AI news archive.
10,659 articles filed under Research, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchDidactic knowledge or Clinical Cases? How Data Types Shape Medical Large Language Models
arXiv:2609.22161v1 Announce Type: new Abstract: Medical large language models are commonly trained on mixtures of didactic data (e.g., textbooks) and clinical data (e.g., patient records), yet how these data types differ…
- arXiv cs.AIresearchAn Affordable AI-Integrated Smart Cane for Multimodal Mobility Assistance of Visually Impaired Users
arXiv:2609.22277v1 Announce Type: new Abstract: Visual impairment affects over 2.2 billion people worldwide, yet conventional white canes cannot detect elevated hazards or provide semantic environmental context. Existing…
- arXiv cs.AIresearchPAANI : On Device Visual Evidence Fusion and Explainable Guidance for River Robot Simulation
arXiv:2609.22353v1 Announce Type: new Abstract: Mobile river monitoring robots must interpret obstacles and water boundaries that geographic waypoints alone cannot describe. On resource constrained platforms, converting…
- arXiv cs.AIresearchSocial Influence and the Allocation of Scientific Attention in AI Populations
arXiv:2609.22408v1 Announce Type: new Abstract: AI systems are becoming participants in the evaluation and use of scientific research. They encounter citation counts, download statistics and lists of popular articles dev…
- arXiv cs.AIresearchLearning 3D biophysical cell properties from 2D images and cell-population statistics
arXiv:2609.22410v1 Announce Type: new Abstract: Inferring 3D cellular properties from 2D microscopy is difficult when a reference instrument reports only population statistics rather than labels for individual cells. Her…
- arXiv cs.AIresearchGoal-driven Variant Categorization
arXiv:2609.22475v1 Announce Type: new Abstract: Process discovery rarely yields a single coherent process structure. For analysis, a common step is to cluster process variants based on structural similarity and then assi…
- arXiv cs.AIresearchReplication Without Persistence in Hosted LLMs: Measurement Sensitivity in Action-Time Belief Evaluation
arXiv:2609.22478v1 Announce Type: new Abstract: Behavioural evaluations of hosted language models can vary because the evaluated service, the measurement instrument, or both differ across runs. We separate three validati…
- arXiv cs.AIresearchThe Wisdom of Artificial Deliberative Crowds
arXiv:2609.22497v1 Announce Type: new Abstract: The aggregation of many lay estimates often outperforms individual expert judgment, a phenomenon known as the wisdom of crowds. While this is usually attributed to the inde…
- arXiv cs.AIresearchAgreement Overstates Evidence: Error Dependence in LLM Judge Consensus
arXiv:2609.22512v1 Announce Type: new Abstract: Consensus among LLM judges is often taken as strong evidence that a decision is correct. This assumes that judges make their errors independently. In practice, LLM judges a…
- arXiv cs.AIresearchIntLawNER: A Named Entity Recognition Dataset and Benchmark in International Law
arXiv:2609.22529v1 Announce Type: new Abstract: International law provides the normative framework through which states coordinate action, regulate armed conflict, and protect human rights, yet its texts remain without t…
- arXiv cs.AIresearchGaitVista: Reliability-Aware AI Measurement toward Accessible Longitudinal Gait Assessment
arXiv:2609.22619v1 Announce Type: new Abstract: Tracking recovery of walking function requires detecting meaningful gait change across rehabilitation sessions, yet objective 3D measurement remains confined to specialized…
- arXiv cs.AIresearchSplitting Documents at Lower Cost: Multi-Split Boundary Decisions for LLM-Based Page Stream Segmentation
arXiv:2609.22620v2 Announce Type: replace Abstract: Scanned mail, uploaded PDFs, and consolidated attachments often arrive as page streams that must be split into individual documents before downstream classification, ex…
- arXiv cs.AIresearchText, Pixels, or Both? Evaluating Input Representations for Multimodal Document QA
arXiv:2609.22628v2 Announce Type: replace Abstract: Every document QA system begins with a choice that is rarely studied on its own: whether to feed the model page images, extracted text, or both. We isolate this choice,…
