AI news archive.
10,659 articles filed under Research, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchSpikeQ: Spike-Guided Post-Training Quantization for Spiking Neural Networks
arXiv:2610.23046v1 Announce Type: cross Abstract: On neuromorphic chips, spiking neural networks (SNNs) consume far less energy than artificial neural networks (ANNs), but the limited memory of these chips requires low-b…
- arXiv cs.AIresearchUnifying Embodied Foundation Models via a Model-to-Policy Formulation
arXiv:2610.23053v1 Announce Type: cross Abstract: Vision-language-action (VLA) models and world-action models (WAMs) have emerged as promising approaches to robot learning and control. These models integrate multimodal p…
- arXiv cs.AIresearchPath to Prior-Data Fitted Relational Models via Learned Latent Multi-table Representations
arXiv:2610.23073v1 Announce Type: cross Abstract: Prior-data fitted networks (PFNs) show that pretraining on large populations of synthetic tasks can enable generalization to unseen datasets with little or no downstream…
- arXiv cs.AIresearchLocal proxies for memory-efficient training
arXiv:2610.23145v1 Announce Type: cross Abstract: Local learning algorithms can reshape resource requirements of artificial intelligence. The memory bottleneck of standard end-to-end backpropagation lies in the need to s…
- arXiv cs.AIresearchExplaining Chess and Go in Natural Language
arXiv:2610.23166v1 Announce Type: cross Abstract: Modern chess engines play far beyond human ability, often choosing moves whose underlying ideas are difficult for humans to understand. We propose an automatic metric for…
- arXiv cs.AIresearchA Stronger Teacher Within: Strengthening MoE Models via On-Policy Bidirectional Distillation
arXiv:2610.23185v2 Announce Type: replace-cross Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has substantially improved Mixture-of-Experts (MoE) LLMs, but its outcome-level rewards provide only sparse…
- arXiv cs.AIresearchLangNCO: Compiling Natural-Language Constraints into Inference-Time Interventions for Neural Combinatorial Optimization
arXiv:2610.23190v1 Announce Type: cross Abstract: Neural combinatorial optimization (NCO) rapidly produces high-quality solutions for problem structures encountered during training, but operational requirements may chang…
- arXiv cs.AIresearchFraming Spatial Hearing within the Free Energy Principle: A Hierarchical Model of Perceptual Learning
arXiv:2610.23196v1 Announce Type: cross Abstract: Spatial hearing relies on dynamic internal representations to decode spatial information from ever-changing acoustic conditions. A fundamental example is sound localisati…
- arXiv cs.AIresearchValidating LLM-generated political networks with survey-reported partisan exposure
arXiv:2610.23199v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used to simulate human behavior in social science research, including decisions, interactions, and social relationships. How…
- arXiv cs.AIresearchqGAMMA: A Framework for Optimal DNN Mapping on Multi-Precision Accelerators
arXiv:2610.23222v1 Announce Type: cross Abstract: This work describes qGAMMA, a flexible framework for exploring and optimizing the mapping of mixed-precision Deep Neural Network (DNN) models onto general-purpose spatial…
- arXiv cs.AIresearchMGE-PO: Entropy-Aware Credit Assignment for Mathematical Reasoning
arXiv:2610.23245v1 Announce Type: cross Abstract: GRPO assigns the same group-relative advantage to equally rewarded responses within a question, leaving their generation uncertainty unused. We introduce MGE-PO, centered…
- arXiv cs.AIresearchFlashReFocus: Interactive Image Refocusing in Seconds
arXiv:2610.23297v1 Announce Type: cross Abstract: Single-image refocusing changes the focal plane and depth of field of a photograph after capture. It is inherently interactive: users try many focal points and blur stren…
- arXiv cs.AIresearchLanguage Models Learn to Improve Language Models
arXiv:2610.23344v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used to automate AI research, including language-model (LM) development, offering a potential path toward recursive self-imp…
