🧮 IA Symbolique — Actualités
Dernière mise à jour : 01/05/2026 à 03:34 UTC
Veille sur l'IA symbolique et neuro-symbolique :
Prolog / ASP / Clingo —
Ada / SPARK —
Julia Symbolics.jl / Turing.jl —
Haskell —
Coq / Lean —
Intégration neuro-symbolique, knowledge graphs, raisonnement formel.
Titres en anglais traduits en vert · PDF = preprint arXiv · Historique : 290 article(s) sur 360 jours.
📰 Actualités du jour
🧮
SWI-Prolog News
Blog officiel / Releases
V10.1.6
V10.1.6
V10.1.5
V10.1.5
V10.1.4
V10.1.4
V10.0.1
V10.0.1
V10.1.3
V10.1.3
V10.1.2
V10.1.2
V10.1.1
V10.1.1
V10.1.0
V10.1.0
V10.0.0
V10.0.0
V9.3.36
V9.3.36
Hacker News
2017-07-06
Logic Programming (Prolog, ASP, etc) and GRAKN.AI (a distributed knowledge base)
HN 57▲
Programmation logique (prologue, ASP, etc.) et GRAKN.AI (base de connaissances distribuée)
2012-04-08
Ask HN: Could a faster Prolog have succeeded in industry?
HN 13▲
Demandez à HN: Un Prolog plus rapide aurait-il pu réussir dans l'industrie?
2010-07-08
Ask HN: Make something people want - 4.5 years left and counting
HN 10▲
Demandez à HN: Faire quelque chose que les gens veulent - 4,5 ans plus tard et compter
2025-11-15
Show HN: DeepClause – A Neurosymbolic AI System Built on WASM and Prolog
HN 7▲
Afficher HN: DeepClause – Un système d'IA neurosymbolique construit sur WASM et Prolog
2025-10-06
Show HN: Mirrors Reasoning Stack (Mrs) – A Neuro-Symbolic Core for Agents
HN 2▲
Afficher HN: Miroirs Raisonnant Stack (Mme) – Un noyau neurosymbolique pour les agents
2022-11-07
Answer set programming (ASP): the powerhouse technology you’ve never heard of
HN 2▲
Programmation de série de réponses (ASP): la technologie de puissance dont vous n'avez jamais entendu parler
🧵
Julia — Symbolics.jl / JuliaAI
Blog officiel / Releases
2026-04-25
Wavelets, sample rate, and replicating Matlab's default call
Wavelets, taux d'échantillonnage et reproduction de l'appel par défaut de Matlab
2026-04-20
Ecosystem Bundle Download
Écosystèmes Télécharger
2026-04-18
In Julia, I accidentally typed "<tab> <tab>". What a nice surprise!
En Julia, j'ai accidentellement tapé "<tab> <tab>". Quelle belle surprise !
2026-04-15
Function works when called in Pluto, but not when copy-pasted into a package
Fonction fonctionne quand appelé dans Pluton, mais pas quand copy-collé dans un paquet
2026-04-15
`using Pycall` on Google Colab makes Julia runtime crash
`utiliser Pycall` sur Google Colab rend Julia runtime crash
2026-04-14
Add versus dev and potential confusion
Ajouter versus dev et risque de confusion
2026-04-12
Adding N to each box
Ajout de N à chaque boîte
2026-04-11
CSV.read with two delimiters
CSV.read avec deux délimiteurs
2026-04-05
A issue to use PythonCall to call a Simple Python File Of WxPython Hello World
Un problème à utiliser PythonCall pour appeler un fichier Python simple de WxPython Hello World
2026-04-04
Documenter.jl cumbersome experience
Documenter.jl expérience lourde
Hacker News
2017-08-24
Turing.jl: A Fresh Approach to Probabilistic Programming in Julia
HN 93▲
Turing.jl: Une nouvelle approche de la programmation probabiliste en Julia
2024-11-18
Symbolicregression.jl: Distributed High-Performance Symbolic Regression in Julia
HN 1▲
Symbolicregression.jl: Régression symbolique distribuée à haute performance en Julia
💻
Ada/SPARK — AdaCore
Aucun article récupéré.
λ
Haskell — Functional AI
Hacker News
2008-12-17
Common Lisp + Machine Learning Internship at Google (Mountain View, CA)
HN 45▲
Common Lisp + Machine Learning Stage chez Google (Montagne, CA)
2013-12-29
Ask HN: What is the best functional programming language for data science?
HN 15▲
Demandez à HN: Quel est le meilleur langage de programmation fonctionnelle pour la science des données?
2020-03-15
Multi-Language Support in Smalltalk and Historical Lisp Environments
HN 10▲
Soutien multi-langues dans les environnements de petits talk et de Lisp historique
2011-11-12
NYC Functional Programmer. Fresh on the job market. What's out there?
HN 6▲
Programmeur fonctionnel NYC. Frais sur le marché du travail. Qu'est-ce qu'il y a ?
2022-12-23
Ask HN: AI Bot for Posting Pro Chinese-State Messages
HN 4▲
Demandez à HN: AI Bot pour poster des messages pro chinois-état
2019-02-15
Ask HN: What languages teach the wisdom of C without the uglyness of it?
HN 1▲
Demandez à HN: Quelles langues enseignent la sagesse de C sans la laideur de celle-ci?
✓
Coq / Lean — Preuve formelle
Hacker News
2026-03-28
Further human + AI + proof assistant work on Knuth's "Claude Cycles" problem
HN 261▲
Autre travail humain + AI + assistant de preuve sur le problème "Claude Cycles" de Knuth
2023-09-20
Lean, Coq and other proof assistants: Visualising proofs as trees
HN 158▲
Lean, Coq et autres assistants d'épreuves : Visualiser les épreuves comme des arbres
2026-03-01
Aura-State: Formally Verified LLM State Machine Compiler
HN 23▲
Aura-State: Compilateur de machines d'État LLM à vérification formelle
2024-03-19
Show HN: Phorm – AI code search that just works
HN 5▲
Afficher HN: Phorm – Recherche de code AI qui fonctionne
2024-09-26
Testing ways of using citizen math, proof assistants, automation tools, and AI
HN 2▲
Tester les façons d'utiliser les mathématiques citoyennes, les assistants de preuve, les outils d'automatisation et l'IA
🤗
Hugging Face — Reasoning & Neuro-Sym
Blog officiel / Releases
2026-04-29
AI evals are becoming the new compute bottleneck
Les évaluations d'IA deviennent le nouveau goulot d'étranglement informatique
2026-04-29
Granite 4.1 LLMs: How They’re Built
Granite 4.1 LLM: Comment ils sont construits
2026-04-29
DeepInfra on Hugging Face Inference Providers 🔥
DeepInfra sur les fournisseurs d'inférences faciales
2026-04-28
Introducing NVIDIA Nemotron 3 Nano Omni: Long-Context Multimodal Intelligence for Documents, Audio and Video Agents
Présentation de NVIDIA Nemotron 3 Nano Omni: Intelligence multimodale longue durée pour les agents de documents, audio et vidéo
2026-04-27
How to build scalable web apps with OpenAI's Privacy Filter
Comment construire des applications web évolutives avec le filtre de confidentialité OpenAI
2026-04-24
DeepSeek-V4: a million-token context that agents can actually use
DeepSeek-V4 : un contexte de millions de jetons que les agents peuvent utiliser
2026-04-23
How to Use Transformers.js in a Chrome Extension
Comment utiliser Transformers.js dans une extension Chrome
2026-04-21
QIMMA قِمّة ⛰: A Quality-First Arabic LLM Leaderboard
QIMMA : Un premier LLM arabe de qualité Tableau de bord
2026-04-21
AI and the Future of Cybersecurity: Why Openness Matters
L'IA et l'avenir de la cybersécurité : pourquoi l'ouverture compte
2026-04-16
Ecom-RLVE: Adaptive Verifiable Environments for E-Commerce Conversational Agents
Ecom-RLVE: Environnements vérifiables adaptatifs pour les agents conversateurs du commerce électronique
Hacker News
2012-10-29
Google Now: behind the predictive future of search
HN 12▲
Google Now: derrière l'avenir prédictif de la recherche
2025-11-15
Show HN: DeepClause – A Neurosymbolic AI System Built on WASM and Prolog
HN 7▲
Afficher HN: DeepClause – Un système d'IA neurosymbolique construit sur WASM et Prolog
2025-10-25
Neurosymbolic AI server combining Prolog's symbolic reasoning with MCP
HN 6▲
Serveur d'IA neurosymbolique combinant le raisonnement symbolique de Prolog et MCP
2025-12-05
The Amazon scientist using automated reasoning to kill AI hallucinations
HN 3▲
Le scientifique amazonien utilisant le raisonnement automatisé pour tuer les hallucinations d'IA
2020-10-27
Spectral Neural Networks for Knowledge Graphs (In Scala)
HN 3▲
Réseaux neuronaux spectraux pour les graphiques de connaissances (En Scala)
2025-09-12
Show HN: Project Chimera v1.2 – Neuro-Symbolic-Causal AI Agent (Open Source)
HN 2▲
Afficher HN: Projet Chimera v1.2 – Agent d'IA Neuro-Symbolique-Causal (Open Source)
🇫🇷
INRIA / HAL — Recherche FR
Aucun article récupéré.
