Publications

EmoFI-TTS: Face-Conditioned Expressive Voice Synthesis with Intensity Modulation
Controlling emotional intensity remains challenging in expressive text-to-speech synthesis, particularly when emotion must be inferred witho… (see more)ut explicit labels. We propose EmoFI-TTS, a face-conditioned framework that derives emotion category and intensity from a single facial image while extracting speaker characteristics from reference audio. Modality-specific representations are fused to condition a pretrained speech synthesizer, with cross-speaker training encouraging separation of affect and vocal identity. An intensity-conditioned refinement module enhances the generated mel-spectrogram, while interpolation of learned intensity embeddings enables continuous control without additional training. On speaker-disjoint MEAD evaluation, EmoFI-TTS achieves on average 64.4% and 75.2% objective and subjective emotion intensity accuracies, while retaining low word error rate and high naturalness.
Feasibility and preliminary efficacy of an intervention combining hypnosis and virtual nature exposure in patients following hematopoietic cell transplantation
Audrey Laurin
Valentyn Fournier
Desjardins Orly
Jean Roy
Jean-Samuel Boudreault
Maïa Labelle
Pierre Rainville
Mathieu Landry
Richard LeBlanc
Floriane Rousseaux
David Ogez
Monitorability Is Trainable: Post-Training for Chain-of-Thought Monitorability
Usman Anwar
Tim Bakker
Christos Louizos
David Krueger
Chain-of-thought (CoT) monitoring is one of the few practical tools available for overseeing capable AI systems, but it is fragile: a model'… (see more)s reasoning is only useful to a monitor if it remains coupled to what the model actually does. This coupling can be degraded during training through, for example, CoT compression, optimization against a monitor, and out-of-context generalization from synthetic documents. In this work, we propose an unsupervised post-training objective based on maximizing mutual information between CoT and the output for improving CoT monitorability. Across three model organisms with degraded CoT, it recovers most or all of the lost monitorability. Applied to undegraded policies, it further improves judged monitorability, improves prediction of unsafe behavior by CoT monitors and activation probes, and increases the prevalence of consequential reasoning. These results suggest that monitorability should be treated as a trainable attribute of the policy. A dedicated monitorability post-training stage can extend current practices that protect CoT from direct optimization pressure.
Predictive Spatio-Temporal Scene Graphs for Semi-Static Scenes
We have seen tremendous recent progress in our ability to build "spatio-semantic" representations that enable robots to perform complex reas… (see more)oning across geometry and semantics. However, the vast majority of these methods lack any ability to perform reasoning across time. This is a desirable property in situations where a robot repeatedly observes an environment where instances may change in between observations, but in a structured way. Consider as an example a home environment where the location of a mug typically moves from the cupboard to a countertop to the sink and then back to the cupboard on a daily basis. We should be able to learn this cyclic behavior and use it to predict the state of the mug in the future. In this work, we propose a method that is able to perform this type of tempo-spatio-semantic reasoning. Underpinning the method is a filter, Perpetua
Privacy in Context Is Being Overlooked in the Age of General-Purpose LLMs
Yash More
Marco Romanelli
Ferdinando Fioretto
As large language models (LLMs) continue to grow in scope and capability, privacy concerns are on the rise. Since users increasingly interac… (see more)t with a single general-purpose system across many distinct contexts, there is a natural tendency to pursue a one-size-fits-all solution to privacy. Unfortunately, this overlooks a crucial insight from decades of privacy research: privacy is inherently contextual. In this paper, we argue that existing work in prompt privacy is drifting towards attempts to design a unified framework, which is highly misleading and can foster a false sense of security. Furthermore, we argue that even future work in this direction needs to wrestle with fundamental tensions across various desirable properties of prompt privacy. Thus, such continued attempts towards a unified framework need to be reconsidered. We recommend three critical paths forward: application-specific deployment of LLMs, context-specific evaluation of privacy frameworks, and better privacy literacy.
