arXiv subjects

Quentin Fournier

Publications and source records attributed to Quentin Fournier.

At least 19 recordsLinked to original sources

arXiv2026

GRAVITY+: reducing non-common-path aberrations for sub-10 {\mu}as astrometric accuracy

GRAVITY is a state-of-the-art instrument for near-infrared astrometric interferometry that routinely achieves astrometric accuracy of 30-100 microarcsecond in its phase-referenced dual-field mode. However, its fundamental limit is not yet reached, and can still be improved by several factors. In this paper, we focus on the effect of systematics, and in particular the effect of non-common path aberrations between the science channel and the metrology signal in the GRAVITY Fiber Coupler. Through comprehensive laboratory measurements using a dedicated fiber coupler replica and phase-shifting interferometry at 1908 nm, we have characterized these high-order wavefront errors with nanometer precision in the laboratory. We characterized on-sky the effect of these high-order wavefront imperfections on narrow-angle astrometry, using observations of the binary system GJ65. As part of the GRAVITY+ project, high-precision mirrors designed for nanometer-level surface quality, bringing an order of magnitude improvement over existing GRAVITY injection optics, are currently in production and will be installed in the fiber coupler units by the end of 2027. This upgrade is expected to enable astrometric accuracy at the sub-10 microarcsecond level in dual-field mode with integration times of just a few minutes.

astro-ph.IM↗

arXiv2026

Using VLTI/GRAVITY+ to determine the identity of a third planet candidate in the PDS 70 system

Detections of protoplanets are rare and protoplanetary disk features mischaracterized as planets are common. PDS 70 is one of only two stars known to host multiple confirmed protoplanets, PDS 70 b and c, and repeat detections of a third point-like source in the system suggest the presence of third inner planet. However, previous observations of this third source are insufficient to distinguish whether it is a planet or a concentrated dust clump in Keplerian motion. Our observations with VLTI/GRAVITY+ did not re-detect this point-like source, suggesting that it is, in fact, a dust clump and not a planet. These observations demonstrate how the angular resolving power of VLTI/GRAVITY+ can be used to distinguish between protoplanets and protoplanetary disk features.

astro-ph.EP↗

arXiv2026

CoPeP: Benchmarking Continual Pretraining for Protein Language Models

Protein language models (pLMs) have recently gained significant attention for their ability to uncover relationships between sequence, structure, and function from evolutionary statistics, thereby accelerating therapeutic drug discovery. These models learn from large protein databases that are continuously updated by the biology community and whose dynamic nature motivates the application of continual learning, not only to keep up with the ever-growing data, but also as an opportunity to take advantage of the temporal meta-information that is created during this process. As a result, we introduce the Continual Pretraining of Protein Language Models (CoPeP) benchmark, a novel benchmark for evaluating continual learning approaches on pLMs. Specifically, we curate a sequence of protein datasets derived from the UniProt Knowledgebase spanning a decade and define metrics to assess pLM performance across 31 protein understanding tasks. We evaluate several methods from the continual learning literature, including replay, unlearning, and plasticity-based methods, some of which have never been applied to models and data of this scale. Our findings reveal that incorporating temporal meta-information improves perplexity by up to 7% even when compared to training on data from all tasks jointly. Moreover, even at scale, several continual learning methods outperform naive continual pretraining. The CoPeP benchmark offers an exciting opportunity to study these methods at scale in an impactful real-world application.

