AI news archive.
19,861 articles, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchAI Security Research Should Better Incentivize Defense Research
arXiv:2605.23448v2 Announce Type: replace-cross Abstract: This work examines an imbalance in artificial intelligence (AI) security research: the field tends to produce more work on attacking AI systems than on defending…
- arXiv cs.AIagentsAdvertising to Agents: Measuring Description-Framing Bias in LLM Tool Selection
arXiv:2605.23916v3 Announce Type: replace-cross Abstract: AI agents often pick tools from registries, where each provider writes its tool's description; we ask whether sales language there changes which tool an agent pic…
- arXiv cs.AIresearchWTKO-CNN: Deep Learning Reveals Sequence Motifs Distinguishing Wild-Type and Knockout ATAC-seq Peaks
arXiv:2605.24034v2 Announce Type: replace-cross Abstract: Chromatin regulators can alter transcriptional programs by modifying the accessibility of regulatory DNA elements. Understanding how regulatory sequences differ b…
- arXiv cs.AIresearchConcept Unlearning via Cross-Attention Activation Projection for Diffusion Models
arXiv:2605.25765v2 Announce Type: replace-cross Abstract: Existing closed-form methods for concept unlearning in text-to-image diffusion models typically derive editing directions from fixed text embeddings, which may no…
- arXiv cs.AIresearchVisualNeedle: Benchmarking Active Visual Search in Information-Dense Scenes
arXiv:2605.26380v2 Announce Type: replace-cross Abstract: Frontier multimodal large language models (MLLMs) have been reported to achieve over 90\% accuracy on fine-grained perception benchmarks. However, such scores do…
- arXiv cs.AIresearchRA-MoE: Routing-Aligned Fine-Tuning for Multilingual Adaptation of Mixture-of-Experts Models
arXiv:2605.28306v2 Announce Type: replace-cross Abstract: Mixture-of-Experts (MoE) models enable efficient LLM scaling, yet adapting them to non-English downstream tasks remains challenging. Standard multilingual fine-tu…
- arXiv cs.AIresearchStochastic Gradient Descent with Momentum is Algorithmically Stable
arXiv:2605.28517v2 Announce Type: replace-cross Abstract: Stochastic gradient descent with momentum (SGDM) is one of the most widely used optimization algorithms in machine learning. While optimization properties of SGDM…
- arXiv cs.AIresearchTaxDistill: Improving Metagenomic Taxonomic Annotation via Distilled Genomic Foundation Models
arXiv:2605.28868v2 Announce Type: replace-cross Abstract: Metagenomic taxonomic annotation is essential for interpreting complex microbial communities, yet reliable annotation remains challenging under reference database…
- arXiv cs.AIagentsGrepSeek: Training Search Agents for Direct Corpus Interaction
arXiv:2605.29307v2 Announce Type: replace-cross Abstract: Large Language Model (LLM) search agents have shown strong promise on knowledge-intensive tasks through iterative reasoning and retrieval. Most existing systems r…
- arXiv cs.AIresearchKBF: Knowledge Boundary as Fingerprint for Language Model and Black-Box API Auditing
arXiv:2605.29524v3 Announce Type: replace-cross Abstract: Relay and reseller APIs mediate access to large language models (LLMs), but users cannot directly verify which model serves them. We introduce \name, a black-box…
- arXiv cs.AIagentsThe Surface You Test Is Not the Surface That Breaks
arXiv:2605.30454v2 Announce Type: replace-cross Abstract: Prompt-injection benchmarks for LLM agents typically test attacks through a single injection surface and report the resulting attack success rate as a property of…
- arXiv cs.AIresearchFoundation-Preserving Optimization in Generalized Eigenspace
arXiv:2606.00132v2 Announce Type: replace-cross Abstract: While finetuning effectively adapts foundation models to specialized downstream tasks, it can degrade nontarget capabilities acquired during pretraining. Existing…
- arXiv cs.AIresearchMean--Fluctuation Dynamics at the Edge of Stability
