Publications

CrediBench: Building Web-Scale Network Datasets for Information Integrity
Emma Kondrup
Sebastian Sabry
Hussein Abdallah
Zachary Yang
James Zhou
Kellin Pelrine
Jean-François Godbout
Michael M. Bronstein
Reihaneh Rabbany
Shenyang Huang
Online misinformation poses an escalating threat, amplified by the Internet's open nature and increasingly capable LLMs that generate persua… (voir plus)sive yet deceptive content. Existing misinformation detection methods typically focus on either textual content or network structure in isolation, failing to leverage the rich, dynamic interplay between website content and hyperlink relationships that characterizes real-world misinformation ecosystems. We introduce CrediBench: a large-scale data processing pipeline for constructing temporal web graphs that jointly model textual content and hyperlink structure for misinformation detection. Unlike prior work, our approach captures the dynamic evolution of general misinformation domains, including changes in both content and inter-site references over time. Our processed one-month snapshot extracted from the Common Crawl archive in December 2024 contains 45 million nodes and 1 billion edges, representing the largest web graph dataset made publicly available for misinformation research to date. From our experiments on this graph snapshot, we demonstrate the strength of both structural and webpage content signals for learning credibility scores, which measure source reliability. The pipeline and experimentation code are all available here, and the dataset is in this folder.
2025-09-27
ArXiv (prépublication)
arxiv.org
arxiv.org
CrystalGym: A New Benchmark for Materials Discovery Using Reinforcement Learning
Prashant Govindarajan
Mathieu Reymond
Antoine Clavaud
Mariano Phielipp
Santiago Miret
Sarath Chandar
In silico design and optimization of new materials primarily relies on high-accuracy atomic simulators that perform density functional theor… (voir plus)y (DFT) calculations. While recent works showcase the strong potential of machine learning to accelerate the material design process, they mostly consist of generative approaches that do not use direct DFT signals as feedback to improve training and generation mainly due to DFT's high computational cost. To aid the adoption of direct DFT signals in the materials design loop through online reinforcement learning (RL), we propose CrystalGym, an open-source RL environment for crystalline material discovery. Using CrystalGym, we benchmark common value- and policy-based reinforcement learning algorithms for designing various crystals conditioned on target properties. Concretely, we optimize for challenging properties like the band gap, bulk modulus, and density, which are directly calculated from DFT in the environment. While none of the algorithms we benchmark solve all CrystalGym tasks, our extensive experiments and ablations show different sample efficiencies and ease of convergence to optimality for different algorithms and environment settings. Additionally, we include a case study on the scope of fine-tuning large language models with reinforcement learning for improving DFT-based rewards. Our goal is for CrystalGym to serve as a test bed for reinforcement learning researchers and material scientists to address these real-world design problems with practical applications. We therefore introduce a novel class of challenges for reinforcement learning methods dealing with time-consuming reward signals, paving the way for future interdisciplinary research for machine learning motivated by real-world applications.
2025-09-27
ArXiv (prépublication)
arxiv.org
arxiv.org
Planner Aware Path Learning in Diffusion Language Models Training
Fred Zhangzhi Peng
Zachary Bezemek
Jarrid Rector-Brooks
Shuibai Zhang
Anru R. Zhang
Michael M. Bronstein
Joey Bose
Alexander Tong
2025-09-27
ArXiv (prépublication)
doi.org
arxiv.org
Planner Aware Path Learning in Diffusion Language Models Training
Fred Zhangzhi Peng
Zachary Bezemek
Jarrid Rector-Brooks
Shuibai Zhang
Anru R. Zhang
Michael M. Bronstein
Joey Bose
Alexander Tong
Diffusion language models have emerged as a powerful alternative to autoregressive models, enabling fast inference through flexible and para… (voir plus)llel generation paths. This flexibility is enabled by new sampling strategies, or planners, that iteratively choose where to denoise along the sequence rather than sampling uniformly at random. However, by modifying reverse paths, planners introduce a mismatch between the uniformly random denoising paths used during training and the planning-based paths used at inference. In this work, we systematically investigate this mismatch and theoretically show that the standard discrete diffusion training evidence lower bound (ELBO) does not accurately describe a denoiser under non-uniform planning. To bridge this gap, we derive a new Planned Evidence Lower Bound (P-ELBO) that directly incorporates planner-based reverse dynamics into the training objective. Building on this, we propose Planner Aware Path Learning (PAPL), a simple and effective modification of the standard masked discrete diffusion loss that aligns training and inference under planned denoisers. Empirically, PAPL delivers consistent improvements across domains, including a 40% relative gain in protein sequence modeling, up to a 4x improvement in MAUVE for text generation, and a 23% relative gain in HumanEval pass@10 for code generation.