cs.LG↗

arXiv2025

NovoMolGen: Rethinking Molecular Language Model Pretraining

Designing de-novo molecules with desired property profiles requires efficient exploration of the vast chemical space ranging from $10^{23}$ to $10^{60}$ possible synthesizable candidates. While various deep generative models have been developed to design small molecules using diverse input representations, Molecular Large Language Models (Mol-LLMs) based on string representations have emerged as a scalable approach capable of exploring billions of molecules. However, there remains limited understanding regarding how standard language modeling practices such as textual representations, tokenization strategies, model size, and dataset scale impact molecular generation performance. In this work, we systematically investigate these critical aspects by introducing NovoMolGen, a family of transformer-based foundation models pretrained on 1.5 billion molecules for de-novo molecule generation. Through extensive empirical analyses, we identify a weak correlation between performance metrics measured during pretraining and actual downstream performance, revealing important distinctions between molecular and general NLP training dynamics. NovoMolGen establishes new state-of-the-art results, substantially outperforming prior Mol-LLMs and specialized generative models in both unconstrained and goal-directed molecular generation tasks, thus providing a robust foundation for advancing efficient and effective molecular modeling strategies.

cs.LG↗

arXiv2025

CADmium: Fine-Tuning Code Language Models for Text-Driven Sequential CAD Design

Computer-aided design (CAD) is the digital construction of 2D and 3D objects, and is central to a wide range of engineering and manufacturing applications like automobile and aviation. Despite its importance, CAD modeling remains largely a time-intensive, manual task. Recent works have attempted to automate this process with small transformer-based models and handcrafted CAD sequence representations. However, there has been little effort to leverage the potential of large language models (LLMs) for sequential CAD design. In this work, we introduce a new large-scale dataset of more than 170k CAD models annotated with high-quality, human-like descriptions generated with our pipeline based on GPT-4.1. Using this dataset, we fine-tune powerful code-LLMs to generate CAD sequences represented in a JSON-based format from natural language descriptions, demonstrating the viability and effectiveness of this approach for text-conditioned CAD generation. Because simple metrics often fail to reflect the quality of generated objects, we introduce geometric and topological metrics based on sphericity, mean curvature, and Euler characteristic to provide richer structural insights. Our experiments and ablation studies on both synthetic and human-annotated data demonstrate that CADmium is able to automate CAD design, drastically speeding up the design of new objects. The dataset, code, and fine-tuned models are available online.

cs.GR↗

arXiv2025

Small Encoders Can Rival Large Decoders in Detecting Groundedness

Augmenting large language models (LLMs) with external context significantly improves their performance in natural language processing (NLP) tasks. However, LLMs struggle to answer queries reliably when the provided context lacks information, often resorting to ungrounded speculation or internal knowledge. Groundedness - generating responses strictly supported by the context - is essential for ensuring factual consistency and trustworthiness. This study focuses on detecting whether a given query is grounded in a document provided in context before the costly answer generation by LLMs. Such a detection mechanism can significantly reduce both inference time and resource consumption. We show that lightweight, task specific encoder models such as RoBERTa and NomicBERT, fine-tuned on curated datasets, can achieve accuracy comparable to state-of-the-art LLMs, such as Llama3 8B and GPT4o, in groundedness detection while reducing inference latency by orders of magnitude. The code is available at : https://github.com/chandarlab/Hallucinate-less

cs.CL↗

arXiv2025

Structure-Aligned Protein Language Model

Protein language models (pLMs) pre-trained on vast protein sequence databases excel at various downstream tasks but often lack the structural knowledge essential for some biological applications. To address this, we introduce a method to enrich pLMs with structural knowledge by leveraging pre-trained protein graph neural networks (pGNNs). First, a latent-level contrastive learning task aligns residue representations from pLMs with those from pGNNs across multiple proteins, injecting inter-protein structural information. Additionally, a physical-level task integrates intra-protein information by training pLMs to predict structure tokens. Together, the proposed dual-task framework effectively incorporates both inter- and intra-protein structural knowledge into pLMs. Given the variability in the quality of protein structures in PDB, we further introduce a residue loss selection module that uses a small model trained on high-quality structures to select reliable yet challenging residue losses for the pLM to learn. Applying our structure alignment method as a simple, lightweight post-training step to the state-of-the-art ESM2 and AMPLIFY yields notable performance gains. These improvements are consistent across a wide range of tasks, including substantial gains in deep mutational scanning (DMS) fitness prediction and a 59% increase in P@L for ESM2 650M contact prediction on CASP16. Furthermore, we demonstrate that these performance gains are robust, scaling with model sizes from 8M to 650M and extending to different downstream tasks.

