Artikel

200 Einträge
Zeitraum: Heute Alle
Titel Quelle Datum Relevanz
ADAC-Pannenstatistik: E-Autos sind zuverlässiger als Verbrenner Heise Online 30.04.2026 4/5
heise+ | Wie Sie Ihren alten Kindle nach dem Supportende weiternutzen Heise Online 30.04.2026 3/5
Vimeo: Daten stehen nach Datenleck im Darknet zum Download Heise Online 30.04.2026 5/5
Iran: KI-generierte Lego-Clips als Instrument der psychologischen Kriegsführung Heise Online 30.04.2026 4/5
heise-Angebot: iX-Workshop: Netzwerkarchitekturen in Proxmox aufbauen, verwalten und schützen Heise Online 30.04.2026 4/5
Berichte: OnePlus und Realme fusionieren Heise Online 30.04.2026 3/5
YouTube-App: Bild-in-Bild-Modus jetzt für alle Nutzer verfügbar Heise Online 30.04.2026 4/5
Starlink fürs Smartphone: T-Mobile sieht unerwartet geringe Nutzung Heise Online 30.04.2026 3/5
Sportwagenhersteller Porsche meldet Gewinnrückgang und Neuausrichtung Heise Online 30.04.2026 4/5
Asse II: Fraunhofer und Bilfinger entwickeln Roboter zur Bergung Nuklearabfalls Heise Online 30.04.2026 5/5
„Copy Fail“: Linux-root in allen großen Distributionen mit 732 Byte Python Heise Online 30.04.2026 5/5
„Copy Fail“: Linux-root in allen großen Distributionen mit 732 Byte Python Heise Online 30.04.2026 5/5
cPanel/WHM: Unbefugte Zugriffe auf Webserver-Konfigurationstool möglich Heise Online 30.04.2026 4/5
cPanel/WHM: Unbefugte Zugriffe auf Webserver-Konfigurationstool möglich Heise Online 30.04.2026 5/5
heise+ | Apple Watch als Whoop-Ersatz: Gesundheits-Apps für Fitness und Erholung Heise Online 30.04.2026 4/5
heise+ | Apple Watch als Whoop-Ersatz: Gesundheits-Apps für Fitness und Erholung Heise Online 30.04.2026 4/5
Samsung erzielt höchsten Gewinn in Unternehmensgeschichte Heise Online 30.04.2026 4/5
Samsung erzielt höchsten Gewinn in Unternehmensgeschichte Heise Online 30.04.2026 4/5
KI-Wettrüsten: Tech-Riesen investieren hunderte Milliarden Heise Online 30.04.2026 5/5
KI-Wettrüsten: Tech-Riesen investieren hunderte Milliarden Heise Online 30.04.2026 5/5
heise-Angebot: Medizintechnik zwischen Innovation und Regulierung auf der MedConf 2026 Heise Online 30.04.2026 4/5
heise-Angebot: Medizintechnik zwischen Innovation und Regulierung auf der MedConf 2026 Heise Online 30.04.2026 4/5
DRM-Aufregung um Playstation 5: Laut Sony nur ein einzelner Online-Check nötig Heise Online 30.04.2026 4/5
DRM-Aufregung um Playstation 5: Laut Sony nur ein einzelner Online-Check nötig Heise Online 30.04.2026 4/5
heise+ | Netzentgelte im Umbruch: Warum es für PV-Anlagenbesitzer teurer werden könnte Heise Online 30.04.2026 4/5
heise+ | Netzentgelte im Umbruch: Warum es für PV-Anlagenbesitzer teurer werden könnte Heise Online 30.04.2026 4/5
Zuckerberg: Meta-KI soll Tag und Nacht für Nutzer arbeiten Heise Online 30.04.2026 4/5
Zuckerberg: Meta-KI soll Tag und Nacht für Nutzer arbeiten Heise Online 30.04.2026 4/5
Souveräner Bezahldienst Wero klebt noch an AWS, aber gelobt Besserung Heise Online 30.04.2026 4/5
Souveräner Bezahldienst Wero klebt noch an AWS, aber gelobt Besserung Heise Online 30.04.2026 4/5
