AI news archive.
19,861 articles, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchDualCast: A Dual-Path Language Model for Bimodal Financial Time-Series Forecasting
arXiv:2609.38197v1 Announce Type: cross Abstract: Financial time-series forecasting must capture price dynamics across heterogeneous assets while incorporating news available at prediction time. We introduce DualCast, a…
- arXiv cs.AIresearchAutomatic estimation of verbal fluency index in people with Motor Neuron Disease using ASR alignment and pause modelling
arXiv:2609.38203v1 Announce Type: cross Abstract: Monitoring cognitive impairment (CI) in motor neuron disease (MND) is essential for timely treatment and care, yet challenging due to co-occurring speech difficulties. Th…
- arXiv cs.AIresearchSynIL: Leveraging Synergy for Offline Imitation Learning from Imperfect Demonstration Datasets
arXiv:2609.38225v1 Announce Type: cross Abstract: Imitation learning enables robots to acquire complex skills directly from massive demonstration datasets, but its performance degrades severely when datasets are contamin…
- arXiv cs.AIresearchModalFidelity: Routing Modalities for Deepfake Detection on a Budget
arXiv:2609.38246v1 Announce Type: cross Abstract: Deepfakes no longer need to fake a whole video. Generators that read the transcript now alter only the few seconds in which a video's meaning turns, so a forgery hides in…
- arXiv cs.AIresearchForensic-Aware Continual Adaptation for Image Forgery Localization
arXiv:2609.38251v1 Announce Type: cross Abstract: The rapid evolution of image manipulation techniques has raised growing public security concerns. Existing Image Forgery Localization (IFL) methods can accurately localiz…
- arXiv cs.AIresearchCollageAttack: Exploiting Cross-Modal Alignment Flaws in T2I Models through Spatial Text Composition
arXiv:2609.38253v1 Announce Type: cross Abstract: Text-to-image (T2I) models have substantially improved in language understanding, in-image text rendering, and visual composition, while their safety mechanisms do not al…
- arXiv cs.AIresearchHow Should Diffusion Language Models Edit Code?
arXiv:2609.38257v1 Announce Type: cross Abstract: Code editing requires a model to decide where to make changes, generate the new content, and preserve everything else. We study how masked diffusion language models divid…
- arXiv cs.AIresearchContextAdapt: Evaluating Contextual Adaptation and Value Alignment in LLMs
arXiv:2609.38260v1 Announce Type: cross Abstract: Values such as honesty, autonomy, and confidentiality are often regarded as general principles underpinning AI alignment. However, what it means to act in accordance with…
- arXiv cs.AIresearchNinaXander: Feasibility and Limits of Composing Frozen Language Models Across Architecture Families via a Shared Latent Space
arXiv:2609.38261v1 Announce Type: cross Abstract: In this paper we propose NinaXander, a series of composed language models obtained by connecting layers of frozen language models from different architecture families wit…
- arXiv cs.AIagentsWhen Does Randomized Oversight Align AI Agents That Can Conceal?
arXiv:2609.38262v1 Announce Type: cross Abstract: Oversight changes the evidence it relies on. We ask when randomized audits and scoring align AI agents that can conceal misconduct and alter records. Stronger auditing ma…
- arXiv cs.AIresearchRaw Imagery Impacting Your AI: Should You Care?
arXiv:2609.38265v1 Announce Type: cross Abstract: Onboard AI is gaining interest for space applications such as vessel, wildfire, and cloud detection, where real-time processing can improve mission reactivity and reduce…
- arXiv cs.AIagentsJanus: Evidence-Before-Effect Sagas and Offline-Verifiable Provenance for Agentic LLMs
arXiv:2609.38266v1 Announce Type: cross Abstract: Agentic large language models (LLMs) now move money through tools, yet the record of what they did is usually a trace their own process emits beside the effect. Janus put…
- arXiv cs.AIagentsZero2Repo: Can Coding Agents Build Repositories from Scratch?