arXiv:2606.05326v2 Announce Type: replace-cross Abstract: We study the dynamics of gradient descent in the Edge of Stability regime, where the learning rate is large enough to induce persistent oscillations in the trajec…
- arXiv cs.AIresearchATM: Why Latent World Models Can Fail to Plan
arXiv:2606.09028v2 Announce Type: replace-cross Abstract: Latent world models can achieve accurate latent prediction yet still differ substantially in downstream planning performance. We argue that a key source of this d…
- arXiv cs.AIresearchLongMoE: Longitudinal Multimodal Learning via Trajectory-Aware Mixture-of-Experts
arXiv:2606.09907v2 Announce Type: replace-cross Abstract: Multimodal clinical learning is increasingly important for integrating diverse patient data, including imaging, text, and personalised health records. However, it…
- arXiv cs.AIresearchEigenism: Ethics for a Human-AI Future
arXiv:2606.12420v2 Announce Type: replace-cross Abstract: Our concepts of survival and self-interest were built for single, continuous biological lives. These ideas break down when applied to artificial intelligence, sin…
- arXiv cs.AIresearchExistence Precedes Value: Joint Modeling of Observational Existence and Evolving States in Time Series Forecasting
arXiv:2606.13571v2 Announce Type: replace-cross Abstract: Real-world time series are often highly incomplete and irregular due to sensor dormancy, transmission delays, and event-driven sampling, making reliable forecasti…
- arXiv cs.AIresearchBeyond the Commitment Boundary: Probing Epiphenomenal Chain-of-Thought in Large Reasoning Models
arXiv:2606.13603v2 Announce Type: replace-cross Abstract: Chain-of-thought (CoT) reasoning is the dominant paradigm for inference-time scaling in language models, yet the causal influence of individual steps on the final…
- arXiv cs.AIresearchA Virtuous AI is an Existential Risk
arXiv:2606.13739v2 Announce Type: replace-cross Abstract: This paper examines trade-offs between AI safety and well-being relative to (i) one of the most promising methods for finetuning super-capable AIs, 'Constitutiona…
- arXiv cs.AIresearchTri-Info: Generalizable, Interpretable Failure Prediction for VLA Models via Information Theory
arXiv:2606.19998v2 Announce Type: replace-cross Abstract: Vision-Language-Action (VLA) models are increasingly deployed across diverse tasks, yet they remain black boxes whose physical interactions can cause irreversible…
- arXiv cs.AIresearchFlow Annealing Posterior Sampling for Function-Space Regression and Inverse Problems
arXiv:2606.22346v2 Announce Type: replace-cross Abstract: Principled regression for stochastic processes is a long-standing challenge with deep connections to scientific inverse problems. We introduce Flow Annealing Post…
- arXiv cs.AIagentsUncertainty Quantification for Computer-Use Agents: A Benchmark across Vision-Language Models and GUI Grounding Datasets
arXiv:2606.25760v2 Announce Type: replace-cross Abstract: Computer-use agents turn vision-language model (VLM) predictions into executable GUI clicks, so reliable uncertainty estimates are essential for rejection, calibr…
- arXiv cs.AIresearchFrom Dataset Spectral Geometry to Network Weights: A Geometry-Aware Initialization for Sigmoidal MLPs in Image Classification
arXiv:2606.28444v2 Announce Type: replace-cross Abstract: Classical universal approximation theorems (UAT) establish the expressive power of sigmoidal multilayer perceptrons, but they do not specify how the weights shoul…
- arXiv cs.AIresearchAdaptive Reparametrized Time for Score-Based Diffusion Sampling
arXiv:2607.02137v3 Announce Type: replace-cross Abstract: We study timestep allocation for score-based diffusion sampling, where a learned reverse-time dynamics is discretized on a finite grid. Uniform and hand-crafted s…
- arXiv cs.AIresearchFedSPM: Routing-Enabled Federated Learning under Dual Heterogeneity via Semiparametric Mixture
arXiv:2607.04085v2 Announce Type: replace-cross Abstract: Routing-prediction federated learning has emerged as a new paradigm that reframes inter-client heterogeneity as a resource for system-level intelligence: at infer…