♾️
RefPerSys — Basile Starynkevitch (GitHub Releases)
Aucun article récupéré.
📘
Publications arXiv
Neuro-symbolique · ASP · Knowledge Graphs · Prolog · Ada · Julia Symbolics — PDF = preprint
2026-04-30
HERMES++: Toward a Unified Driving World Model for 3D Scene Understanding and Generation
PDF
HERMES++: Vers un modèle de monde de conduite unifié pour la compréhension et la génération des scènes 3D
— Xin Zhou
Driving world models serve as a pivotal technology for autonomous driving by simulating environmental dynamics. However, existing approaches predominantly focus on future scene generation, often overlooking comprehensive 3D scene understanding. Conversely, while Large Language Models (LLMs) demonstr
2026-04-30
LaST-R1: Reinforcing Action via Adaptive Physical Latent Reasoning for VLA Models
PDF
LaST-R1: Renforcement de l'action par le biais d'un raisonnement adaptatif pour les modèles VLA
— Dingkang Liang
Vision-Language-Action (VLA) models have increasingly incorporated reasoning mechanisms for complex robotic manipulation. However, existing approaches share a critical limitation: whether employing explicit linguistic reasoning that suffers from latency and discretization, or utilizing more expressi
2026-04-30
Visual Generation in the New Era: An Evolution from Atomic Mapping to Agentic World Modeling
PDF
La génération visuelle dans la nouvelle ère : une évolution de la cartographie atomique à la modélisation du monde agentique
— Xiwu Chen
Recent visual generation models have made major progress in photorealism, typography, instruction following, and interactive editing, yet they still struggle with spatial reasoning, persistent state, long-horizon consistency, and causal understanding. We argue that the field should move beyond appea
2026-04-30
Exploration Hacking: Can LLMs Learn to Resist RL Training?
PDF
Exploration Hacking: Les LLM peuvent-ils apprendre à résister à l'entraînement RL?
— Feiyang Tan
Reinforcement learning (RL) has become essential to the post-training of large language models (LLMs) for reasoning, agentic capabilities and alignment. Successful RL relies on sufficient exploration of diverse actions by the model during training, which creates a potential failure mode: a model cou
2026-04-30
LLM as Clinical Graph Structure Refiner: Enhancing Representation Learning in EEG Seizure Diagnosis
PDF
LLM comme Raffineur de structure de graphique clinique: améliorer l'apprentissage de la représentation dans le diagnostic de saisie EEG
— Dingyuan Zhang
Electroencephalogram (EEG) signals are vital for automated seizure detection, but their inherent noise makes robust representation learning challenging. Existing graph construction methods, whether correlation-based or learning-based, often generate redundant or irrelevant edges due to the noisy nat
2026-04-30
AEGIS: A Holistic Benchmark for Evaluating Forensic Analysis of AI-Generated Academic Images
PDF
AEGIS: un point de repère holistique pour l'évaluation de l'analyse médico-légale des images académiques produites par l'IA
— Hengshuang Zhao
We introduce AEGIS, A holistic benchmark for Evaluating forensic analysis of AI-Generated academic ImageS. Compared to existing benchmarks, AEGIS features three key advances: (1) Domain-Specific Complexity: covering seven academic categories with 39 fine-grained subtypes, exposing intrinsic forensic
2026-04-30
Essential, Yet Overlooked: Identity Verification Barriers for Blind and Low Vision People in Government Services
PDF
Essentiel, pourtant surestimé : Obstacles à la vérification de l'identité pour les personnes aveugles et malvoyantes dans les services gouvernementaux
— Xiang Bai
Identity verification is a critical gateway to accessing government services and public benefits, yet contemporary systems are typically designed around visual interaction, leaving blind and low vision (BLV) individuals disproportionately burdened. In this work, we examine how BLV users navigate ide
2026-04-30
Intern-Atlas: A Methodological Evolution Graph as Research Infrastructure for AI Scientists
PDF
Intern-Atlas: Un graphique d'évolution méthodologique comme infrastructure de recherche pour les scientifiques de l'IA
— Hao Chen
Existing research infrastructure is fundamentally document-centric, providing citation links between papers but lacking explicit representations of methodological evolution. In particular, it does not capture the structured relationships that explain how and why research methods emerge, adapt, and b
2026-04-30
OmniRobotHome: A Multi-Camera Platform for Real-Time Multiadic Human-Robot Interaction
PDF
OmniRobotHome: Une plate-forme multi-caméra pour l'interaction multi-humaine-robot en temps réel
— Junyoung Lee
Human-robot collaboration has been studied primarily in dyadic or sequential settings. However, real homes require multiadic collaboration, where multiple humans and robots share a workspace, acting concurrently on interleaved subtasks with tight spatial and temporal coupling. This regime remains un
2026-04-30
Generalizable Sparse-View 3D Reconstruction from Unconstrained Images
PDF
Généralisable Sparse-View Reconstruction 3D à partir d'images sans contrainte
— Sookwan Han
Reconstructing 3D scenes from sparse, unposed images remains challenging under real-world conditions with varying illumination and transient occlusions. Existing methods rely on scene-specific optimization using appearance embeddings or dynamic masks, which requires extensive per-scene training and
2026-04-30
Enhancement of superconducting stiffness in hybrid superconducting-metallic bilayers
PDF
Amélioration de la rigidité supraconductrice dans les bicouches hybrides supraconductrices-métalliques
— Inhee Lee
Boosting superconductivity by metallic reservoirs is the essence of Kivelson's bilayer proposal. One layer provides pairing to the electrons, while the weakly coupled metal provides additional phase coherence to those pairs by mediating extended-range pair-pair coupling. Demonstrating significa
2026-04-30
Computing Equilibrium beyond Unilateral Deviation
PDF
Équilibre informatique au-delà de la déviation unilatérale
— Mingi Choi
Most familiar equilibrium concepts, such as Nash and correlated equilibrium, guarantee only that no single player can improve their utility by deviating unilaterally. They offer no guarantees against profitable coordinated deviations by coalitions. Although the literature proposes solution concepts
2026-04-30
Uniaxial strain-driven ferroelastic domain control in LaAlO3
PDF
Contrôle de domaine ferroélastique uniaxial par déformation dans LaAlO3
— Jisoo Kim
Multiferroic domain walls in functional oxides exhibit properties distinct from the bulk and are increasingly exploited as active elements in nanoelectronic and photonic devices. Deterministic control of domain populations has typically remained limited to local control, or removal with temperature.
