Search Results for author:
Found 39 papers, 22 papers with code
Learning Natural Language Generation with Truncated Reinforcement Learning
To our knowledge, it is the first approach that successfully learns a language generation policy without pre-training, using only reinforcement learning.
Aya Expanse: Combining Research Breakthroughs for a New Multilingual Frontier
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 performant multilingual models that match or surpass the capabilities of monolingual models.
Averaging log-likelihoods in direct alignment
To reconcile these approaches, we introduce a principled approach for making direct alignment length-invariant.
Contrastive Policy Gradient: Aligning LLMs on sequence-level scores in a supervised-friendly fashion
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.
Countering Reward Over-optimization in LLM with Demonstration-Guided Reinforcement Learning
While Reinforcement Learning (RL) has been proven essential for tuning large language models (LLMs), it can lead to reward over-optimization (ROO).
Language Evolution with Deep Learning
Computational modeling plays an essential role in the study of language emergence.
Language Model Alignment with Elastic Reset
We periodically reset the online model to an exponentially moving average (EMA) of itself, then reset the EMA model to the initial model.
The Edge of Orthogonality: A Simple View of What Makes BYOL Tick
With simple linear algebra, we show that when using a linear predictor, the optimal predictor is close to an orthogonal projection, and propose a general framework based on orthonormalization that enables to interpret and give intuition on why BYOL works.
SemPPL: Predicting pseudo-labels for better contrastive representations
We propose a new semi-supervised learning method, Semantic Positives via Pseudo-Labels (SemPPL), that combines labelled and unlabelled data to learn informative representations.
Over-communicate no more: Situated RL agents learn concise communication protocols
While it is known that communication facilitates cooperation in multi-agent settings, it is unclear how to design artificial agents that can learn to effectively and efficiently communicate with each other.
Emergent Communication: Generalization and Overfitting in Lewis Games
Lewis signaling games are a class of simple communication games for simulating the emergence of language.
Developing, Evaluating and Scaling Learning Agents in Multi-Agent Environments
The Game Theory & Multi-Agent team at DeepMind studies several aspects of multi-agent learning ranging from computing approximations to fundamental concepts in game theory to simulating social dilemmas in rich spatial environments and training 3-d humanoids in difficult team coordination tasks.
Mastering the Game of Stratego with Model-Free Multiagent Reinforcement Learning
It has the additional complexity of requiring decision-making under imperfect information, similar to Texas hold'em poker, which has a significantly smaller game tree (on the order of $10^{164}$ nodes).
Emergent Communication at Scale
Emergent communication aims for a better understanding of human language evolution and building more efficient representations.
Learning Natural Language Generation from Scratch
This paper introduces TRUncated ReinForcement Learning for Language (TrufLL), an original ap-proach to train conditional language models from scratch by only using reinforcement learning (RL).
Don't Do What Doesn't Matter: Intrinsic Motivation with Action Usefulness
Sparse rewards are double-edged training signals in reinforcement learning: easy to design but hard to optimize.
Broaden Your Views for Self-Supervised Video Learning
Most successful self-supervised learning methods are trained to align the representations of two independent views from the data.
Relevant Action Matters : Motivating agent with action usefulness
We evaluate RAM on the procedurally-generated environment MiniGrid, against state-of-the-art methods.
Bootstrap Your Own Latent - A New Approach to Self-Supervised Learning
From an augmented view of an image, we train the online network to predict the target network representation of the same image under a different augmented view.
BYOL works even without batch statistics
Bootstrap Your Own Latent (BYOL) is a self-supervised learning approach for image representation.
Supervised Seeded Iterated Learning for Interactive Language Learning
Language drift has been one of the major obstacles to train language models through interaction.
A Machine of Few Words -- Interactive Speaker Recognition with Reinforcement Learning
To do so, we cast the speaker recognition task into a sequential decision-making problem that we solve with Reinforcement Learning.
The Monte Carlo Transformer: a stochastic self-attention model for sequence prediction
This paper introduces the Sequential Monte Carlo Transformer, an original approach that naturally captures the observations distribution in a transformer architecture.
Bootstrap your own latent: A new approach to self-supervised Learning
From an augmented view of an image, we train the online network to predict the target network representation of the same image under a different augmented view.
Ranked #2 on
Self-Supervised Person Re-Identification
on SYSU-30k
Countering Language Drift with Seeded Iterated Learning
At each time step, the teacher is created by copying the student agent, before being finetuned to maximize task completion.
HIGhER : Improving instruction following with Hindsight Generation for Experience Replay
Language creates a compact representation of the world and allows the description of unlimited situations and objectives through compositionality.
Self-Educated Language Agent with Hindsight Experience Replay for Instruction Following
Language creates a compact representation of the world and allows the description of unlimited situations and objectives through compositionality.
Correction of Electron Back-scattered Diffraction datasets using an evolutionary algorithm
The quality of the reconstruction of the maps is critical to study the spatial distribution of phases and crystallographic orientation relationships between phases, a key interest in materials science.
Accurate reconstruction of EBSD datasets by a multimodal data approach using an evolutionary algorithm
This function is then applied to un-distort the EBSD data, and the phase information is inferred using the data of the segmented speckle.
Deep Reinforcement Learning and the Deadly Triad
In this work, we investigate the impact of the deadly triad in practice, in the context of a family of popular deep reinforcement learning models - deep Q-networks trained with experience replay - analysing how the components of this system play a role in the emergence of the deadly triad, and in the agent's performance
Visual Reasoning with Multi-hop Feature Modulation
Recent breakthroughs in computer vision and natural language processing have spurred interest in challenging multi-modal tasks such as visual question-answering and visual dialogue.
HoME: a Household Multimodal Environment
We introduce HoME: a Household Multimodal Environment for artificial agents to learn from vision, audio, semantics, physics, and interaction with objects and other agents, all within a realistic context.
FiLM: Visual Reasoning with a General Conditioning Layer
We introduce a general-purpose conditioning method for neural networks called FiLM: Feature-wise Linear Modulation.
Ranked #3 on
Visual Question Answering (VQA)
on CLEVR-Humans
Image Retrieval with Multi-Modal Query
Visual Question Answering (VQA)
+3
Learning Visual Reasoning Without Strong Priors
Previous work has operated under the assumption that visual reasoning calls for a specialized architecture, but we show that a general architecture with proper conditioning can learn to visually reason effectively.
Modulating early visual processing by language
It is commonly assumed that language refers to high-level visual concepts while leaving low-level visual processing unaffected.
End-to-end optimization of goal-driven and visually grounded dialogue systems
End-to-end design of dialogue systems has recently become a popular research topic thanks to powerful tools such as encoder-decoder architectures for sequence-to-sequence learning.
GuessWhat?! Visual object discovery through multi-modal dialogue
Our key contribution is the collection of a large-scale dataset consisting of 150K human-played games with a total of 800K visual question-answer pairs on 66K images.
Hybrid Recommender System based on Autoencoders
A standard model for Recommender Systems is the Matrix Completion setting: given partially known matrix of ratings given by users (rows) to items (columns), infer the unknown ratings.
Ranked #1 on
Recommendation Systems
on Douban
Hybrid Collaborative Filtering with Autoencoders
Such algorithms look for latent variables in a large sparse matrix of ratings.
