Augmenting large language models with chemistry tools

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

The ability to reason, plan and solve highly abstract problems is a hallmark of human intelligence. Recent advancements in artificial intelligence, propelled by deep neural networks, have revolutionized disciplines like computer vision and natural language ...

Beliefs inform the behaviour of forward-thinking agents in complex environments. Recently, sequential Bayesian inference has emerged as a mechanism to study belief formation among agents adapting to dynamical conditions. However, we lack critical theory to ...

Traditional martial arts are treasures of humanity's knowledge and critical carriers of sociocultural memories throughout history. However, such treasured practices have encountered various challenges in knowledge transmission and now feature many entries ...

Organic solvents are ubiquitous in industrial and domestic applications from the production of pharmaceuticals to household consumer products. The negative impact of most traditional solvents, especially aprotic types, on the environment, health, and safet ...

Under resource constraints, LLMs are usually fine- tuned with additional knowledge using Parameter Efficient Fine-Tuning (PEFT), using Low-Rank Adaptation (LoRA) modules. In fact, LoRA injects a new set of small trainable matrices to adapt an LLM to a new ...

Under resource constraints, LLMs are usually fine-tuned with additional knowledge using Parameter Efficient Fine-Tuning (PEFT), using Low-Rank Adaptation (LoRA) modules. In fact, LoRA injects a new set of small trainable matrices to adapt an LLM to a new t ...

The proliferation of microscopy methods for live-cell imaging offers many new possibilities for users but can also be challenging to navigate. The prevailing challenge in live-cell fluorescence microscopy is capturing intra-cellular dynamics while preservi ...

Background and Objective: Computational models of the cardiovascular system allow for a detailed and quantitative investigation of both physiological and pathological conditions, thanks to their ability to combine clinical-possibly patient-specific-data wi ...

EncodingActs investigates how computational methods can facilitate the transmission of multifaceted knowledge within intangible cultural heritage (ICH). ICH, characterized by living, tacit, yet complex epistemic systems, is conventionally viewed as challen ...

Sample efficiency is a fundamental challenge in de novo molecular design. Ideally, molecular generative models should learn to satisfy a desired objective under minimal calls to oracles (computational property predictors). This problem becomes more apparen ...

Geometric properties of lattice quantum gravity in two dimensions are studied numerically via Monte Carlo on Euclidean Dynamical Triangulations. A new computational method is proposed to simulate gravity coupled with fermions, which allows the study of int ...

Human babies have a natural desire to interact with new toys and objects, through which they learn how the world around them works, e.g., that glass shatters when dropped, but a rubber ball does not. When their predictions are proven incorrect, such as whe ...

Transformer models such as GPT generate human-like language and are predictive of human brain responses to language. Here, using functional-MRI-measured brain responses to 1,000 diverse sentences, we first show that a GPT-based encoding model can predict t ...

The escalating energy demand and the imperative necessity to reduce the carbon footprint require transformative approaches to energy conversion. Materials chemistry plays a pivotal role in addressing these global challenges by developing novel materials fo ...

Genome-wide chromatin conformation capture assays provide formidable insights into the spatial organization of genomes. However, due to the complexity of the data structure, their integration in multi-omics workflows remains challenging. We present data st ...

Accurate human trajectory prediction is crucial for applications such as autonomous vehicles, robotics, and surveillance systems. Yet, existing models often fail to fully leverage the non-verbal social cues human subconsciously communicate when navigating ...

Informed by longstanding artistic practice, this doctoral thesis approaches entanglements of Swiss coloniality in Brazil and Switzerland under the lens of land, archive, and visuality. The enduring legacies of imperial capitalism in the former Colonia Leop ...

Geomembrane systems have been used at hydropower plants as rehabilitation and mitigation technology for several decades and are now used worldwide. In the context of planning an energy transition that promotes the sustainable use of water resources for ene ...

A hybrid photothermal catalytic system, which combines both the photochemical (light) and thermal (heat) activation pathways over a bifunctional catalyst, has demonstrated remarkable levels of reaction activity and selectivity when compared with individual ...

It is of great interest to the energy community to understand how the mechano-physico-chemical phenomena that eventually lead to device degradation are related to the startup, operation, and shutdown phases. For electrocatalytic systems operating in liquid ...

Augmenting large language models with chemistry tools

Chat with Graph Search

Infusing structured knowledge priors in neural models for sample-efficient symbolic reasoning

Stochastic pairwise preference convergence in Bayesian agents

Ontology-based Knowledge Representation for Traditional Martial Arts

Development of Sustainable Carbohydrate-Based Solvents by Acetal Functionalisation of Biomass

Beyond fine-tuning: LoRA modules boost near-OOD detection and LLM security

Beyond fine-tuning: LoRA modules boost near-OOD detection and LLM security

Live-cell imaging powered by computation

The role of computational methods in cardiovascular medicine: a narrative review

EncodingActs: Modeling, Representing and Transmitting Embodied Knowledge in Traditional Martial Arts

Augmented Memory: Sample-Efficient Generative Molecular Design with Reinforcement Learning

Hausdorff dimension of fermions on a random lattice

Seeking the new, learning from the unexpected: Computational models of surprise and novelty in the brain

Driving and suppressing the human language network using large language models

Hybrid organic/metal-oxide shells on semiconductor nanocrystals via colloidal atomic layer deposition

Orchestrating chromosome conformation capture analysis with Bioconductor

Social-Transmotion: Promptable Human Trajectory Prediction

Echoing Swiss Coloniality. Land, Archive and Visuality between Brazil and Switzerland

A comprehensive review on geomembrane systems application in hydropower

Heterogeneous catalysis via light-heat dual activation: A path to the breakthrough in C1 chemistry

Quasi-operando Transmission Electron Microscopy Diagnostics for Electrocatalytic Processes in Liquids