2025-09-27
ArXiv (prépublication)
arxiv.org
arxiv.org
Planning with Unified Multimodal Models
Yihao Sun
Zhilong Zhang
Yang Yu
Pierre-Luc Bacon
With the powerful reasoning capabilities of large language models (LLMs) and vision-language models (VLMs), many recent works have explored … (voir plus)using them for decision-making. However, most of these approaches rely solely on language-based reasoning, which limits their ability to reason and make informed decisions. Recently, a promising new direction has emerged with unified multimodal models (UMMs), which support both multimodal inputs and outputs. We believe such models have greater potential for decision-making by enabling reasoning through generated visual content. To this end, we propose Uni-Plan, a planning framework built on UMMs. Within this framework, a single model simultaneously serves as the policy, dynamics model, and value function. In addition, to avoid hallucinations in dynamics predictions, we present a novel approach self-discriminated filtering, where the generative model serves as a self-discriminator to filter out invalid dynamics predictions. Experiments on long-horizon planning tasks show that Uni-Plan substantially improves success rates compared to VLM-based methods, while also showing strong data scalability, requiring no expert demonstrations and achieving better performance under the same training-data size. This work lays a foundation for future research in reasoning and decision-making with UMMs.
2025-09-27
ArXiv (prépublication)
doi.org
arxiv.org
Planning with Unified Multimodal Models
Yihao Sun
Zhilong Zhang
Yang Yu
Pierre-Luc Bacon
With the powerful reasoning capabilities of large language models (LLMs) and vision-language models (VLMs), many recent works have explored … (voir plus)using them for decision-making. However, most of these approaches rely solely on language-based reasoning, which limits their ability to reason and make informed decisions. Recently, a promising new direction has emerged with unified multimodal models (UMMs), which support both multimodal inputs and outputs. We believe such models have greater potential for decision-making by enabling reasoning through generated visual content. To this end, we propose Uni-Plan, a planning framework built on UMMs. Within this framework, a single model simultaneously serves as the policy, dynamics model, and value function. In addition, to avoid hallucinations in dynamics predictions, we present a novel approach self-discriminated filtering, where the generative model serves as a self-discriminator to filter out invalid dynamics predictions. Experiments on long-horizon planning tasks show that Uni-Plan substantially improves success rates compared to VLM-based methods, while also showing strong data scalability, requiring no expert demonstrations and achieving better performance under the same training-data size. This work lays a foundation for future research in reasoning and decision-making with UMMs.
2025-09-27
ArXiv (prépublication)
arxiv.org
arxiv.org
Robust Fine-Tuning from Non-Robust Pretrained Models: Mitigating Suboptimal Transfer With Adversarial Scheduling
Jonas Ngnawe
Maxime Heuillet
Sabyasachi Sahoo
Yann Batiste Pequignot
Ola Ahmad
Audrey Durand
Frederic Precioso
Christian Gagné
Fine-tuning pretrained models is a standard and effective workflow in modern machine learning. However, robust fine-tuning (RFT), which aims… (voir plus) to simultaneously achieve adaptation to a downstream task and robustness to adversarial examples, remains challenging. Despite the abundance of non-robust pretrained models in open-source repositories, their potential for RFT is less understood. We address this knowledge gap by systematically examining RFT from such non-robust models. Our experiments reveal that fine-tuning non-robust models with a robust objective, even under small perturbations, can lead to poor performance, a phenomenon that we dub \emph{suboptimal transfer}. In challenging scenarios (eg, difficult tasks, high perturbation), the resulting performance can be so low that it may be considered a transfer failure. We find that fine-tuning using a robust objective impedes task adaptation at the beginning of training and eventually prevents optimal transfer. However, we propose a novel heuristic, \emph{Epsilon-Scheduling}, a schedule over perturbation strength used during training that promotes optimal transfer. Additionally, we introduce \emph{expected robustness}, a metric that captures performance across a range of perturbations, providing a more comprehensive evaluation of the accuracy-robustness trade-off for diverse models at test time. Extensive experiments on a wide range of configurations (six pretrained models and five datasets) show that \emph{Epsilon-Scheduling} successfully prevents \emph{suboptimal transfer} and consistently improves expected robustness.
2025-09-27
ArXiv (prépublication)
doi.org
arxiv.org
Robust Fine-Tuning from Non-Robust Pretrained Models: Mitigating Suboptimal Transfer With Adversarial Scheduling
Jonas Ngnawe
Maxime Heuillet
Sabyasachi Sahoo
Yann Batiste Pequignot
Ola Ahmad
Audrey Durand
Frederic Precioso
Christian Gagné
Fine-tuning pretrained models is a standard and effective workflow in modern machine learning. However, robust fine-tuning (RFT), which aims… (voir plus) to simultaneously achieve adaptation to a downstream task and robustness to adversarial examples, remains challenging. Despite the abundance of non-robust pretrained models in open-source repositories, their potential for RFT is less understood. We address this knowledge gap by systematically examining RFT from such non-robust models. Our experiments reveal that fine-tuning non-robust models with a robust objective, even under small perturbations, can lead to poor performance, a phenomenon that we dub \emph{suboptimal transfer}. In challenging scenarios (eg, difficult tasks, high perturbation), the resulting performance can be so low that it may be considered a transfer failure. We find that fine-tuning using a robust objective impedes task adaptation at the beginning of training and eventually prevents optimal transfer. However, we propose a novel heuristic, \emph{Epsilon-Scheduling}, a schedule over perturbation strength used during training that promotes optimal transfer. Additionally, we introduce \emph{expected robustness}, a metric that captures performance across a range of perturbations, providing a more comprehensive evaluation of the accuracy-robustness trade-off for diverse models at test time. Extensive experiments on a wide range of configurations (six pretrained models and five datasets) show that \emph{Epsilon-Scheduling} successfully prevents \emph{suboptimal transfer} and consistently improves expected robustness.