2026-04-30
Synthetic Computers at Scale for Long-Horizon Productivity Simulation
PDF
Ordinateurs synthétiques à l'échelle pour la simulation de productivité de longue durée
— Hanbyul Joo
Realistic long-horizon productivity work is strongly conditioned on user-specific computer environments, where much of the work context is stored and organized through directory structures and content-rich artifacts. To scale synthetic data creation for such productivity scenarios, we introduce Synt
2026-04-30
Covariant Locally Localized Gravity and vDVZ Continuity
PDF
Gravité localisée et continuité vDVZ
— Dingkang Liang
The Karch-Randall braneworld concerns the physics of an AdS$_{d}$ brane embedded in an ambient gravitational AdS$_{d+1}$ spacetime. The gravitational theory induced on the AdS$_{d}$ brane has a very light but massive graviton. It has been established that the zero graviton mass limit of the $d$-dime
2026-04-30
Fillable structures on negative-definite Seifert fibred spaces
PDF
Structures rechargeables sur espaces en fibre de Seifert à définition négative
— Hengshuang Zhao
We classify fillable contact structures on all negative-definite star-shaped plumbings. Along the way, we show that such Seifert fibred spaces admit a unique negative maximal twisting number, and compute it explicitly using the Alexander filtration in lattice cohomology. In particular, we show that
2026-04-30
Heegaard Floer homology and maximal twisting numbers
PDF
Hegaard Floer homologie et nombres de torsions maximaux
— Xiang Bai
We adapt the Ozsváth-Szabó full path algorithm to every star-shaped graph and establish a correspondence between negative-twisting tight contact structures on any Seifert fibred space over $S^2$, and its Heegaard Floer homology groups equipped with the Alexander filtration induced by the regular fib
2026-04-30
RopeDreamer: A Kinematic Recurrent State Space Model for Dynamics of Flexible Deformable Linear Objects
PDF
RopeDreamer: Un modèle d'espace d'état à répétition cinématique pour les dynamiques d'objets linéaires déformables flexibles
— Hao Geng
The robotic manipulation of Deformable Linear Objects (DLOs) is a fundamental challenge due to the high-dimensional, non-linear dynamics of flexible structures and the complexity of maintaining topological integrity during contact-rich tasks. While recent data-driven methods have utilized Recurrent
2026-04-30
Representation Fréchet Loss for Visual Generation
PDF
Représentation Fréchet Perte pour la génération visuelle
— Dingkang Liang
We show that Fréchet Distance (FD), long considered impractical as a training objective, can in fact be effectively optimized in the representation space. Our idea is simple: decouple the population size for FD estimation (e.g., 50k) from the batch size for gradient computation (e.g., 1024). We term
2026-04-30
Non-negative Rational Semantic Numeration Systems
PDF
Systèmes de numération sémantique rationnelle non négatifs
— Feiyang Tan
A new class of Semantic Numeration Systems, namely, positive rational Semantic Numeration Systems is introduced. For cardinal semantic operators, differences in the formation of carry (common carry) and remainders are defined. The properties of positive rational Semantic Numeration Systems as dynami
2026-04-30
PhyCo: Learning Controllable Physical Priors for Generative Motion
PDF
PhyCo: Apprentissage des antécédents physiques contrôlables pour le mouvement génétique
— Dingyuan Zhang
Modern video diffusion models excel at appearance synthesis but still struggle with physical consistency: objects drift, collisions lack realistic rebound, and material responses seldom match their underlying properties. We present PhyCo, a framework that introduces continuous, interpretable, and ph
2026-04-30
Continuous-tone Simple Points: An $\ell_0$-Norm of Cyclic Gradient for Topology-Preserving Data-Driven Image Segmentation
PDF
Points simples en ton continu : Un $\ell 0$-Norm de dégradé cyclique pour la topologie-préservation de la segmentation de l'image d'origine de données
— Hengshuang Zhao
Topological features play an essential role in ensuring geometric plausibility and structural consistency in image analysis tasks such as segmentation and skeletonization. However, integrating topology-preserving learning based on simple points into deep learning tasks remains challenging, as existi
2026-04-30
FlexiTac: A Low-Cost, Open-Source, Scalable Tactile Sensing Solution for Robotic Systems
PDF
FlexiTac : une solution de détection tactile à faible coût, ouverte et évolutive pour les systèmes robotiques
— Xiang Bai
We present FlexiTac, a low-cost, open-source, and scalable piezoresistive tactile sensing solution designed for robotic end-effectors. FlexiTac is a practical "plug-in" module consisting of (i) thin, flexible tactile sensor pads that provide dense tactile signals and (ii) a compact multi-c
2026-04-30
Beyond first-order accuracy in continuous-forcing immersed boundary methods, and their well-conditioned projection-based solution
PDF
Au-delà de la précision du premier ordre dans les méthodes de limite immergée à force continue, et leur solution de projection bien conditionnée
— Jiawei Yang
We introduce a refined immersed boundary (IB) methodology that is better-than-first-order accurate in practice, while preserving key properties of "continuous-forcing" IB approaches that retain a singular source term in the governing equations. Our method leverages a smoothed indicator (He
2026-04-30
Global Optimality for Constrained Exploration via Penalty Regularization
PDF
Optimisation mondiale pour l'exploration forcée par la régularisation des pénalités
— Jeonghwan Kim
Efficient exploration is a central problem in reinforcement learning and is often formalized as maximizing the entropy of the state-action occupancy measure. While unconstrained maximum-entropy exploration is relatively well understood, real-world exploration is often constrained by safety, resource
2026-04-30
BV quantization of $φ^3$-theory on $λ$-Minkowski space: Tree-level correlation functions
PDF
Quantification BV de $λ^3$-théorie sur l'espace $λ$-Minkowski: Fonctions de corrélation au niveau des arbres
— Inhee Lee
We review the quantization of scalar field theory on $λ$-Minkowski space using the Batalin--Vilkovisky (BV) formalism. We consider $φ^3$-theory in two different quantization schemes: standard and braided. While standard BV quantization is based on an ordinary $L_\infty$-algebra, braided BV quantizat
2026-04-30
Splitting Argumentation Frameworks with Collective Attacks and Supports
PDF
Séparer les cadres d'argumentation avec les attaques et les soutiens collectifs
— Mingi Choi
This work proposes novel splitting techniques for argumentation formalisms that incorporate supports between defeasible elements. We base our studies on bipolar set-based argumentation frameworks (BSAFs) which generalize argumentation frameworks with collective attacks (SETAFs), as well as bipolar a
2026-04-30
What Makes a Good Terminal-Agent Benchmark Task: A Guideline for Adversarial, Difficult, and Legible Evaluation Design
PDF
Qu'est-ce qui constitue une bonne tâche de référence pour l'agent terminal : une ligne directrice pour la conception de l'évaluation adversaire, difficile et lisible
— Jisoo Kim
