Skip to content
THE AI WIREINTELLIGENCE THAT MATTERS
Archive

AI news archive

294 articles filed under Research, newest first, from the outlets listed on the sources page.

All topicsModelsAgentsResearchChips and computeOpen sourceSafetyPolicy and regulationStartups and fundingCommunity
  1. arXiv cs.AIresearch
    From a River in Gilead to the Inference Distributions of Large Language Models: Covert Dialect Bias and Linguistic Profiling at Scale

    arXiv:2609.18068v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed in high-stakes domains such as housing screening. While alignment techniques mitigate explicit racial bias in gener…

  2. arXiv cs.AIresearch
    Mask 2D-3D: Adaptive Dual-Masked Autoencoder Network for Image-to-Point Cloud Registration

    arXiv:2609.18088v1 Announce Type: cross Abstract: Detection-free methods for image-to-point cloud registration are prone to erroneous correspondences caused by domain and modality discrepancies, limited sensitivity of fe…

  3. arXiv cs.AIresearch
    Linguistic Triggers of Gender and Racial Bias in Open-Weight LLMs Applied to Recruitment

    arXiv:2609.18106v1 Announce Type: cross Abstract: Open-weight large language models are rapidly entering hiring pipelines, yet their discriminatory failure modes -- and the regulatory exposure these create under the EU A…

  4. arXiv cs.AIresearch
    Rethinking How We Evaluate Methodological Progress in Health AI

    arXiv:2609.18134v1 Announce Type: cross Abstract: Methodological progress in artificial intelligence (AI) for electronic health records (EHRs) depends on our ability to determine which algorithms work better, and under w…

  5. arXiv cs.AIresearch
    MoRE: Mixture of Reused Experts

    arXiv:2609.18176v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) architectures decouple model capacity from computational cost, yet incur high memory footprints as parameters grow linearly with the number of ex…

  6. arXiv cs.AIresearch
    Beyond Accuracy: How Procedural Traces Shift the Decision Criterion of LLM Overseers

    arXiv:2609.18204v1 Announce Type: cross Abstract: Organizations increasingly use oversight loops where one large language model (LLM) audits another's outputs alongside procedural traces of claimed steps. A common concer…

  7. arXiv cs.AIresearch
    CapMap-MS-TTA: 3rd Place Solution for the MUMU Track of the 8th LSVOS Challenge at ECCV 2026

    arXiv:2609.18206v1 Announce Type: cross Abstract: The MUMU track of the 8th Large-scale Video Object Segmentation (LSVOS) Challenge requires a single unified multimodal model to jointly solve image tagging (Task A), open…

  8. arXiv cs.AIresearch
    A Lightweight CNN Integrated Compact Convolutional Transformer for Multi-Scale Feature Learning and reducing computational complexity for breast cancer mammography image detection and classification

    arXiv:2609.18212v1 Announce Type: cross Abstract: Over the years, Convolutional Neural Networks (CNNs) have demonstrated strong capability in cancer detection and classification using medical images. However, CNN-based m…

  9. arXiv cs.AIresearch
    CPR: Combining global composing, local performing and full-sequence refining in piano rendering with continuous autoregressive modelling

    arXiv:2609.18216v1 Announce Type: cross Abstract: Prompt-conditioned piano MIDI-to-Music rendering aims to faithfully render target notes while reproducing the timbre of a reference recording. Existing approaches primari…

  10. arXiv cs.AIresearch
    APGEM: Adaptive Policy-Guided Error Mitigation for Quantum Reinforcement Learning on a Real-World CVRP Case Study

    arXiv:2609.18219v1 Announce Type: cross Abstract: Quantum Reinforcement Learning (QRL) represents policies as variational quantum circuits (VQCs), making it attractive for combinatorial optimization such as the Capacitat…

  11. arXiv cs.AIresearch
    Remembering Solomon Marcus

    arXiv:2609.18224v1 Announce Type: cross Abstract: From the manifest of Andre Breton, through the transdisciplinary understanding, we arrive at a post-modern manifest. A talk by Laura De Marco (Harvard) will provide scien…

  12. arXiv cs.AIresearch
    Quanta: A Self-Contained Python Library for Hybrid Retrieval over Quantised Embeddings, Lexical Indexes, and Knowledge Graphs

    arXiv:2609.18248v1 Announce Type: cross Abstract: An advanced retrieval-augmented generation pipeline is typically assembled from three or four independently operated systems: an approximate nearest-neighbour index, a fu…

