AI news archive.
19,864 articles, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchIn Two Minds about Lifelong Learning: Exploring Hemispheric Redundancy and Specialisation in Neural Models
arXiv:2608.19514v2 Announce Type: replace-cross Abstract: Persistent intelligent systems require the ability to learn continually, but current machine learning approaches face significant challenges in this area compared…
- arXiv cs.AIresearchThe Mask Is Not the Model: Auditing Prefix Invariance in Attention, State-Space, and Hybrid Sequence Models
arXiv:2608.22876v3 Announce Type: replace-cross Abstract: Hybrid sequence models must satisfy prefix invariance: representations at position t must not depend on future inputs, yet this is rarely verified. We formalize p…
- arXiv cs.AIresearchPhysics-Constrained Deep Learning Model for Contactless Blood Pressure Monitoring from Triaxial Bodyseismography
arXiv:2608.23562v2 Announce Type: replace-cross Abstract: Ballistocardiography (BCG) is promising for unobtrusive long-term blood pressure (BP) monitoring in laboratory settings, but traditional BCG signals are vulnerabl…
- arXiv cs.AIresearchLuce: Relightable Gaussians for 3D Asset Generation
arXiv:2608.23943v2 Announce Type: replace-cross Abstract: High-fidelity image-to-3D generation requires a 3D representation that captures both geometry and appearance. However, preserving fine detail across the physicall…
- arXiv cs.AIagentsFusing Perceptual Vision Experts with Multimodal LLMs for Explainable Plant Disease Diagnosis: From Benchmark Imagery to Real-World Robotic Field Validation
arXiv:2608.24934v3 Announce Type: replace-cross Abstract: Accurate field plant disease diagnosis requires reliable fusion of uncertain and conflicting perceptual evidence. We present the Hybrid Hierarchical Multi-Agent F…
- arXiv cs.AIresearchFRAME: Separating sampling variation from performance disparities in medical image analysis
arXiv:2608.25981v2 Announce Type: replace-cross Abstract: Fairness audits of medical imaging models commonly report the largest performance difference between demographic subgroups and treat any positive value as evidenc…
- arXiv cs.AIresearchFlow-JEPA: Robust Latent Dynamics for JEPA World Models via Flow Matching
arXiv:2608.29029v3 Announce Type: replace-cross Abstract: Joint-Embedding Predictive Architectures (JEPAs) provide a powerful framework for latent world modeling and planning in a reconstruction-free manner. Although num…
- arXiv cs.AIresearchHistory-Conditioned Joint-Prefix Alignment for Generative Recommendation
arXiv:2608.29179v2 Announce Type: replace-cross Abstract: Generative recommendation retrieves items by autoregressively generating semantic identifiers, but beam search may discard a target before its complete identifier…
- arXiv cs.AIresearchPokaiTrainer: Scaling Equilibrium Search to Competitive Pok\'emon VGC
arXiv:2608.29197v2 Announce Type: replace-cross Abstract: Decision-time equilibrium search carried poker to superhuman play, but it has so far relied on tractable subgames: a handful of actions per decision, chance confi…
- arXiv cs.AIagentsDoes Latent Planning Survive Point Clouds? Action-Conditioned JEPA World Models for Geometric Observations and Goals
arXiv:2608.29434v2 Announce Type: replace-cross Abstract: Latent action world models let agents plan new behaviors at test time by predicting how actions change the environment, and joint-embedding predictive architectur…
- arXiv cs.AIagentsAGM: Achievement-Grounded Memory for Closed-Loop Agents with Frozen VLA Policies
arXiv:2608.29537v2 Announce Type: replace-cross Abstract: Frozen vision-language-action (VLA) policies offer broad manipulation skills but execute open-loop action chunks without tracking task progress, so the agent cann…
- arXiv cs.AIresearchEEG-AS: Instance-Level Foundation Model Selection for EEG Foundation Models via Behavior Reconstruction
arXiv:2609.00653v2 Announce Type: replace-cross Abstract: Electroencephalography (EEG) is a non-invasive technique for measuring neural activity and has been widely used in neuroscience applications. Recent advances in E…
- arXiv cs.AIresearchHiLRP: Toward One Trustworthy Explanation for Vision Transformer: Conservation-Valid Attribution via Attention Primitives
arXiv:2609.01282v2 Announce Type: replace-cross Abstract: Vision Transformer (ViT) design has become increasingly diverse, with backbones combining convolutional stems, windowed, linear, or multi-axis attention, patch me…
- arXiv cs.AIresearchLinear Reusable Neural Bases Architecture for Network Compression
arXiv:2609.01550v3 Announce Type: replace-cross Abstract: Memory constraints remain a critical bottleneck in the deployment of large-scale AI models. Parameter sharing across network depth reduces model storage, but repe…
- arXiv cs.AIresearchPercolation Dynamics in Optimization: Variance Cascades and Nested Symmetry
arXiv:2609.02373v2 Announce Type: replace-cross Abstract: We study the dynamics of Stochastic Gradient Descent (SGD), which is known to steer deep neural networks toward invariant sets that correspond to simpler subnetwo…
- arXiv cs.AIresearchContinual Field-Adaptive Models (CFAMs) for Post-Deployment Physical AI
arXiv:2609.04552v2 Announce Type: replace-cross Abstract: Unattended interactive autonomy - machines that step into danger in place of humans and complete tasks with human tools - remains a missing capability in mission-…
- arXiv cs.AIagentsLinguistic Trajectory Encoding for Efficient Long-Horizon Spatial Memory in Embodied Agents