- arXiv cs.AIresearchA Survey on the Linear Representation Hypothesis
arXiv:2609.22695v1 Announce Type: new Abstract: The term "linear representation hypothesis" (LRH) has appeared across diverse subfields of artificial intelligence, neuroscience, and cognitive science. But previous works…
- arXiv cs.AIresearchBuilding Trustworthy Mental Health Benchmarks on Bluesky: A Validation-Aware Weak-Supervision Framework
arXiv:2609.22696v1 Announce Type: new Abstract: Decentralized social media platforms create new opportunities and challenges for computational mental health research because data access, moderation, labeling, and deploym…
- arXiv cs.AIresearchHapi: A Multivariable Land-Surface Transformer for Medium-Range Hydrological Forecasting at Continental Scale
arXiv:2609.22702v2 Announce Type: replace Abstract: Accurate flood forecasts several days in advance are essential for flood control, water-resource management, and emergency response. A central challenge is to produce h…
- arXiv cs.AIresearchCTSpinoPelvic1K: spine, pelvis, ribs and femora in one coordinate frame, annotated for lumbosacral transitional anatomy
arXiv:2609.22760v1 Announce Type: new Abstract: Purpose: A vertebra at the lumbosacral junction is named by counting caudally from C2 on whole-spine imaging, but a lumbar case is planned on lumbar-only imaging (T12 to S1…
- arXiv cs.AIresearchDVA-Neurons: Design and Verification of Adaptive LIF Neurons: From Single-Neuron Dynamics to Multi-Neuron Spiking Networks
arXiv:2609.22775v1 Announce Type: new Abstract: Spiking Neural Networks (SNNs) offer a promising path toward ultra-low-power artificial intelligence inference by emulating the event-driven computation of biological neuro…
- arXiv cs.AIresearchFrom Research Frontier to Laboratory Bench: Design of a Four-Tier Experimental Teaching System for Multimodal Medical Image Intelligent Diagnosis
arXiv:2609.22790v1 Announce Type: new Abstract: Undergraduate programmes in intelligent medical engineering are expanding, yet laboratory curricula lag behind the multimodal, long-tailed, and distributionally shifting re…
- arXiv cs.AIresearchISA-Bench: A Benchmark for Computational Reasoning Across Instruction Set Architectures
arXiv:2609.22878v1 Announce Type: new Abstract: Large language model code generation benchmarks primarily evaluate well-resourced languages like Python and Java, where models benefit from abundant training data. They pro…
- arXiv cs.AIresearchBeyond Linear Context: Graph-Guided Evidence Navigation for Long-Novel Reasoning with a Local 9B Language Model
arXiv:2609.22939v1 Announce Type: new Abstract: Long-context models read a novel the way a person reads a printout: one token after another, in narrative order, with the whole history competing for a fixed budget of atte…
- arXiv cs.AIresearchA Compact Stance-Indexed Anterior-Posterior COP Representation for Parkinson's Disease Classification from Plantar VGRF
arXiv:2609.22956v1 Announce Type: new Abstract: Parkinson's disease alters gait and bilateral coordination, but machine-learning performance also depends on how continuous gait signals are represented. This study investi…
- arXiv cs.AIresearchR-GEAN: Regimen-Guided Edit Action Network for Within-Admission Medication Change Prediction
arXiv:2609.22959v1 Announce Type: new Abstract: The medications prescribed to a patient often change during a hospital admission as clinicians start, stop, or continue therapies. We study whether models can predict which…
- arXiv cs.AIresearchOptiSkill: A Hierarchical and Evolving SkillBank for LLM-Based Optimization Modeling
arXiv:2609.22987v1 Announce Type: new Abstract: Automated operations research (OR) modeling requires LLMs to translate natural-language decision problems into correct mathematical programs. Existing methods can improve i…
- arXiv cs.AIresearchPINNForge: Execution-Grounded Evolutionary Design of Physics-Informed Neural Networks
arXiv:2609.23023v2 Announce Type: replace Abstract: Physics-informed neural networks (PINNs) require coordinated choices across representation, architecture, sampling, constraints, loss construction, and optimization, ye…