2025-09-27
ArXiv (prépublication)
arxiv.org
arxiv.org
$\texttt{BluePrint}$: A Social Media User Dataset for LLM Persona Evaluation and Training
Aur'elien Buck-Kaeffer
Je Qin Chooi
Dan Zhao
Maximilian Puelma Touzel
Kellin Pelrine
Jean-François Godbout
Reihaneh Rabbany
Zachary Yang
Large language models (LLMs) offer promising capabilities for simulating social media dynamics at scale, enabling studies that would be ethi… (voir plus)cally or logistically challenging with human subjects. However, the field lacks standardized data resources for fine-tuning and evaluating LLMs as realistic social media agents. We address this gap by introducing SIMPACT, the SIMulation-oriented Persona and Action Capture Toolkit, a privacy respecting framework for constructing behaviorally-grounded social media datasets suitable for training agent models. We formulate next-action prediction as a task for training and evaluating LLM-based agents and introduce metrics at both the cluster and population levels to assess behavioral fidelity and stylistic realism. As a concrete implementation, we release BluePrint, a large-scale dataset built from public Bluesky data focused on political discourse. BluePrint clusters anonymized users into personas of aggregated behaviours, capturing authentic engagement patterns while safeguarding privacy through pseudonymization and removal of personally identifiable information. The dataset includes a sizable action set of 12 social media interaction types (likes, replies, reposts, etc.), each instance tied to the posting activity preceding it. This supports the development of agents that use context-dependence, not only in the language, but also in the interaction behaviours of social media to model social media users. By standardizing data and evaluation protocols, SIMPACT provides a foundation for advancing rigorous, ethically responsible social media simulations. BluePrint serves as both an evaluation benchmark for political discourse modeling and a template for building domain specific datasets to study challenges such as misinformation and polarization.
2025-09-27
ArXiv (prépublication)
arxiv.org
arxiv.org
$\texttt{BluePrint}$: A Social Media User Dataset for LLM Persona Evaluation and Training
Aur'elien Buck-Kaeffer
Je Qin Chooi
Dan Zhao
Maximilian Puelma Touzel
Kellin Pelrine
Jean-François Godbout
Reihaneh Rabbany
Zachary Yang
Large language models (LLMs) offer promising capabilities for simulating social media dynamics at scale, enabling studies that would be ethi… (voir plus)cally or logistically challenging with human subjects. However, the field lacks standardized data resources for fine-tuning and evaluating LLMs as realistic social media agents. We address this gap by introducing SIMPACT, the SIMulation-oriented Persona and Action Capture Toolkit, a privacy respecting framework for constructing behaviorally-grounded social media datasets suitable for training agent models. We formulate next-action prediction as a task for training and evaluating LLM-based agents and introduce metrics at both the cluster and population levels to assess behavioral fidelity and stylistic realism. As a concrete implementation, we release BluePrint, a large-scale dataset built from public Bluesky data focused on political discourse. BluePrint clusters anonymized users into personas of aggregated behaviours, capturing authentic engagement patterns while safeguarding privacy through pseudonymization and removal of personally identifiable information. The dataset includes a sizable action set of 12 social media interaction types (likes, replies, reposts, etc.), each instance tied to the posting activity preceding it. This supports the development of agents that use context-dependence, not only in the language, but also in the interaction behaviours of social media to model social media users. By standardizing data and evaluation protocols, SIMPACT provides a foundation for advancing rigorous, ethically responsible social media simulations. BluePrint serves as both an evaluation benchmark for political discourse modeling and a template for building domain specific datasets to study challenges such as misinformation and polarization.
2025-09-27
ArXiv (prépublication)
arxiv.org
arxiv.org
Tracing the Representation Geometry of Language Models from Pretraining to Post-training
Melody Zixuan Li
Kumar Krishna Agrawal
Arna Ghosh
Komal K. Teru
Adam Santoro
Guillaume Lajoie
Blake A. Richards
Standard training metrics like loss fail to explain the emergence of complex capabilities in large language models. We take a spectral appro… (voir plus)ach to investigate the geometry of learned representations across pretraining and post-training, measuring effective rank (RankMe) and eigenspectrum decay (
2025-09-27
ArXiv (prépublication)
arxiv.org
arxiv.org
Tracing the Representation Geometry of Language Models from Pretraining to Post-training
Melody Zixuan Li
Kumar Krishna Agrawal
Arna Ghosh
Komal K. Teru
Adam Santoro
Guillaume Lajoie
Blake A. Richards
Standard training metrics like loss fail to explain the emergence of complex capabilities in large language models. We take a spectral appro… (voir plus)ach to investigate the geometry of learned representations across pretraining and post-training, measuring effective rank (RankMe) and eigenspectrum decay (
2025-09-27
ArXiv (prépublication)
arxiv.org
arxiv.org