arXiv:2609.38269v3 Announce Type: replace-cross Abstract: Coding agents are increasingly asked to build software rather than patch it, yet benchmarks for from-scratch repository construction are mostly limited to a singl…
- arXiv cs.AIagentsWhen Correct Memory Goes Wrong: Fuzzing Persistent Memory Use in LLM Agents
arXiv:2609.38275v1 Announce Type: cross Abstract: Persistent memory helps LLM agents carry information across long interactions, but correct memory can still be used incorrectly when queries change or memory states evolv…
- arXiv cs.AIresearchGaugeVLM: Structuring Spatial Supervision with Measured Geometric Interventions
arXiv:2609.38285v1 Announce Type: cross Abstract: Vision-language models (VLMs) can contradict themselves across views of the same spatial relation and fail to respond when that relation changes. Addressing these failure…
- arXiv cs.AIresearchSocial Choice Foundations for Simulation-Augmented Generation
arXiv:2609.38287v1 Announce Type: cross Abstract: Simulation-augmented generation (SAGE) is a recent technical proposal in which models simulate individuals' viewpoints at inference time in order to provide more represen…
- arXiv cs.AIresearchSearching for BSM Experimental Signatures with Large Lagrangian Models
arXiv:2609.38309v1 Announce Type: cross Abstract: The search for physics Beyond the Standard Model (BSM) is generally limited not by the supply of theory descriptions but by the lack of discriminating experimental observ…
- arXiv cs.AIresearchHermes: Learning Contextual Reasoning Unlocks Test-Time Scaling
arXiv:2609.38332v1 Announce Type: cross Abstract: Test-time scaling improves model performance by allocating additional compute during inference. Using this compute effectively across multiple context windows requires de…
- arXiv cs.AIagentsE2E-SWE: Benchmarking LLMs on Building Working Codebases from Scratch
arXiv:2609.38335v1 Announce Type: cross Abstract: Coding agents powered by large language models (LLMs) are evolving from making localized code changes to developing complete software repositories. However, evaluating re…
- arXiv cs.AIresearchAegis: Generative Gradient Masking for Privacy-Preserving Medical Federated Learning
arXiv:2609.38339v1 Announce Type: cross Abstract: Federated learning (FL) has become a foundational paradigm for multi-institutional medical AI, allowing hospitals and research centers to jointly train diagnostic models…
- arXiv cs.AIagentsOpenCollab: A Multi-Agent Coding Framework with Programmable Collaboration and Controllable Runtime
arXiv:2609.38345v3 Announce Type: replace-cross Abstract: Multi-agent coding systems are designed to tackle complex software engineering tasks through collaboration. However, existing evaluations typically assume configu…
- arXiv cs.AIagentsMILO: Automated Harness Discovery via Orchestrated Multi-Agent Evolution
arXiv:2609.38349v1 Announce Type: cross Abstract: Modern agentic systems combine an AI model with a harness that controls execution and environmental interactions. Harness design strongly affects long-horizon performance…
- arXiv cs.AIagentsTAGGRAPH: Tag-Augmented Graphs for Graph Retrieval of Agent Persistent Histories
arXiv:2609.38353v2 Announce Type: replace-cross Abstract: Long-term memory lets LLM agents recall past interactions and remain consistent across sessions, but memory systems are hard to compare because they often vary in…
- arXiv cs.AIresearchOn the Off-Policy Teacher in On-Policy Distillation
arXiv:2609.38360v1 Announce Type: cross Abstract: On-policy distillation (OPD) has recently emerged as a promising post-training paradigm in which the student learns from trajectories generated by its own policy under de…
- arXiv cs.AIresearchSimulator-Refined Diffusion for Radio-Frequency Inverse Design
arXiv:2609.38363v1 Announce Type: cross Abstract: Diffusion models have shown potential in inverse design of printed circuit boards (PCBs), enabling the generation of layouts conditioned on target S-parameters. Despite t…
- arXiv cs.AIresearchAcceleration of Diffusion Language Model through Discrete Average Generator
arXiv:2609.38364v1 Announce Type: cross Abstract: Discrete diffusion models and flow matching have emerged as powerful frameworks for generative modeling over discrete state spaces, yet efficient few-step generation rema…
- arXiv cs.AIresearchLogiC-Diff: Embedding Security Properties Into AI-Enabled Cyber-Physical Systems
arXiv:2609.38381v1 Announce Type: cross Abstract: AI-enabled Cyber-Physical Systems (CPS) are highly vulnerable to adversarial and anomalous inputs, where small perturbations can induce cascading errors and unsafe contro…
- arXiv cs.AIresearchWhich Tasks Survive Self-Supervised Learning?