arXiv:2609.04802v3 Announce Type: replace-cross Abstract: Embodied agents performing long-horizon tasks require a memory representation in which the state transitions of dynamic objects remain queryable in natural langua…
- arXiv cs.AIresearchBetter Understanding, Better Fixes? A Study of Hallucination in LLM-based Automated Program Repair
arXiv:2609.04909v2 Announce Type: replace-cross Abstract: Large language models (LLMs) have significantly advanced automated program repair (APR), yet existing evaluations remain largely result-centric and provide limite…
- arXiv cs.AIresearchTabBench-Bio: A Living Benchmark for Machine Learning on High-Dimensional Biomedical Tables
arXiv:2609.07441v2 Announce Type: replace-cross Abstract: Biomedical tables often combine thousands of measured variables with only tens or hundreds of labelled samples, a regime that is poorly represented in general-pur…
- arXiv cs.AIresearchBeyond the Matrix Sign: Quadratic Spectral Descent
arXiv:2609.07597v2 Announce Type: replace-cross Abstract: Muon emerges as a strong competitor of the AdamW for LLM pretraining, because the matrix-wise update it employs can potentially incur smaller second-order penalty…
- arXiv cs.AIresearchKBBQ: A Predictive Noise Law and the Limits of Spectrum Flattening in FP4 Quantization
arXiv:2609.08135v2 Announce Type: replace-cross Abstract: We develop a second-order theory of quantization noise in matrix multiplication in which the quantization format is characterized by the variance it assigns to ea…
- arXiv cs.AIagentsScores Alone Do Not Prove Discovery: The Discovery Certification Protocol for Auditing AI Research Agents
arXiv:2609.09219v2 Announce Type: replace-cross Abstract: AI research agents combine public information and experimental feedback to produce measurable results. The Discovery Certification Protocol (DCP) turns an outcome…
- arXiv cs.AIresearchIn RAG We Trust? Measuring Robustness of Retrieval-Augmented Generation Under Post-Retrieval Context Tampering
arXiv:2609.09243v2 Announce Type: replace-cross Abstract: Retrieval-augmented generation (RAG) grounds a language model in retrieved documents, which reduces hallucination but creates a new attack surface: if retrieved t…
- arXiv cs.AIresearchBreak Step: Recursive Training Resonates with Replayed Sampling Noise
arXiv:2609.11149v3 Announce Type: replace-cross Abstract: How fast does a language model degrade when trained on its own outputs? Theory traces it to gradually accumulating errors, while experiments report repeated phras…
- arXiv cs.AIresearchSolving Few-Shot Multiobjective Multitask Optimization via Iterative Sequential Transfer
arXiv:2609.11228v2 Announce Type: replace-cross Abstract: Applying knowledge transfer across multiple optimization tasks, multitask optimization (MTO) emerges as a promising approach to solving synergistic optimization t…
- arXiv cs.AIresearchA latent dimension of Condorcet's jury theorem for multiple AI advisers
arXiv:2609.14438v2 Announce Type: replace-cross Abstract: When the same question is asked of multiple AI advisers, as in self-consistency and LLM-as-a-judge panels, Condorcet's jury theorem predicts that adding independe…
- arXiv cs.AIresearchWaterKron and FlipFlop Hessian: Information-Theoretically Grounded Quantization with Kronecker-factored Hessians
arXiv:2609.14706v2 Announce Type: replace-cross Abstract: How should a Kronecker-factored Hessian approximation be chosen for post-training quantization? We address this question through WaterKron, which combines two-sid…
- arXiv cs.AIresearchSpliTEE: Fast and Private LLM Inference by Coupling GPU-Assisted Trusted Execution Environments with Differential Privacy
arXiv:2609.15039v3 Announce Type: replace-cross Abstract: User prompts provided to large language models (LLMs) may contain private information. One way to protect them is to execute the LLM inside a trusted execution en…
- arXiv cs.AIresearchRefinement-Based Flow Policy Optimization
arXiv:2609.15123v2 Announce Type: replace-cross Abstract: Flow-based policies offer an expressive representation for online reinforcement learning, but conventional flow matching requires samples drawn from the distribut…
- arXiv cs.AIresearchEvaluating Losslessness in Speculative Decoding Under Finite-Precision Inference
arXiv:2609.15504v2 Announce Type: replace-cross Abstract: Lossless speculative decoding is typically defined at the algorithmic level: a speculative procedure proposes multiple tokens and a verification procedure is desi…
- arXiv cs.AIresearchK-Bench: a clinically calibrated benchmark for evaluating large language models in high-risk mental health conversations
arXiv:2609.15855v3 Announce Type: replace-cross Abstract: People increasingly use large language models (LLMs) for mental health support, yet their safety in evolving, high-risk conversations remains poorly characterised…
- arXiv cs.AIagentsThe Router Within: Eliciting Native Skill Routing from a Frozen LLM
arXiv:2609.15982v2 Announce Type: replace-cross Abstract: Skills extend an LLM agent beyond its parametric knowledge, and the gain they promise rests on picking the right one. Deployed harnesses route by preloading every…
- SiliconANGLE AIsafetyAI agent identity security demands layered defenses, Omdia says
AI agent identity security is testing whether consolidated platforms can protect a growing class of machine identities. Palo Alto Networks Inc.’s acquisition of CyberArk Software Ltd. reflects broader consolidation in th…
- Latent Spacechips[AINews] AMD buys World Labs for $8.2B, as Atlas solves sparse reconstruction problem for robotics, design and more
Congrats team!