Terminal-agent benchmarks have become a primary signal for measuring the coding and system-administration capabilities of large language models. As the market for evaluation environments grows, so does the pressure to ship tasks quickly, often without thorough adversarial review of the verification
2026-04-30
Towards Neuro-symbolic Causal Rule Synthesis, Verification, and Evaluation Grounded in Legal and Safety Principles
PDF
Vers une synthèse, une vérification et une évaluation des règles causales neurosymboliques fondées sur des principes juridiques et de sécurité
— Wonjung Woo
Rule-based systems remain central in safety-critical domains but often struggle with scalability, brittleness, and goal misspecification. These limitations can lead to reward hacking and failures in formal verification, as AI systems tend to optimize for narrow objectives. In previous research, we d
2026-04-30
Intelligent Self-tuning Active EMI Filtering for Electrified Automotive Power Systems Using Reinforcement Learning
PDF
Filtre EMI actif intelligent pour les systèmes électriques de l'automobile utilisant l'apprentissage du renforcement
— Hanbyul Joo
The rapid electrification and intelligence of modern transportation systems place stringent demands on the electromagnetic compatibility, reliability, and adaptability of automotive power electronics. In electric and autonomous vehicles, electromagnetic interference (EMI) generated by high-frequency
2026-04-30
An adaptive wavelet-based PINN for problems with localized high-magnitude source
PDF
Un PINN adaptatif basé sur les vagues pour les problèmes avec la source localisée de haute magnitude
— Robin Buschbeck
In recent years, physics-informed neural networks (PINNs) have gained significant attention for solving differential equations, although they suffer from two fundamental limitations, namely, spectral bias inherent in neural networks and loss imbalance arising from multiscale phenomena. This paper pr
2026-04-30
Strait: Perceiving Priority and Interference in ML Inference Serving
PDF
Détroit : Percevoir la priorité et l'interférence dans le service de l'inférence ML
— Jakob Wetzel
Machine learning (ML) inference serving systems host deep neural network (DNN) models and schedule incoming inference requests across deployed GPUs. However, limited support for task prioritization and insufficient latency estimation under concurrent execution may restrict their applicability in on-
2026-04-30
Mapping the Phase Diagram of the Vicsek Model with Machine Learning
PDF
Cartographie du diagramme de phase du modèle Vicsek avec l'apprentissage automatique
— Anna-Lena Hofmann
In this study, we use machine learning to classify and interpolate the phase structure of the Vicsek flocking model across the three-dimensional parameter space $(η,ρ,v_0)$. We construct a dataset of simulated parameter points and characterize each point using long-time dynamical observables. These
2026-04-30
Index-Assisted Stratified Sampling for Online Aggregation
PDF
Échantillonnage stratifié assisté par index pour l'agrégation en ligne
— Javier Taboada-Gutiérrez
Ad-hoc queries over frequently updated data in a flat schema are common in real-time data analysis applications and often require very low latency. Online aggregation can achieve so by providing approximate aggregation answers with confidence bound guarantees. It relies on the ability to draw sample
2026-04-30
Chemical Taxonomy of $ω$~Centauri: Ten Populations Reveal a Multi-Phase Enrichment History
PDF
Taxonomie chimique du Centauri : Dix populations dévoilent une histoire d'enrichissement multiphasé
— Furkan Akbaba
$ω$~Centauri, the most massive globular cluster in the Milky Way, exhibits a level of stellar population complexity that has long resisted a unified chemical characterisation. We exploit high-resolution near-infrared spectroscopy from the Milky Way Mapper survey (MWM DR19) to construct one of the la
2026-04-30
Intrinsic anomalous thermal hall effect as a signature of quantum metric in d-wave altermagnets
PDF
Effet thermal anomal intrinsèque comme signature de métrique quantique dans les alteraimants d-onde
— Sookwan Han
We investigate the intrinsic anomalous thermal Hall effect in d-wave altermagnets, where a transverse heat current is generated by a longitudinal temperature gradient in the absence of a magnetic field, with the leading response proportional to $(\nabla T)^3$. In these systems, the intrinsic Berry c
2026-04-30
Cosmology of fractional gravity
PDF
Cosmologie de la gravité fractionnelle
— Feiyang Tan
This is a first study of the cosmology of classical fractional gravity, a nonlocal proposal endowed with self-adjoint fractional d'Alembertian operators which serves as the basis for an ultraviolet-complete theory of quantum gravity. We derive the classical covariant nonlocal equations of motio
2026-04-30
Stop Holding Your Breath: CT-Informed Gaussian Splatting for Dynamic Bronchoscopy
PDF
Arrêtez de retenir votre souffle: CT-informed Gaussian Splating pour la Bronchoscopie Dynamique
— Xiang Bai
Bronchoscopic navigation relies on registering endoscopic video to a preoperative CT scan, but respiratory motion deforms the airway by 5-20 mm, creating CT-to-body divergence that limits localization accuracy. In practice, this is mitigated through breath-hold protocols, which attempt to match the
🔬
OpenAlex — Publications académiques
Corpus académique indexé par OpenAlex (ResearchGate, Crossref, PubMed…)
2026-12-31
Main rooms and coffered ceilings as definers of a noble palace model in renaissance Spain. The case study of the palace of Peñaranda de Duero, Spain
Les salles principales et les plafonds coffered en tant que définitions d'un modèle de palais noble en renaissance Espagne. Étude de cas du palais de Peñaranda de Duero, Espagne
— Manuel de Miguel Sánchez, Miguel Carlos Fernández Cabo, Ana González Uriel
2026-12-17
Natural Agents, Complex Systems and Uncertain Environments: Results from Simulations on Heuristic Organizations
Agents naturels, systèmes complexes et milieux incertains : résultats des simulations sur les organisations heuristiques
— Lorenzo Corno
2026-12-14
From the old to the new generation of a product : unlearn, improve, and prosper
De l'ancienne à la nouvelle génération d'un produit : désapprendre, améliorer et prospérer
— Nikolaos Kyriakopoulos, Paraskevas C. Argouslidis, Dionysis Skarmeas et al.
2026-12-01
Reconstruction and Renaissance of Dongbei China:A Multimodal Metaphor Analysis of New Media on Harbin
Reconstruction et Renaissance de Dongbei Chine: analyse de métaphore multimodale des nouveaux médias sur Harbin
— Amily; id_orcid 0000-0001-5583-9442 Wang Guenier
2026-10-05
Debugging debugging information using dynamic call trees
Débogage des informations de débogage en utilisant des arbres d'appel dynamiques
— J. Ryan Stinnett, Stephen Kell
2026-08-12
Leveraging Cryptographic Simulator Synthesis for Formally Verifying the FOO E-Voting Protocol
Tirer parti de la synthèse des simulations cryptographiques pour vérifier formellement le protocole FOO E-Voting
— David Baelde, Adrien Koutsos, Justine Sauvage
2026-05-21
Understanding Data-Sharing with AI Systems: The Roles of Transparency, Trust, and the Processing Entity
Comprendre le partage des données avec les systèmes d'IA : les rôles de la transparence, de la confiance et de l'entité de traitement
— Rosenberger, Julian, Kuhlemann, Sophie, Tiefenbeck, Verena et al.