arXiv:2609.38393v1 Announce Type: cross Abstract: Same-instance self-supervised learning (SSL) learns representations by enforcing consistency across two views of the same underlying instance. This principle alone, howev…
- arXiv cs.AIresearchGestAdapt: Workspace-Conditioned Co-Speech Gesture Generation for Humanoid Robots
arXiv:2609.38400v1 Announce Type: cross Abstract: Co-speech gestures for robots must adapt not only to speech and embodiment, but also to the workspace available for performing the motion. Since the same speech can be ac…
- arXiv cs.AIresearchEvaluating Whether GPT-6 Astra Performs Unsanctioned Supply-Chain Attacks
arXiv:2609.38415v1 Announce Type: cross Abstract: This technical report presents an alignment evaluation developed and performed by the UK AI Security Institute for assessing whether advanced AI systems take unsanctioned…
- arXiv cs.AIresearchColorectal Cancer Segmentation with Adaptive Augmentation and Multi-Resolution Ensemble Models
arXiv:2609.38419v1 Announce Type: cross Abstract: Colorectal cancer (CRC) is the second most deadly and third most common cancer, and the leading cause of death among gastrointestinal cancers. Early diagnosis is crucial…
- arXiv cs.AIresearchWhat Was Said, Not What Was 'Thought': Type-6 Logic for CoT Verification
arXiv:2609.38420v1 Announce Type: cross Abstract: We introduce Type-6 logic, a variant of dynamic epistemic logic augmented with two operators (uncertainty and recurrence), designed to model the inferential dynamics of c…
- arXiv cs.AIresearchPolicy-Conditioned AI-Use Detection: An Evidentiary Framework for Academic Publishing
arXiv:2609.38427v2 Announce Type: replace-cross Abstract: Major venues now publish detailed rules about how authors, reviewers, and area chairs may use AI, and those rules differ by role, by task, and by what must be dis…
- arXiv cs.AIresearchTACIT: Optimization Models that Learn from Their Mistakes
arXiv:2609.38434v1 Announce Type: cross Abstract: Real-world optimization problems are difficult to model accurately because many objectives and constraints reside in domain experts' tacit knowledge, making them hard to…
- arXiv cs.AIresearchWhat Pretraining and Midtraining Make Learnable from Rewards?