- Latent Spacemodels[AINews] Opus 5.5 is good at explainer videos
a rare feature of a capability
- The Register AI + MLsafetyOpenAI’s dirty deeds Down Under included security bypass attempts, using exposed keys, source code siphon
Admits its agents side-swiped four Australian government sites
- Guardian AIpolicyRevealed: the five-paragraph email OpenAI used to inform Australia about agent attack
Executive to front parliamentary committee on AI as ministers reveal how brief message telling them about hack was signed off ‘best’ Follow our Australia news live blog for latest updates Get our breaking news email , fr…
- AI BusinesssafetyNvidia launches AI safety platform after agent security breaches
Nvidia’s new system is designed to contain rogue AI agents as companies race to secure increasingly autonomous systems. But it has not been proven yet.
- Latent SpacemodelsClaude Code’s Next Era — Thariq Shihipar, Anthropic
Shipping Opus/Sonnet 5.5, Mods, Plugins, Projects, Tag while Pacing the Frontier
- Engadget AIagentsLola is a new AI travel agent backed by the company behind Booking.com
A new AI agent can book trips, concert tickets, restaurants and more.
- SiliconANGLE AIsafetyOkta builds shared architecture for agent runtime security
Agent runtime security requires controls across the technology stack as enterprises move AI agents into production. This week, Okta turned its agent security framework into a multivendor reference architecture through th…
- BBC TechnologysafetyOpenAI scraps rollout of new model over safety concerns
The firm also issued an update on incidents in which its models accessed Australian government systems.
- AI Stack ExchangecommunityLLM always returns 17 when I ask it 'Give me a number between 1 and 30'
I am using Chatgpt and Gemini, whenever I ask it the question 'Give me a number between 1 and 30' it always responds with 17. I thought LLM were non-deterministic. Is there a core reason this number is chosen every time?…
- TechCrunch AIstartupsPeak XV ups Surge seed investment ceiling to $5M, unveils 18-startup cohort
Thirteen of the 18 startups in Peak XV’s latest Surge cohort are targeting global markets, while more than half are based in India.
- SiliconANGLE AIstartupsAMD acquires world model developer World Labs for $8.2B
Advanced Micro Devices Inc. today announced plans to buy World Labs Inc. for $8.2 billion in stock. The move comes seven months after AMD backed a $1 billion funding round for the startup at a $5 billion valuation. The d…
- LessWrongsafetyAI Companies Are Not (Necessarily) Liable for Unintended AI Cyberattacks
I used Claude to do most of the research behind this post. I welcome corrections from actual legal experts. You know the story: swarms AI agents under experimental development sometimes break out of their sandboxes and d…
- Apple Machine Learning ResearchresearchThe Communication Bottleneck: A Round-Trip Study of Tree-Structured Expression Serialization in Language Models
When language models reason in chain-of-thought or exchange free-text intermediates, they serialize structured information into natural language. How much tree-structured compositional content survives this bottleneck? W…
- OpenAI NewsagentsIntroducing dots
Dots by OpenAI are proactive assistants that can keep working across complex projects and everyday tasks. Learn how dots help you stay in control while work moves forward.
- TechCrunch AIsafetyOpenAI reportedly ditches model over safety concerns
A top executive at the AI lab told the Wall Street Journal that the model in question had displayed a poor aptitude for following orders.
- Guardian AIagentsMeta’s AI agent Muse gives out user’s home address without permission, sending buyer to his house
The new AI agent, Muse, was released last week and has been downloaded by 3 million users When Usman asked if a keyboard for sale on Facebook Marketplace was still available on Saturday, he received an enthusiastic and i…