AI news archive
294 articles filed under Research, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchDouble descent is the principle of least action
arXiv:2609.19076v1 Announce Type: cross Abstract: The test error of a model plotted against its number of parameters $d$ falls, peaks when the model can just fit the training data, and falls again, exhibiting the double…
- arXiv cs.AIresearchProbabilistic Linear Explanations
arXiv:2609.19077v1 Announce Type: cross Abstract: Formal explainability provides mathematically grounded justifications for individual predictions. However, abductive explanations often exceed human cognitive limits by i…
- arXiv cs.AIresearchReporting Practice Matters: The Impact of Reference Choice on Chest X-ray Report Evaluation
arXiv:2609.19093v1 Announce Type: cross Abstract: Radiologists follow heterogeneous reporting practices. Two radiologists examining the same image and identifying the same clinical findings might nevertheless compose sup…
- arXiv cs.AIresearchPrepared Or Unprepared? Evaluating Healthcare Workforce Readiness for Clinical Adoption of Artificial Intelligence in Nigeria
arXiv:2609.19096v1 Announce Type: cross Abstract: Artificial intelligence (AI) is increasingly integrated into healthcare systems worldwide, yet its successful clinical adoption depends critically on workforce readiness,…
- arXiv cs.AIresearchrMuscle: Robotic Muscle Memory for Efficient Vision-Language-Action Model Inference
arXiv:2609.19104v1 Announce Type: cross Abstract: Factory work is a promising early scenario for embodied AI: assigning repetitive manual jobs to robots has clear economic payoff, and a structured station keeps the jobs…
- arXiv cs.AIresearchDreaming the Sound of Contact: Leveraging Video and Audio Generation for Zero-Shot Force-Aware Manipulation and Data Generation
arXiv:2609.19137v1 Announce Type: cross Abstract: Recent advances in video generation allow robots to learn manipulation trajectories from generated videos. However, these approaches produce purely kinematic trajectories…
- arXiv cs.AIresearchA Zeroth-Order Paradigm for LLM Preference Alignment
arXiv:2609.19144v1 Announce Type: cross Abstract: Direct preference alignment methods are widely used to align large language models (LLMs) with human preferences because of their computational and memory efficiency. How…
- arXiv cs.AIresearchObjective vs. Search: Decomposing What Makes a Good Tokeniser
arXiv:2609.19145v1 Announce Type: cross Abstract: Two dominant tokenisation algorithms are used by modern language models: byte-pair encoding (BPE) and UnigramLM. These differ along two orthogonal axes: their optimisatio…
- arXiv cs.AIresearchA Survey on Bridging EEG Signals and Generative AI: From Image and Text to Beyond
arXiv:2502.12048v4 Announce Type: replace Abstract: Decoding neural activity into human-interpretable representations is a key research direction in brain-computer interfaces (BCIs) and computational neuroscience. Recent…
- arXiv cs.AIresearchBridging the Gap in Ophthalmic AI: MM-Retinal-Reason Dataset and OphthaReason Model toward Dynamic Multimodal Reasoning
arXiv:2508.16129v5 Announce Type: replace Abstract: Multimodal large language models (MLLMs) have recently demonstrated remarkable reasoning abilities under reinforcement learning (RL) paradigm. However, most existing mu…
- arXiv cs.AIresearchLM Fight Arena: Benchmarking Large Multimodal Models via Game Competition
arXiv:2510.08928v2 Announce Type: replace Abstract: Existing benchmarks for large multimodal models (LMMs) often fail to capture their performance in real-time, adversarial environments. We introduce LM Fight Arena (Larg…
- arXiv cs.AIresearchEnhancing knowledge tracing robustness for new question cold start in Intelligent Tutoring Systems
arXiv:2512.07179v2 Announce Type: replace Abstract: Intelligent Tutoring Systems (ITS) provide personalized learning paths by diagnosing learners' proficiency. Knowledge Tracing (KT) models play a central role in this di…
- arXiv cs.AIresearchAssessing the Effect of Cross-Domain Mapping on Creativity in Humans and Large Language Models
