AI news archive.
10,659 articles filed under Research, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchAFFORD2ACT: How Far Can Sparse Keypoints Go for Robot Manipulation?
arXiv:2510.01433v3 Announce Type: replace-cross Abstract: Vision-based manipulation policies are commonly learned from rich visual observations, typically using dense visual features extracted from full resolution images…
- arXiv cs.AIresearchProtecting De-identified Documents from Search-based Linkage Attacks
arXiv:2510.06383v3 Announce Type: replace-cross Abstract: While de-identification models can help conceal the identity of the individuals mentioned in a document, they fail to address linkage risks, defined as the potent…
- arXiv cs.AIresearchSculpting the Latent Space: Disentanglement with WAE-MMD and Programmable Priors
arXiv:2510.11953v2 Announce Type: replace-cross Abstract: Learning disentangled representations, where semantic features are independently captured in a latent space, is dominated by Variational Auto Encoders (VAE) and A…
- arXiv cs.AIresearchStructured Temporal Causality for Interpretable Multivariate Time Series Anomaly Detection
arXiv:2510.16511v2 Announce Type: replace-cross Abstract: Real-world multivariate time series anomalies are rare and often unlabeled. Additionally, prevailing methods rely on increasingly complex architectures tuned to b…
- arXiv cs.AIresearchAlign, Don't Blend: Orthogonal Supervision Disentanglement As the Key to Generalizable AI-Generated Image Detection
arXiv:2512.06746v3 Announce Type: replace-cross Abstract: Recent advances in AI-Generated Image (AIGI) detection have largely focused on model architectures, loss design, and training strategies, while overlooking a more…
- arXiv cs.AIresearchAlgorithmic Reflectivity in Large Language Models: Methodological Study of Linguistic Structure in Mentalization
arXiv:2512.08945v2 Announce Type: replace-cross Abstract: Mentalization is a core human capacity involving the interpretation of one's own and others' behavior in terms of underlying mental states. Large language models…
- arXiv cs.AIresearchEvolutionary BP+OSD Decoding for Low-Latency Quantum Error Correction
arXiv:2512.18273v3 Announce Type: replace-cross Abstract: Quantum error correction (QEC) for fault-tolerant quantum computing requires a balanced decoding solution that offers high performance, low complexity, and low la…
- arXiv cs.AIresearchRubRIX: Rubric-Driven Risk Mitigation in Caregiver-AI Interactions
arXiv:2601.13235v2 Announce Type: replace-cross Abstract: Caregivers seeking AI-mediated support express complex needs---information-seeking, emotional validation, and distress cues---that warrant careful evaluation of r…
- arXiv cs.AIresearchDisentangling generalization and memorization in large language models using chess
arXiv:2601.16823v3 Announce Type: replace-cross Abstract: Large Language Models (LLMs) exhibit remarkable capabilities, yet it remains unclear to what extent these reflect sophisticated recall or genuine reasoning abilit…
- arXiv cs.AIresearchFrom Fuzzy to Exact: The Halo Architecture for Infinite-Depth Reasoning via Rational Arithmetic
arXiv:2601.18702v5 Announce Type: replace-cross Abstract: The prevailing scaling paradigm of Large Language Models (LLMs) rests on a substrate of "Fuzzy" floating-point arithmetic. To mitigate the inherent instability of…
- arXiv cs.AIresearchControlling Output Rankings in LLM-Based Search via Generative Engine Optimization
arXiv:2602.03608v2 Announce Type: replace-cross Abstract: The way customers search for and choose products is changing with the rise of large language models (LLMs). LLM-based search, or generative engines, provides dire…
- arXiv cs.AIresearchHealthMamba: An Uncertainty-aware Spatiotemporal Graph State Space Model for Effective and Reliable Healthcare Facility Visit Prediction
arXiv:2602.05286v4 Announce Type: replace-cross Abstract: Healthcare facility visit prediction is essential for optimizing healthcare resource allocation and informing public health policy. Despite advanced machine learn…