  13. arXiv cs.AIresearch
    ${M}^2$Tok: Multi-head Multi-codebook Discrete Action Tokenization for Vision-Language-Action Models

    arXiv:2609.18259v1 Announce Type: cross Abstract: Recent advancements have successfully adapted autoregressive language models to process multimodal signals, such as images and actions. Since raw action signals are conti…

  14. arXiv cs.AIresearch
    I code or AI code: A comparative evaluation of AI-rated scores in classroom observations

    arXiv:2609.18274v1 Announce Type: cross Abstract: Classroom observations are widely recognized as a key tool for establishing benchmarks of education quality and guiding pedagogical improvement, yet they remain resource-…

  15. arXiv cs.AIresearch
    Knowledge-Graph Based Augmentation versus Retrieval Augmented Generation for Cultural-Related Question Answering

    arXiv:2609.18317v1 Announce Type: cross Abstract: Large language models (LLMs) suffer from a long-tail deficit: culturally specific facts, particularly those concerning underrepresented regions such as Latin America, app…

  16. arXiv cs.AIresearch
    Trajectory Learnability for Offline On-Policy Distillation with Imperfect Teachers

    arXiv:2609.18321v1 Announce Type: cross Abstract: Offline on-policy distillation gains efficiency by collecting student trajectories and teacher supervision once and reusing them throughout optimization. The same reuse m…

  17. arXiv cs.AIresearch
    Look Less, Hear Better: Jointly Rewarded GRPO for Streaming ASR

    arXiv:2609.18333v1 Announce Type: cross Abstract: Streaming automatic speech recognition (ASR) must be judged jointly on what it transcribes and on how quickly it commits each word. Delayed streams modeling (DSM) has bec…

  18. arXiv cs.AIresearch
    Semantic CSI Feedback for Beam Selection: When Task-Aware Embeddings from Sparse Pilots Outperform Full-Bandwidth Reconstruction

    arXiv:2609.18368v1 Announce Type: cross Abstract: Classical CSI feedback in FDD massive MIMO transmits a compressed reconstruction of the channel, optimizing fidelity to the original signal regardless of the downstream t…

  19. arXiv cs.AIresearch
    GYROval: A Robust Benchmark for Cultural Value Orientation in Large Language Models

    arXiv:2609.18384v1 Announce Type: cross Abstract: We present a robust benchmark for measuring cultural value orientation in large language models on the two Inglehart-Welzel axes over several domains and roles (hence GYR…

  20. arXiv cs.AIresearch
    Reliable Virtual Sensing: A Multi-Domain Benchmark for Robustness Under Sensor Failures

    arXiv:2609.18396v1 Announce Type: cross Abstract: Virtual sensing, the estimation of hard-to-measure quantities from available sensor measurements, is a critical enabler for control and monitoring in cyber-physical syste…

  21. arXiv cs.AIresearch
    A Non-Linear Neuron Based Detection of Isolated Pixels in Binary and Grayscale Images using Contrast Sensitive Receptive Fields

    arXiv:2609.18399v1 Announce Type: cross Abstract: Identifying isolated points is important in image processing applications such as medical imaging, astronomy and quality control management. Other domains, such as cybers…

  22. arXiv cs.AIresearch
    TERN: A Delta-rule Memory with a Seasonal Reference and Online Adaptation for Epidemic Forecasting

    arXiv:2609.18407v1 Announce Type: cross Abstract: Weekly influenza surveillance counts guide vaccine distribution and public-health alerts, yet they are hard to forecast. Each region offers only a few seasons, waves shif…

  23. arXiv cs.AIresearch
    Multitask Reinforcement Learning for Assisting Choice Model Specification

    arXiv:2609.18441v1 Announce Type: cross Abstract: Discrete choice model specification is a time-consuming task in which modellers often specify and estimate multiple models while balancing goodness-of-fit, parsimony, and…

  24. arXiv cs.AIresearch
    CSWAM: Better Causal Semantic Representations for Out-of-Distribution Generalization in World Action Models

    arXiv:2609.18462v1 Announce Type: cross Abstract: FastWAM-style world action models enable efficient action-only inference, but generalize poorly under visual distribution shifts. Their reconstruction-oriented representa…

