6 citations · 21 across the 21 of their papers we have counts for
23 papers
Shieldstral
Antonia Calvi, Avinash Sooriyarachchi, Giada Pistilli +273
We introduce Shieldstral, a 3B-parameter policy-adaptive multimodal safety classifier that matches or outperforms models nearly 7 its size on text safety benchmarks and set…
LKValues: Aligning Large Language Models with Sri Lankan Societal Values
Nethmi Muthugala, Supryadi, Surangika Ranathunga +7
Value alignment of Large Language Models (LLMs) has been shown to be culturally biased toward Western norms. This results in the mishandling of local values in multilingual societi…
Voxtral TTS
Mistral-AI, :, Alexander H. Liu +186
We introduce Voxtral TTS, an expressive multilingual text-to-speech model that generates natural speech from as little as 3 seconds of reference audio. Voxtral TTS adopts a hybrid…
Voxtral Realtime
Mistral-AI, :, Alexander H. Liu +166
We introduce Voxtral Realtime, a natively streaming automatic speech recognition model that matches offline transcription quality at sub-second latency. Unlike approaches that adap…
Ministral 3
Alexander H. Liu, Kartik Khandelwal, Sandeep Subramanian +116
We introduce the Ministral 3 series, a family of parameter-efficient dense language models designed for compute and memory constrained applications, available in three model sizes:…
ShiQ: Bringing back Bellman to LLMs
Pierre Clavier, Nathan Grinsztajn, Raphael Avalos +8
The fine-tuning of pre-trained large language models (LLMs) using reinforcement learning (RL) is generally formulated as direct policy optimization. This approach was naturally fav…
Command A: An Enterprise-Ready Large Language Model
Team Cohere, :, Aakanksha +227
In this report we describe the development of Command A, a powerful large language model purpose-built to excel at real-world enterprise use cases. Command A is an agent-optimised…
Overconfident Oracles: Limitations of In Silico Sequence Design Benchmarking
Shikha Surana, Nathan Grinsztajn, Timothy Atkinson +2
Machine learning methods can automate the in silico design of biological sequences, aiming to reduce costs and accelerate medical research. Given the limited access to wet labs, in…
Multilingual Machine Translation with Open Large Language Models at Practical Scale: An Empirical Study
Menglong Cui, Pengzhi Gao, Wei Liu +2
Large language models (LLMs) have shown continuously improving multilingual capabilities, and even small-scale open-source models have demonstrated rapid performance enhancement. I…
Aya Expanse: Combining Research Breakthroughs for a New Multilingual Frontier
John Dang, Shivalika Singh, Daniel D'souza +42
We introduce the Aya Expanse model family, a new generation of 8B and 32B parameter multilingual language models, aiming to address the critical challenge of developing highly perf…
Averaging log-likelihoods in direct alignment
Nathan Grinsztajn, Yannis Flet-Berliac, Mohammad Gheshlaghi Azar +8
To better align Large Language Models (LLMs) with human judgment, Reinforcement Learning from Human Feedback (RLHF) learns a reward model and then optimizes it using regularized RL…
Contrastive Policy Gradient: Aligning LLMs on sequence-level scores in a supervised-friendly fashion
Yannis Flet-Berliac, Nathan Grinsztajn, Florian Strub +8
Reinforcement Learning (RL) has been used to finetune Large Language Models (LLMs) using a reward model trained from preference data, to better align with human judgment. The recen…
Memory-Enhanced Neural Solvers for Routing Problems
Felix Chalumeau, Refiloe Shabe, Noah De Nicola +3
Routing Problems are central to many real-world applications, yet remain challenging due to their (NP-)hard nature. Amongst existing approaches, heuristics often offer the best tra…
Should we be going MAD? A Look at Multi-Agent Debate Strategies for LLMs
Andries Smit, Paul Duckworth, Nathan Grinsztajn +2
Recent advancements in large language models (LLMs) underscore their potential for responding to inquiries in various domains. However, ensuring that generative agents provide accu…
Combinatorial Optimization with Policy Adaptation using Latent Space Search
Felix Chalumeau, Shikha Surana, Clement Bonnet +4
Combinatorial Optimization underpins many real-world applications and yet, designing performant algorithms to solve these complex, typically NP-hard, problems remains a significant…
Jumanji: a Diverse Suite of Scalable Reinforcement Learning Environments in JAX
Clément Bonnet, Daniel Luo, Donal Byrne +21
Open-source reinforcement learning (RL) environments have played a crucial role in driving progress in the development of AI algorithms. In modern RL research, there is a need for…
Winner Takes It All: Training Performant RL Populations for Combinatorial Optimization
Nathan Grinsztajn, Daniel Furelos-Blanco, Shikha Surana +2
Applying reinforcement learning (RL) to combinatorial optimization problems is attractive as it removes the need for expert knowledge or pre-solved instances. However, it is unreal…
Meta-learning from Learning Curves Challenge: Lessons learned from the First Round and Design of the Second Round
Manh Hung Nguyen, Lisheng Sun, Nathan Grinsztajn +1
Meta-learning from learning curves is an important yet often neglected research area in the Machine Learning community. We introduce a series of Reinforcement Learning-based meta-l…
More Efficient Exploration with Symbolic Priors on Action Sequence Equivalences
Toby Johnstone, Nathan Grinsztajn, Johan Ferret +1
Incorporating prior knowledge in reinforcement learning algorithms is mainly an open question. Even when insights about the environment dynamics are available, reinforcement learni…
Low-Rank Projections of GCNs Laplacian
Nathan Grinsztajn, Philippe Preux, Edouard Oyallon
In this work, we study the behavior of standard models for community detection under spectral manipulations. Through various ablation experiments, we evaluate the impact of bandpas…
Interferometric Graph Transform for Community Labeling
Nathan Grinsztajn, Louis Leconte, Philippe Preux +1
We present a new approach for learning unsupervised node representations in community graphs. We significantly extend the Interferometric Graph Transform (IGT) to community labelin…
There Is No Turning Back: A Self-Supervised Approach for Reversibility-Aware Reinforcement Learning
Nathan Grinsztajn, Johan Ferret, Olivier Pietquin +2
We propose to learn to distinguish reversible from irreversible actions for better informed decision-making in Reinforcement Learning (RL). From theoretical considerations, we show…
Geometric Deep Reinforcement Learning for Dynamic DAG Scheduling
Nathan Grinsztajn, Olivier Beaumont, Emmanuel Jeannot +1
In practice, it is quite common to face combinatorial optimization problems which contain uncertainty along with non-determinism and dynamicity. These three properties call for app…