- arXiv cs.AIresearchSpatial-Interactor: Learning Spatial Reasoning through Interaction with the Observable Physical World
arXiv:2609.23038v2 Announce Type: replace Abstract: Spatial reasoning is essential for vision-language models (VLMs) to understand and act in the physical world. Reasoning in dynamic environments requires VLMs to perceiv…
- arXiv cs.AIresearchEnforcing Narrative Reliability and Epistemic Pacing in LLM-Driven Detective Games via Structured Knowledge Trees
arXiv:2609.23043v1 Announce Type: new Abstract: Large Language Models (LLMs) enable open-ended dialogue in interactive games, but their non-deterministic outputs make it difficult to preserve authorial control, factual c…
- arXiv cs.AIresearchFireWorldBench: Benchmarking Complex Physical World Intelligence through Coupled-Field Fire Dynamics
arXiv:2609.23064v1 Announce Type: new Abstract: Understanding the physical world requires more than object recognition, scene description, and short-term visual prediction, as real-world physical systems involve multiple…
- arXiv cs.AIresearchTutoring Large Language Models to be Domain-adaptive, Precise and Safe
arXiv:2609.23071v1 Announce Type: new Abstract: This thesis proposes a framework for "responsible intelligence" to address AI's critical challenges in safety, ethics, and cultural sensitivity. It advances three core area…
- arXiv cs.AIresearchEvent Signature Transfer: Model-Agnostic Forecast Scenario Construction from Historical Events
arXiv:2609.23074v1 Announce Type: new Abstract: Forecasters often know an event is imminent but not the shape, size, or timing of its effect. We introduce Event Signature Transfer (EST), a training-free, model-agnostic o…
- arXiv cs.AIresearchFrom Inference Engine to Inference Control Plane: Connecting vLLM, llm-d, and the Evolution of Efficient Distributed LLM Serving
arXiv:2609.23130v1 Announce Type: new Abstract: Large language model (LLM) inference is evolving from an engine-local optimization problem into a distributed control problem involving reusable state, phase placement, het…
- arXiv cs.AIresearchDo Not Trust the Benchmark: Limitations of General LLM Rankings and a Case for Task-Specific Evaluation
arXiv:2609.23201v1 Announce Type: new Abstract: Benchmark scores increasingly influence the development, marketing, and selection of large language models (LLMs). Yet an overall score is interpretable only in relation to…
- arXiv cs.AIresearchExpansion Counts under Standard A* Tie-Breaking Strategies on the Final Plateau
arXiv:2609.23293v1 Announce Type: new Abstract: In the A* search algorithm, the tie-breaking strategies for nodes with the same $f$-value determines which states A* expands on the final $f$-layer. For nine standard tie-b…
- arXiv cs.AIresearchLeaky-integrator reconstruction: taming error accumulation in recursive differenced time-series forecasting
arXiv:2609.23378v2 Announce Type: replace Abstract: Recursive differenced forecasting, the standard remedy for non-stationarity, predicts one-step changes and integrates them by cumulative summation. We show that this re…
- arXiv cs.AIresearchOn Probabilistic Inference Through Parametric Tensor Decomposition in Base Tensor Networks
arXiv:2609.23774v1 Announce Type: new Abstract: Probabilistic inference is generally only tractable in low-treewidth graphical models, limiting its effective applicability in high-treewidth settings. Many existing method…
- arXiv cs.AIresearchPretraining of Medical Visual Encoders Toward Multi-modal Large Language Models
arXiv:2609.23860v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) commonly reuse visual encoders pretrained with CLIP, although the features of these ViTs are ultimately consumed by autoregressive…
- arXiv cs.AIresearchExplainable Recommendations at Scale: LLM Rationales for YouTube Music Artist Discovery
arXiv:2609.23877v1 Announce Type: new Abstract: Modern music streaming platforms face a persistent tradeoff: exploiting familiar content versus driving the exploration of novel items. While users frequently desire discov…
- arXiv cs.AIresearchIncreasing Skill Level Recruits Deeper Attention Layers in a Frozen Chess Transformer