cs.LG↗

arXiv2025

NeoBERT: A Next-Generation BERT

Recent innovations in architecture, pre-training, and fine-tuning have led to the remarkable in-context learning and reasoning abilities of large auto-regressive language models such as LLaMA and DeepSeek. In contrast, encoders like BERT and RoBERTa have not seen the same level of progress despite being foundational for many downstream NLP applications. To bridge this gap, we introduce NeoBERT, a next-generation encoder that redefines the capabilities of bidirectional models by integrating state-of-the-art advancements in architecture, modern data, and optimized pre-training methodologies. NeoBERT is designed for seamless adoption: it serves as a plug-and-play replacement for existing base models, relies on an optimal depth-to-width ratio, and leverages an extended context length of 4,096 tokens. Despite its compact 250M parameter footprint, it achieves state-of-the-art results on the massive MTEB benchmark, outperforming BERT large, RoBERTa large, NomicBERT, and ModernBERT under identical fine-tuning conditions. In addition, we rigorously evaluate the impact of each modification on GLUE and design a uniform fine-tuning and evaluation framework for MTEB. We release all code, data, checkpoints, and training scripts to accelerate research and real-world adoption.

cs.CL↗

arXiv2024

Combining Domain and Alignment Vectors to Achieve Better Knowledge-Safety Trade-offs in LLMs

There is a growing interest in training domain-expert LLMs that excel in specific technical fields compared to their general-purpose instruction-tuned counterparts. However, these expert models often experience a loss in their safety abilities in the process, making them capable of generating harmful content. As a solution, we introduce an efficient and effective merging-based alignment method called \textsc{MergeAlign} that interpolates the domain and alignment vectors, creating safer domain-specific models while preserving their utility. We apply \textsc{MergeAlign} on Llama3 variants that are experts in medicine and finance, obtaining substantial alignment improvements with minimal to no degradation on domain-specific benchmarks. We study the impact of model merging through model similarity metrics and contributions of individual models being merged. We hope our findings open new research avenues and inspire more efficient development of safe expert LLMs.

cs.AI↗

arXiv2024

Exploring Quantization for Efficient Pre-Training of Transformer Language Models

The increasing scale of Transformer models has led to an increase in their pre-training computational requirements. While quantization has proven to be effective after pre-training and during fine-tuning, applying quantization in Transformers during pre-training has remained largely unexplored at scale for language modeling. This study aims to explore the impact of quantization for efficient pre-training of Transformers, with a focus on linear layer components. By systematically applying straightforward linear quantization to weights, activations, gradients, and optimizer states, we assess its effects on model efficiency, stability, and performance during training. By offering a comprehensive recipe of effective quantization strategies to be applied during the pre-training of Transformers, we promote high training efficiency from scratch while retaining language modeling ability. Code is available at https://github.com/chandar-lab/EfficientLLMs.

cs.LG↗

arXiv2024

A Deep Dive into the Trade-Offs of Parameter-Efficient Preference Alignment Techniques

Large language models are first pre-trained on trillions of tokens and then instruction-tuned or aligned to specific preferences. While pre-training remains out of reach for most researchers due to the compute required, fine-tuning has become affordable thanks to parameter-efficient methods such as LoRA and QLoRA. Alignment is known to be sensitive to the many factors involved, including the quantity and quality of data, the alignment method, and the adapter rank. However, there has not yet been an extensive study of their effect on downstream performance. To address this gap, we conduct an in-depth investigation of the impact of popular choices for three crucial axes: (i) the alignment dataset (HH-RLHF and BeaverTails), (ii) the alignment technique (SFT and DPO), and (iii) the model (LLaMA-1, Vicuna-v1.3, Mistral-7b, and Mistral-7b-Instruct). Our extensive setup spanning over 300 experiments reveals consistent trends and unexpected findings. We observe how more informative data helps with preference alignment, cases where supervised fine-tuning outperforms preference optimization, and how aligning to a distinct preference boosts performance on downstream tasks. Through our in-depth analyses, we put forward key guidelines to help researchers perform more effective parameter-efficient LLM alignment.