- arXiv cs.AIresearchAnalyzing and Improving Chain-of-Thought Monitorability Through Information Theory
arXiv:2602.18297v2 Announce Type: replace-cross Abstract: Chain-of-thought (CoT) monitors are LLM-based systems that analyze reasoning traces to detect when outputs may exhibit attributes of interest, such as test-hackin…
- arXiv cs.AIresearchData-Free Finite-Volume Convolutional Neural Networks for Steady Compressible Euler Flow around a Circular Cylinder
arXiv:2603.01001v2 Announce Type: replace-cross Abstract: A data-free finite-volume convolutional neural network (FV-CNN) is formulated for steady Euler flow around a cylinder at eight Mach numbers, 2--15. Shared-face fl…
- arXiv cs.AIresearchStructLens: A Structural Lens for Language Models via Maximum Spanning Trees
arXiv:2603.03328v3 Announce Type: replace-cross Abstract: Language exhibits inherent structures, a property that explains both language acquisition and language change. Given this characteristic, we expect language model…
- arXiv cs.AIresearchMICA: Multi-granularity Intertemporal Credit Assignment for Long-Horizon Emotional Support Dialogue
arXiv:2603.06194v4 Announce Type: replace-cross Abstract: Reinforcement learning (RL) for large language models (LLMs) has shown strong performance in single-turn tasks, but extending it to multi-turn interaction remains…
- arXiv cs.AIresearchSYNAPSE: Framework for Neuron Analysis and Perturbation in Sequence Encoding
arXiv:2603.08424v2 Announce Type: replace-cross Abstract: In recent years, Artificial Intelligence has become a powerful partner for complex tasks such as data analysis, prediction, and problem-solving, yet its lack of t…
- arXiv cs.AIresearchMCLR: Improving Conditional Modeling via Inter-Class Likelihood-Ratio Maximization and Unifying Classifier-Free Guidance with Alignment Objectives
arXiv:2603.22364v4 Announce Type: replace-cross Abstract: Diffusion models achieve strong generative performance but often rely on classifier-free guidance (CFG), an inference-time intervention that modifies the sampling…
- arXiv cs.AIresearchThe Stepwise Informativeness Assumption: When Do Entropy Dynamics Track Reasoning Correctness in LLMs?
arXiv:2604.06192v2 Announce Type: replace-cross Abstract: Recent work uses entropy-based signals at multiple representation levels to study reasoning in large language models, but the field remains largely empirical. Fro…
- arXiv cs.AIresearchGeneralization and Scaling Laws for Mixture-of-Experts Transformers
arXiv:2604.09175v2 Announce Type: replace-cross Abstract: We develop a theory of generalization and scaling for Mixture-of-Experts (MoE) Transformers that cleanly separates \emph{active} per-input capacity from routing c…
- arXiv cs.AIresearchIt Takes a Forum: Resources & Stakeholders Sustaining the Online Synthetic Non-Consensual Intimate Image Creation Ecosystem
arXiv:2604.12190v2 Announce Type: replace-cross Abstract: Many malicious actors responsible for disseminating synthetic non-consensual intimate imagery (SNCII) operate within internet forums to exchange resources, strate…
- arXiv cs.AIresearchOn the Expressive Power and Limitations of Multi-Layer SSMs
arXiv:2604.14501v3 Announce Type: replace-cross Abstract: We study how depth, finite precision, state dimension, and chain-of-thought (CoT) affect the expressive power of multi-layer state-space models (SSMs). For the ex…
- arXiv cs.AIresearchFine-Tuning Small Reasoning Models for Quantum Field Theory
arXiv:2604.18936v2 Announce Type: replace-cross Abstract: Despite the growing application of large language models (LLMs) to theoretical physics, there has been little academic exploration of how domain-specific physics…
- arXiv cs.AIresearchOn the Complementarity of Quantum and Classical Features: Adaptive Hybrid Quantum-Classical Feature Fusion for Breast Cancer Classification
arXiv:2604.22903v2 Announce Type: replace-cross Abstract: The integration of quantum machine learning with classical deep learning offers promising avenues for medical image analysis by mapping data into high-dimensional…