Reference Manual of MEDiml
Élodie Gillard
Moustafa Amine Bezzahi
Alexander Chum
Ben Coull-Neveu
Mariem Kallel
Oliver Lefebvre
Nicolas Longchamps
Thanh-Tri Nguyen
Ouael Nedjem Eddine Sahbi
Jérémy Dana
Radiomics is the high-throughput extraction of quantitative features (e.g., tumor shape, intensity distributions, and texture) from medical … (see more)images to characterize tissues and uncover disease patterns invisible to the human eye. These features can serve as candidate imaging biomarkers for cancer diagnosis, prognosis, and classification. However, extracting thousands of features makes it difficult to identify the most informative ones for a given clinical task, while implementing an end-to-end workflow can require programming expertise that limits accessibility for clinical researchers. Hence, we propose MEDiml, an open-source, standards-compliant radiomics platform connecting feature extraction, predictive modeling, and interpretation through complementary graphical and programmatic interfaces. MEDiml combines a Python package (MEDiml-pkg) with a graphical desktop application (MEDiml-app) that enables researchers to conduct experiments without writing code. Both interfaces use the same computational implementation, and code generation exports graphically configured workflows as executable Python code, facilitating reproducibility and collaboration between clinical researchers and computational scientists. A typical MEDiml workflow includes image preprocessing, radiomic feature extraction, feature set reduction, model training and evaluation, and interpretation using feature importance. Feature sets can be grouped into levels of radiomic complexity (morphological, intensity-based, textural, and filter-based) to evaluate whether more complex features provide additional predictive value. This reference manual documents the radiomics concepts, workflow, software components, architecture, and installation, compares MEDiml with existing tools, and demonstrates its complexity-driven workflow on five oncological imaging cohorts comprising 2,104 patients. Resources: www.mediml.app.
Towards Faithful Data Selection: Statistical Limits and Scalable Algorithms
Ahmed Mehdi Inane
MAHDI HAGHIFAM
What does it mean to have an optimal data selection algorithm? Optimality is conventionally framed as finding a subset that minimizes the po… (see more)pulation error of the classifier trained only on that subset. Our starting point in this work is first to show that this goal is information-theoretically impossible unless the data selection algorithm has access to a validation set order-wise larger than the training set. This impossibility result motivates shifting from unverifiable population risk minimization to a one-sided guarantee that we refer to as faithfulness: for any candidate subset, we provide an estimable proxy that upper-bounds the difference between training on the full training data and on only the subset. We model training with the Unadjusted Langevin Algorithm and bound the Kullback--Leibler divergence between subset-trained and full-data-trained parameter distributions by the trajectory-accumulated gradient discrepancy. Minimizing this discrepancy gives a principled way to select a subset. Even though the resulting problem is NP-hard, we propose a swap-based local search that decreases the bound at every accepted step. It can therefore refine the output of any selector without worsening its bound. Finally, we provide experimental results on CIFAR10 and CIFAR100 showing that it matches existing data selection baselines. Implementation of our algorithm and the code for reproducing the results are available at: https://github.com/Mehdi-Inane/data_selection_swap.
Towards Consistent Geospatial Representations: Aligning One Encoder to Many Foundation Models
Geospatial foundation models (GFMs) differ widely in pretraining objective, modality and resolution, and none leads across benchmarks. We as… (see more)k whether their representations are complementary, and whether a single encoder can inherit that complementarity. We introduce Pangaea-Latents, an extension of the Pangaea benchmark providing frozen embeddings of
Turning TS2Vec into a Foundation Model for Time Series Classification
Vasilii Feofanov
Zhenghan Tai
Andrei Ermakov
TS2Vec is one of the strongest self-supervised methods for time series classification, introduced in 2022. It is designed to be trained anew… (see more) on every dataset: self-supervised pre-training followed by linear probing. Since then, the field has shifted towards foundation models that reuse one encoder across datasets. Yet TS2Vec offers a compact convolutional architecture that operates directly on temporal samples and accepts variable-length inputs without resampling. We ask whether these properties can be retained when the encoder is pre-trained only once, and show that they can: TS2Vec can essentially be turned into a foundation model. Three changes suffice: pre-train on a synthetic corpus, feed the encoder a raw amplitude view and an instance-normalized shape view of the input through two small stems, and distill one specialist encoder per view into a single encoder. The result, TS2Vec-FM, is a 1.6M-parameter dilated convolutional network that, kept frozen, reaches 83.3% on UCR-128 and 75.3% on UEA-27 under linear probing, within 0.3 pp of MantisV2, the current state of the art, and above TS2Vec trained separately on each target dataset. What we find most interesting is how different TS2Vec-FM is from other foundation models in design: near-parity is reached without attention, without a patch tokenizer, and without intermediate-layer extraction, using an "old-school" convolutional encoder and a two-layer MLP stem.
