Research Papers

SMX: Sequential Monte Carlo Planning for Expert Iteration

Edan Toledo | Matthew Macfarlane | Donal John Byrne | Siddarth Singh | Paul Duckworth | Alexandre Laterre

ICML 2024 Jul 2024
Figure 1: Diagram depicting a representation of SMX search from left to right. N Rollouts are executed in parallel according to πθ (the sampling policy β). At each step in the environment the particle weights are adjusted, indicated by the particle sizes. We depict two resampling zones where particles are resampled (favouring higher weights) and weights are reset. Finally an improved policy π ′ = Iˆ βπ is constructed from the initial actions from the remaining particles, furthest to the right. This improved policy is then used to update πθ.

Multi-Objective Quality-Diversity for Crystal Structure Prediction

Hannah Janmohamed | Marta Wolinska | Shikha Surana | Aaron Walsh | Thomas Pierrot | Antoine Cully

Gecco 2024 Jul 2024

Overconfident Oracles: Limitations of In Silico Sequence Design Benchmarking

Shikha Surana | Nathan Grinsztajn | Timothy Atkinson | Paul Duckworth | Thomas D. Barrett

ICML 2024 workshop Jul 2024

Generative Model for Small Molecules with Latent Space RL Fine-Tuning to Protein Targets

Ulrich A. Mbou So | Qiulin Li | Dries Smit | Arnu Pretorius | Oliver Bent | Miguel Arbesú

ICML 2024 workshop Jul 2024
Figure 1. Schematic representation of our model’s architecture. A sequence of N tokens is passed as input to our encoder which is a transformer model. The output encoded embeddings of shape N × E are either passed directly to the mean and logvar layers (path 1) or they are first passed to the perceiver resampler layer which maps the encoded embeddings to a reduced dimension of shape LS ×LE (path 2). The mean and logvar layers are linear layers that are applied independently to each sequence dimension. The final reparametrised embeddings are then passed to the decoder transformer model to be used as encoder embeddings in the decoder’s cross-attention layers.

Should we be going MAD?
A Look at Multi-Agent Debate Strategies for LLMs

Andries Petrus Smit | Nathan Grinsztajn | Paul Duckworth | Thomas D Barrett | Arnu Pretorius

ICML 2024 Jul 2024
Recent advancements in large language models (LLMs) underscore their potential for responding to inquiries in various domains. However, ensuring that generative agents provide accurate and reliable answers remains an ongoing challenge. In this context, multi-agent debate (MAD) has emerged as a promising strategy for enhancing the truthfulness of LLMs. We benchmark a range of debating and prompting strategies to explore the trade-offs between cost, time, and accuracy. Importantly, we nd that multi-agent debating systems, in their current form, do not reliably outperform other proposed prompting strategies, such as self-consistency and ensembling using multiple reasoning paths. However, when performing hyperparameter tuning, several MAD systems, such as Multi-Persona, perform better. This suggests that MAD protocols might not be inherently worse than other approaches, but that they are more sensitive to different hyperparameter settings and difcult to optimize. We build on these results to offer insights into improving debating strategies, such as adjusting agent agreement levels, which can signicantly enhance performance and even surpass all other non-debate protocols we evaluated. We provide an open-source repository to the community with several state-of-theart protocols together with evaluation scripts to benchmark across popular research datasets.

Quality-Diversity for One-Shot Biological Sequence Design

Jérémie DONA | Arthur Flajolet | Andrei Marginean | Antoine Cully | Thomas PIERROT

ICML 20224 Jul 2024
Figure 1. Left. Schematic overview of our experimental protocol. An oracle, e.g. an expressive neural network is learned from real data. It enables us to relabel the dataset and emulates wet-lab results. An ensemble of scoring functions are learned from this relabelled dataset. Right. We optimize a MAP-ELITES grid with respect to this ensemble of scoring functions, following eq. (2), and the descriptors of eq. (4)

Likelihood-based fine-tuning of protein language models for few-shot fitness prediction and design

Alex Hawkins-Hooker | Jakub Kmec | Oliver Bent | Paul Duckworth

ICML 2024 workshop Jul 2024
We plot the fraction of the top 30% of sequences in the initial candidate pool that are retrieved by the optimisation process as a function of the number of optimisation rounds for both single and multi-mutant in Figure 1. Across both sets of landscapes, the PoET ranking ensemble outperforms all other methods. In general, the design curves show similar trends to the supervised results

A large language foundational model for edible plant genomes

Javier Mendoza-Revilla | Evan Trop | Liam Gonzalez | Maša Roller | Hugo Dalla-Torre | Bernado de Almedia | Nicolas Lopez Carranza | Guillaume Richard | Marcin Skwark | Karim Beguir | Thomas Pierrot | Marie Lopez

Nature Communications Biology 2024 Jul 2024
AgroNT: a novel large language model that integrates genomes across plants species We developed a transformer-based DNA language model named the Agronomic Nucleotide Transformer (AgroNT), which learned general nucleotide sequence representations from genomic DNA sequences of 48 different plant species (Fig. 1a, Supplementary Fig. 1 and Supplementary Table 1; Methods). Building upon our previous work23, our pre-training strategy involves performing masked language modeling (MLM) on a DNA sequence consisting of ~ 6000 base pairs (bp). Our tokenization algorithm splits the DNA sequence into 6-mers, treating each 6-mer as a token, and masks 15% of the tokens for prediction (Fig. 1b; Methods). For our finetuning strategy, we implemented parameter-efficient fine-tuning using the IA3 technique30. In this approach, we replaced the language model head with a prediction head, using either a classification or regression head based on the task. We kept the weights of the transformer layers and embedding layers frozen, or alternatively, unfroze a small number of the final layers to reduce training time for specific downstream tasks (Fig. 1c; Methods).

Coordination Failure in Cooperative Offline MARL

Callum Rhys Tilbury | Claude Formanek | Louise Beyers | Jonathan Shock | Arnu Pretorius

ICML 2024 ARLET Workshop Jul 2024
Results of PJAP in the Twin Peaks game

Machine Learning of Force Fields for Molecular Dynamics Simulations of Proteins at DFT Accuracy

Mustafa Omar | Sebastien Boyer | Christoph Brunken | Bakary Diallo | Nicolas Lopez Carranza | Oliver Bent

ICLR 2024 GEM Workshop May 2024

Model-Based Reinforcement Learning for Protein Backbone Design

Frédéric Renard | Cyprien Courtot | Oliver Bent

ICLR 2024 GEM Workshop May 2024

Protein binding affinity prediction under multiple substitutions based on eGNNs with residue and atomic graphs and language model information: eGRAL

Arturo Fiorellini-Bernardis | Sebastien Boyer | Christoph Brunken | Bakary Diallo | Karim Beguir | Nicolas Lopez Carranza | Oliver Bent

ICLR 2024 GEM Workshop May 2024