- arXiv cs.AIresearchAWAM: Active Trajectory-Conditioned View Imagination for Robust Robot Manipulation
arXiv:2610.23396v1 Announce Type: cross Abstract: Rapid progress in embodied intelligence has enabled increasingly capable robots to follow language instructions and manipulate diverse objects. However, strong results in…
- arXiv cs.AIresearchA Topological Signature of Learning under Noisy Labels
arXiv:2610.23491v1 Announce Type: cross Abstract: How does noisy supervision change the representations learned by a neural network? Training accuracy measures agreement with training labels but provides little informati…
- arXiv cs.AIresearchTruth in Contrast: Calibrated Factual Evidence from Language Model Likelihoods
arXiv:2610.23527v1 Announce Type: cross Abstract: Large Language Models (LLMs) encode substantial factual knowledge. Yet, estimating confidence in factual claims reliably remains challenging. We study likelihood-based fa…
- arXiv cs.AIresearchReason-guided Human Reward Modeling for Preference-based Reinforcement Learning
arXiv:2610.23550v1 Announce Type: cross Abstract: Reinforcement learning (RL) policies optimized for task rewards may produce behaviors that are efficient but misaligned with human expectations, safety preferences, or in…
- arXiv cs.AIresearchBeyond Action Prediction: Learning Search-Free Planning in Latent Space
arXiv:2610.23615v1 Announce Type: cross Abstract: Latent world models learn action-conditioned state transitions in a compact representation space, providing a predictive model for visual planning and control. However, p…
- arXiv cs.AIresearchPresenceBench: An Exploratory Evaluation of Large Language Model Adaptation to User State
arXiv:2610.23625v1 Announce Type: cross Abstract: Presence-aware intelligence is the capacity of an AI system's intelligence layer to adapt appropriately to the functional state of the person it serves (here readiness, f…
- arXiv cs.AIresearchTUPLE-Bench: Evaluating and Mitigating Privacy-Utility Trade-offs in Typed Decision Models
arXiv:2610.23668v1 Announce Type: cross Abstract: Typed decision models often return more than a selected category. They also expose probabilities for each candidate and, sometimes, a separate confidence score. These fie…
- arXiv cs.AIresearchNeural Expansion: A Unified Mechanism for How Deep Neural Networks Generalize
arXiv:2610.23716v1 Announce Type: cross Abstract: Deep neural networks demonstrate remarkable generalization despite being highly over-parameterized, challenging traditional statistical learning theories. While several t…
- arXiv cs.AIresearchBehavioral Couplings: From Formation to Behavioral Emergence in Language Models
arXiv:2610.23847v2 Announce Type: replace-cross Abstract: Fine-tuning large language models (LLMs) can induce behaviors beyond those explicitly targeted. For example, training a model to respond more warmly can make it m…
- arXiv cs.AIresearchRethinking the design space of Vanilla Pixel Diffusion Transformers
arXiv:2610.23854v1 Announce Type: cross Abstract: Pixel-space diffusion models have recently re-emerged as a compelling alternative to latent diffusion, avoiding the lossy latent bottleneck and separately trained autoenc…
- arXiv cs.AIresearchGVPO: Group Variance Policy Optimization for Large Language Model Post-Training
arXiv:2504.19599v4 Announce Type: replace Abstract: Post-training plays a crucial role in refining and aligning large language models to meet specific tasks and human preferences. While recent advancements in post-traini…
- arXiv cs.AIresearchA Survey of Explainable Reinforcement Learning: Targets, Methods and Needs
arXiv:2507.12599v2 Announce Type: replace Abstract: The success of recent Artificial Intelligence (AI) models has been accompanied by the opacity of their internal mechanisms, due notably to the use of deep neural networ…
- arXiv cs.AIresearchHow RLHF Amplifies Sycophancy