2026-05-01
MEASE: Multi-agent Episodic Action Sequence Explanation
MESURE: Séquençage d'action épisodique multi-agents Explication
— Phyo Wai KHAING, Minghong Geng, Shubham PATERIA et al.
2026-04-28
Human brain data: a valuable and open-ended resource for artificial intelligence
Données du cerveau humain : une ressource précieuse et ouverte pour l'intelligence artificielle
— Maël Donoso
2026-04-28
Artificial intelligence, machine learning, and deep learning-based cybersecurity: Techniques, challenges, and future directions
Intelligence artificielle, apprentissage automatique et cybersécurité fondée sur l'apprentissage profond : Techniques, défis et orientations futures
— Lebar-Ndibiri Esther Chinyere
2026-04-28
Contribution of immune cells and cytokines to radiation-induced injury: the key roles and potential targets
Contribution des cellules immunitaires et des cytokines aux lésions causées par le rayonnement : rôles clés et cibles potentielles
— Yanan Wu, Yuanjing Tian, YingYing Zhang et al.
2026-04-28
Understanding AI Agents—A Data-Driven Literature Review
Comprendre les agents de l'IA — Une revue documentaire axée sur les données
— Johannes Stübinger, Fabio Metz
2026-04-28
Debating debates: a deliberative alternative for televised electoral discussions
Débat : une alternative délibérative pour les débats électoraux télévisés
— Paul Saproza
2026-04-28
AI agent behavioral science
Science comportementale de l'agent d'IA
— Lin Chen, Yunke Zhang, Jie Feng et al.
2026-04-27
CogDoc: A Knowledge Centric Multi Model LLM for Clause Level Extraction, Structured Representation, and Consistency Reasoning over Legal and Policy Documents
CogDoc: Un LLM centric multimodèle de connaissances pour l'extraction des niveaux de clause, la représentation structurée et la cohérence des documents juridiques et politiques
— Veerababu Reddy, Pravallika Bhosale, Sreeja Alle et al.
2026-04-27
‘Systematic Alignment Decay’: a robust, technology-agnostic hazard associated with the advancement and proliferation of artificial intelligence
«Décay» d'alignement systématique: un risque technologique-agnostique solide associé à l'avancement et à la prolifération de l'intelligence artificielle
— Brendan Kelters
2026-04-27
Proceedings of the XVII International Scientific and Practical Conference
Actes de la XVIIe Conférence scientifique et pratique internationale
— Giovanna Siedina
2026-04-27
TECHNOLOGY AS AN EXTENSION OF MAN: THE LIMITS OF THE POSSIBLE AND NEW PARADIGMS
TECHNOLOGIE EN TANT QU'EXTENSION DE L'HOMME : LES LIMITES DES PARADIMES POSSIBLES ET NOUVEAUX
— Denis Vladlenov
📅 Historique — 360 derniers jours
May 2026 — 44 article(s)
2024-03-19
Show HN: Phorm – AI code search that just works
HN 5▲
Afficher HN: Phorm – Recherche de code AI qui fonctionne
2024-09-26
Testing ways of using citizen math, proof assistants, automation tools, and AI
HN 2▲
Tester les façons d'utiliser les mathématiques citoyennes, les assistants de preuve, les outils d'automatisation et l'IA
2026-04-30
HERMES++: Toward a Unified Driving World Model for 3D Scene Understanding and Generation
PDF
HERMES++: Vers un modèle de monde de conduite unifié pour la compréhension et la génération des scènes 3D
— Xin Zhou
Driving world models serve as a pivotal technology for autonomous driving by simulating environmental dynamics. However, existing approaches predominantly focus on future scene generation, often overlooking comprehensive 3D scene understanding. Conversely, while Large Language Models (LLMs) demonstr
2026-04-30
LaST-R1: Reinforcing Action via Adaptive Physical Latent Reasoning for VLA Models
PDF
LaST-R1: Renforcement de l'action par le biais d'un raisonnement adaptatif pour les modèles VLA
— Dingkang Liang
Vision-Language-Action (VLA) models have increasingly incorporated reasoning mechanisms for complex robotic manipulation. However, existing approaches share a critical limitation: whether employing explicit linguistic reasoning that suffers from latency and discretization, or utilizing more expressi
2026-04-30
Visual Generation in the New Era: An Evolution from Atomic Mapping to Agentic World Modeling
PDF
La génération visuelle dans la nouvelle ère : une évolution de la cartographie atomique à la modélisation du monde agentique
— Xiwu Chen
Recent visual generation models have made major progress in photorealism, typography, instruction following, and interactive editing, yet they still struggle with spatial reasoning, persistent state, long-horizon consistency, and causal understanding. We argue that the field should move beyond appea
2026-04-30
Exploration Hacking: Can LLMs Learn to Resist RL Training?
PDF
Exploration Hacking: Les LLM peuvent-ils apprendre à résister à l'entraînement RL?