- arXiv cs.AIresearchPrompting Image Generators for Training-free Primitive Shape Abstraction
arXiv:2607.05568v2 Announce Type: replace-cross Abstract: Compact primitive abstractions represent 3D shapes with a few geometric primitives while preserving recognizable components. Learned methods depend on their train…
- arXiv cs.AIresearchThe Hitchhiker's Guide to Monoculture: AI Homogenizes Syntax, Not (Necessarily) Semantics
arXiv:2607.13077v3 Announce Type: replace-cross Abstract: Large language models (LLMs) have been widely reported to homogenize human expression and thought. However, I argue that convergence in language need not imply co…
- arXiv cs.AIresearchArm2Air: Cross-Embodiment Skeleton Transfer for 3D Relay Formation
arXiv:2607.27627v4 Announce Type: replace-cross Abstract: Unmanned aerial vehicle (UAV) relay networks can restore connectivity after communication infrastructure is damaged. Urban relay placement is difficult because li…
- arXiv cs.AIresearchRamanPFN: learning from Raman spectral structure with a tabular foundation model
arXiv:2608.02157v2 Announce Type: replace-cross Abstract: Raman spectroscopy enables label-free molecular characterization across materials science, analytical chemistry, biomedicine, and industrial process monitoring. H…
- arXiv cs.AIresearchConstructing Disambiguated Knowledge Bases from Large Language Models at Scale
arXiv:2608.03729v4 Announce Type: replace-cross Abstract: Automated Knowledge Base Construction (AKBC) is a core NLP task, and recent work proposes generating knowledge bases directly from large language models (LLMs), t…
- arXiv cs.AIresearchSoRoMoX: Fast, Differentiable, and Parallelizable Soft Robot Models
arXiv:2608.06650v2 Announce Type: replace-cross Abstract: Reduced-order models based on Cosserat-rod theory are now well established, and modeling theory is no longer the primary bottleneck in soft-robot control. Their i…
- arXiv cs.AIresearchRouter Sensitivity Under Lightweight Fine-Tuning Identifies Prunable Experts in Mixture-of-Experts Models
arXiv:2608.07890v3 Announce Type: replace-cross Abstract: Mixture-of-Experts (MoE) models decouple parameter count from per-token compute, but deployment still requires hosting every expert in memory. Recent theory shows…
- arXiv cs.AIresearchDo AI chatbots find what experts would? Effects of model, user role, and sample size on study retrieval for medical questions
arXiv:2608.13786v2 Announce Type: replace-cross Abstract: Large language model (LLM) chatbots are increasingly used to answer clinical questions with citations to relevant studies, yet the quality of retrieved evidence a…
- arXiv cs.AIresearchFrozen Memory Is Not Enough: Rethinking External Memory as Extraction
arXiv:2608.17050v5 Announce Type: replace-cross Abstract: Methods for improving knowledge use in large language models typically fall into two regimes. Non-parametric retrieval offers flexible access to external knowledg…
- arXiv cs.AIagentsHarness Continual Learning: Continual Adaptation Beyond Model Parameters
arXiv:2608.19013v2 Announce Type: replace-cross Abstract: Continual learning has largely been model-centric, treating model parameters as the state that changes with sequential experience. Modern agents can also adapt th…
- arXiv cs.AIresearchChorusTIC: Training-Free Multivariate Time Series Classification via Chorus In-Context Learning
arXiv:2608.24033v2 Announce Type: replace-cross Abstract: Time series classification underpins applications in healthcare, sensing, and industrial monitoring. Although time series foundation models support forecasting an…
- arXiv cs.AIagentsReconstructing the Right Episode: Evaluating Interleaved Conversational Memory Beyond Long Context
arXiv:2608.25655v2 Announce Type: replace-cross Abstract: Conversations with chat assistants increasingly span many topics in a single long-running thread, challenging memory systems. Existing long-context and memory ben…
- arXiv cs.AIresearchSimultaneous Envy and Equitability Guarantees