arXiv:2603.19087v3 Announce Type: replace Abstract: Creative ideas often arise by associating remote concepts. Can random associations reliably increase originality, and do they help humans and large language models (LLM…
- arXiv cs.AIresearchExploratory Responsiveness and Adaptive Rigidity under AI-Assisted Optimization
arXiv:2606.10086v2 Announce Type: replace Abstract: This paper develops a theory of exploratory adaptation under AI-assisted optimization. The central argument is that the long-run adaptive effects of AI systems depend c…
- arXiv cs.AIresearchPredictive Assistance and the Temporal Dynamics of Exploratory Compression
arXiv:2606.10094v2 Announce Type: replace Abstract: Classical theories of cognition describe problem solving as exploratory search through structured problem spaces in which repeated interaction gradually compresses sear…
- arXiv cs.AIresearchHyQuant: Hybrid-Precision Quantization for LLM Attention
arXiv:2608.27875v3 Announce Type: replace Abstract: Quantization has been widely adopted in LLM training and inference to reduce cost and improve efficiency. However, low-bit quantization of the \emph{attention} module o…
- arXiv cs.AIresearchA visual large language foundational model for medical image recognition using clinician-contributed online resources
arXiv:2609.06914v2 Announce Type: replace Abstract: Large language models (LLMs) have demonstrated strong capabilities across diverse domains, showing considerable potential in medicine. However, their application in med…
- arXiv cs.AIresearchLightning Weave: Improving the Accuracy-Efficiency Frontier of Reasoning Models through Capability Composition
arXiv:2609.14708v2 Announce Type: replace Abstract: A core goal of efficient reasoning is to improve the accuracy-efficiency frontier. However, jointly improving reasoning accuracy and inference efficiency can be challen…
- arXiv cs.AIresearchAI Persuasion as a Threat to Human Control
arXiv:2609.14796v2 Announce Type: replace Abstract: The threat that AI persuasion poses to human control has been acknowledged in the literature, but not yet systematically studied. Now that persuasion attacks are no lon…
- arXiv cs.AIresearchCan We Do Interpretable NLI with Graphs Based on Atomic Propositions?
arXiv:2609.16814v2 Announce Type: replace Abstract: While Large Language Model (LLM)-based Natural Language Inference (NLI) systems achieve high accuracy, their decision-making processes lack auditable structures. This p…
- arXiv cs.AIresearchLimits of Transfer Learning
arXiv:2006.12694v2 Announce Type: replace-cross Abstract: Transfer learning involves taking information and insight from one problem domain and applying it to a new problem domain. Although widely used in practice, theor…
- arXiv cs.AIresearchAbstention vs. Hallucination: Benchmarking LLM Source Attribution for Scientific Citations
arXiv:2405.02228v5 Announce Type: replace-cross Abstract: Large language models (LLMs) increasingly generate citation-backed responses, yet citation hallucination remains a major challenge for trustworthy scientific info…
- arXiv cs.AIresearchUnleash LLMs Potential for Sequential Recommendation by Coordinating Dual Dynamic Index Mechanism
arXiv:2409.09253v2 Announce Type: replace-cross Abstract: Owing to the unprecedented capability in semantic understanding and logical reasoning, large language models (LLMs) have shown fantastic potential in developing n…
- arXiv cs.AIresearchLabel-Confidence-Aware Uncertainty Estimation in Natural Language Generation
arXiv:2412.07255v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) demonstrate remarkable capabilities in generative tasks but pose potential risks due to their tendency to generate hallucinatory resp…
- arXiv cs.AIresearchCompArt: Operationalizing Aesthetic Alignment in Text-to-Image Generation via Principles of Art
arXiv:2503.12018v2 Announce Type: replace-cross Abstract: Text-to-Image (T2I) diffusion models have made rapid progress on semantic alignment (generating what is described in the prompt), yet users still lack reliable co…