cs.CL↗

arXiv2024

Manifold Metric: A Loss Landscape Approach for Predicting Model Performance

Determining the optimal model for a given task often requires training multiple models from scratch, which becomes impractical as dataset and model sizes grow. A more efficient alternative is to expand smaller pre-trained models, but this approach is underutilized due to a limited understanding of its impact on the training dynamics. Existing methods for quantifying this impact have notable limitations, including computation cost. To address this, we introduce a new perspective based on the loss landscape, which has been shown to contain a manifold of linearly connected minima. Specifically, we propose a metric that estimates the size of this manifold to study the impact of model expansion. Our experiments reveal a strong correlation between performance gains and our manifold metric, enabling more informed model comparison and offering a first step toward a geometry-driven approach for reliable model expansion. Notably, our metric outperforms other baselines, even when different types of expansion with equivalent number of parameters are applied to a model.

cs.LG↗

arXiv2023

Language Models for Novelty Detection in System Call Traces

Due to the complexity of modern computer systems, novel and unexpected behaviors frequently occur. Such deviations are either normal occurrences, such as software updates and new user activities, or abnormalities, such as misconfigurations, latency issues, intrusions, and software bugs. Regardless, novel behaviors are of great interest to developers, and there is a genuine need for efficient and effective methods to detect them. Nowadays, researchers consider system calls to be the most fine-grained and accurate source of information to investigate the behavior of computer systems. Accordingly, this paper introduces a novelty detection methodology that relies on a probability distribution over sequences of system calls, which can be seen as a language model. Language models estimate the likelihood of sequences, and since novelties deviate from previously observed behaviors by definition, they would be unlikely under the model. Following the success of neural networks for language models, three architectures are evaluated in this work: the widespread LSTM, the state-of-the-art Transformer, and the lower-complexity Longformer. However, large neural networks typically require an enormous amount of data to be trained effectively, and to the best of our knowledge, no massive modern datasets of kernel traces are publicly available. This paper addresses this limitation by introducing a new open-source dataset of kernel traces comprising over 2 million web requests with seven distinct behaviors. The proposed methodology requires minimal expert hand-crafting and achieves an F-score and AuROC greater than 95% on most novelties while being data- and task-agnostic. The source code and trained models are publicly available on GitHub while the datasets are available on Zenodo.

cs.LG↗

arXiv2022

Automated Cause Analysis of Latency Outliers Using System-Level Dependency Graphs

Detecting performance issues and identifying their root causes in the runtime is a challenging task. Typically, developers use methods such as logging and tracing to identify bottlenecks. These solutions are, however, not ideal as they are time-consuming and require manual effort. In this paper, we propose a method to automate the task of detecting latency outliers using system-level traces and then comparing them to identify the root cause(s). Our method makes use of dependency graphs to show internal interactions between threads and system resources. With these graphs, one can pinpoint where performance issues occur. However, a single trace can be composed of a large number of requests, each generating one graph. To automate the task of identifying outliers within the dataset, we use machine learning density-based models and statistical calculations such as -score. Our evaluation shows an accuracy greater than 97 % on outlier detection, making them appropriate for in-production servers and industry-level use cases.