arXiv:2608.26410v3 Announce Type: replace-cross Abstract: Recent work in fair division has focused on either simultaneously satisfying closely related fairness notions or achieving a single notion across the ex-ante and…
- arXiv cs.AIagentsDAMP: Decay-Aware Mixed-Precision Recurrent-State Quantization
arXiv:2608.27513v2 Announce Type: replace-cross Abstract: Complex reasoning and agentic applications increasingly rely on long-context inference, where growing KV caches increase both memory usage and decoding overhead.…
- arXiv cs.AIresearchEquivariant Sheaf Neural Networks: Learning Geometric Transport on Graphs
arXiv:2608.28853v3 Announce Type: replace-cross Abstract: Equivariant graph neural networks provide a principled way to model geometric systems, but efficient first-order architectures remain limited in how vector inform…
- arXiv cs.AIresearchDec-BFTRL: Squre-Root Regret for Decentralized Online Upper-Linearizable Optimization under Separation Access with Application to Continuous Submodular Maximization
arXiv:2608.30271v3 Announce Type: replace-cross Abstract: We study decentralized online optimization of upper-linearizable payoffs over an action set under efficient separation access, with applications to online continu…
- arXiv cs.AIresearchLot Machine: Multimodal Lot Extraction from Auction Catalogs
arXiv:2608.30510v3 Announce Type: replace-cross Abstract: For provenance research and art market studies, auction catalogs are an essential resource to trace specific objects over time and space. While historical auction…
- arXiv cs.AIresearchGeometry-aware Latent Autoregressive Generative Model for PDEs in Complex Domains
arXiv:2609.00297v2 Announce Type: replace-cross Abstract: Solving multiphysics partial differential equations (PDEs) remains a major challenge in scientific computing, especially for highly complex $\mu$m-scale tortuous…
- arXiv cs.AIresearchHEAT: Faster Fully Homomorphic Inference via Approximations-Weights Co-Adaptation
arXiv:2609.01730v2 Announce Type: replace-cross Abstract: Fully homomorphic encryption (FHE) allows a server to run a language model directly on encrypted user prompts, but current approaches remain prohibitively slow. C…
- arXiv cs.AIresearchAdaptive Vision-Language Grasping via Composable Foundation Priors and Generalizable Grasp Synthesis
arXiv:2609.04096v2 Announce Type: replace-cross Abstract: This paper proposes AdaRoboVLG, a task-adaptive Vision-Language-Grasp (VLG) framework that supports generalizable grasp synthesis across different robotic hands.…
- arXiv cs.AIresearchWSPolypNet: Weakly Supervised Polyp Localization in Colonoscopy Videos
arXiv:2609.08182v2 Announce Type: replace-cross Abstract: Because dense frame-level annotation of colonoscopy videos is costly, we propose WSPolypNet, a weakly supervised framework for polyp localization using only video…
- arXiv cs.AIresearchEquivariance Breaks the Learning Rate
arXiv:2609.08381v2 Announce Type: replace-cross Abstract: Equivariant networks are commonly trained with Adam, yet recent work reports that matrix structured optimizers such as Muon can perform better, with the reasons f…
- arXiv cs.AIresearchAttention Is All You Need (to Avoid Spurious Oscillations)
arXiv:2609.13531v2 Announce Type: replace-cross Abstract: Can attention move a shock across several cells in one update without breaking it? We develop a conservative, fixed grid finite-volume scheme in which a CFL-condi…
- arXiv cs.AIresearchDiagnosing Temporal Misalignment in Multichannel Time-Series Classification with Minimum Description Length
arXiv:2609.14595v2 Announce Type: replace-cross Abstract: Multichannel time-series classification commonly assumes synchronized sensor streams, although latency, clock drift, and preprocessing can introduce relative dela…
- LessWrongresearchEvaluation Awareness in Small(ish) Models
TL;DR We seek to identify open source reasoning models which are both small enough for white-box interpretability and display evaluation-gaming behavior. We find that how often models verbalize their awareness varies fro…