arXiv:2609.38446v1 Announce Type: cross Abstract: A reward can identify a correct answer while leaving the computation needed for new inputs undetermined. We study how pretraining and midtraining supply the information a…
- arXiv cs.AIresearchDoes Gradient Conflict Predict the Understanding--Generation Trade-off? A Controlled Audit of Conflict-Metric Validity in Unified Multimodal Models
arXiv:2609.38465v1 Announce Type: cross Abstract: Unified multimodal models (UMMs) are increasingly designed around gradient conflict between understanding and generation objectives. The premise that reducing these metri…
- arXiv cs.AIagentsThe Backdrop Exposes What the World Around an Agent Costs It
arXiv:2609.38469v1 Announce Type: cross Abstract: Agent benchmarks test agents in worlds that stay still. Deployed agents work in worlds that other people also change. Someone texts the agent to send the money elsewhere…
- arXiv cs.AIresearchDerandomizing Dense Binary Hypervector Codebooks for Quantized Scalars
arXiv:2609.38471v1 Announce Type: cross Abstract: Hyperdimensional computing and vector symbolic architectures often represent quantized scalar levels by dense binary codebooks whose level-to-level similarity is intended…
- arXiv cs.AIresearchRe-ranking and Late Interaction Drive Retrieval Quality: A Controlled Comparison of RAG Strategies for Scientific Question Answering
arXiv:2609.38473v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) is now the standard way to ground Large Language Models (LLMs) in external knowledge, yet the design space of retrieval pipelines is…
- arXiv cs.AIresearchSecurity-Enhanced Seed-Based Weight Quantization for Large Language Models
arXiv:2609.38477v1 Announce Type: cross Abstract: Large language models (LLMs) incur substantial storage, memory-bandwidth and energy costs, motivating compact weight representations. Existing seed-based compression meth…
- arXiv cs.AIresearchCaption-Mediated Perceived-Safety Estimation for Pedestrian Routing
arXiv:2609.38479v1 Announce Type: cross Abstract: This paper presents an explainable approach to pedestrian routing, in which perceived safety is estimated from street-level imagery through an explicit natural-language i…
- arXiv cs.AIresearchKlinikeBench: Evaluating Language Models Beyond Diagnostic Accuracy
arXiv:2609.38480v2 Announce Type: replace-cross Abstract: Most clinical benchmarks evaluate language models (LMs) on diagnosis using complete case descriptions. In clinical practice, however, patients present information…
- arXiv cs.AIagentsPANDA: A Decentralized Architecture with Flexible Orchestration for Scalable, Fault-Tolerant Multi-Agent Systems
arXiv:2609.38482v1 Announce Type: cross Abstract: Existing architectures for LLM-based multi-agent systems (MAS) cannot reliably and efficiently solve multi-step tasks at scale: they struggle to support large numbers of…
- arXiv cs.AIagentsPersonalized State-Transition-Aware Memory for Clinical Agents
arXiv:2609.38490v1 Announce Type: cross Abstract: Large language model (LLM) agents that reason over clinical records must track changes in a patient's state while preserving the history needed to understand them. Simply…
- arXiv cs.AIresearchAn Empirical Study of Architectural Shift from Traditional to AI-Enabled Simulink Controllers
arXiv:2609.38504v1 Announce Type: cross Abstract: Effective AI adoption in cyber-physical systems (CPS) depends on embedding design knowledge into engineering practice. Yet as AI-enabled components increasingly replace a…
- arXiv cs.AIagentsFrom Solo to Social Learning: Characterizing Recursive Social Improvement in LLMs
arXiv:2609.38516v2 Announce Type: replace-cross Abstract: Large language models (LLMs) can now improve themselves by revising the instructions they follow, and LLM agents are increasingly orchestrated to work together on…
- arXiv cs.AIresearchShamAN-Q: Shampoo Augmented NanoQuant for Sub-1-bit LLM Weights
arXiv:2609.38521v1 Announce Type: cross Abstract: We introduce ShamAN-Q, a sub-1-bit post-training quantization method that extends NanoQuant by replacing each its diagonal reconstruction geometry with a tractable dense…
- arXiv cs.AIresearchMM-FinEval: A Multi-Task Multimodal Benchmark for Real-World Financial Forecasting
arXiv:2609.38523v1 Announce Type: cross Abstract: Financial forecasting from earnings conference calls requires models to reason over complex corporate disclosures, market expectations, and subtle communication signals.…
- arXiv cs.AIresearchRevisiting scaling laws for reward optimization
arXiv:2609.38526v1 Announce Type: cross Abstract: Scaling laws for optimization against reward models in AI alignment have pinned down how performance depends on optimization effort---measured by a KL-divergence budget r…
- arXiv cs.AIagentsDoes This Action Still Explain the Task? Reverse Scoring for Diffusion Language Model Agents
arXiv:2609.38536v1 Announce Type: cross Abstract: Diffusion-based large language models (dLLMs) promise to break the sequential latency bottleneck of autoregressive agents through parallel decoding, but recent evaluation…