Publications

The Untapped Potential of Food Webs in Systematic Conservation Planning
Louise M. J. O'Connor
Wilfried Thuiller
Ulrich Brose
Éléonore Chenevois
Carla Freund
Benoit Gauzens
Pierre Gaüzere
Catherine Graham
Michael Harfoot
Myriam R. Hirt
Sébastien Lavergne
Luigi Maiorano
Atte Moilanen
Peter H. Verburg
Piero Visconti
Laura J. Pollock
International conservation policy includes the dual aims of protecting biodiversity and nature's contributions to people (NCP). Achieving th… (voir plus)ese goals requires protecting not only species and habitats but also the networks of biotic interactions that sustain them. Food webs, which represent predator‐prey interactions between species, are increasingly recognised as a link between ecosystem structure, function, and resilience, which are concepts that are frequently cited in conservation policy. Yet, conservation planning and policy typically focus on individual species and habitats and overlook the interactions that support their persistence. We review the literature at the intersection of food web ecology and conservation, and highlight how food webs can inform three conservation goals: preventing species extinctions, maintaining ecosystem functions and NCP, and fostering ecosystem resilience. Food web data and metrics, such as interaction diversity, trophic diversity, connectance, or modularity, can be used to prioritize species that are key to ecosystem structure and functioning, and to guide spatial prioritization to protect functionally diverse and resilient communities. Given the growing availability of food web data, incorporating food webs in conservation planning can lead to more effective and resilient conservation outcomes that sustain biodiversity and ecosystem functions in the long term.
2026-02-09
Conservation Letters (publié)
doi.org
Inverting Data Transformations via Diffusion Sampling
Jinwoo Kim
Sékou-Oumar Kaba
Jiyun Park
Seunghoon Hong
Siamak Ravanbakhsh
2026-02-08
ArXiv (prépublication)
arxiv.org
arxiv.org
Sparsity-Aware Evolution for Model Merging
Huan Zhang
Yanjian Zhang
Nadi Tomeh
Guillaume Wisniewski
Bang Liu
We propose a sparsity-aware evolutionary (SAE) framework for model merging that involves iterative pruning-merging cycles to act as a novel … (voir plus)mutation operator. We incorporate the sparsity constraints into the score function, which steers the evolutionary process to favor more sparse models, in addition to other conventional performance scores. Interestingly, the by-product of \textit{competition} for sparsity introduces an extra local \textit{attraction} and interplay into the evolutionary process: if one competitor has more zero elements, the other competitor's non-zero elements will occupy those positions, even though the less sparse competitor loses to the more sparse competitor in other positions. The proposed pipeline is evaluated on a variety of large-scale LLM benchmarks. Experiments demonstrate that our approach can improve model merging reliability across multiple benchmarks, and is easy to incorporate due to its simplicity and being orthogonal to most existing approaches.
2026-02-08
arXiv (prépublication)
doi.org
arxiv.org
HypRAG: Hyperbolic Dense Retrieval for Retrieval Augmented Generation
Hiren Madhu
Ngoc Bui
Ali Maatouk
Leandros Tassiulas
Smita Krishnaswamy
Menglin Yang 0001
Sukanta Ganguly
Kiran Srinivasan
Rex Ying
Embedding geometry plays a fundamental role in retrieval quality, yet dense retrievers for retrieval-augmented generation (RAG) remain large… (voir plus)ly confined to Euclidean space. However, natural language exhibits hierarchical structure from broad topics to specific entities that Euclidean embeddings fail to preserve, causing semantically distant documents to appear spuriously similar and increasing hallucination risk. To address these limitations, we introduce hyperbolic dense retrieval, developing two model variants in the Lorentz model of hyperbolic space: HyTE-FH, a fully hyperbolic transformer, and HyTE-H, a hybrid architecture projecting pre-trained Euclidean embeddings into hyperbolic space. To prevent representational collapse during sequence aggregation, we introduce the Outward Einstein Midpoint, a geometry-aware pooling operator that provably preserves hierarchical structure. On MTEB, HyTE-FH outperforms equivalent Euclidean baselines, while on RAGBench, HyTE-H achieves up to 29% gains over Euclidean baselines in context relevance and answer relevance using substantially smaller models than current state-of-the-art retrievers. Our analysis also reveals that hyperbolic representations encode document specificity through norm-based separation, with over 20% radial increase from general to specific concepts, a property absent in Euclidean embeddings, underscoring the critical role of geometric inductive bias in faithful RAG systems.
2026-02-07
ArXiv (prépublication)
arxiv.org
arxiv.org
Riemannian MeanFlow
Dongyeop Woo
Marta Skreta
Seonghyun Park
Kirill Neklyudov
Sungsoo Ahn
Diffusion and flow models have become the dominant paradigm for generative modeling on Riemannian manifolds, with successful applications in… (voir plus) protein backbone generation and DNA sequence design. However, these methods require tens to hundreds of neural network evaluations at inference time, which can become a computational bottleneck in large-scale scientific sampling workflows. We introduce Riemannian MeanFlow~(RMF), a framework for learning flow maps directly on manifolds, enabling high-quality generations with as few as one forward pass. We derive three equivalent characterizations of the manifold average velocity (Eulerian, Lagrangian, and semigroup identities), and analyze parameterizations and stabilization techniques to improve training on high-dimensional manifolds. In promoter DNA design and protein backbone generation settings, RMF achieves comparable sample quality to prior methods while requiring up to 10
2026-02-07
Zenodo (prépublication)
doi.org
arxiv.org
BRIDGE: Predicting Human Task Completion Time From Model Performance
Fengyuan Liu
Jay Gala
Nilaksh
Dzmitry Bahdanau
Siva Reddy
Hugo Larochelle
Evaluating the real-world capabilities of AI systems requires grounding benchmark performance in human-interpretable measures of task diffic… (voir plus)ulty. Existing approaches that rely on direct human task completion time annotations are costly, noisy, and difficult to scale across benchmarks. In this work, we propose BRIDGE, a unified psychometric framework that learns the latent difficulty scale from model responses and anchors it to human task completion time. Using a two-parameter logistic Item Response Theory model, we jointly estimate latent task difficulty and model capability from model performance data across multiple benchmarks. We demonstrate that latent task difficulty varies linearly with the logarithm of human completion time, allowing human task completion time to be inferred for new benchmarks from model performance alone. Leveraging this alignment, we forecast frontier model capabilities in terms of human task length and independently reproduce METR's exponential scaling results, with the 50% solvable task horizon doubling approximately every 6 months.
