🧠 Yann LeCun & Luc Julia — IA Post-LLM
Dernière mise à jour : 01/05/2026 à 03:32 UTC
Veille sur les travaux de Yann LeCun (FAIR/Meta) : JEPA, World Models, Energy-Based Models, SSL —
Luc Julia (co-créateur de Siri avec Adam Cheyer, ex-VP Apple & Samsung AI, Orange, auteur de « L'IA n'existe pas ») —
SRI International berceau de Siri —
Apple ML Research.
Titres en anglais traduits en vert · PDF = preprint arXiv · Historique : 287 article(s) sur 360 jours.
📰 Actualités du jour
🧠
Meta AI — FAIR Research
Aucun article récupéré.
🎤
Luc Julia — Medium
Aucun article récupéré.
🟠
Orange Hello Future — Innovation IA
Blog officiel
2026-04-30
Self-healing: How AI Improves Telecom Network Operations
Autoguérison : comment l'IA améliore les opérations des réseaux de télécommunications
2026-04-28
Advertising in AI and Agentic Commerce: The Challenges of Conversational E-commerce
La publicité dans l'IA et le commerce des agents : les défis du commerce électronique conversationnel
2026-04-21
Strengthening Anti-Malware Defenses with Artificial Intelligence
Renforcement des défenses anti-malware avec l'intelligence artificielle
2026-04-17
What is the Climate Cost of Satellite Broadband Connectivity?
Quel est le coût climatique de la connectivité à large bande par satellite?
2026-04-16
Frugal AI: When Simplicity and Quality Go Hand in Hand
L'IA frugale : quand la simplicité et la qualité vont de pair
2026-04-16
Connected Mobility and Federated AI: How Can We Quantify and Minimize Energy Costs?
Mobilité connectée et AI fédérée : comment quantifier et réduire au minimum les coûts énergétiques?
2026-04-09
Domain Hijacking, Cookie Theft, and Conducting Quality DNS Audits: How to Protect Your Company and Improve Your Cyber-Rating ?
Le détournement de domaine, le vol de cookies et la conduite d'audits DNS de qualité : comment protéger votre entreprise et améliorer votre cyberévaluation ?
2026-04-08
At ChangeNow, Socially Conscious Startups Use AI to Turn Data into Concrete Action
À ChangeNow, les startups socialement conscientes utilisent l'IA pour transformer les données en actions concrètes
2026-04-03
Sharlie: Behind the Scenes of a Speech-to-Speech Voice Assistant
Sharlie : Dans les coulisses d'une assistante vocale de discours à discours
2026-03-26
Rising Cloud Costs: Should AI Bots That Overload the Web Be Charged?
L'augmentation des coûts du Cloud : L'IA devrait-elle mettre en place des systèmes qui surchargent le Web?
Hacker News
2023-11-01
Open source AI need to look at Section 4.6 of Biden's Executive Order
HN 8▲
Open source AI doit regarder la section 4.6 du décret de Biden
2024-07-25
Show HN: NetFabric – next-gen network monitoring solution
HN 6▲
Afficher HN: NetFabric – solution de surveillance réseau next-gen
🧬
SRI International — AI Research (berceau Siri)
Aucun article récupéré.
