AI news archive.
10,660 articles filed under Research, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchStochastic World Models for Verifying Vision-Based Neural Feedback Systems
arXiv:2609.38120v1 Announce Type: new Abstract: Verifying a vision-based neural feedback system requires a model of the observations its controller acts upon. Such a model must capture the variation the sensor produces,…
- arXiv cs.AIresearchAdviSD: Learning to Advise Frontier LLMs via Targeted Multi-Turn Self-Distillation
arXiv:2609.38142v1 Announce Type: new Abstract: A small trainable advisor can steer a frozen language-model executor using natural-language advice. In addition to learning from task rewards, the advisor can use feedback…
- arXiv cs.AIresearchBathtubs, Boundaries, and Sandboxes: AI Regulatory Learning under Legal Uncertainty
arXiv:2601.04094v4 Announce Type: cross Abstract: Effective regulation of AI is a defining policy challenge, driven by their integration into all aspects of society. To remain responsive to their rapid development and em…
- arXiv cs.AIresearchSage: Formalization with Semantic Correction
arXiv:2609.35790v2 Announce Type: replace-cross Abstract: While neural theorem provers have achieved impressive milestones in formal mathematics, they largely operate on the assumption that faithful Lean 4 formal stateme…
- arXiv cs.AIresearchCalibration-First Cross-Cohort Multimodal Temporal Learning for Transferable Asthma-Risk Forecasting
arXiv:2609.35795v1 Announce Type: cross Abstract: Asthma deterioration forecasting must remain reli- able when patient populations, sensor ecosystems, and available modalities change across cohorts. Existing models commo…
- arXiv cs.AIresearchBinarization Flattens the Score Space
arXiv:2609.35797v2 Announce Type: replace-cross Abstract: Large language model (LLM) judges are often used as rewards to train policies on objectives that deterministic verifiers cannot capture. However, these rewards ar…
- arXiv cs.AIresearchAlignment Forecasting: Predicting Misalignment From Training Data
arXiv:2609.35805v2 Announce Type: replace-cross Abstract: Training a language model on data with a narrow flaw can sometimes make the model broadly misaligned. Inspecting the data at face value often does not settle whet…
- arXiv cs.AIresearchCan Multimodal Large Language Models Generate and Detect Multimodal Social Media Fake News?
arXiv:2609.35809v1 Announce Type: cross Abstract: The rapid advancement of generative AI raises concerns about the misuse of Multimodal LLMs (MLLMs) for large-scale disinformation campaigns on social media. Despite exist…
- arXiv cs.AIresearchTRACE: Deployable Tree-Relational Structure Enhancement for Oncology LLMs
arXiv:2609.35810v1 Announce Type: cross Abstract: Large language models are increasingly used in oncology applications, but their predictions are often weakly grounded in explicit medical structure. We present TRACE, a d…
- arXiv cs.AIresearchHow to Run Statistics over LLM Judges and Trust the Results: Calibrated Inference for Small-Sample AI Evaluation with evalstats
arXiv:2609.35815v1 Announce Type: cross Abstract: Researchers across academia increasingly base significance claims on LLM judge scores and small-sample AI evaluations. Yet without well-calibrated confidence intervals (C…
- arXiv cs.AIresearchLess Uniform Discrete Diffusion is More Powerful and Scalable
arXiv:2609.35817v1 Announce Type: cross Abstract: Although uniform diffusion language models (UDLMs) represent a promising diffusion paradigm, scaling them remains challenging. We identify the core obstacle as an over-un…
- arXiv cs.AIresearchWhen Should LLMs Trust Their Own Revisions? A Risk-Aware Study of Intrinsic Self-Correction
arXiv:2609.35832v1 Announce Type: cross Abstract: Intrinsic self-correction asks a language model to revise its own answer without receiving new external evidence. A second pass can recover mistakes, but it can also over…
- arXiv cs.AIresearchEstimation of Room Impulse Responses from Handclaps
arXiv:2609.35839v1 Announce Type: cross Abstract: Handclaps provide an equipment-free excitation for room acoustics, but their unknown and variable source waveform makes room impulse response (RIR) estimation challenging…
- arXiv cs.AIresearchBeyond Rule-Based Mutation Testing: Test-Aware Mutant Generation Using Large Language Models