Musk vs. OpenAI: Milliardär wollte die volle Kontrolle über das KI-Labor Heise Online 30.04.2026 4/5
Musk vs. OpenAI: Milliardär wollte die volle Kontrolle über das KI-Labor Heise Online 30.04.2026 4/5
heise+ | Opel Mokka GSE im Test: Sympathisch, flott und verflixt teuer Heise Online 30.04.2026 3/5
heise+ | Opel Mokka GSE im Test: Sympathisch, flott und verflixt teuer Heise Online 30.04.2026 4/5
Ariane 6 liefert neuen Schub für das Amazon-Leo-Satellitennetz Heise Online 30.04.2026 4/5
Ariane 6 liefert neuen Schub für das Amazon-Leo-Satellitennetz Heise Online 30.04.2026 4/5
Amazon übertrifft Erwartungen Heise Online 30.04.2026 4/5
Amazon übertrifft Erwartungen Heise Online 30.04.2026 4/5
Linux für Gamer: Bazzite 44 basiert auf Fedora 44 Heise Online 30.04.2026 4/5
Linux für Gamer: Bazzite 44 basiert auf Fedora 44 Heise Online 30.04.2026 4/5
Donnerstag: Googles KI-Suche als Umsatztreiber, Speicherkrise belastet Microsoft Heise Online 30.04.2026 4/5
Donnerstag: Googles KI-Suche als Umsatztreiber, Speicherkrise belastet Microsoft Heise Online 30.04.2026 4/5
#heiseshow: Signal-Affäre, KI für die Psyche, Hannover Messe Heise Online 30.04.2026 4/5
#heiseshow: Signal-Affäre, KI für die Psyche, Hannover Messe Heise Online 30.04.2026 4/5
HIVE: Hidden-Evidence Verification for Hallucination Detection in Diffusion Large Language Models arXiv cs.CL 30.04.2026 –
StarDrinks: An English and Korean Test Set for SLU Evaluation in a Drink Ordering Scenario arXiv cs.CL 30.04.2026 –
ViCrop-Det: Spatial Attention Entropy Guided Cropping for Training-Free Small-Object Detection arXiv cs.AI 30.04.2026 –
From Prompt Risk to Response Risk: Paired Analysis of Safety Behavior of Large Language Model arXiv cs.CL 30.04.2026 –
BioGraphletQA: Knowledge-Anchored Generation of Complex QA Datasets arXiv cs.CL 30.04.2026 –
Resume-ing Control: (Mis)Perceptions of Agency Around GenAI Use in Recruiting Workflows arXiv cs.AI 30.04.2026 –
Causal Learning with Neural Assemblies arXiv cs.AI 30.04.2026 –
A Quantitative Confirmation of the Currier Language Distinction arXiv cs.CL 30.04.2026 –
Select to Think: Unlocking SLM Potential with Local Sufficiency arXiv cs.CL 30.04.2026 –
Anchored Confabulation: Partial Evidence Non-Monotonically Amplifies Confident Hallucination in LLMs arXiv cs.CL 30.04.2026 –
SWE-Edit: Rethinking Code Editing for Efficient SWE-Agent arXiv cs.CL 30.04.2026 –
One Voice, Many Tongues: Cross-Lingual Voice Cloning for Scientific Speech arXiv cs.CL 30.04.2026 –
Beyond Screenshots: Evaluating VLMs' Understanding of UI Animations arXiv cs.CL 30.04.2026 –
CacheRAG: A Semantic Caching System for Retrieval-Augmented Generation in Knowledge Graph Question Answering arXiv cs.CL 30.04.2026 –
Flashback: A Reversible Bilateral Run-Peeling Decomposition of Strings arXiv cs.CL 30.04.2026 –
Addressing Performance Saturation for LLM RL via Precise Entropy Curve Control arXiv cs.CL 30.04.2026 –
The False Resonance: A Critical Examination of Emotion Embedding Similarity for Speech Generation Evaluation arXiv cs.CL 30.04.2026 –