  25. arXiv cs.AIresearch
    ActionPiece: Rethinking Action Tokenization for Autoregressive Vision-Language-Action Models

    arXiv:2609.18487v1 Announce Type: cross Abstract: Action tokenizers play a central role in autoregressive vision-language-action (VLA) models, determining both the targets for policy training and the executable commands…

  26. arXiv cs.AIresearch
    MiST: Mid-Training LLMs for Cybersecurity

    arXiv:2609.18496v1 Announce Type: cross Abstract: Cybersecurity combines high-stakes analysis with complex technical language, making it an impactful and challenging domain for LLMs. We present MiST (Mid-trained Security…

  27. arXiv cs.AIresearch
    VoiceTrace: A Benchmark and Retrieval Framework for Who-Said-What Speech Retrieval

    arXiv:2609.18521v1 Announce Type: cross Abstract: Speech retrieval has become increasingly important as spoken content continues to grow across meetings, lectures, podcasts, and videos. Existing benchmarks and models hav…

  28. arXiv cs.AIresearch
    Interpretable Patch-Based Deep Learning for Wildfire Spread Prediction from Ensemble Simulations

    arXiv:2609.18555v1 Announce Type: cross Abstract: Wildfire spread is traditionally predicted using physics-based simulators, which are physically interpretable but whose cost increases with each additional ensemble membe…

  29. arXiv cs.AIresearch
    On-the-Fly Homographies Calibration for Multi-Camera Tracking

    arXiv:2609.18582v1 Announce Type: cross Abstract: Precise multi-camera tracking traditionally relies on rigorous 3D site calibration, yet this requirement is often operationally impossible in large-scale deployments. Pri…

  30. arXiv cs.AIresearch
    Label-free steering: Compressing test-time reinforcement learning into bias-only subspaces

    arXiv:2609.18587v1 Announce Type: cross Abstract: Test-time reinforcement learning (TTRL) enables models to improve their reasoning without relying on labeled training data, but existing approaches typically optimize a l…

  31. arXiv cs.AIresearch
    Online Robust Reinforcement Learning Through Monte-Carlo Planning

    arXiv:2609.18599v1 Announce Type: cross Abstract: Monte Carlo Tree Search (MCTS) is a powerful framework for solving complex decision-making problems, yet it often relies on the assumption that the simulator and the real…

  32. arXiv cs.AIresearch
    GenStream: Semantic Streaming Framework for Generative Reconstruction of Human-centric Media

    arXiv:2609.18634v1 Announce Type: cross Abstract: Video streaming dominates global internet traffic, yet conventional pipelines remain inefficient for structured, human-centric content such as sports, performance, or int…

  33. arXiv cs.AIresearch
    Beyond EER: Multi-Dimensional Evaluation of Information Leakage in Speaker De-Identification

    arXiv:2609.18673v1 Announce Type: cross Abstract: Speaker de-identification (SDID) aims to preserve privacy by concealing speaker identity while maintaining speech utility. However, current evaluations often reduce priva…

  34. arXiv cs.AIresearch
    Generalist-Specialist Mixture-of-Experts for Rare Pathology Detection in Multimodal Imaging

    arXiv:2609.18688v1 Announce Type: cross Abstract: AI models for multimodal medical imaging must balance modality-specific specialization with cross-modal shared representations, a trade-off that pure Mixture-of-Experts (…

  35. arXiv cs.AIresearch
    Echo: Learning-based Matching Decompilation using Trusted Back Translation

    arXiv:2609.18706v1 Announce Type: cross Abstract: Neural decompilers can recover readable and recompilable source code from binaries, but their predictions remain difficult to trust. Matching decompilation addresses this…

  36. arXiv cs.AIresearch
    Rethinking Critic Learning in PPO: Understanding and Mitigating Value Flattening

    arXiv:2609.18708v1 Announce Type: cross Abstract: In reinforcement learning for large language models, Proximal Policy Optimization (PPO) commonly uses a critic to estimate state values and reduce the variance of policy…

  37. arXiv cs.AIresearch
    A Scalable Framework for Automated NER Annotation Correction in Low-Resource Languages

    arXiv:2609.18739v1 Announce Type: cross Abstract: Poor quality or noisy annotations in Named Entity Recognition (NER), as in any other NLP task, make it challenging to achieve state-of-the-art performance. In this paper,…