🍎
Apple Machine Learning Research
Blog officiel
2026-04-30
STARFlow-V: End-to-End Video Generative Modeling with Normalizing Flows
STARFlow-V: Modélisation vidéo de bout en bout avec des flux de normalisation
2026-04-30
International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2026
Conférence internationale sur l'acoustique, le traitement des discours et des signaux (ICASSP) 2026
2026-04-30
Bootstrapping Sign Language Annotations with Sign Language Models
Annotations en langue des signes avec modèles de langue des signes
2026-04-29
DSO: Direct Steering Optimization for Bias Mitigation
DSO : Optimisation de la direction directe pour l'atténuation des préjugés
2026-04-29
Adaptive Thinking: Large Language Models Know When to Think in Latent Space
Pensée adaptative : Les grands modèles linguistiques savent quand penser dans l'espace latent
2026-04-28
StereoFoley: Object-Aware Stereo Audio Generation from Video
StereoFoley: Stéréo Production Audio à partir de la vidéo
2026-04-28
Local Mechanisms of Compositional Generalization in Conditional Diffusion
Mécanismes locaux de généralisation de la composition dans la diffusion conditionnelle
2026-04-28
LaDiR: Latent Diffusion Enhances LLMs for Text Reasoning
LaDiR : La diffusion latente améliore les LLM pour la raisonnement textuel
2026-04-24
Learning Long-Term Motion Embeddings for Efficient Kinematics Generation
Apprendre le mouvement à long terme Embeddings for Efficient Kinematics Generation
2026-04-23
ParaRNN: Large-Scale Nonlinear RNNs, Trainable in Parallel
ParaRNN : RNN non linéaires à grande échelle, entraînées en parallèle
🤗
Hugging Face Blog
Blog officiel
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
2021-08-05
Yann LeCun on his start in AI, recent self-supervised learning research [video]
HN 111▲
Yann LeCun au départ de l'IA, recherche d'apprentissage auto-supervisée récente [vidéo]
2018-09-11
Launch HN: Sterblue (YC S18) – Software for drones to inspect power lines
HN 84▲
Lancement HN: Sterblue (YC S18) – Logiciel pour les drones pour inspecter les lignes électriques
2019-08-31
Yann LeCun: Self-Supervised Learning [video]
HN 3▲
Yann LeCun : L'auto-apprentissage [vidéo]
2020-05-03
LeCun and Bengio: Self-supervised learning is the key to human-level AI
HN 3▲
LeCun et Bengio : l'auto-apprentissage est la clé de l'IA au niveau humain
2026-02-24
Explanation of JEPA – Yann LeCun's proposed solution to self-supervised learning
HN 2▲
Explication de JEPA – La solution proposée par Yann LeCun pour l'auto-apprentissage
📘
Publications arXiv
JEPA · World Models · EBM · Siri · Luc Julia · IA réelle — PDF = preprint direct
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
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
Generalizable Sparse-View 3D Reconstruction from Unconstrained Images
PDF
Généralisable Sparse-View Reconstruction 3D à partir d'images sans contrainte
— Xiwu Chen
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
Observation of Vinen turbulence during far-from-equilibrium Bose-Einstein condensation
PDF
Observation des turbulences de Vinen pendant la condensation de Bose-Einstein, loin de l'équilibre
— Feiyang Tan
Relaxation of far-from-equilibrium quantum fluids, intimately related to the emergence of long-range order, is theoretically associated with the decay of a turbulent isotropic tangle of vortex lines. We observe and study such decaying quantum turbulence in a homogeneous 3D atomic Bose gas. Using mat
2026-04-30
Uniaxial strain-driven ferroelastic domain control in LaAlO3
PDF
Contrôle de domaine ferroélastique uniaxial par déformation dans LaAlO3
— Dingyuan Zhang
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
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
— Hengshuang Zhao
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
Defending Quantum Classifiers against Adversarial Perturbations through Quantum Autoencoders
PDF
Défense des classificateurs quantiques contre les perturbations adversaires par l'intermédiaire des codeurs automatiques quantiques
— Xiang Bai
Machine learning models can learn from data samples to carry out various tasks efficiently. When data samples are adversarially manipulated, such as by insertion of carefully crafted noise, it can cause the model to make mistakes. Quantum machine learning models are also vulnerable to such adversari
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
— Hao Geng
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
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
— Dingkang Liang
$ω$~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
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
— Xiwu Chen
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
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
— Hengshuang Zhao
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
Representation Fréchet Loss for Visual Generation
PDF
Représentation Fréchet Perte pour la génération visuelle
— Xiang Bai
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
Towards Systematics of Calabi-Yau Landscape for String Cosmology
PDF
Vers la systématique du paysage de Calabi-Yau pour la cosmologie à cordes
— Furkan Akbaba
In this review, we discuss the relevance and impact of studying Calabi-Yau threefolds in the context of global model building in string phenomenology. First, taking a phenomenologist-friendly approach, we review how the topologies of the various divisors and curves of the compactifying CY threefolds
2026-04-30
Cosmology of fractional gravity
PDF
Cosmologie de la gravité fractionnelle
— Junyoung Lee
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
Enhancement of superconducting stiffness in hybrid superconducting-metallic bilayers
PDF
Amélioration de la rigidité supraconductrice dans les bicouches hybrides supraconductrices-métalliques
— Dingyuan Zhang
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
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
— Hengshuang Zhao
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
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
— Xiang Bai
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
Exploration Hacking: Can LLMs Learn to Resist RL Training?