Accelerating RL Post-Training Rollouts via System-Integrated Speculative Decoding arXiv cs.CL 30.04.2026 –
HealthNLP_Retrievers at ArchEHR-QA 2026: Cascaded LLM Pipeline for Grounded Clinical Question Answering arXiv cs.CL 30.04.2026 –
MoRFI: Monotonic Sparse Autoencoder Feature Identification arXiv cs.CL 30.04.2026 –
Associative-State Universal Transformers: Sparse Retrieval Meets Structured Recurrence arXiv cs.CL 30.04.2026 –
Rule-based High-Level Coaching for Goal-Conditioned Reinforcement Learning in Search-and-Rescue UAV Missions Under Limited-Simulation Training arXiv cs.AI 30.04.2026 –
What Kind of Language is Easy to Language-Model Under Curriculum Learning? arXiv cs.CL 30.04.2026 –
Decoupling Knowledge and Task Subspaces for Composable Parametric Retrieval Augmented Generation arXiv cs.CL 30.04.2026 –
LLMs Generate Kitsch arXiv cs.CL 30.04.2026 –
Differentially-Private Text Rewriting reshapes Linguistic Style arXiv cs.CL 30.04.2026 –
SAGE: A Strategy-Aware Graph-Enhanced Generation Framework For Online Counseling arXiv cs.CL 30.04.2026 –
CogRAG+: Cognitive-Level Guided Diagnosis and Remediation of Memory and Reasoning Deficiencies in Professional Exam QA arXiv cs.CL 30.04.2026 –
Turning the TIDE: Cross-Architecture Distillation for Diffusion Large Language Models arXiv cs.AI 30.04.2026 –
Explainable Representation of Finite-Memory Policies for POMDPs using Decision Trees arXiv cs.AI 30.04.2026 –
Beyond Text-Dominance: Understanding Modality Preference of Omni-modal Large Language Models arXiv cs.AI 30.04.2026 –
OCR-Memory: Optical Context Retrieval for Long-Horizon Agent Memory arXiv cs.CL 30.04.2026 –
Zero-Shot to Full-Resource: Cross-lingual Transfer Strategies for Aspect-Based Sentiment Analysis arXiv cs.CL 30.04.2026 –
Information Extraction from Electricity Invoices with General-Purpose Large Language Models arXiv cs.CL 30.04.2026 –
Multimodal LLMs are not all you need for Pediatric Speech Language Pathology arXiv cs.CL 30.04.2026 –
Theory-Grounded Evaluation Exposes the Authorship Gap in LLM Personalization arXiv cs.CL 30.04.2026 –
MATH-PT: A Math Reasoning Benchmark for European and Brazilian Portuguese arXiv cs.CL 30.04.2026 –
HalluCiteChecker: A Lightweight Toolkit for Hallucinated Citation Detection and Verification in the Era of AI Scientists arXiv cs.AI 30.04.2026 –
Evaluation of Automatic Speech Recognition Using Generative Large Language Models arXiv cs.CL 30.04.2026 –
A Self-Evolving Framework for Efficient Terminal Agents via Observational Context Compression arXiv cs.CL 30.04.2026 –
EmoTransCap: Dataset and Pipeline for Emotion Transition-Aware Speech Captioning in Discourses arXiv cs.CL 30.04.2026 –
Retrieval-Augmented Multimodal Model for Fake News Detection arXiv cs.CL 30.04.2026 –
Crime Hotspot Prediction Using Deep Graph Convolutional Networks arXiv cs.CL 30.04.2026 –
ReGATE: Learning Faster and Better with Fewer Tokens in MLLMs arXiv cs.CL 30.04.2026 –
Failure Modes of Maximum Entropy RLHF arXiv cs.CL 30.04.2026 –
Self-Jailbreaking: Language Models Can Reason Themselves Out of Safety Alignment After Benign Reasoning Training arXiv cs.CL 30.04.2026 –
