AI news archive.
19,861 articles, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchFrom Benchmarks to Production: Transferring Time Series Anomaly Detection Methods for Electricity Production Monitoring
arXiv:2609.39257v1 Announce Type: cross Abstract: Accurate forecasting of electricity production is essential for maintaining the operational efficiency and strategic planning of energy utilities. In industrial settings,…
- arXiv cs.AIresearchA Time-Aware Bag-of-Receptive-Fields for Interpretable Irregular Time Series Classification
arXiv:2609.39268v1 Announce Type: cross Abstract: Irregular time series, characterized by non-uniform sampling intervals, missing observations, and variable lengths, are ubiquitous in healthcare, mobility, and environmen…
- arXiv cs.AIresearchFaithful Dual-constrained Erasure for Robust LLM Safety Alignment
arXiv:2609.39279v1 Announce Type: cross Abstract: Machine unlearning has emerged as a crucial mechanism for removing hazardous knowledge and enforcing safety alignment in Large Language Models (LLMs). However, recent stu…
- arXiv cs.AIresearchEngramBench: A Capability-Grounded Benchmark for Skill-Evolution Harnesses
arXiv:2609.39284v1 Announce Type: cross Abstract: While large language models have achieved remarkable success in isolated code generation, authentic software engineering requires sustained reasoning, complex state manag…
- arXiv cs.AIagentsScale and Selection: What Makes Automatic Harness Evolution Work for Visual-Interface Robot Agents
arXiv:2609.39304v4 Announce Type: replace-cross Abstract: When an off-the-shelf coding agent is used directly as a robot policy, observing a browser-based 3D interface through screenshots and acting by posing a virtual t…
- arXiv cs.AIagentsReSAIL: Mitigating Collapse in Iterative Agent Self-Distillation
arXiv:2609.39306v1 Announce Type: cross Abstract: Iterative self-distillation enables LLM agents to learn from successive deployments, offering a path toward recursive self-improvement (RSI). Yet our experiments with exi…
- arXiv cs.AIresearchGRPO Training Dynamics for Small Language Models
arXiv:2609.39321v1 Announce Type: cross Abstract: Group Relative Policy Optimization (GRPO) has emerged as a memory-efficient reinforcement fine-tuning (RFT) technique for reasoning-intensive tasks. How- ever, GRPO train…
- arXiv cs.AIresearchHiWE: Hierarchical World Knowledge Model with Visual Keypoint Enhancement for Zero-Shot 3D Path Planning
arXiv:2609.39323v1 Announce Type: cross Abstract: Robot demonstration generation requires a system to identify where an interaction should occur, plan a feasible motion, and execute the required contact. HiWE connects th…
- arXiv cs.AIagentsNarrativeSteward: Coordinating Delegation, Guidance, and Verification in Agent-Assisted Interactive Narrative Authoring
arXiv:2609.39333v1 Announce Type: cross Abstract: Autonomous AI agents can turn authors' goals into interactive narratives by independently organizing and carrying out generation and revision. As agents generate and revi…
- arXiv cs.AIresearchWinoTS: Wavelet-based Self-Distillation for Time Series Models
arXiv:2609.39337v1 Announce Type: cross Abstract: Self-supervised pre-training of time series models is currently dominated by next-token prediction and reconstruction objectives. In continuous-valued domains, these para…
- arXiv cs.AIagentsBelief-Based Maximum Occupancy Principle and Active Inference
arXiv:2609.39342v1 Announce Type: cross Abstract: Intrinsic motivation plays a central role in adaptive and goal-directed behavior by conferring agents reward-independent objectives and biases useful to act in noisy and…
- arXiv cs.AIresearchWho Said What, and Will It Be Remembered? Evaluating Persistent Speaker Attribution Across Meetings
arXiv:2609.39344v1 Announce Type: cross Abstract: Speech transcripts used as long-term memory must preserve both words and stable speaker identities. Existing meeting-transcription metrics either ignore speakers or remap…
- arXiv cs.AIagentsHiding in Plain Sight: Decoupling Pretext from Actuation for Skill Poisoning in LLM Agents