arXiv:2609.35841v1 Announce Type: cross Abstract: Mutation testing evaluates test-suite adequacy by injecting synthetic faults into program code. However, traditional rule-based tools often generate large numbers of triv…
- arXiv cs.AIresearchPosition: Let's Strengthen Verifiability If We Can't Enforce Reproducibility
arXiv:2609.35854v1 Announce Type: cross Abstract: In the field of Machine Learning, many papers contain empirical results supporting claimed statements or illustrating the performance of a proposed method. However, most…
- arXiv cs.AIresearchMara Chain: Rethinking Failure as a Stepping Stone for AI System Auto-Evolution
arXiv:2609.35855v1 Announce Type: cross Abstract: Optimizing deployed AI systems increasingly amounts to editing prompts, skills, harnesses, and code rather than model weights. Existing approaches commonly optimize these…
- arXiv cs.AIresearchBeyond Keywords: Leveraging Generative LLMs and Label Aggregation to Classify Economic Policy Uncertainty in News Articles
arXiv:2609.35856v1 Announce Type: cross Abstract: This research describes the adaptation of Large Language Models (LLMs) for economic monitoring in the public sector to automatically determine whether an article discusse…
- arXiv cs.AIresearchThe Detectability Gap: Hidden Heterogeneity in Hallucination Detection Across Language Models
arXiv:2609.35860v1 Announce Type: cross Abstract: Sampling based consistency is widely used for hallucination detection, yet aggregate performance can conceal systematic differences in which errors are detectable. This w…
- arXiv cs.AIresearchPACT: Pairwise-Anchored Calibrated Tuning for Single-Token Typed Decisions
arXiv:2609.35865v1 Announce Type: cross Abstract: Single-token typed-decision models answer a schema question by reading the logits of a few one-letter answer codes at a single position: they are fast and return a probab…
- arXiv cs.AIresearchCruxBench: A Benchmark of Information Discovery
arXiv:2609.35879v1 Announce Type: cross Abstract: Benchmarks for large language models (LLMs) typically evaluate the accuracy of answers against fixed reference labels. But a central step in many complex real-world tasks…
- arXiv cs.AIresearchSimilarity Is Not Validity: Defending LLM Semantic Caches Against Poisoning
arXiv:2609.35908v1 Announce Type: cross Abstract: Semantic caches reduce LLM serving costs by reusing previously generated answers for semantically similar queries. However, retrieval is based solely on embedding similar…
- arXiv cs.AIresearchUNBIND: UNlearning By INference-time Directional Steering for Code LLMs
arXiv:2609.35913v1 Announce Type: cross Abstract: Code large language models acquire programming capabilities from large code corpora, but can also memorize implementations that later require removal. Code unlearning is…
- arXiv cs.AIresearchNormative Loss Landscape Navigation: A Trajectory-Based Approach to Mitigating Forgetting in Incremental Learning
arXiv:2609.35926v1 Announce Type: cross Abstract: Continual learning models suffer from catastrophic forgetting when trained sequentially on non-stationary data distributions. Previously, this has been addressed through…
- arXiv cs.AIresearchGraph neural networks for sampling-invariant embeddings of organized signal sets
arXiv:2609.35934v1 Announce Type: cross Abstract: Sensor networks and radars can deliver signals as organized sets, e.g. ordered signals, signals describing range cells within a grid or signals perceived as graph nodes.…
- arXiv cs.AIresearchIntrinsic Associative Memory on Riemannian Manifolds: Curvature, Capacity, and Emergent Modes
arXiv:2609.35948v1 Announce Type: cross Abstract: Geometry does more than constrain an associative memory: curvature determines what it remembers and which states it creates. We develop intrinsic dense associative memori…
- arXiv cs.AIresearchHEAR: Real Voices, Real Bias: A Large-Scale Human-Recorded, Demographically Diverse Benchmark for Audio Language Models
arXiv:2609.35952v1 Announce Type: cross Abstract: We introduce HEAR (Human-recorded Evaluation of Audio-LLM bias by Real speakers), a large-scale, ecologically valid benchmark comprising 87k real human audio samples from…
- arXiv cs.AIresearchROSS: Relearning from Self-Generated Rollouts through Selective Supervision
arXiv:2609.35954v2 Announce Type: replace-cross Abstract: Large language model post-training generates self-generated rollouts through reinforcement learning and on-policy distillation, yet this experience is often treat…