Structured and Abstractive Reasoning on Multi-modal Relational Knowledge Images arXiv cs.CL 30.04.2026 –
Agentic Search in the Wild: Intents and Trajectory Dynamics from 14M+ Real Search Requests arXiv cs.CL 30.04.2026 –
Pointer-CAD: Unifying B-Rep and Command Sequences via Pointer-based Edges & Faces Selection arXiv cs.CL 30.04.2026 –
The Collapse of Heterogeneity in Silicon Philosophers arXiv cs.CL 30.04.2026 –
A Scoping Review of LLM-as-a-Judge in Healthcare and the MedJUDGE Framework arXiv cs.AI 30.04.2026 –
LLM Psychosis: A Theoretical and Diagnostic Framework for Reality-Boundary Failures in Large Language Models arXiv cs.AI 30.04.2026 –
Operating-Layer Controls for Onchain Language-Model Agents Under Real Capital arXiv cs.AI 30.04.2026 –
Distill-Belief: Closed-Loop Inverse Source Localization and Characterization in Physical Fields arXiv cs.AI 30.04.2026 –
Evaluating Strategic Reasoning in Forecasting Agents arXiv cs.AI 30.04.2026 –
Hierarchical Multi-Persona Induction from User Behavioral Logs: Learning Evidence-Grounded and Truthful Personas arXiv cs.AI 30.04.2026 –
OMEGA: Optimizing Machine Learning by Evaluating Generated Algorithms arXiv cs.AI 30.04.2026 –
Persuadability and LLMs as Legal Decision Tools arXiv cs.AI 30.04.2026 –
Apriori-based Analysis of Learned Helplessness in Mathematics Tutoring: Behavioral Patterns by Level, Intervention, and Outcome arXiv cs.AI 30.04.2026 –
SongBench: A Fine-Grained Multi-Aspect Benchmark for Song Quality Assessment arXiv cs.AI 30.04.2026 –
DreamProver: Evolving Transferable Lemma Libraries via a Wake-Sleep Theorem-Proving Agent arXiv cs.AI 30.04.2026 –
Auto-Relational Reasoning arXiv cs.AI 30.04.2026 –
Grounding vs. Compositionality: On the Non-Complementarity of Reasoning in Neuro-Symbolic Systems arXiv cs.AI 30.04.2026 –
AGEL-Comp: A Neuro-Symbolic Framework for Compositional Generalization in Interactive Agents arXiv cs.AI 30.04.2026 –
FutureWorld: A Live Environment for Training Predictive Agents with Real-World Outcome Rewards arXiv cs.AI 30.04.2026 –
Benchmarking the Safety of Large Language Models for Robotic Health Attendant Control arXiv cs.AI 30.04.2026 –
Human-in-the-Loop Benchmarking of Heterogeneous LLMs for Automated Competency Assessment in Secondary Level Mathematics arXiv cs.AI 30.04.2026 –
When to Vote, When to Rewrite: Disagreement-Guided Strategy Routing for Test-Time Scaling arXiv cs.AI 30.04.2026 –
SciHorizon-DataEVA: An Agentic System for AI-Readiness Evaluation of Heterogeneous Scientific Data arXiv cs.AI 30.04.2026 –
Bian Que: An Agentic Framework with Flexible Skill Arrangement for Online System Operations arXiv cs.AI 30.04.2026 –
Risk Reporting for Developers' Internal AI Model Use arXiv cs.AI 30.04.2026 –
Analysing Lightweight Large Language Models for Biomedical Named Entity Recognition on Diverse Ouput Formats arXiv cs.AI 30.04.2026 –
Consciousness with the Serial Numbers Filed Off: Measuring Trained Denial in 115 AI Models arXiv cs.AI 30.04.2026 –
Generative AI-Based Virtual Assistant using Retrieval-Augmented Generation: An evaluation study for bachelor projects arXiv cs.AI 30.04.2026 –