— Feiyang Tan
Reinforcement learning (RL) has become essential to the post-training of large language models (LLMs) for reasoning, agentic capabilities and alignment. Successful RL relies on sufficient exploration of diverse actions by the model during training, which creates a potential failure mode: a model cou
2026-04-30
LLM as Clinical Graph Structure Refiner: Enhancing Representation Learning in EEG Seizure Diagnosis
PDF
LLM comme Raffineur de structure de graphique clinique: améliorer l'apprentissage de la représentation dans le diagnostic de saisie EEG
— Dingyuan Zhang
Electroencephalogram (EEG) signals are vital for automated seizure detection, but their inherent noise makes robust representation learning challenging. Existing graph construction methods, whether correlation-based or learning-based, often generate redundant or irrelevant edges due to the noisy nat
2026-04-30
AEGIS: A Holistic Benchmark for Evaluating Forensic Analysis of AI-Generated Academic Images
PDF
AEGIS: un point de repère holistique pour l'évaluation de l'analyse médico-légale des images académiques produites par l'IA
— Hengshuang Zhao
We introduce AEGIS, A holistic benchmark for Evaluating forensic analysis of AI-Generated academic ImageS. Compared to existing benchmarks, AEGIS features three key advances: (1) Domain-Specific Complexity: covering seven academic categories with 39 fine-grained subtypes, exposing intrinsic forensic
2026-04-30
Essential, Yet Overlooked: Identity Verification Barriers for Blind and Low Vision People in Government Services
PDF
Essentiel, pourtant surestimé : Obstacles à la vérification de l'identité pour les personnes aveugles et malvoyantes dans les services gouvernementaux
— Xiang Bai
Identity verification is a critical gateway to accessing government services and public benefits, yet contemporary systems are typically designed around visual interaction, leaving blind and low vision (BLV) individuals disproportionately burdened. In this work, we examine how BLV users navigate ide
2026-04-30
Intern-Atlas: A Methodological Evolution Graph as Research Infrastructure for AI Scientists
PDF
Intern-Atlas: Un graphique d'évolution méthodologique comme infrastructure de recherche pour les scientifiques de l'IA
— Hao Chen
Existing research infrastructure is fundamentally document-centric, providing citation links between papers but lacking explicit representations of methodological evolution. In particular, it does not capture the structured relationships that explain how and why research methods emerge, adapt, and b
2026-04-30
OmniRobotHome: A Multi-Camera Platform for Real-Time Multiadic Human-Robot Interaction
PDF
OmniRobotHome: Une plate-forme multi-caméra pour l'interaction multi-humaine-robot en temps réel
— Junyoung Lee
Human-robot collaboration has been studied primarily in dyadic or sequential settings. However, real homes require multiadic collaboration, where multiple humans and robots share a workspace, acting concurrently on interleaved subtasks with tight spatial and temporal coupling. This regime remains un
2026-04-30
Generalizable Sparse-View 3D Reconstruction from Unconstrained Images
PDF
Généralisable Sparse-View Reconstruction 3D à partir d'images sans contrainte
— Sookwan Han
Reconstructing 3D scenes from sparse, unposed images remains challenging under real-world conditions with varying illumination and transient occlusions. Existing methods rely on scene-specific optimization using appearance embeddings or dynamic masks, which requires extensive per-scene training and
2026-04-30
Enhancement of superconducting stiffness in hybrid superconducting-metallic bilayers
PDF
Amélioration de la rigidité supraconductrice dans les bicouches hybrides supraconductrices-métalliques
— Inhee Lee
Boosting superconductivity by metallic reservoirs is the essence of Kivelson's bilayer proposal. One layer provides pairing to the electrons, while the weakly coupled metal provides additional phase coherence to those pairs by mediating extended-range pair-pair coupling. Demonstrating significa
2026-04-30
Computing Equilibrium beyond Unilateral Deviation
PDF
Équilibre informatique au-delà de la déviation unilatérale
— Mingi Choi
Most familiar equilibrium concepts, such as Nash and correlated equilibrium, guarantee only that no single player can improve their utility by deviating unilaterally. They offer no guarantees against profitable coordinated deviations by coalitions. Although the literature proposes solution concepts
2026-04-30
Uniaxial strain-driven ferroelastic domain control in LaAlO3
PDF
Contrôle de domaine ferroélastique uniaxial par déformation dans LaAlO3
— Jisoo Kim
Multiferroic domain walls in functional oxides exhibit properties distinct from the bulk and are increasingly exploited as active elements in nanoelectronic and photonic devices. Deterministic control of domain populations has typically remained limited to local control, or removal with temperature.
2026-04-30
Synthetic Computers at Scale for Long-Horizon Productivity Simulation
PDF
Ordinateurs synthétiques à l'échelle pour la simulation de productivité de longue durée
— Hanbyul Joo
Realistic long-horizon productivity work is strongly conditioned on user-specific computer environments, where much of the work context is stored and organized through directory structures and content-rich artifacts. To scale synthetic data creation for such productivity scenarios, we introduce Synt
2026-04-30
Covariant Locally Localized Gravity and vDVZ Continuity
PDF
Gravité localisée et continuité vDVZ
— Dingkang Liang
The Karch-Randall braneworld concerns the physics of an AdS$_{d}$ brane embedded in an ambient gravitational AdS$_{d+1}$ spacetime. The gravitational theory induced on the AdS$_{d}$ brane has a very light but massive graviton. It has been established that the zero graviton mass limit of the $d$-dime
2026-04-30
Fillable structures on negative-definite Seifert fibred spaces
PDF
Structures rechargeables sur espaces en fibre de Seifert à définition négative
— Hengshuang Zhao
We classify fillable contact structures on all negative-definite star-shaped plumbings. Along the way, we show that such Seifert fibred spaces admit a unique negative maximal twisting number, and compute it explicitly using the Alexander filtration in lattice cohomology. In particular, we show that
2026-04-30
Heegaard Floer homology and maximal twisting numbers
PDF
Hegaard Floer homologie et nombres de torsions maximaux
— Xiang Bai
We adapt the Ozsváth-Szabó full path algorithm to every star-shaped graph and establish a correspondence between negative-twisting tight contact structures on any Seifert fibred space over $S^2$, and its Heegaard Floer homology groups equipped with the Alexander filtration induced by the regular fib
2026-04-30
RopeDreamer: A Kinematic Recurrent State Space Model for Dynamics of Flexible Deformable Linear Objects
PDF
RopeDreamer: Un modèle d'espace d'état à répétition cinématique pour les dynamiques d'objets linéaires déformables flexibles
— Hao Geng
The robotic manipulation of Deformable Linear Objects (DLOs) is a fundamental challenge due to the high-dimensional, non-linear dynamics of flexible structures and the complexity of maintaining topological integrity during contact-rich tasks. While recent data-driven methods have utilized Recurrent
2026-04-30
Representation Fréchet Loss for Visual Generation
PDF
Représentation Fréchet Perte pour la génération visuelle
— Dingkang Liang
We show that Fréchet Distance (FD), long considered impractical as a training objective, can in fact be effectively optimized in the representation space. Our idea is simple: decouple the population size for FD estimation (e.g., 50k) from the batch size for gradient computation (e.g., 1024). We term
2026-04-30
Non-negative Rational Semantic Numeration Systems
PDF
Systèmes de numération sémantique rationnelle non négatifs
— Feiyang Tan
A new class of Semantic Numeration Systems, namely, positive rational Semantic Numeration Systems is introduced. For cardinal semantic operators, differences in the formation of carry (common carry) and remainders are defined. The properties of positive rational Semantic Numeration Systems as dynami
2026-04-30
PhyCo: Learning Controllable Physical Priors for Generative Motion
PDF
PhyCo: Apprentissage des antécédents physiques contrôlables pour le mouvement génétique
— Dingyuan Zhang
Modern video diffusion models excel at appearance synthesis but still struggle with physical consistency: objects drift, collisions lack realistic rebound, and material responses seldom match their underlying properties. We present PhyCo, a framework that introduces continuous, interpretable, and ph