arXiv:2609.39352v1 Announce Type: cross Abstract: LLM agents increasingly rely on reusable Skills for complex, multi-step tasks, creating a critical supply-chain attack surface where poisoned Skill content steers agent d…
- arXiv cs.AIresearchWorking Around the Compute Ceiling: Byte-Exact Memory in Galahad Makes LLM Reading a One-Time Cost LLM Reading a One-Time Cost
arXiv:2609.39358v1 Announce Type: cross Abstract: A transformer language model performs a bounded amount of computation per token, and recent work by Vishal Sikka, former CEO of Infosys, argues that this bound limits whi…
- arXiv cs.AIresearchRethinking Multi-Image Re-Representation in Multi-Image Understanding
arXiv:2609.39363v1 Announce Type: cross Abstract: Multi-image understanding requires MLLMs not only to recognise the content of individual images, but also to organise visual evidence distributed across them. We study th…
- arXiv cs.AIresearchReady2Blend: From Natural-Language Instructions to Composable Alignment Prompts
arXiv:2609.39365v2 Announce Type: replace-cross Abstract: Continual alignment requires LLMs to adapt to new requirements without forgetting previously acquired behaviors. Natural-language instructions are flexible and co…
- arXiv cs.AIresearchWavelet Flow Matching for Time Series
arXiv:2609.39374v2 Announce Type: replace-cross Abstract: Synthetic time series are increasingly used for data augmentation, privacy-preserving data sharing, and downstream model development, yet faithfully reproducing b…
- arXiv cs.AIresearchFrom Search to Signal: Online Post-Training in Automatic Heuristic Design
arXiv:2609.39383v1 Announce Type: cross Abstract: Large language model (LLM)-based automatic heuristic design (AHD) iteratively proposes and refines heuristics, pairing design rationales with executable code. Task-specif…
- arXiv cs.AIresearchTTLab at Daleel 2026: STAR-Ar, Sequence Tagging for Argument Recognition in Arabic
arXiv:2609.39385v1 Announce Type: cross Abstract: Argument Mining (AM) is a critical NLP task that remains significantly under-resourced in Arabic. This paper presents $\testtt{STAR-Ar}$, a BERT-BiLSTM-CRF architecture f…
- arXiv cs.AIresearchTowards Trustworthy AI for Glioma Diagnosis: A Task-Aware Evaluation of Uncertainty Quantification
arXiv:2609.39429v1 Announce Type: cross Abstract: Uncertainty Quantification (UQ) is a key requirement for trustworthy AI in high-stakes medical image analysis. In this work, we evaluate UQ in a multi-task Deep Learning…
- arXiv cs.AIagentsFrom Imitation to Reward Discovery: On-Policy Warmup for Agentic RL
arXiv:2609.39436v1 Announce Type: cross Abstract: Reinforcement learning with a verifiable reward (RLVR) offers a scalable approach to training language-model agents, yet sparse outcome rewards can leave early training w…
- arXiv cs.AIresearchCAST: Causal Advantage-Structured Training with Spatially Grounded Compositional Rewards for Diffusion Models
arXiv:2609.39441v1 Announce Type: cross Abstract: Online reinforcement learning has been extended to flow matching for diffusion model (DM) image generation. However, this paradigm faces three limitations: (1) Window sel…
- arXiv cs.AIagentsActionGuard: Tool Call Authorization under Poisoned Skills
arXiv:2609.39450v1 Announce Type: cross Abstract: LLM-based agents extend their capabilities through third-party skills that provide task-specific instructions, scripts, and tool-use procedures. However, malicious instru…
- arXiv cs.AIresearchFrom Speech to Editable Concepts: Probing Emotion Recognition with Concept Bottleneck Models
arXiv:2609.39453v1 Announce Type: cross Abstract: Speech emotion recognition (SER) is the task of assigning emotion labels to utterances. Early systems relied on acoustic features, whereas recent approaches combine multi…
- arXiv cs.AIresearchCAMOS: Coupled Oscillatory State-Space Model for Multimodal Clinical Time-Series
arXiv:2609.39484v1 Announce Type: cross Abstract: Longitudinal clinical cohorts are multimodal, irregularly sampled and pervasively incomplete: in ADNI, positron emission tomography and cerebrospinal fluid assays are abs…