arXiv:2602.01002v2 Announce Type: replace Abstract: Large language models often exhibit increased sycophantic behavior after preference-based post-training, showing a stronger tendency to affirm a user's stated or implie…
- arXiv cs.AIresearchMoral Sycophancy in Vision Language Models
arXiv:2602.08311v2 Announce Type: replace Abstract: Sycophancy in Vision-Language Models (VLMs) refers to their tendency to align with user opinions, often at the expense of moral or factual accuracy. While prior studies…
- arXiv cs.AIresearchAccurate and Efficient Multi-Channel Time Series Forecasting via Sparse Attention Mechanism
arXiv:2603.18712v3 Announce Type: replace Abstract: The task of multi-channel time series forecasting is ubiquitous in numerous fields such as finance, supply chain management, and energy planning. It is critical to effe…
- arXiv cs.AIresearchTowards Reliable Truth-Aligned Uncertainty Estimation in Large Language Models
arXiv:2604.00445v2 Announce Type: replace Abstract: Uncertainty estimation (UE) aims to quantify uncertainty in large language model (LLM) outputs to flag potential hallucinations and support reliable deployment. However…
- arXiv cs.AIresearchCrystalReasoner: Reasoning and RL for Property-Conditioned Crystal Structure Generation
arXiv:2605.14344v3 Announce Type: replace Abstract: Generative modeling has emerged as a promising approach for crystal structure discovery. However, existing LLM-based generative models struggle with low-level atomic pr…
- arXiv cs.AIresearchBrain Vascular Age Prediction Using Cerebral Blood Flow Velocity and Machine Learning Algorithms
arXiv:2605.16969v3 Announce Type: replace Abstract: Defining vascular age in terms of physiological function has become one focal point of the extensive studies to categorize and track chronological age. Transcranial Dop…
- arXiv cs.AIresearchHyperPersona: A Multi-Level Hypergraph Framework for Text-Based Automatic Personality Prediction
arXiv:2605.17355v2 Announce Type: replace Abstract: As a modern commodity, language has become a vast repository of socially and psychologically significant traits and concepts, reflecting the ways people encode pattern…
- arXiv cs.AIresearchExploration and Experimentation with a Misspecified Simulator
arXiv:2605.21458v2 Announce Type: replace Abstract: Randomized experiments are the standard for measuring causal effects that guide decisions, but are costly. Simulators calibrated to historical data offer a cheaper alte…
- arXiv cs.AIresearchECPO: Evidence-Coupled Policy Optimization for Verifier-Audited Candidate Ranking
arXiv:2605.21993v2 Announce Type: replace Abstract: Ranking systems used for decision support should expose evidence that can be audited independently of the model's ranking scores. We study a closed-roster setting in wh…
- arXiv cs.AIresearchLearning to Reason About Implicit Multimodal Harm: From Diagnosis to Generalization
arXiv:2605.29951v2 Announce Type: replace Abstract: A benign image paired with a benign caption can become harmful only in combination, making detection fundamentally a cross-modal reasoning problem. Existing multimodal…
- arXiv cs.AIresearchWho Can Change Course? An Integrative Review of AI Sovereignty and Collective Learning Capacity
arXiv:2606.00729v4 Announce Type: replace Abstract: AI sovereignty is commonly associated with control over data, infrastructure and technological dependencies. This integrative review examines how institutions convert t…
- arXiv cs.AIresearchLarge Language Models in Transportation Systems Management and Operations: From Text Reasoning to Multi-modal Decision Support
arXiv:2606.00991v2 Announce Type: replace Abstract: Transportation systems management and operations (TSMO) increasingly depends on timely interpretation of heterogeneous data, from various sensor streams, incident repor…
- arXiv cs.AIresearchCross-Dialect Generalization Without Retraining: Benchmarks and Evaluation of Schema-Derived Constrained Decoding for MLIR
arXiv:2607.18254v2 Announce Type: replace Abstract: Multi-Level Intermediate Representation (MLIR) underlies modern ML compiler infrastructure (TensorFlow, JAX/StableHLO, PyTorch Inductor, IREE), yet appears only in trac…