2026-04-30
Continuous-tone Simple Points: An $\ell_0$-Norm of Cyclic Gradient for Topology-Preserving Data-Driven Image Segmentation
PDF
Points simples en ton continu : Un $\ell 0$-Norm de dégradé cyclique pour la topologie-préservation de la segmentation de l'image d'origine de données
— Hengshuang Zhao
Topological features play an essential role in ensuring geometric plausibility and structural consistency in image analysis tasks such as segmentation and skeletonization. However, integrating topology-preserving learning based on simple points into deep learning tasks remains challenging, as existi
2026-04-30
FlexiTac: A Low-Cost, Open-Source, Scalable Tactile Sensing Solution for Robotic Systems
PDF
FlexiTac : une solution de détection tactile à faible coût, ouverte et évolutive pour les systèmes robotiques
— Xiang Bai
We present FlexiTac, a low-cost, open-source, and scalable piezoresistive tactile sensing solution designed for robotic end-effectors. FlexiTac is a practical "plug-in" module consisting of (i) thin, flexible tactile sensor pads that provide dense tactile signals and (ii) a compact multi-c
2026-04-30
Beyond first-order accuracy in continuous-forcing immersed boundary methods, and their well-conditioned projection-based solution
PDF
Au-delà de la précision du premier ordre dans les méthodes de limite immergée à force continue, et leur solution de projection bien conditionnée
— Jiawei Yang
We introduce a refined immersed boundary (IB) methodology that is better-than-first-order accurate in practice, while preserving key properties of "continuous-forcing" IB approaches that retain a singular source term in the governing equations. Our method leverages a smoothed indicator (He
2026-04-30
Global Optimality for Constrained Exploration via Penalty Regularization
PDF
Optimisation mondiale pour l'exploration forcée par la régularisation des pénalités
— Jeonghwan Kim
Efficient exploration is a central problem in reinforcement learning and is often formalized as maximizing the entropy of the state-action occupancy measure. While unconstrained maximum-entropy exploration is relatively well understood, real-world exploration is often constrained by safety, resource
2026-04-30
BV quantization of $φ^3$-theory on $λ$-Minkowski space: Tree-level correlation functions
PDF
Quantification BV de $λ^3$-théorie sur l'espace $λ$-Minkowski: Fonctions de corrélation au niveau des arbres
— Inhee Lee
We review the quantization of scalar field theory on $λ$-Minkowski space using the Batalin--Vilkovisky (BV) formalism. We consider $φ^3$-theory in two different quantization schemes: standard and braided. While standard BV quantization is based on an ordinary $L_\infty$-algebra, braided BV quantizat
2026-04-30
Splitting Argumentation Frameworks with Collective Attacks and Supports
PDF
Séparer les cadres d'argumentation avec les attaques et les soutiens collectifs
— Mingi Choi
This work proposes novel splitting techniques for argumentation formalisms that incorporate supports between defeasible elements. We base our studies on bipolar set-based argumentation frameworks (BSAFs) which generalize argumentation frameworks with collective attacks (SETAFs), as well as bipolar a
April 2026 — 246 article(s)
2026-04-29
AI evals are becoming the new compute bottleneck
Les évaluations d'IA deviennent le nouveau goulot d'étranglement informatique
2026-04-29
Granite 4.1 LLMs: How They’re Built
Granite 4.1 LLM: Comment ils sont construits
2026-04-29
DeepInfra on Hugging Face Inference Providers 🔥
DeepInfra sur les fournisseurs d'inférences faciales
2026-04-29
Turning the TIDE: Cross-Architecture Distillation for Diffusion Large Language Models
PDF
Tourner le TIDE: Distillation d'Architecture croisée pour les modèles de langue de diffusion
— Gongbo Zhang
Diffusion large language models (dLLMs) offer parallel decoding and bidirectional context, but state-of-the-art dLLMs require billions of parameters for competitive performance. While existing distillation methods for dLLMs reduce inference steps within a single architecture, none address cross-arch
2026-04-29
Select to Think: Unlocking SLM Potential with Local Sufficiency
PDF
Choisir de penser: Débloquer le potentiel de la GDT avec suffisance locale
— Wen Wang
Small language models (SLMs) offer computational efficiency for scalable deployment, yet they often fall short of the reasoning power exhibited by their larger counterparts (LLMs). To mitigate this gap, current approaches invoke an LLM to generate tokens at points of reasoning divergence, but these
2026-04-29
Meta-learning-enhanced implicit full waveform inversion
PDF
Inversion implicite de pleine forme d'onde renforcée par le méta-apprentissage
— Ye Tian
Implicit full waveform inversion (IFWI) introduces implicit neural representations to parameterize the subsurface velocity model as a continuous function of spatial coordinates, which alleviates the dependence on the initial model and improves inversion flexibility. However, IFWI still requires a la
2026-04-29
World2VLM: Distilling World Model Imagination into VLMs for Dynamic Spatial Reasoning
PDF
World2VLM: L'imagination du modèle mondial de distillation en VLM pour la raison spatiale dynamique
— Li Yuan
Vision-language models (VLMs) have shown strong performance on static visual understanding, yet they still struggle with dynamic spatial reasoning that requires imagining how scenes evolve under egocentric motion. Recent efforts address this limitation either by scaling spatial supervision with synt
2026-04-29
Rethinking Nonlocality: Locality, Counterfactuals, and the EPR-Bell Argument
PDF
Repenser la non-localité : localité, contrefaits et argumentation EPR-Bell
— Wenxuan Ye
The widespread claim that violations of Bell inequalities establish the nonlocality of nature is critically reexamined. It is argued that this conclusion is not logically compelled by either the Einstein--Podolsky--Rosen (EPR) argument or Bell's theorem. The analysis highlights the central role
2026-04-29
Graph-based Semantic Calibration Network for Unaligned UAV RGBT Image Semantic Segmentation and A Large-scale Benchmark
PDF
Réseau d'étalonnage sémantique basé sur des graphiques pour la segmentation sémantique de l'image RGBT UAV non alignée et un repère à grande échelle
— Yangyang Zhang
Fine-grained RGBT image semantic segmentation is crucial for all-weather unmanned aerial vehicle (UAV) scene understanding. However, UAV RGBT semantic segmentation faces two coupled challenges: cross-modal spatial misalignment caused by sensor parallax and platform vibration, and severe semantic con
2026-04-29
Hot Fixing in the Wild
PDF
Fixation chaude dans la nature
— Xueli An
Despite the operational importance of hot fixes, large-scale evidence on how they reshape routine maintenance workflows, particularly in the era of autonomous coding agents, remains limited. We analyse hot fixes present in over 61,000 GitHub repositories from the Hao-Li/AIDev dataset and find consis
2026-04-29
Systems of Nonlocal Conservation Laws with Memory and Their Zero Retention Limit
PDF
Systèmes de lois de conservation non locales avec mémoire et leur limite zéro de conservation
— Georg Carle
We study the entropy solution for a class of systems of nonlocal conservation laws in which the convective flux is convoluted with a kernel in both spatial and temporal variables. This formulation models the flux dependence on the solution within its spatial neighbourhood (nonlocal in space) as well
2026-04-29
Outer-Crust Equations of State for Neutron Stars
PDF
Équations d'état pour les étoiles de Neutron
— P. S. Koliogiannis
We construct and systematically assess four outer-crust equations of state based on relativistic nuclear mass models and a machine-learning mass table. Our aim is to quantify the sensitivity of the equilibrium composition and thermodynamic properties of the outer crust to the underlying nuclear inpu
2026-04-29
Simulating dynamics of RLC circuits with a quantum differential-algebraic equations solver
PDF
Simulation de la dynamique des circuits RLC avec un solveur quantique différentiel-algébrique
— Gongbo Zhang
We introduce a quantum algorithm for simulating the dynamics of electrical circuits consisting of resistors, inductors and capacitors (aka RLC circuits) along with power sources. Given oracle access to the connectivity of the circuit and values of the electrical elements, our algorithm prepares a qu
2026-04-29
Hyper Input Convex Neural Networks for Shape Constrained Learning and Optimal Transport
PDF
Hyper Input Convex Réseaux neuronaux pour l'apprentissage de la forme et le transport optimal