2026-02-05
arXiv (prépublication)
doi.org
openreview.net
Position: Auditing Is Not Evaluating; LLM Audit Requires Dynamic, Contextual, Budget-Aware and Reliable Evidence
Cléa Chataigner
Pablo Piantanida
Golnoosh Farnadi
Auditing large language models (LLMs) is increasingly urgent as these systems are deployed in high-stakes settings, yet existing evaluation … (voir plus)practices are ill-suited to meet auditing requirements. Directly repurposing standard evaluation tools can yield incomplete or misleading conclusions, e.g. overstating robustness when evidence comes from static prompts rather than adaptive, real-world interactions. This position paper argues that effective LLM audits must instead generate dynamic, context-sensitive, budget-aware, and reliable evidence. To support this position, we analyze how each of these principles can be operationalized through a four-component framework: Auditing Scope, Interactor, Evaluator, and Output. We highlight design requirements, assumptions, limitations and research directions, demonstrating how high-level principles can be translated into concrete, actionable, evidence-based procedures.
2026-02-05
2026 (prépublication)
openalex.org
Constrained Group Relative Policy Optimization
Roger Girgis
Rodrigue De Schaetzen
Luke Rowe
Azalee Robitaille
Christopher Pal
Liam Paull
2026-02-04
arXiv (prépublication)
doi.org
arxiv.org
Learning the Principles of T Cell Antigen Discernment
François X. P. Bourassa
Sooraj Achar
Grégoire Altan-Bonnet
Paul François
T cells are central to the adaptive immune response, capable of detecting pathogenic antigens while ignoring healthy tissues with remarkable… (voir plus) specificity and sensitivity. Quantitatively understanding how T cell receptors discern among antigens requires biophysical models and theoretical analyses of signaling networks. Here, we review current theoretical frameworks of antigen recognition in the context of modern experimental and computational advances. Antigen potency spans a continuum and exhibits nonlinear effects within complex mixtures, challenging discrete classification and simple threshold-based models. This complexity motivates the development of models, such as adaptive kinetic proofreading, that integrate both activating and inhibitory signals. Advances in high-throughput technologies now generate large-scale, quantitative data sets, enabling the refinement of such models through statistical and machine learning approaches. This convergence of theory, data, and computation promises deeper insights into immune decision-making and opens new avenues for rational immunotherapy design.
2026-02-04
Annual Review of Biophysics (publié)
doi.org
Logarithmic-time Schedules for Scaling Language Models with Momentum
Damien Ferbach
Courtney Paquette
Gauthier Gidel
Katie Everett
Elliot Paquette
In practice, the hyperparameters …
2026-02-04
arXiv (prépublication)
doi.org
arxiv.org
Mining Generalizable Activation Functions
Alex Vitvitskyi
Michael Boratko
Matej Grcic
Razvan Pascanu
Deep Shah
Petar Veličković
2026-02-04
ArXiv (prépublication)
arxiv.org
arxiv.org
Multi agent deep reinforcement learning for supervising local controllers in energy-intensive industrial processes
Karim Nadim
Ahmed Ragab
Hakim Ghezzaz
Industrial plants are equipped with several local controllers with a high degree of interaction. Controllers in complex systems tend to oper… (voir plus)ate in a competitive way to achieve their own objective, which can negatively impact other controllers and consequently the global KPI. In addition, the rapid changes in process dynamics, the variations, and fluctuations in the process conditions and production targets introduce major challenges in optimizing the whole process. As a result, operators struggle to adjust the controllers’ setpoints to optimize the process operation. Therefore, there is a clear need for an approach that captures the controllers’ interdependence and optimizes the setpoints in real-time to ensure energy-efficient operations. This paper proposes an intelligent decentralized supervisory control approach based on multi-agent deep reinforcement learning (MADRL) to recommend the optimal combinations of controllers’ setpoints that maintain desired process operation. Multiple agents are developed based on the deep deterministic policy gradient algorithm to collaborate and control different interconnected subsystems. The agents are trained via interacting with a process simulation, where each agent performs actions (setpoint changes) and observes certain rewards (global KPI to be maximized) and states (measured variables) from the simulation. The approach is validated on a case study based on a heat recovery network of a thermomechanical pulp mill comprising four different subsystems. The proposed decentralized approach was compared to two centralized approaches: a baseline control set by the process expert and a single DDPG agent. The multi-agent approach was able to reduce the steam flow consumption by 6.7 % compared to the experts’ baseline and 5.3% compared to the single agent with faster convergence. Two possible strategies were proposed to implement this approach in the industry, depending on the criticality of the process and the degree of fidelity of its process simulation.
2026-02-04
Control Engineering Practice (publié)
doi.org