- arXiv cs.AIresearchProMORNA: An End-to-End Generative Framework for Full-Length mRNA Design
arXiv:2605.01513v2 Announce Type: replace-cross Abstract: Designing therapeutic messenger RNA (mRNA) requires generating full-length transcripts that optimally balance intracellular stability and translation efficiency.…
- arXiv cs.AIresearchDooly: Configuration-Agnostic, Redundancy-Aware Profiling for LLM Inference Simulation
arXiv:2605.07985v3 Announce Type: replace-cross Abstract: Selecting the optimal LLM inference configuration requires evaluation across hardware, serving engines, attention backends, and model architectures, since no sing…
- arXiv cs.AIresearchPath-Coupled Bellman Flows for Distributional Reinforcement Learning
arXiv:2605.08253v3 Announce Type: replace-cross Abstract: Distributional reinforcement learning (DRL) models the full return distribution, but existing finite-support or quantile-based methods rely on projections, while…
- arXiv cs.AIresearchFeedback World Model Enables Precise Guidance of Diffusion Policy
arXiv:2605.15705v2 Announce Type: replace-cross Abstract: World models aim to improve robotic decision making by predicting the consequences of actions. However, in practice, their predictions often become unreliable onc…
- arXiv cs.AIresearchCAVE: A Structured Credit Assignment Approach for Fragmented Visual Evidence Reasoning
arXiv:2605.16416v2 Announce Type: replace-cross Abstract: Vision-Language Models (VLMs) have achieved strong performance on general multimodal reasoning, yet remain challenged in integrating nonlocal visual information t…
- arXiv cs.AIresearchDualView: Adaptive Local-Global Fusion for Multi-Hop Document Reranking
arXiv:2605.18767v2 Announce Type: replace-cross Abstract: Multi-hop question answering requires aggregating information from multiple documents, a critical capability for knowledge-intensive applications. A fundamental c…
- arXiv cs.AIresearchLearning Altruistic Collaboration in Heterogeneous Multi-Team Systems
arXiv:2605.21723v2 Announce Type: replace-cross Abstract: This paper studies heterogeneous multi-team collaboration through dynamic robot allocation, where the robots themselves are treated as transferable resources. Lev…
- arXiv cs.AIresearchFrom Theory to Decision Rule: Calibrating the Noisy-Label Crossover for Vision-Language Model Weak Supervision Across Three Medical-Imaging Benchmarks
arXiv:2605.24771v2 Announce Type: replace-cross Abstract: In medical imaging, small sets of expert labels are often combined with zero-shot pseudo-labels from a vision-language model (VLM). When the expert-labeled set is…
- arXiv cs.AIresearchMetropolis-Scale Resilient and Trustworthy Traffic Flow Inference Using Multi-Source Data
arXiv:2605.25004v2 Announce Type: replace-cross Abstract: Inferring network-wide traffic states from sparse observations with high accuracy and trustworthy uncertainty quantification is essential for intelligent transpor…
- arXiv cs.AIresearchInfoQuant: Shaping Activation Distributions for Low-Bit LLM Quantization
arXiv:2605.26175v2 Announce Type: replace-cross Abstract: Low-bit activation quantization remains a major bottleneck in efficient large language model (LLM) deployment. The difficulty is not only that activations contain…
- arXiv cs.AIresearchLet It Be Simple: One-Step Action Generation for Vision-Language-Action Models
arXiv:2606.05737v3 Announce Type: replace-cross Abstract: One-step generation from standard diffusion or Flow-Matching training is rarely effective for text-to-image or video generation without distillation or specialize…
- arXiv cs.AIresearchEHRNote-ChatQA: A Benchmark for Evidence-Grounded Multi-Turn Clinical Question Answering over Longitudinal Discharge Summaries
arXiv:2606.15735v4 Announce Type: replace-cross Abstract: Discharge summaries are crucial clinical documents containing the context of a patient's overall hospital stay, and are routinely reviewed by medical experts for…
- arXiv cs.AIresearchLatent Bridges for Multi-Table Question Answering
arXiv:2606.28916v3 Announce Type: replace-cross Abstract: We introduce GRAB, a constructor-encoder-bridge pipeline for table question answering. Our method lifts relational data into an heterogeneous graph, encodes it vi…