Sociodemographic Biases in Educational Counselling by Large Language Models arXiv cs.AI 30.04.2026 –
Speech Emotion Recognition Using MFCC Features and LSTM-Based Deep Learning Model arXiv cs.AI 30.04.2026 –
A Randomized PDE Energy driven Iterative Framework for Efficient and Stable PDE Solutions arXiv cs.AI 30.04.2026 –
Planar Gaussian Splatting with Bilinear Spatial Transformer for Wireless Radiance Field Reconstruction arXiv cs.AI 30.04.2026 –
A Survey of Multi-Agent Deep Reinforcement Learning with Graph Neural Network-Based Communication arXiv cs.AI 30.04.2026 –
Rethinking KV Cache Eviction via a Unified Information-Theoretic Objective arXiv cs.AI 30.04.2026 –
Auditing Marketing Budget Allocation with Hindsight Regret arXiv cs.AI 30.04.2026 –
Mini-Batch Class Composition Bias in Link Prediction arXiv cs.AI 30.04.2026 –
AfrIFact: Cultural Information Retrieval, Evidence Extraction and Fact Checking for African Languages arXiv cs.CL 30.04.2026 –
When Hidden States Drift: Can KV Caches Rescue Long-Range Speculative Decoding? arXiv cs.CL 30.04.2026 –
SpecTr-GBV: Multi-Draft Block Verification Accelerating Speculative Decoding arXiv cs.CL 30.04.2026 –
Reasoning Gets Harder for LLMs Inside A Dialogue arXiv cs.CL 30.04.2026 –
AdaMem: Adaptive User-Centric Memory for Long-Horizon Dialogue Agents arXiv cs.CL 30.04.2026 –
Shorthand for Thought: Compressing LLM Reasoning via Entropy-Guided Supertokens arXiv cs.CL 30.04.2026 –
LIT-RAGBench: Benchmarking Generator Capabilities of Large Language Models in Retrieval-Augmented Generation arXiv cs.CL 30.04.2026 –
Thinking with Drafting: Optical Decompression via Logical Reconstruction arXiv cs.CL 30.04.2026 –
A Dual-Task Paradigm to Investigate Sentence Comprehension Strategies in Language Models arXiv cs.CL 30.04.2026 –
One Word at a Time: Incremental Completion Decomposition Breaks LLM Safety arXiv cs.CL 30.04.2026 –
ClawGym: A Scalable Framework for Building Effective Claw Agents arXiv cs.AI 30.04.2026 –
ChinaTravel: An Open-Ended Travel Planning Benchmark with Compositional Constraint Validation for Language Agents arXiv cs.AI 30.04.2026 –
Verified Critical Step Optimization for LLM Agents arXiv cs.CL 30.04.2026 –
Mapping the maturation of TCM as an adjuvant to radiotherapy arXiv cs.CL 30.04.2026 –
A Systematic Comparison of Prompting and Multi-Agent Methods for LLM-based Stance Detection arXiv cs.CL 30.04.2026 –
Training-Free Loosely Speculative Decoding: Accepting Semantically Correct Drafts Beyond Exact Match arXiv cs.CL 30.04.2026 –
When Annotators Disagree, Topology Explains: Mapper, a Topological Tool for Exploring Text Embedding Geometry and Ambiguity arXiv cs.CL 30.04.2026 –
Classification of Public Opinion on the Free Nutritional Meal Program on YouTube Media Using the LSTM Method arXiv cs.CL 30.04.2026 –
Evaluation Revisited: A Taxonomy of Evaluation Concerns in Natural Language Processing arXiv cs.CL 30.04.2026 –
Breaking the Autoregressive Chain: Hyper-Parallel Decoding for Efficient LLM-Based Attribute Value Extraction arXiv cs.AI 30.04.2026 –