cs.PF↗

arXiv2021

A Practical Survey on Faster and Lighter Transformers

Recurrent neural networks are effective models to process sequences. However, they are unable to learn long-term dependencies because of their inherent sequential nature. As a solution, Vaswani et al. introduced the Transformer, a model solely based on the attention mechanism that is able to relate any two positions of the input sequence, hence modelling arbitrary long dependencies. The Transformer has improved the state-of-the-art across numerous sequence modelling tasks. However, its effectiveness comes at the expense of a quadratic computational and memory complexity with respect to the sequence length, hindering its adoption. Fortunately, the deep learning community has always been interested in improving the models' efficiency, leading to a plethora of solutions such as parameter sharing, pruning, mixed-precision, and knowledge distillation. Recently, researchers have directly addressed the Transformer's limitation by designing lower-complexity alternatives such as the Longformer, Reformer, Linformer, and Performer. However, due to the wide range of solutions, it has become challenging for researchers and practitioners to determine which methods to apply in practice in order to meet the desired trade-off between capacity, computation, and memory. This survey addresses this issue by investigating popular approaches to make Transformers faster and lighter and by providing a comprehensive explanation of the methods' strengths, limitations, and underlying assumptions.

cs.LG↗

arXiv2021

On Improving Deep Learning Trace Analysis with System Call Arguments

Kernel traces are sequences of low-level events comprising a name and multiple arguments, including a timestamp, a process id, and a return value, depending on the event. Their analysis helps uncover intrusions, identify bugs, and find latency causes. However, their effectiveness is hindered by omitting the event arguments. To remedy this limitation, we introduce a general approach to learning a representation of the event names along with their arguments using both embedding and encoding. The proposed method is readily applicable to most neural networks and is task-agnostic. The benefit is quantified by conducting an ablation study on three groups of arguments: call-related, process-related, and time-related. Experiments were conducted on a novel web request dataset and validated on a second dataset collected on pre-production servers by Ciena, our partnering company. By leveraging additional information, we were able to increase the performance of two widely-used neural networks, an LSTM and a Transformer, by up to 11.3% on two unsupervised language modelling tasks. Such tasks may be used to detect anomalies, pre-train neural networks to improve their performance, and extract a contextual representation of the events.

cs.LG↗

arXiv2021

Empirical comparison between autoencoders and traditional dimensionality reduction methods

In order to process efficiently ever-higher dimensional data such as images, sentences, or audio recordings, one needs to find a proper way to reduce the dimensionality of such data. In this regard, SVD-based methods including PCA and Isomap have been extensively used. Recently, a neural network alternative called autoencoder has been proposed and is often preferred for its higher flexibility. This work aims to show that PCA is still a relevant technique for dimensionality reduction in the context of classification. To this purpose, we evaluated the performance of PCA compared to Isomap, a deep autoencoder, and a variational autoencoder. Experiments were conducted on three commonly used image datasets: MNIST, Fashion-MNIST, and CIFAR-10. The four different dimensionality reduction techniques were separately employed on each dataset to project data into a low-dimensional space. Then a k-NN classifier was trained on each projection with a cross-validated random search over the number of neighbours. Interestingly, our experiments revealed that k-NN achieved comparable accuracy on PCA and both autoencoders' projections provided a big enough dimension. However, PCA computation time was two orders of magnitude faster than its neural network counterparts.

cs.LG↗

arXiv2021

Automatic Cause Detection of Performance Problems in Web Applications

The execution of similar units can be compared by their internal behaviors to determine the causes of their potential performance issues. For instance, by examining the internal behaviors of different fast or slow web requests more closely and by clustering and comparing their internal executions, one can determine what causes some requests to run slowly or behave in unexpected ways. In this paper, we propose a method of extracting the internal behavior of web requests as well as introduce a pipeline that detects performance issues in web requests and provides insights into their root causes. First, low-level and fine-grained information regarding each request is gathered by tracing both the user space and the kernel space. Second, further information is extracted and fed into an outlier detector. Finally, these outliers are then clustered by their behavior, and each group is analyzed separately. Experiments revealed that this pipeline is indeed able to detect slow web requests and provide additional insights into their true root causes. Notably, we were able to identify a real PHP cache contention using the proposed approach.

cs.LG↗