- arXiv cs.AIresearchBOOM: Benchmarking Out-Of-distribution Molecular Property Predictions of Machine Learning Models
arXiv:2505.01912v3 Announce Type: replace-cross Abstract: Data-driven molecular discovery leverages artificial intelligence/machine learning (AI/ML) and generative modeling to filter and design novel molecules. Discoveri…
- arXiv cs.AIresearchExtracting Probabilistic Knowledge from Large Language Models for Bayesian Network Parameterization
arXiv:2505.15918v3 Announce Type: replace-cross Abstract: In this work, we evaluate the potential of Large Language Models (LLMs) in building Bayesian Networks (BNs) by approximating domain expert priors. LLMs have demon…
- arXiv cs.AIresearchDiff-SPORT: Diffusion-based Sensor Placement Optimization and Reconstruction of Turbulent flows in urban environments
arXiv:2506.00214v2 Announce Type: replace-cross Abstract: Rapid urbanization demands efficient monitoring of turbulent wind and pollutant dispersion, yet existing reconstruction and sensor placement strategies fail under…
- arXiv cs.AIresearchFrom Alignment to Synthesis: Contrastive Volumetric Grounding for Text-to-CT Generation
arXiv:2506.00633v4 Announce Type: replace-cross Abstract: Generating semantically controllable 3D CT volumes from radiology reports requires more than a rich text encoder, it requires vision-language alignment grounded i…
- arXiv cs.AIresearchAlgorithmic Shortlisting in Participatory Budgeting
arXiv:2508.06577v4 Announce Type: replace-cross Abstract: Participatory budgeting is a democratic innovation that allows citizens to propose and vote on public investment projects. To help organizers manage large volumes…
- arXiv cs.AIresearchConstrained PSLQ Search for Machin-like Identities Achieving Record-Low Lehmer Measures
arXiv:2508.08307v2 Announce Type: replace-cross Abstract: Machin-like arctangent relations are classical tools for computing $\pi$, with efficiency quantified by the Lehmer measure ($\lambda$). We present a framework for…
- arXiv cs.AIresearchVisual Perception Engine: Fast and Flexible Multi-Head Inference for Robotic Vision Tasks
arXiv:2508.11584v3 Announce Type: replace-cross Abstract: Deploying multiple machine learning models on resource-constrained robotic platforms for different perception tasks often results in redundant computations, large…
- arXiv cs.AIresearchUltralytics YOLO Evolution: An Overview of YOLO27, YOLO26, YOLO11, YOLOv8, and YOLOv5 Object Detectors for Computer Vision and Pattern Recognition
arXiv:2510.09653v4 Announce Type: replace-cross Abstract: This paper presents a comprehensive overview of the Ultralytics YOLO family, emphasizing architectural evolution, benchmarking, deployment, and emerging direction…
- arXiv cs.AIresearchHuman Resilience in the AI Era -- What Machines Can't Replace
arXiv:2510.25218v2 Announce Type: replace-cross Abstract: AI is changing work and decision making faster than many institutions can adapt their operating practices. We argue that this adaptation gap makes human resilienc…
- arXiv cs.AIresearchNeuroSketch: A Practical Design Recipe for Neural Decoding
arXiv:2512.09524v2 Announce Type: replace-cross Abstract: Neural decoding is fundamental to brain-computer interfaces, with growing applications in healthcare. Previous research has focused on leveraging signal processin…
- arXiv cs.AIresearchPerformance and Complexity Trade-off Optimization of Speech Models During Training
arXiv:2601.13704v4 Announce Type: replace-cross Abstract: In speech machine learning, neural network models are typically designed by choosing an architecture with fixed layer sizes and structure. These models are then t…
- arXiv cs.AIresearchShotFinder: Imagination-Driven Open-Domain Video Shot Retrieval via Web Search
arXiv:2601.23232v4 Announce Type: replace-cross Abstract: In recent years, large language models (LLMs) have made rapid progress in information retrieval, yet existing research has mainly focused on text or static multim…
- arXiv cs.AIresearchVariational Approach for Job Shop Scheduling