  38. arXiv cs.AIresearch
    Using OCR Heads to Verbalize Image Semantics

    arXiv:2609.18823v1 Announce Type: cross Abstract: How do VLMs map from pixels to semantics? To understand this general question, we focus on a narrow one: studying how VLMs perform optical character recognition (OCR). Ac…

  39. arXiv cs.AIresearch
    GrainSpeech: Less Context, More Detail for Compact Speech Synthesis

    arXiv:2609.18856v1 Announce Type: cross Abstract: Compact acoustic models face a challenging quality-capacity trade-off. We investigate two factors in this regime: encoder context and Mel-spectrogram supervision. A recep…

  40. arXiv cs.AIresearch
    Decodable but Misrouted: Sparse Features Uncover a Readout Gap in Vision-Language Models for Harmful Meme Detection

    arXiv:2609.18860v1 Announce Type: cross Abstract: When a large vision-language model misclassifies a harmful meme, the failure may reflect missing internal evidence or an inability to route represented evidence to its ou…

  41. arXiv cs.AIresearch
    NeuroECG: ECGFounder-Based Deep ECG Representation for EEG-Free Neurological Prognostication After Cardiac Arrest

    arXiv:2609.18891v1 Announce Type: cross Abstract: Neurological prognostication after cardiac arrest commonly relies on electroencephalography (EEG). However, EEG demands high clinical resources. Bedside electrocardiograp…

  42. arXiv cs.AIresearch
    Higher-order pruning of experts in mixture-of-experts language models

    arXiv:2609.18916v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) language models suffer from large parameter counts, which create a significant memory bottleneck. Expert pruning is the most direct approach for…

  43. arXiv cs.AIresearch
    Dose-Aware Cold Diffusion with Physics Consistency for Generalizable Low-Dose CT Reconstruction

    arXiv:2609.18943v1 Announce Type: cross Abstract: Reducing radiation dose in computed tomography significantly degrades image quality and poses challenges for accurate and clinically reliable reconstruction. While recent…

  44. arXiv cs.AIresearch
    Automated Dental Caries Segmentation in Panoramic Radiographs Using Dual-Stage Deep Learning

    arXiv:2609.18952v1 Announce Type: cross Abstract: Early detection of dental caries remains challenging due to limitations in traditional diagnostic methods, particularly for proximal lesions in posterior teeth. Deep lear…

  45. arXiv cs.AIresearch
    Transcribe, Then Reason: Two-Pass Decomposition for Multimodal Review

    arXiv:2609.18958v1 Announce Type: cross Abstract: The natural way to review a long recording or document with a multimodal model is to hand it the raw source and ask for a review in one call. We show that this quietly fa…

  46. arXiv cs.AIresearch
    BadQubits: An LLM-Based Framework for Static Pre-Execution Detection of Structurally Harmful Quantum Circuits

    arXiv:2609.18965v1 Announce Type: cross Abstract: This paper presents BadQubits, an LLM-based framework for static pre-execution detection of structurally harmful OpenQASM 2.0 circuits. The framework targets physical-exe…

  47. arXiv cs.AIresearch
    WordPolo: Evaluating Language Models Through Iterative Semantic Feedback

    arXiv:2609.19006v1 Announce Type: cross Abstract: Large Language Models (LLMs) and Large Reasoning Models (LRMs) are typically evaluated on challenging benchmarks through dataset accuracy alone, providing no insight into…

  48. arXiv cs.AIresearch
    Tabular Deep Learning vs Classical Machine Learning for Urban Land Cover Classification

    arXiv:2609.19010v1 Announce Type: cross Abstract: Urban Land Cover (ULC) classification plays a crucial role in urban planning, environmental monitoring, and sustainable development. We study this task using the ULC data…

  49. arXiv cs.AIresearch
    TalkMatrix: Generating Character Dialogue that is Both Consistent and Diverse

    arXiv:2609.19022v1 Announce Type: cross Abstract: Candidate-based decoding typically selects a completion for each prompt independently, but many applications require a collection of outputs that satisfies global, non-de…

  50. arXiv cs.AIresearch
    RLLBC-Lib: An Educational Code Library for Reinforcement Learning and Learning-Based Control

    arXiv:2609.19074v1 Announce Type: cross Abstract: Reinforcement learning (RL) is an exciting concept as well as a remarkable success story worth sharing. However, RL builds on rather complex interactions between differen…