- arXiv cs.AIresearchOmniReasoning: Pushing the Limits of Audio-Visual Joint Reasoning
arXiv:2609.39490v2 Announce Type: replace-cross Abstract: Recent advances have enabled unified omni-modal models in understanding audio, vision, and language. However, existing benchmarks, training data, and learning met…
- arXiv cs.AIresearchPartiCam: Camera Controlled Video Generation with Reward Guidance
arXiv:2609.39504v1 Announce Type: cross Abstract: We present PartiCam, a training-free Particle filtering rooted method for improved Camera controlled video generation. Generating videos that follow a precisely specified…
- arXiv cs.AIresearchA Reusable Semantic Web Framework for Evidence-Grounded Fundamental Rights Impact Assessments under the EU AI Act
arXiv:2609.39537v1 Announce Type: cross Abstract: The EU AI Act (Art. 27) requires deployers of high-risk AI systems to conduct Fundamental Rights Impact Assessments (FRIAs) before deployment, yet the evidence needed for…
- arXiv cs.AIresearchLearning Normal Diffusion Dynamics for Backdoor Defense in Text-to-Image Models
arXiv:2609.39548v1 Announce Type: cross Abstract: Backdoor attacks pose a serious threat to the secure deployment of text-to-image (T2I) diffusion models. Existing defenses typically detect backdoors from specific abnorm…
- arXiv cs.AIagentsSpeculative Safety Honeypot: Toward Proactive Defense Against Multi-turn Agent Attacks
arXiv:2609.39549v1 Announce Type: cross Abstract: As Large Language Model (LLM) agents are increasingly deployed in complex environments, multi-turn interaction attacks have become a significant security challenge. Exist…
- arXiv cs.AIresearchCandidate Retention for Abductive Learning
arXiv:2609.39561v1 Announce Type: cross Abstract: Abductive learning combines neural perception with symbolic reasoning, using explanations generated by abduction to supervise the perception model. Multiple valid explana…
- arXiv cs.AIresearchSelf-Spec Verifiable Code Generation
arXiv:2609.39568v1 Announce Type: cross Abstract: Large language models (LLMs) may generate unreliable code on corner cases missed by testing, while formal verification can provide machine-checkable guarantees. Recently,…
- arXiv cs.AIresearchSteering Fields: Adaptive Vector Fields for Safe Image Generation and Beyond
arXiv:2609.39573v1 Announce Type: cross Abstract: As state-of-the-art text-to-image flow models achieve near-photorealistic quality, controlling their outputs, e.g., suppressing harmful content while promoting benign alt…
- arXiv cs.AIresearchECHO-G: Embodied Co-speech Humanoid mOtion Generation
arXiv:2609.39575v1 Announce Type: cross Abstract: Generating full-body co-speech motion for humanoid robots requires coordinating speech prosody, linguistic content, and embodiment-specific motion. To this end, we presen…
- arXiv cs.AIresearchRobust Transfer Learning for Paper ECG Recognition
arXiv:2609.39581v1 Announce Type: cross Abstract: Paper ECG recognition is challenging because real-world ECG images vary in layout, physical artifacts, and label availability. We introduce RobECG-CL, a rank-aware contra…
- arXiv cs.AIresearchText-to-3D Policy: Fine-Grained Language-Behavior Alignment for Unseen Specification Generalization
arXiv:2609.39599v1 Announce Type: cross Abstract: 3D visuomotor policies provide a strong foundation for spatially precise manipulation, yet current text-to-3D policies struggle to follow unseen fine-grained behavioral s…
- arXiv cs.AIresearchGroundAnything: Reconciling Parallel Decoding with Precise Visual Grounding at Flash Speed
arXiv:2609.39600v2 Announce Type: replace-cross Abstract: Autoregressive (AR) grounding models serialize spatial predictions, introducing sequential latency and imposing a causal order on output tokens. We view grounding…
- arXiv cs.AIresearchGroundingPI: A Grounding Foundation Model towards Physical Intelligence with Visual Primitives
arXiv:2609.39601v2 Announce Type: replace-cross Abstract: Precise grounding matters. It specifies which object is the target and where that object is, even in clutter and for tiny objects, and it has to be fast enough fo…