PDF
Exploration Hacking: Les LLM peuvent-ils apprendre à résister à l'entraînement RL?
— Junyoung Lee
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
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
— Xiang Bai
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
— Junyoung Lee
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
Computing Equilibrium beyond Unilateral Deviation
PDF
Équilibre informatique au-delà de la déviation unilatérale
— Xiang Bai
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
🔬
OpenAlex — Publications académiques
Corpus académique indexé par OpenAlex (ResearchGate, Crossref, PubMed…)
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
2026-12-01
Dark personality traits in project management : A bibliometric analysis and agenda for future research
Des traits de personnalité sombres dans la gestion de projet : Une analyse bibliométrique et un agenda pour la recherche future
— Udechukwu Ojiako, Malcolm Higgs, Khalid Khalfan Mohamed Al Naqbi et al.
2026-12-01
Security- as- a- service: enhancing cloud security through managed security solutions
Sécurité en tant que service : améliorer la sécurité dans le cloud grâce à des solutions de sécurité gérées
— Zainab S. Attarbashi, Azana Hafizah Mohd Aman, Salem Sati et al.
2026-10-31
Complaints about the Weather: Eco-Neurosis in Jonathan Safran Foer and Jenny Offill
Plaintes sur la météo: Eco-Neurose à Jonathan Safran Foer et Jenny Offill
— Demeyer, Hans
2026-09-01
Universal Audio Generation
Génération audio universelle
— Antoine Laurent, Sameer Khurana, Anthony Larcher et al.
2026-09-01
The Relationship Between Adverse Childhood Experiences, Protective and Compensatory Experiences, and Parenting Attitudes Among Fathers
La relation entre les expériences d'enfants indésirables, les expériences de protection et de compensation et les attitudes parentales des pères
— kylie Schmidt
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
2026-04-27
Reflections of Artificial Intelligence Use on Student Achievement and Attitudes in Biology Classes
Réflexions de l'utilisation de l'intelligence artificielle sur les réalisations et les attitudes des élèves dans les classes de biologie
— Meryem Konu Kadirhanoğulları
2026-04-27
La interpretación en los servicios públicos en la era de la IA: retos, oportunidades y tendencias emergentes
La interpretation en los servicios públicos en la era de la IA: retos, oportunidades y tendencias émergent
— Luis Ángel Pastor Fernández
2026-04-27
Thinking towards the Future: Reflections on Engaging with AI for Visual Data Presentation in Qualitative Research
Penser à l'avenir : Réflexions sur la participation à l'IA pour la présentation de données visuelles dans la recherche qualitative
— Chloe Le, Anh Ngoc Quynh Phan
2026-04-26
The Migration of Business Ethics within Artificial Intelligence (AI)
Migration de l'éthique des affaires au sein de l'intelligence artificielle (IA)
— Khaled M. Musa, Cecilia Walsh, Laila Akhavi et al.
2026-04-24
Uni-Encoder Meets Multi-Encoders: Representation Before Fusion for Brain Tumor Segmentation with Missing Modalities
Uni-Encoder rencontre plusieurs encodeurs: Représentation avant fusion pour segmentation des tumeurs cérébrales avec des modalités manquantes
— Peibo Song, Xiaotian Xue, Jinshuo Zhang et al.
2026-04-24
ASPIRE: Make Spectral Graph Collaborative Filtering Great Again via Adaptive Filter Learning
ASPIRE: Faire Spectral Graph en collaboration Filtering Great à nouveau via l'apprentissage du filtre adaptatif
— Yunhang He, Cong Xu, Zhangchi Zhu et al.