- arXiv cs.AIresearchSTAIF: A Stage-wise Optimization for Complex Instruction Following
arXiv:2607.22649v2 Announce Type: replace Abstract: Following complex instructions with multiple explicit constraints remains a fundamental challenge for large language models (LLMs). Existing alignment methods, such as…
- arXiv cs.AIresearchCDAE: Enhancing Perturbation Robustness in Pretrained Language Models with Contrastive Denoising
arXiv:2607.28236v2 Announce Type: replace Abstract: Pre-trained language models have significantly improved sentence representation learning, yet their embeddings remain sensitive to textual perturbations such as synonym…
- arXiv cs.AIresearchPoli-Bias: Understanding and Measuring Large Language Model Biases in International Political Conflicts
arXiv:2608.06123v3 Announce Type: replace Abstract: Measuring political bias in large language models (LLMs) remains challenging as it can manifest through subtle differences in framing, argumentation, and legal reasonin…
- arXiv cs.AIresearchLocating Failure in Multi-Page Visually Rich Document Understanding Systems: An Empirical Attribution
arXiv:2608.07943v2 Announce Type: replace Abstract: Multi-page visually rich document understanding (MP-VRDU) systems can fail when evidence is not faithfully represented, not selected, or not used correctly, yet final a…
- arXiv cs.AIresearchHarnessing Trust in Directed Graphs: Redefining Robustness of Graph Learning
arXiv:2306.02002v2 Announce Type: replace-cross Abstract: Existing research on robust Graph Neural Networks (GNNs) focuses predominantly on undirected graphs, overlooking the trustworthiness inherent in the link directio…
- arXiv cs.AIresearchPluvio: Assembly Clone Search for Out-of-domain Architectures and Libraries through Transfer Learning and Conditional Variational Information Bottleneck
arXiv:2307.10631v2 Announce Type: replace-cross Abstract: The practice of code reuse is crucial in software development for a faster and more efficient development lifecycle. In reality, however, code reuse practices lac…
- arXiv cs.AIresearchBeyond Boundaries: A Comprehensive Survey of Transferable Attacks on AI Systems
arXiv:2311.11796v3 Announce Type: replace-cross Abstract: Transferable attacks allow adversarial manipulations or learned attack mechanisms constructed in one setting to compromise other AI systems, potentially reducing…
- arXiv cs.AIresearchVietMed: A Dataset and Benchmark for Automatic Speech Recognition of Vietnamese in the Medical Domain
arXiv:2404.05659v4 Announce Type: replace-cross Abstract: Due to privacy restrictions, there's a shortage of publicly available speech recognition datasets in the medical domain. In this work, we present VietMed - a Viet…
- arXiv cs.AIresearchHarmful YouTube Video Detection: A Taxonomy of Online Harm and MLLMs as Alternative Annotators
arXiv:2411.05854v2 Announce Type: replace-cross Abstract: Video platforms, used by billions globally, are criticized for exposing users to harmful content. Yet, detecting online harm remains challenging due to inconsiste…
- arXiv cs.AIresearchPaint Outside the Box: Synthesizing and Selecting Training Data for Visual Grounding
arXiv:2412.00684v3 Announce Type: replace-cross Abstract: Visual grounding aims to localize the image regions based on a textual query. Given the difficulty of large-scale data curation, we investigate how to effectively…
- arXiv cs.AIresearchRethinking Negative Prompting for Concept Suppression: Unconditional Anchoring and Localized Guidance
arXiv:2412.07658v3 Announce Type: replace-cross Abstract: Text-to-image diffusion models have rapidly transitioned from research prototypes to widely deployed tools. Along with their impressive capabilities, these models…
- arXiv cs.AIresearchWhat is causal about causal models and representations?
arXiv:2501.19335v3 Announce Type: replace-cross Abstract: Causal Bayesian networks are often described as causal because they support reasoning about interventions. Yet interventions are defined in the mathematical model…