- arXiv cs.AIresearchMixture-of-Control: State-Aware Fine-Tuning for Transformer-based Models
arXiv:2606.31397v2 Announce Type: replace-cross Abstract: State-based fine-tuning has emerged as a compelling alternative to weight-based adaptation for transformers, updating lightweight controls into states rather than…
- arXiv cs.AIresearchTo Retain or to Adapt? Generalizing Continual Learning
arXiv:2607.05609v2 Announce Type: replace-cross Abstract: The Continual Learning (CL) literature has long been driven by the goal of mitigating catastrophic forgetting. This objective rests on an often unstated assumptio…
- arXiv cs.AIresearchConditional Optimal Bridge for Riemannian Activation Steering
arXiv:2607.10517v2 Announce Type: replace-cross Abstract: Activation steering offers a lightweight alternative to fine-tuning for controlling large language models at inference time. Many existing steering methods implic…
- arXiv cs.AIresearchFlout at Your Own Risk: LLMs Struggle with Pragmatic Cooperativity Under Epistemic Asymmetry
arXiv:2607.11053v2 Announce Type: replace-cross Abstract: Fruitful collaborations require effective communication of privately-held information. The increasing use of LLMs as "collaborators" raises questions about the ex…
- arXiv cs.AIresearchOn the Role of Citations in Preference Data
arXiv:2608.21376v2 Announce Type: replace-cross Abstract: Many NLP tasks require systems to provide attribution in their outputs--i.e. citations to grounding sources. Attribution serves as a bulwark against model halluci…
- arXiv cs.AIresearchDrugReason: Dynamic Multi-View Reasoning over Knowledge Graph and Language Evidence for Drug Repurposing
arXiv:2609.06779v2 Announce Type: replace-cross Abstract: Drug repurposing aims to identify new therapeutic uses for existing compounds and, compared with de novo drug discovery, offers a faster and more cost-effective p…
- arXiv cs.AIresearchCausal Discovery via Transformed Low-Rank Quantile Surfaces
arXiv:2609.16931v2 Announce Type: replace-cross Abstract: We propose Low-Rank Quantile Surfaces (LRQS), a bivariate causal model in which, in the causal direction, an unknown monotone transformation of the conditional qu…
- LessWrongresearchExploring Unsupervised Methods for Recovering the Refusal Direction in LLMs
Introduction This is the first part of what we plan to be a research exploration into the geometries of LLMs. We start with building off existing work by Arditi et al focused on the refusal direction in LLMs. Background…
- LessWrongresearchWhat's in CODI's latent recurrent thoughts?
What's in CODI's latent recurrent thoughts? TL;DR CODI is a model using latent reasoning. Previous work by Cywiński et al. (2025) has found that CODI's latent recurrent states (“thoughts”) do causally carry a computation…
- LessWrongresearchEven GPT-2 passes most functional global workspace tests
tl;dr Anthropic’s global workspace paper (Gurnee et al., 2026) proposes five functional tests for a global workspace and, using the Jacobian lens (J-lens), finds representations in Claude that pass all five. It also find…
- LessWrongresearchHow does Fable 5.1 hide messages in images?
TL;DR Frontier LLMs are now capable of generating artistic images using SVG. We ask – if these LLMs had to hide a message in an image – how would they do so? And if they hid such messages, could they be successfully deco…
- LessWrongresearchTowards Robust Model Organisms for Eliciting Latent Knowledge
TL;DR: We argue that a useful model organism should satisfy three properties: selectivity, robustness, and retention. We build a model organism for finding security vulnerabilities in code which selectively withholds har…
- LessWrongresearchAutonomous researchers will strain peer review, funding, and oversight
Summary : Autonomous AI researchers could greatly accelerate AI safety research, but even if we solve sabotage, they will strain the research ecosystem. They will multiply the volume of research and make researchers homo…