2026-04-24
Beyond Patient Invariance: Learning Cardiac Dynamics via Action-Conditioned JEPAs
Au-delà de l'invariance du patient : apprentissage de la dynamique cardiaque grâce aux JEPAs sous condition action
— José Geraldo Fernandes, Luiz Facury, Pedro Robles Dutenhefner et al.
2026-04-24
Peer Review Report For: Towards Protecting the Injured Party from Errors and Hallucinations of Artificial Intelligence: A Contemporary Legal Perspective [version 1; peer review: 2 approved]
Rapport d'examen par les pairs pour : Protéger la partie blessée des erreurs et des hallucinations de l'intelligence artificielle : une perspective juridique contemporaine [version 1; examen par les pairs : 2 approuvés]
— Jamal Barafi
2026-04-23
Uncertainty Estimation in Neural Network-enabled Side-channel Analysis and Links to Explainability
Estimation de l'incertitude dans l'analyse des canaux latéraux et des liens vers l'explicabilité grâce au réseau neuronal
— Seyedmohammad Nouraniboosjin, Fatemeh Ganji
2026-04-23
Drug Synergy Prediction via Residual Graph Isomorphism Networks and Attention Mechanisms
Prédiction de la synergie médicamenteuse par l'intermédiaire des réseaux d'isomorphisme et des mécanismes d'attention résiduels
— Jiyan Song, Wenyang Wang, Chengcheng Yan et al.
2026-04-23
From Tokens to Concepts: Leveraging SAE for SPLADE
Des jetons aux concepts : tirer parti de SAE pour SPLADE
— Yuxuan Zong, Mathias Vast, Basile Van Cooten et al.
📅 Historique — 360 derniers jours
May 2026 — 29 article(s)
2026-04-30
Self-healing: How AI Improves Telecom Network Operations
Autoguérison : comment l'IA améliore les opérations des réseaux de télécommunications
2026-04-30
STARFlow-V: End-to-End Video Generative Modeling with Normalizing Flows
STARFlow-V: Modélisation vidéo de bout en bout avec des flux de normalisation
2026-04-30
International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2026
Conférence internationale sur l'acoustique, le traitement des discours et des signaux (ICASSP) 2026
2026-04-30
Bootstrapping Sign Language Annotations with Sign Language Models
Annotations en langue des signes avec modèles de langue des signes
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
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
Generalizable Sparse-View 3D Reconstruction from Unconstrained Images
PDF
Généralisable Sparse-View Reconstruction 3D à partir d'images sans contrainte
— Xiwu Chen
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
Observation of Vinen turbulence during far-from-equilibrium Bose-Einstein condensation
PDF
Observation des turbulences de Vinen pendant la condensation de Bose-Einstein, loin de l'équilibre
— Feiyang Tan
Relaxation of far-from-equilibrium quantum fluids, intimately related to the emergence of long-range order, is theoretically associated with the decay of a turbulent isotropic tangle of vortex lines. We observe and study such decaying quantum turbulence in a homogeneous 3D atomic Bose gas. Using mat
2026-04-30
Uniaxial strain-driven ferroelastic domain control in LaAlO3
PDF
Contrôle de domaine ferroélastique uniaxial par déformation dans LaAlO3
— Dingyuan Zhang
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
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
— Hengshuang Zhao
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
Defending Quantum Classifiers against Adversarial Perturbations through Quantum Autoencoders
PDF
Défense des classificateurs quantiques contre les perturbations adversaires par l'intermédiaire des codeurs automatiques quantiques
— Xiang Bai
Machine learning models can learn from data samples to carry out various tasks efficiently. When data samples are adversarially manipulated, such as by insertion of carefully crafted noise, it can cause the model to make mistakes. Quantum machine learning models are also vulnerable to such adversari
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
— Hao Geng
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
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
— Dingkang Liang
$ω$~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
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
— Xiwu Chen
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
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
— Hengshuang Zhao
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
Representation Fréchet Loss for Visual Generation
PDF
Représentation Fréchet Perte pour la génération visuelle
— Xiang Bai
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
Towards Systematics of Calabi-Yau Landscape for String Cosmology
PDF
Vers la systématique du paysage de Calabi-Yau pour la cosmologie à cordes
— Furkan Akbaba
In this review, we discuss the relevance and impact of studying Calabi-Yau threefolds in the context of global model building in string phenomenology. First, taking a phenomenologist-friendly approach, we review how the topologies of the various divisors and curves of the compactifying CY threefolds
2026-04-30
Cosmology of fractional gravity
PDF
Cosmologie de la gravité fractionnelle
— Junyoung Lee
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
Enhancement of superconducting stiffness in hybrid superconducting-metallic bilayers
PDF
Amélioration de la rigidité supraconductrice dans les bicouches hybrides supraconductrices-métalliques
— Dingyuan Zhang
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
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
— Hengshuang Zhao
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
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
— Xiang Bai
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
Exploration Hacking: Can LLMs Learn to Resist RL Training?
