, a family of lightweight, state-of-the art open models built from the research and technology used to create Gemini models. Gemma models demonstrate stro…
RecurrentGemma: Moving Past Transformers for Efficient Open Language Models
Aleksandar Botev, Soham De, Samuel L Smith +59
We introduce RecurrentGemma, a family of open language models which uses Google's novel Griffin architecture. Griffin combines linear recurrences with local attention to achieve ex…
DockGame: Cooperative Games for Multimeric Rigid Protein Docking
Vignesh Ram Somnath, Pier Giuseppe Sessa, Maria Rodriguez Martinez +1
Protein interactions and assembly formation are fundamental to most biological processes. Predicting the assembly structure from constituent proteins -- referred to as the protein…
Distributionally Robust Model-based Reinforcement Learning with Large State Spaces
Shyam Sundhar Ramesh, Pier Giuseppe Sessa, Yifan Hu +2
Three major challenges in reinforcement learning are the complex dynamical systems with large state spaces, the costly data acquisition processes, and the deviation of real-world d…
Multitask Learning with No Regret: from Improved Confidence Bounds to Active Learning
Pier Giuseppe Sessa, Pierre Laforgue, Nicolò Cesa-Bianchi +1
Multitask learning is a powerful framework that enables one to simultaneously learn multiple related tasks by sharing information between them. Quantifying uncertainty in the estim…
Adversarial Causal Bayesian Optimization
Scott Sussex, Pier Giuseppe Sessa, Anastasiia Makarova +1
In Causal Bayesian Optimization (CBO), an agent intervenes on an unknown structural causal model to maximize a downstream reward variable. In this paper, we consider the generaliza…
Model-based Causal Bayesian Optimization
Scott Sussex, Anastasiia Makarova, Andreas Krause
How should we intervene on an unknown structural equation model to maximize a downstream variable of interest? This setting, also known as causal Bayesian optimization (CBO), has i…
How Bad is Selfish Driving? Bounding the Inefficiency of Equilibria in Urban Driving Games
Alessandro Zanardi, Pier Giuseppe Sessa, Nando Käslin +3
We consider the interaction among agents engaging in a driving task and we model it as general-sum game. This class of games exhibits a plurality of different equilibria posing the…
Movement Penalized Bayesian Optimization with Application to Wind Energy Systems
Shyam Sundhar Ramesh, Pier Giuseppe Sessa, Andreas Krause +1
Contextual Bayesian optimization (CBO) is a powerful framework for sequential decision-making given side information, with important applications, e.g., in wind energy systems. In…
Efficient Model-based Multi-agent Reinforcement Learning via Optimistic Equilibrium Computation
Pier Giuseppe Sessa, Maryam Kamgarpour, Andreas Krause
We consider model-based multi-agent reinforcement learning, where the environment transition model is unknown and can only be learned via expensive interactions with the environmen…
Contextual Games: Multi-Agent Learning with Side Information
Pier Giuseppe Sessa, Ilija Bogunovic, Andreas Krause +1
We formulate the novel class of contextual games, a type of repeated games driven by contextual information at each round. By means of kernel-based regularity assumptions, we model…
Learning to Play Sequential Games versus Unknown Opponents
Pier Giuseppe Sessa, Ilija Bogunovic, Maryam Kamgarpour +1
We consider a repeated sequential game between a learner, who plays first, and an opponent who responds to the chosen action. We seek to design strategies for the learner to succes…
Mixed Strategies for Robust Optimization of Unknown Objectives
Pier Giuseppe Sessa, Ilija Bogunovic, Maryam Kamgarpour +1
We consider robust optimization problems, where the goal is to optimize an unknown objective function against the worst-case realization of an uncertain parameter. For this setting…
No-Regret Learning from Partially Observed Data in Repeated Auctions
Orcun Karaca, Pier Giuseppe Sessa, Anna Leidi +1
We study a general class of repeated auctions, such as the ones found in electricity markets, as multi-agent games between the bidders. In such a repeated setting, bidders can adap…
No-Regret Learning in Unknown Games with Correlated Payoffs
Pier Giuseppe Sessa, Ilija Bogunovic, Maryam Kamgarpour +1
We consider the problem of learning to play a repeated multi-agent game with an unknown reward function. Single player online learning algorithms attain strong regret bounds when p…
Bounding Inefficiency of Equilibria in Continuous Actions Games using Submodularity and Curvature
Pier Giuseppe Sessa, Maryam Kamgarpour, Andreas Krause
Games with continuous strategy sets arise in several machine learning problems (e.g. adversarial learning). For such games, simple no-regret learning algorithms exist in several ca…
From Uncertainty Data to Robust Policies for Temporal Logic Planning
Pier Giuseppe Sessa, Damian Frick, Tony A. Wood +1
We consider the problem of synthesizing robust disturbance feedback policies for systems performing complex tasks. We formulate the tasks as linear temporal logic specifications an…