Publications

What Makes Value Learning Efficient in Residual Reinforcement Learning?
Guozheng Ma
Li Li
Haoyu Wang
Zixuan Liu
Pierre-Luc Bacon
Dacheng Tao
Residual reinforcement learning (RL) enables stable online refinement of expressive pretrained policies by freezing the base and learning on… (voir plus)ly bounded corrections. However, value learning in residual RL poses unique challenges that remain poorly understood. In this work, we identify two key bottlenecks: cold start pathology, where the critic lacks knowledge of the value landscape around the base policy, and structural scale mismatch, where the residual contribution is dwarfed by the base action. Through systematic investigation, we uncover the mechanisms underlying these bottlenecks, revealing that simple yet principled solutions suffice: base-policy transitions serve as an essential value anchor for implicit warmup, and critic normalization effectively restores representation sensitivity for discerning value differences. Based on these insights, we propose DAWN (Data-Anchored Warmup and Normalization), a minimal approach targeting efficient value learning in residual RL. By addressing these bottlenecks, DAWN demonstrates substantial efficiency gains across diverse benchmarks, policy architectures, and observation modalities.
2026-02-10
ArXiv (prépublication)
arxiv.org
arxiv.org
What do people want to fact-check?
Bijean Ghafouri
Dorsaf Sallami
Luca Luceri
Taylor Lynn Curtis
Jean-François Godbout
Emilio Ferrara
Reihaneh Rabbany
2026-02-10
arXiv (prépublication)
doi.org
arxiv.org
Position: Message-passing and spectral GNNs are two sides of the same coin
Antonis Vasileiou
Juan Cervino
Pascal Frossard
Charilaos I. Kanatsoulis
Christopher Morris
Michael T. Schaub
Pierre Vandergheynst
Zhiyang Wang
Guy Wolf
Ron Levie
Graph neural networks (GNNs) are commonly divided into message-passing neural networks (MPNNs) and spectral graph neural networks, reflectin… (voir plus)g two largely separate research traditions in machine learning and signal processing. This paper argues that this divide is mostly artificial, hindering progress in the field. We propose a viewpoint in which both MPNNs and spectral GNNs are understood as different parametrizations of permutation-equivariant operators acting on graph signals. From this perspective, many popular architectures are equivalent in expressive power, while genuine gaps arise only in specific regimes. We further argue that MPNNs and spectral GNNs offer complementary strengths. That is, MPNNs provide a natural language for discrete structure and expressivity analysis using tools from logic and graph isomorphism research, while the spectral perspective provides principled tools for understanding smoothing, bottlenecks, stability, and community structure. Overall, we posit that progress in graph learning will be accelerated by clearly understanding the key similarities and differences between these two types of GNNs, and by working towards unifying these perspectives within a common theoretical and conceptual framework rather than treating them as competing paradigms.
2026-02-09
arXiv (prépublication)
doi.org
arxiv.org
Squeezing More from the Stream : Learning Representation Online for Streaming Reinforcement Learning
Nilaksh
Antoine Clavaud
Mathieu Reymond
Francois Rivest
Sarath Chandar
2026-02-09
arXiv (prépublication)
doi.org
arxiv.org
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
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