PDF
Exploration Hacking: Les LLM peuvent-ils apprendre à résister à l'entraînement RL?
— Junyoung Lee
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
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
— Xiang Bai
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
— Junyoung Lee
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
Computing Equilibrium beyond Unilateral Deviation
PDF
Équilibre informatique au-delà de la déviation unilatérale
— Xiang Bai
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
2026-04-28
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
2026-04-24
Uni-Encoder Meets Multi-Encoders: Representation Before Fusion for Brain Tumor Segmentation with Missing Modalities
Uni-Encoder rencontre plusieurs encodeurs: Représentation avant fusion pour segmentation des tumeurs cérébrales avec des modalités manquantes
— Peibo Song, Xiaotian Xue, Jinshuo Zhang et al.
2026-04-24
ASPIRE: Make Spectral Graph Collaborative Filtering Great Again via Adaptive Filter Learning
ASPIRE: Faire Spectral Graph en collaboration Filtering Great à nouveau via l'apprentissage du filtre adaptatif
— Yunhang He, Cong Xu, Zhangchi Zhu et al.
2026-04-24
Beyond Patient Invariance: Learning Cardiac Dynamics via Action-Conditioned JEPAs
Au-delà de l'invariance du patient : apprentissage de la dynamique cardiaque grâce aux JEPAs sous condition action
— José Geraldo Fernandes, Luiz Facury, Pedro Robles Dutenhefner et al.
April 2026 — 258 article(s)
2026-04-29
Adaptive Thinking: Large Language Models Know When to Think in Latent Space
Pensée adaptative : Les grands modèles linguistiques savent quand penser dans l'espace latent
2026-04-29
DSO: Direct Steering Optimization for Bias Mitigation
DSO : Optimisation de la direction directe pour l'atténuation des préjugés
2026-04-28
LaDiR: Latent Diffusion Enhances LLMs for Text Reasoning
LaDiR : La diffusion latente améliore les LLM pour la raisonnement textuel
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
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
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
— N. Paar
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
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
— Gongbo Zhang
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
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
Select to Think: Unlocking SLM Potential with Local Sufficiency
PDF
Choisir de penser: Débloquer le potentiel de la GDT avec suffisance locale
— Ye Tian
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
Degree-dependent and distance-dependent contact rates interpolate between explosive, exponential and polynomial epidemic growth
PDF
Les taux de contact dépendants du degré et de la distance interpolent entre la croissance épidémique explosive, exponentielle et polynôme
— Li Yuan
It is a fundamental question in epidemiology to estimate, model and predict the growth rate of a pandemic. Analogously, analysing the diffusion of innovation, (fake) news, memes, and rumours is of key importance in the social sciences. The resulting epidemic growth curves can be classified according
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
— Jean Tapie
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
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
— Philipp del Hougne
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
Anomalous Transport and Explicit Symmetry Breaking in Holography
PDF
Transport anomal et symmétrie explicite Breaking in Holographie
— Gongbo Zhang
We consider a holographic Einstein-Maxwell model in five dimensions with pure gauge and mixed gauge-gravitational Chern-Simons terms to study anomaly-induced transport in the presence of explicit symmetry breaking. We include the full backreaction of the scalar field and gauge fields on the metric a
2026-04-29
Large quantum dot energy level shifts in anomalous photon-assisted tunneling
PDF
Changements de niveau d'énergie de point quantique dans un tunnel anomale assisté au photon
— Ye Tian
Orbital energy splittings are important quantum dot parameters for the operation of hole spin qubits. They are known to depend on the lateral confinement of the quantum dots. However, when changing top, plunger gate voltages, which are the typical control parameter for qubit applications, such energ
2026-04-29