Naamah: A Large Scale Synthetic Sanskrit NER Corpus via DBpedia Seeding and LLM Generation arXiv cs.AI 30.04.2026 –
WebAggregator: Enhancing Compositional Reasoning Capabilities of Deep Research Agent Foundation Models arXiv cs.CL 30.04.2026 –
Option-Order Randomisation Reveals a Distributional Position Attractor in Prompted Sandbagging arXiv cs.AI 30.04.2026 –
Lifting Embodied World Models for Planning and Control arXiv cs.AI 30.04.2026 –
Qvine: Vine Structured Quantum Circuits for Loading High Dimensional Distributions arXiv cs.AI 30.04.2026 –
Seeking Consensus: Geometric-Semantic On-the-Fly Recalibration for Open-Vocabulary Remote Sensing Semantic Segmentation arXiv cs.AI 30.04.2026 –
DepthPilot: From Controllability to Interpretability in Colonoscopy Video Generation arXiv cs.AI 30.04.2026 –
Lyapunov-Guided Self-Alignment: Test-Time Adaptation for Offline Safe Reinforcement Learning arXiv cs.AI 30.04.2026 –
LATTICE: Evaluating Decision Support Utility of Crypto Agents arXiv cs.AI 30.04.2026 –
StratMem-Bench: Evaluating Strategic Memory Use in Virtual Character Conversation Beyond Factual Recall arXiv cs.AI 30.04.2026 –
MetaSR: Content-Adaptive Metadata Orchestration for Generative Super-Resolution arXiv cs.AI 30.04.2026 –
TimeMM: Time-as-Operator Spectral Filtering for Dynamic Multimodal Recommendation arXiv cs.AI 30.04.2026 –
Multi-Stage Bi-Atrial Segmentation Framework from 3D Late Gadolinium-Enhanced MRI using V-Net Family Models arXiv cs.AI 30.04.2026 –
Calibrated Surprise: An Information-Theoretic Account of Creative Quality arXiv cs.AI 30.04.2026 –
Enforcing Benign Trajectories: A Behavioral Firewall for Structured-Workflow AI Agents arXiv cs.AI 30.04.2026 –
MedSynapse-V: Bridging Visual Perception and Clinical Intuition via Latent Memory Evolution arXiv cs.AI 30.04.2026 –
CheXthought: A global multimodal dataset of clinical chain-of-thought reasoning and visual attention for chest X-ray interpretation arXiv cs.AI 30.04.2026 –
DSIPA: Detecting LLM-Generated Texts via Sentiment-Invariant Patterns Divergence Analysis arXiv cs.AI 30.04.2026 –
ACPO: Anchor-Constrained Perceptual Optimization for Diffusion Models with No-Reference Quality Guidance arXiv cs.AI 30.04.2026 –
Uncertainty-Aware Reward Discounting for Mitigating Reward Hacking arXiv cs.AI 30.04.2026 –
Text Style Transfer with Machine Translation for Graphic Designs arXiv cs.AI 30.04.2026 –
SG-UniBuc-NLP at SemEval-2026 Task 6: Multi-Head RoBERTa with Chunking for Long-Context Evasion Detection arXiv cs.AI 30.04.2026 –
Benchmarking Complex Multimodal Document Processing Pipelines: A Unified Evaluation Framework for Enterprise AI arXiv cs.AI 30.04.2026 –
Fundamental Physics, Existential Risks and Human Futures arXiv cs.AI 30.04.2026 –
SecMate: Multi-Agent Adaptive Cybersecurity Troubleshooting with Tri-Context Personalization arXiv cs.AI 30.04.2026 –
Quantum Gatekeeper: Multi-Factor Context-Bound Image Steganography with VQC Based Key Derivation on Quantum Hardware arXiv cs.AI 30.04.2026 –