arXiv:2602.00408v3 Announce Type: replace-cross Abstract: This paper proposes a novel Variational Graph-to-Scheduler (VG2S) framework for solving the Job Shop Scheduling Problem (JSSP), a critical task in manufacturing t…
- arXiv cs.AIresearchHALT: Hallucination Assessment via Log-probs as Time series
arXiv:2602.02888v2 Announce Type: replace-cross Abstract: Hallucinations remain a major obstacle for large language models (LLMs), especially in safety-critical domains. We present HALT (Hallucination Assessment via Log-…
- arXiv cs.AIresearchBypassing the Rationale: Causal Auditing of Implicit Reasoning in Language Models
arXiv:2602.03994v3 Announce Type: replace-cross Abstract: Chain-of-thought (CoT) prompting is widely used as a reasoning aid and is often treated as a transparency mechanism. Yet behavioral gains under CoT do not imply t…
- arXiv cs.AIresearchPACT-WAM: Predicting Actions and Visual Foresight with Compact Temporal Encoding for Robot Manipulation
arXiv:2602.15882v2 Announce Type: replace-cross Abstract: Robot manipulation uses temporal context to select actions and visual foresight to assess their consequences, yet dense representations of past and future observa…
- arXiv cs.AIresearchMINT: Multimodal Imaging-to-Speech Knowledge Transfer for Early Alzheimer's Screening
arXiv:2602.23994v2 Announce Type: replace-cross Abstract: Alzheimer's disease is a progressive neurodegenerative disorder in which mild cognitive impairment (MCI) precedes dementia. Structural MRI provides biomarkers but…
- arXiv cs.AIresearchUniversal NP-Hardness of Clustering under General Utilities
arXiv:2603.00210v2 Announce Type: replace-cross Abstract: Clustering is a central primitive in unsupervised learning, yet practice is dominated by heuristics whose outputs can be unstable and highly sensitive to represen…
- arXiv cs.AIresearchEnhancing Physics-Informed Neural Networks with Domain-aware Fourier Features: Towards Improved Performance and Interpretable Results
arXiv:2603.02948v2 Announce Type: replace-cross Abstract: Physics-Informed Neural Networks (PINNs) incorporate physics into neural networks by embedding partial differential equations (PDEs) into their loss function. Des…
- arXiv cs.AIresearchCzechTopic: A Benchmark for Zero-Shot Topic Localization in Historical Czech Documents
arXiv:2603.03884v2 Announce Type: replace-cross Abstract: Topic localization aims to identify spans of text that express a given topic defined by a name and description. To study this task, we introduce a human-annotated…
- arXiv cs.AIresearchAuthorMix: Modular Authorship Style Transfer via Layer-wise Adapter Mixing
arXiv:2603.23069v4 Announce Type: replace-cross Abstract: The task of authorship style transfer involves rewriting text in the style of a target author while preserving the meaning of the original text. Existing style tr…
- arXiv cs.AIresearchCan We Still Trace L1 Signals? Investigating the Resilience of Native Language Signals in the LLM Era
arXiv:2604.08568v4 Announce Type: replace-cross Abstract: The widespread use of LLM-based writing assistance has raised an interesting question about the homogenization of English. As LLMs tend to revise texts toward mai…
- arXiv cs.AIresearchDeep Learning for Sequential Decision Making under Uncertainty: Foundations, Frameworks, and Frontiers
arXiv:2604.11507v2 Announce Type: replace-cross Abstract: Artificial intelligence (AI) is moving increasingly beyond prediction to support decisions in complex, uncertain, and dynamic environments. This shift creates a n…
- arXiv cs.AIresearchVISTA: Validation-Informed Trajectory Adaptation via Self-Distillation
arXiv:2604.12044v2 Announce Type: replace-cross Abstract: Deep learning models may converge to suboptimal solutions despite strong validation accuracy, masking an optimization failure we term Trajectory Deviation. This i…
- arXiv cs.AIresearchSchema-Key Wording as an Instruction Channel in Structured Generation under Constrained Decoding
arXiv:2604.14862v3 Announce Type: replace-cross Abstract: Constrained decoding is widely used to make large language models produce structured outputs that satisfy schemas such as JSON. Existing work mainly treats schema…