Three-Step Nav: A Hierarchical Global-Local Planner for Zero-Shot Vision-and-Language Navigation
PDF
Trois étapes Nav : un planificateur hiérarchique mondial-local pour la navigation en vision et en langue zéro
— Li Yuan
Breakthrough progress in vision-based navigation through unknown environments has been achieved by using multimodal large language models (MLLMs). These models can plan a sequence of motions by evaluating the current view at each time step against the task and goal given to the agent. However, curre
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
— Ashis Tamang
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
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
— Nishal Rai
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
Weighted Linearization of Vector Fields via a Formal Moser Trick
PDF
Linéarisation pondérée des champs vectoriaux via un trick formel
— Wen Wang
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
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
— A. R. Huffman
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
High Coupling Tunable Acoustic Resonators in Monolithic Barium Titanate
PDF
Résonateurs acoustiques à couple élevé en titane de baryum monolithique
— Sanghyeok Park
The growing number of wireless communication bands has driven demand for compact, low-loss, and frequency adjustable RF filtering. Tunable acoustic resonators are well suited to address these needs, offering a path toward reconfigurable front ends with reduced component count. In this work, we exten
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
— Valentin John
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
Digital Simulation of Non-Hermitian Knotted Bands on Quantum Hardware
PDF
Simulation numérique de bandes non-hermitiennes sur matériel quantique
— Brighton X. Coe
Knots and links represent a fundamental motif of non-local connectivity that permeates the physical sciences from string theory to protein folds. While spectral braiding has been explored in two-band non-Hermitian models across various platforms, its direct simulation and characterization on program
2026-04-29
Bi-Level Optimization for Contact and Motion Planning in Rope-Assisted Legged Robots
PDF
Optimisation bi-niveau pour la planification du contact et du mouvement dans les robots à cordes
— Tyler J. Kovach
This paper presents a planning pipeline framework for locomotion in rope-assisted robots climbing vertical surfaces. The proposed framework is formulated as a bi-level optimization scheme that addresses a mixed-integer problem: selecting feasible terrain regions for landing while simultaneously opti
2026-04-29
ClawGym: A Scalable Framework for Building Effective Claw Agents
PDF
ClawGym: Un cadre évolutif pour la construction d'agents efficaces en matière de griffe
— Stefan D. Oosterhout
Claw-style environments support multi-step workflows over local files, tools, and persistent workspace states. However, scalable development around these environments remains constrained by the absence of a systematic framework, especially one for synthesizing verifiable training data and integratin
2026-04-29
ProcFunc: Function-Oriented Abstractions for Procedural 3D Generation in Python
PDF
ProcFunc: Abstractions orientées fonction pour la génération 3D procédurale en Python
— Ashis Tamang
We introduce ProcFunc, a library for Blender-based procedural 3D generation in Python. ProcFunc provides a library of easy-to-use Python functions, which streamline creating, combining, analyzing, and executing procedural generation code. ProcFunc makes it easy to create large-scale diverse training
2026-04-29
Schwinger-Keldysh Path Integral for Gauge theories
PDF
Schwinger-Keldysh Path Integral pour les théories de la jauge
— Ye Tian
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
Meta-learning-enhanced implicit full waveform inversion
PDF
Inversion implicite de pleine forme d'onde renforcée par le méta-apprentissage
— Wanrong Zheng
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
2026-04-27
Reflections of Artificial Intelligence Use on Student Achievement and Attitudes in Biology Classes
Réflexions de l'utilisation de l'intelligence artificielle sur les réalisations et les attitudes des élèves dans les classes de biologie
— Meryem Konu Kadirhanoğulları