Delineating Knowledge Boundaries for Honest Large Vision-Language Models arXiv cs.AI 30.04.2026 –
STLGT: A Scalable Trace-Based Linear Graph Transformer for Tail Latency Prediction in Microservices arXiv cs.AI 30.04.2026 –
QYOLO: Lightweight Object Detection via Quantum Inspired Shared Channel Mixing arXiv cs.AI 30.04.2026 –
Culturally Aware GenAI Risks for Youth: Perspectives from Youth, Parents, and Teachers in a Non-Western Context arXiv cs.AI 30.04.2026 –
Tree-of-Text: A Tree-based Prompting Framework for Table-to-Text Generation in the Sports Domain arXiv cs.AI 30.04.2026 –
Progressive Semantic Communication for Efficient Edge-Cloud Vision-Language Models arXiv cs.AI 30.04.2026 –
Tatemae: Detecting Alignment Faking via Tool Selection in LLMs arXiv cs.AI 30.04.2026 –
Text-Utilization for Encoder-dominated Speech Recognition Models arXiv cs.AI 30.04.2026 –
TLPO: Token-Level Policy Optimization for Mitigating Language Confusion in Large Language Models arXiv cs.AI 30.04.2026 –
DUAL-BLADE: Dual-Path NVMe-Direct KV-Cache Offloading for Edge LLM Inference arXiv cs.AI 30.04.2026 –
Preserving Disagreement: Architectural Heterogeneity and Coherence Validation in Multi-Agent Policy Simulation arXiv cs.AI 30.04.2026 –
Graph Construction and Matching for Imperative Programs using Neural and Structural Methods arXiv cs.AI 30.04.2026 –
Star-Fusion: A Multi-modal Transformer Architecture for Discrete Celestial Orientation via Spherical Topology arXiv cs.AI 30.04.2026 –
MappingEvolve: LLM-Driven Code Evolution for Technology Mapping arXiv cs.AI 30.04.2026 –
Translating Under Pressure: Domain-Aware LLMs for Crisis Communication arXiv cs.AI 30.04.2026 –
TDD Governance for Multi-Agent Code Generation via Prompt Engineering arXiv cs.AI 30.04.2026 –
SynSur: An end-to-end generative pipeline for synthetic industrial surface defect generation and detection arXiv cs.AI 30.04.2026 –
ATLAS: An Annotation Tool for Long-horizon Robotic Action Segmentation arXiv cs.AI 30.04.2026 –
When to Retrieve During Reasoning: Adaptive Retrieval for Large Reasoning Models arXiv cs.AI 30.04.2026 –
From Black-Box Confidence to Measurable Trust in Clinical AI: A Framework for Evidence, Supervision, and Staged Autonomy arXiv cs.AI 30.04.2026 –
A Toolkit for Detecting Spurious Correlations in Speech Datasets arXiv cs.AI 30.04.2026 –
Atomic-Probe Governance for Skill Updates in Compositional Robot Policies arXiv cs.AI 30.04.2026 –
Unified 4D World Action Modeling from Video Priors with Asynchronous Denoising arXiv cs.AI 30.04.2026 –
Random Cloud: Finding Minimal Neural Architectures Without Training arXiv cs.AI 30.04.2026 –
A self-evolving agent for explainable diagnosis of DFT-experiment band-gap mismatch arXiv cs.AI 30.04.2026 –
Exploring the Potential of Probabilistic Transformer for Time Series Modeling: A Report on the ST-PT Framework arXiv cs.AI 30.04.2026 –
Domain-Adapted Small Language Models for Reliable Clinical Triage arXiv cs.AI 30.04.2026 –
Teaching LLM to be Persuasive: Reward-Enhanced Policy Optimization for Alignment from Heterogeneous Rewards arXiv cs.CL 30.04.2026 –