— Wen Wang
We introduce Hyper Input Convex Neural Networks (HyCNNs), a novel neural network architecture designed for learning convex functions. HyCNNs combine the principles of Maxout networks with input convex neural networks (ICNNs) to create a neural network that is always convex in the input, theoreticall
2026-04-29
Designing Solutions to Geophysical Inverse Problems by Changing Variables
PDF
Concevoir des solutions aux problèmes géophysiques inverses en modifiant les variables
— Li Yuan
Geoscientists often solve inverse problems to estimate values of parameters of interest given relevant data sets. Bayesian inference solves these problems by combining probability distributions that describe uncertainties in both observations and unknown parameters, and we require that the solution
2026-04-29
Data-driven discovery of polynomial ODEs with provably bounded solutions
PDF
Découverte par des données d'ODE polynômes avec des solutions clairement délimitées
— Arkopal Dutt
We introduce SILAS, a data-driven framework for discovering polynomial ordinary differential equations (ODEs) with provably bounded trajectories. Boundedness is certified by compact absorbing sets defined via polynomial Lyapunov functions. We jointly identify the ODE vector field and the Lyapunov fu
2026-04-29
Learning Over-Relaxation Policies for ADMM with Convergence Guarantees
PDF
Politiques d'apprentissage en matière de sur-dilatation pour les SMAM avec garanties de convergence
— Anirban Chowdhury
The Alternating Direction Method of Multipliers (ADMM) is a widely used method for structured convex optimization, and its practical performance depends strongly on the choice of penalty and relaxation parameters. Motivated by settings such as Model Predictive Control (MPC), where one repeatedly sol
2026-04-29
Fractions of Recurrence Operators for Generalized Fourier Series in Classical Orthogonal Polynomials
PDF
Fractions des opérateurs de récurrence pour les séries de Fourier généralisées en polynômes orthogonaux classiques
— Wen Wang
We consider series expansions in bases of classical orthogonal polynomials. When such a series solves a linear differential equation with polynomial coefficients, its coefficients satisfy a linear recurrence equation. We interpret this equation as the numerator of a fraction of linear recurrence ope
2026-04-29
Thermodynamics formalism for singular flows
PDF
Formalisme thermodynamique pour les flux singuliers
— Li Yuan
We establish that $C^\infty$ three-dimensional flows with positive topological entropy admit only finitely many ergodic measures of maximal entropy, even when singularities (zero-velocity points) are present. Furthermore, every ergodic measure of maximal entropy is rapid mixing for such flows within
2026-04-29
Energy-Dependent Polarization Angle Variability as a Robust Diagnostic for Blazar Flaring Mechanisms
PDF
Variabilité de l'angle de polarisation en fonction de l'énergie comme diagnostic robuste pour les mécanismes de blason
— Alexandre Benoit
Identifying the physical mechanism driving blazar flares remains a central challenge in high-energy astrophysics. We show that the energy dependence of the standard deviation of the polarization angle variability ($σ_\text{PA}$) provides a powerful and robust discriminator of blazar flaring mechanis
2026-04-29
On a relationship between orthogonal projections and Toeplitz operators on poly-Bergman spaces of the upper half-plane: vertical symbols
PDF
Sur une relation entre les projections orthogonales et les opérateurs Toeplitz sur les espaces poly-bergman du demi-plan supérieur: symboles verticaux
— Nicolas Brisebarre
In the context of studying $C^*$-algebras generated by Toeplitz operators acting on the poly-Bergman space $\mathcal{A}^2_{n}(Π)$ of the upper half-plane $Π$, we introduce a system of all-but-one orthogonal projections in generic position. We show that the $C^*$-algebra generated by these orthoproje
2026-04-29
Revealing NVIDIA Closed-Source Driver Command Streams for CPU-GPU Runtime Behavior Insight
PDF
Réviser les flux de commande du pilote NVIDIA à source fermée pour CPU-GPU Runtime Comportement Insight
— Huan Song
For NVIDIA GPUs, CUDA is the primary interface through which applications orchestrate GPU execution, yet much of the logic that realizes CUDA operations resides in NVIDIA's closed-source userspace driver. As a result, the translation from high-level CUDA APIs to low-level hardware commands rema
2026-04-29
Optimizing Dynamic Metasurface Antenna Configurations for Direction-of-Arrival and Polarization Estimation Using an Experimentally Calibrated Multiport-Network Model
PDF
Optimisation des configurations d'antenne dynamique de métasurface pour l'estimation de la direction d'arrivée et de la polarisation à l'aide d'un modèle de réseau multiports étalonné expérimentalement
— N. Paar
Sensing the direction of arrival and polarization of impinging signals is a key prerequisite for beamforming and interference mitigation in modern wireless communication systems. Dynamic metasurface antennas (DMAs) can multiplex direction- and polarization-dependent field information onto a single d
2026-04-29
Exact Dynamic Programming for Solow--Polasky Diversity Subset Selection on Lines and Staircases
PDF
Programmation dynamique exacte pour Solow--Polasky Diversity Subset Selection sur les lignes et les escaliers
— Anirban Chowdhury
We study exact fixed-cardinality Solow--Polasky diversity subset selection on ordered finite $\ell_1$ sets, with monotone biobjective Pareto fronts and their higher-dimensional staircase analogues as central applications. Solow--Polasky diversity was introduced in biodiversity conservation, whereas
2026-04-29
The effect of spectral resolution on biosignature detection via reflected light observations of the Earth through time
PDF
L'effet de la résolution spectrale sur la détection de la biosignature par des observations de la lumière réfléchie de la Terre dans le temps
— Kristan Temme
NASA's Habitable Worlds Observatory (HWO) will search for biosignatures on Earth-like exoplanets using reflected light spectroscopy. A critical instrument design parameter is resolving power, which must balance biosignature detectability against exposure time and detector noise constraints. We
2026-04-29
ClassEval-Pro: A Cross-Domain Benchmark for Class-Level Code Generation
PDF
ClassEval-Pro: Un point de repère trans-domaine pour la génération de codes de niveau de classe
— Hari Krovi
LLMs have achieved strong results on both function-level code synthesis and repository-level code modification, yet a capability that falls between these two extremes -- compositional code creation, i.e., building a complete, internally structured class from a specification -- remains underserved. C
2026-04-29
Weighted Linearization of Vector Fields via a Formal Moser Trick
PDF
Linéarisation pondérée des champs vectoriaux via un trick formel
— Arthur Lei Qiu
Many well-known theorems establish sufficient criteria for linearizability of a vector field in terms of the eigenvalues of its linear approximation. By attaching weights to coordinates so that some directions are considered "linear", others "quadratic", and so on, one can define
2026-04-29
Schwinger-Keldysh Path Integral for Gauge theories
PDF
Schwinger-Keldysh Path Integral pour les théories de la jauge
— Greg Kaplanek
We develop the Schwinger-Keldysh path-integral formalism for open non-Abelian gauge theories that are gauge-fixed via the BRST method in covariant gauges. We focus on generic initial states, pure and mixed, specified at finite times suitable for non-equilibrium processes. We pay particular attention
2026-04-29
Artistic Practice Opportunities in CST Evaluations: A Longitudinal Group Deployment of ArtKrit
PDF
Opportunités de pratique artistique dans les évaluations du CST : Déploiement d'ArtKrit par un groupe longitudinal
— Andrew J. Tolley
Creativity support tools (CSTs) aim to elevate the quality of artists' creative processes and artifacts. Yet most current CST evaluations overlook temporal and social aspects of tool use. To address this gap, we present a longitudinal, group-based CST evaluation through a three-week deployment
2026-04-29
On the Learning Curves of Revenue Maximization
PDF
Sur les courbes d'apprentissage de la maximisation des revenus
— Ming Li
Learning curves are a fundamental primitive in supervised learning, describing how an algorithm's performance improves with more data and providing a quantitative measure of its generalization ability. Formally, a learning curve plots the decay of an algorithm's error for a fixed underlyin