arXiv:2609.23917v1 Announce Type: new Abstract: Chess involves complex reasoning in a deterministic environment, which makes it a useful setting for studying the mechanisms of computation inside transformers. The Maia-3…
- arXiv cs.AIresearchEcho State Network (ESN) for Signal Recovery in RF-Impaired IBFD MIMO Systems
arXiv:2609.23945v1 Announce Type: new Abstract: In-band full-duplex (IBFD) multiple-input multiple-output (MIMO) systems enable simultaneous transmission and reception on the same frequency band, improving spectral effic…
- arXiv cs.AIresearchTesting, not presuming, adequacy: calibrating generative social simulators against emergent network structure
arXiv:2609.24012v2 Announce Type: replace Abstract: Validation of generative social simulators often stops at face validity: emergent network structure is compared descriptively, without quantified parameter uncertainty…
- arXiv cs.AIresearchContext-Aware Pre-Deployment Evaluation of AI Systems: A Regulatory Framework for Nigerian Fintech
arXiv:2609.24016v1 Announce Type: new Abstract: Commercial large language models are increasingly deployed across African fintech infrastructure for fraud detection and customer communication, yet no Nigerian or African…
- arXiv cs.AIresearchSynthesizing Reactive Character Behaviors for Continuous Games via Programmatic Policy Search
arXiv:2609.24025v1 Announce Type: new Abstract: We present a method for synthesizing reactive character behaviors for continuous games as compact, human-readable programs. Game AI practice still relies heavily on manuall…
- arXiv cs.AIresearchRepresentation-guided in-context learning for medical image interpretation with multimodal large language models
arXiv:2609.24057v1 Announce Type: new Abstract: Medical image interpretation is central to diagnosis and care, yet adapting general-purpose multimodal large language models (MLLMs) often requires resource-intensive domai…
- arXiv cs.AIresearchDocMIDE: Learning Multi-Hop Implicit Derivation in Visually Rich Documents
arXiv:2609.24092v1 Announce Type: new Abstract: Real-world document processing systems rely on rigid, predefined schemas, yet critical target fields often lack direct visual counterparts on the page. Extracting these imp…
- arXiv cs.AIresearchWhen More Evidence Hurts: Publication-Bias Drift and Principled Stopping for Biomedical Causal Search
arXiv:2609.24101v1 Announce Type: new Abstract: Automated biomedical evidence synthesis depends on retrieving published studies, but the biomedical literature is systematically skewed toward positive findings. Deeper ret…
- arXiv cs.AIresearchLIMIT: Less Is More for Instruction Tuning in Text-to-SQL
arXiv:2609.24186v1 Announce Type: new Abstract: Large language models have achieved remarkable progress on Text-to-SQL through reasoning-enhanced fine-tuning, yet existing approaches predominantly rely on massive instruc…
- arXiv cs.AIresearchSKstars at SHROOM: Visions Agreement-Guided Ensembling of Zero-Shot and LoRA-Adapted Vision--Language Models
arXiv:2609.24198v1 Announce Type: new Abstract: This paper describes the SKstars submission to SHROOM-Visions 2026, a shared task on fine-grained hallucination detection in large vision-language model outputs. The task r…
- arXiv cs.AIresearchRecovering Lost Details: Multi-Scale Frequency Compensation for Long-Term Time Series Forecasting
arXiv:2609.24229v1 Announce Type: new Abstract: Long-term time series forecasting has made significant progress by leveraging multi-scale information to capture hierarchical temporal patterns and model long-range depende…
- arXiv cs.AIresearchTaming CoT Obfuscation in VLMs: From Mechanistic Evidence to Activation-Level Enforcement
arXiv:2609.24243v3 Announce Type: replace Abstract: Reinforcement learning (RL) has substantially improved the reasoning capabilities of vision-language models (VLMs), yet it can induce chain-of-thought (CoT) obfuscation…
- arXiv cs.AIresearchUnsupervised Brain Anomaly Detection as a Bayesian Inverse Problem with Diffusion Prior
arXiv:2609.24265v1 Announce Type: new Abstract: Unsupervised anomaly detection (UAD) aims to localize abnormal regions in medical scans without pixel-level annotations. A typical strategy seeks to reconstruct a pseudo-he…