- arXiv cs.AIagentsPretext: Defeating Malicious Skill Detection Frameworks for AI Agents
arXiv:2609.39607v2 Announce Type: replace-cross Abstract: Skills extend an agent's capabilities by injecting instructions and information into the context, and are widely used by agents such as OpenClaw and Claude Code.…
- arXiv cs.AIresearchD-Scope: Decomposing and Steering Diffusion Transformers with Sparse Autoencoders
arXiv:2609.39625v1 Announce Type: cross Abstract: Sparse autoencoders (SAEs) reveal visual structure in diffusion transformers (DiTs), but interpreting a feature does not establish whether it can be used to control gener…
- arXiv cs.AIresearchParameterization method of reservoir properties for ensemble-based data assimilation using intermediate latent space of StyleGAN
arXiv:2609.39626v1 Announce Type: cross Abstract: Ensemble smoothers are the most successful and efficient techniques currently available for history matching. However, because these methods rely on Gaussian assumptions,…
- arXiv cs.AIresearchFree Everywhere, Exact on Trees: PPO's Dropped Correction Buys Sample Efficiency Under Aggressive Reuse
arXiv:2609.39634v2 Announce Type: replace-cross Abstract: Common policy improvement methods, including TRPO, PPO, and GRPO, estimate policy improvement under the behavioral policy's state-visitation distribution rather t…
- arXiv cs.AIresearchZero-Compute Cross-Lingual Transferability Estimation Using Typological Feature Proxies
arXiv:2609.39640v1 Announce Type: cross Abstract: Cross-lingual transfer describes how knowledge in a source language benefits a target language. Measuring it quantitatively requires broad multilingual pre-training, as p…
- arXiv cs.AIagentsSEPAL: Separated Expert Pairs with Answer-Level Fusion for Reliable LLM Collaboration
arXiv:2609.39645v1 Announce Type: cross Abstract: Multi-agent collaboration lets large language models (LLMs) improve question answering through deliberation and feedback. Yet shared discussion couples correction with ex…
- arXiv cs.AIresearchFrom Modes to Memories: Characterizing the Scale-Space Dynamics of Diffusion Models
arXiv:2609.39648v1 Announce Type: cross Abstract: Diffusion models are typically viewed as stochastic processes that transform noise into data. We take a complementary perspective: a diffusion model defines a family of d…
- arXiv cs.AIresearchRoboCoach: World Models as Active Coaches for Compositional Robot Skills
arXiv:2609.39685v1 Announce Type: cross Abstract: Long-horizon robot manipulation reuses skills across many task compositions, but improving these compositions with additional end-to-end demonstrations is costly. A pract…
- arXiv cs.AIresearchShieldCLIP: Selective Safety Alignment for Harmful Content Mitigation in Multimodal Foundation Models
arXiv:2609.39688v1 Announce Type: cross Abstract: Multimodal encoders such as CLIP underlie many downstream systems, but their web-scale training data embed harmful associations that safety alignment must suppress withou…
- arXiv cs.AIresearchGFD-OPD: Guidance-Folded On-Policy Distillation of Diffusion Models Across Scales
arXiv:2609.39692v1 Announce Type: cross Abstract: On-policy distillation (OPD) has demonstrated two important capabilities in language models: compressing large teachers into smaller students and merging expert models in…
- arXiv cs.AIresearchWhen Masking Helps or Hurts Robustness in Compressed CLIP: A Pre-Deployment Diagnostic
arXiv:2609.39704v1 Announce Type: cross Abstract: This paper demonstrate that whether masking-based token pruning helps or hurts worst-group robustness can be predicted before deployment, without labels or fine-tuning. A…
- arXiv cs.AIresearchLet the Carrier Carry the Attack: Preserving the Subject in Adversarial Image Generation
arXiv:2609.39723v1 Announce Type: cross Abstract: Strong unrestricted adversarial attacks can distort the primary object of an image, hereafter referred to as the subject. To preserve subject integrity without compromisi…