African Languages AI Safety Readiness Report
Israel Abebe Azime
Jesujoba O. Alabi
Tajuddeen Gwadabe
With the widespread adoption of large language models (LLMs) across languages and domains, AI safety has emerged as a critical global concer… (see more)n. However, due to resource constraints, research and development efforts tend to prioritize a limited number of high-resource languages, leaving many others, especially those spoken in Africa, underrepresented. While existing research on language "resource-ness" has largely examined whether sufficient resources are available to develop language technologies, the question of whether languages are adequately represented in AI safety research has received attention only more recently. This report examines the readiness of African languages for inclusion in AI safety discussions, drawing on existing literature and data. It considers four factors: the availability of AI-relevant resources, including text data; national AI policy support; performance on established text benchmarks; and speaker population. Based on these factors, languages are grouped into four readiness categories: fully ready, mostly ready, emerging, and foundational support needed. This classification is intended to inform the inclusion of African languages in AI safety benchmarks, highlight varying levels of preparedness, and guide strategic investment in data development, policy, and community engagement for underrepresented languages.
Exposing Vulnerability Monoculture Through Systemic Adversarial Robustness
Leo Elmecker-Plakolm
Lukasz Szpruch
Avishek Joey Bose
Matthew Wicker
Beneath the apparent diversity of foundation models lies an increasingly homogeneous technical stack of common training pipelines, distillat… (see more)ion methods, and data. These shared algorithmic choices can expose an otherwise distinct model ecosystem to concentrated risks leading to a vulnerability monoculture. Yet current practice in assessing adversarial robustness is restricted to individual robustness scores and attack transfer rates, leaving open the unexplored fundamental question: how many attacks suffice for catastrophic widespread compromise? In this paper, we investigate the empirical nature of shared vulnerabilities within a model pool and introduce Systemic Adversarial Robustness (SAR), a novel measure of shared vulnerability of a model pool through the attack diversity needed to exploit it. Specifically, SAR interpolates between single-attack transferability and independent per-model robustness: small values reveal a vulnerability monoculture, whereas large values indicate that failures are dispersed across models. We theoretically formulate SAR as a partial set-cover problem with provable approximation guarantees---enabling the development of scalable algorithms to empirically measure the systemic adversarial robustness. We empirically test the shared vulnerability of vision and large language models and characterize their shared collective vulnerability curve. Specifically, we demonstrate that model pools distilled from DeepSeek-R1 and Claude Opus 4.6 exhibit lower estimated systemic robustness than their corresponding parent pools, revealing a potential systemic cost of frontier-model distillation. Our framework seeks to establish vulnerability monoculture as a measurable target for a more wholistic adversarial evaluation of model populations.
HarnessRL: Co-Evolving Policies with a Just-in-Time Training Harness for Open-Ended RL
Ting-En Lin
Yuchuan Wu
Pinyi Zhang
Caixin Kang
Ling Li
Bingxue Qiu
Jieping Ye
Yongbin Li
Rubric-based reinforcement learning (RL) trains policies for open-ended generation with natural-language criteria as rewards, but these rewa… (see more)rds can become ineffective as training progresses. We identify two failure modes. Under non-discriminative rewards, scores collapse to uniformly low or high values due to insufficient exploration or a mismatch between task difficulty and policy capability. Under spurious rewards, higher scores do not correspond to better responses. Both reflect a training configuration whose task sampling, exploration, and evaluation stay fixed as the policy evolves. We introduce HarnessRL, a training-time harness that co-evolves with the policy through three interfaces for task sampling, rollout guidance, and rubric criteria. HarnessRL maintains a training-time memory from which a harness evolver retrieves within-task history and cross-task evidence. Using this evidence, the evolver attributes each reward failure to the interface whose update can address it. It then runs a proposer and just-in-time critic loop in which the critic accepts a candidate update only after measuring its effect on the current frozen policy, returning rejected candidates for revision. We also curate Rubric-Mix-10k, a five-domain training and evaluation suite for open-ended RL across medical, science, writing, role-play, and instruction-following tasks. On Rubric-Mix-10k, HarnessRL outperforms the strongest baselines by 2.8 to 3.1 points across both 4B and 9B model scales and nearly halves the training steps to its best checkpoint. Code and data are available at https://github.com/Tongyi-ConvAI/Qwen-Character/tree/main/HarnessRL.