- arXiv cs.AIresearchCausal and Interpretable Structures in LLM Compositional Tasks
arXiv:2609.35970v1 Announce Type: cross Abstract: Large language models are able to solve tasks whose answers depend on not only individual input tokens, but also on relations among them. How is such relational informati…
- arXiv cs.AIresearchInfrared Subtraction with Artificial Intelligence
arXiv:2609.36007v3 Announce Type: replace-cross Abstract: We present AI-developed local infrared subtraction, building on projection to Born and EFT matching. The framework separates an integrable radiation term from a f…
- arXiv cs.AIresearchTORQUE: Optimizing What (not) to Quantize Before and After Rotation
arXiv:2609.36032v1 Announce Type: cross Abstract: Uniform random rotations are an effective preprocessing step for quantization: they make normalized coordinate distributions approximately Gaussian, enabling the use of c…
- arXiv cs.AIresearchNeural networks for spectral optimization
arXiv:2609.36047v1 Announce Type: cross Abstract: Given a functional dependent on the spectrum of a differential operator, we address the problem of finding a domain which optimizes this functional. PDE solvers might be…
- arXiv cs.AIresearchImproving scalable oversight with co-trained monitors
arXiv:2609.36049v1 Announce Type: cross Abstract: Worker-monitor setups are a promising approach to AI oversight, but training workers against fixed monitors can incentivize monitor evasion. We study whether this failure…
- arXiv cs.AIresearchWhat if automating AI R&D triggers an intelligence explosion?
arXiv:2609.36054v2 Announce Type: replace-cross Abstract: In contrast to even a year ago, AI systems now write most of the code inside the companies that build them. As more of the AI research and development (R&D) pipel…
- arXiv cs.AIresearchUnderstanding Decision-Making Mechanisms in Neural Routing Solvers
arXiv:2609.36063v1 Announce Type: cross Abstract: Neural Combinatorial Optimization (NCO) has achieved strong empirical success, yet the internal mechanisms driving model decisions remain largely unexplored. In this pape…
- arXiv cs.AIresearchFLOORA: A Human-Aligned Domain-Specific Language Model for Architectural Design
arXiv:2609.36064v1 Announce Type: cross Abstract: Foundation models are powerful generators, but many engineering domains require structured representations that general-purpose systems handle poorly. We introduce FLOORA…
- arXiv cs.AIresearchThe Uneven Decline of Collective Knowledge Production: Evidence from Stack Overflow After Generative AI
arXiv:2609.36069v1 Announce Type: cross Abstract: Generative AI (Gen AI) is reshaping how individuals learn and work, but its consequences for collective knowledge, the shared body of knowledge that online communities pr…
- arXiv cs.AIresearchMeasuring trainable degrees of freedom in materials graph neural networks: a random-subspace intrinsic dimension analysis
arXiv:2609.36084v1 Announce Type: cross Abstract: Final predictive accuracy is the standard basis for comparing graph neural networks (GNNs) in materials-property prediction, but it does not show how strongly performance…
- arXiv cs.AIresearchPHASE: A Physiology-Guided Hierarchical Foundation Model for Intracranial EEG
arXiv:2609.36087v2 Announce Type: replace-cross Abstract: Clinicians and neuroscientists have long analyzed intracranial electroencephalography (iEEG) through directly measurable physiological characteristics, which carr…
- arXiv cs.AIresearchOne Geometry, Different Outcomes: Readout-Dependent Effects of the Modality Gap in Vision-Language Models
arXiv:2609.36101v1 Announce Type: cross Abstract: Contrastive vision-language models learn shared embedding spaces by aligning matched image-text pairs, yet their representations remain separated by a modality gap. Prior…
- arXiv cs.AIresearchLoopICL: Looping a single transformer block to solve tabular tasks
arXiv:2609.36108v1 Announce Type: cross Abstract: Tabular foundation models using in-context learning have recently surpassed gradient-boosted trees on predictive tabular tasks. However, recent mechanistic insights sugge…
- arXiv cs.AIresearchThinQuant: Scalable Rotation Learning for Weight and Activation Quantization of LLMs
arXiv:2609.36120v1 Announce Type: cross Abstract: Learned rotations play an important role in enabling low-bit weight and activation quantization of large language models by smoothing outliers in the activation distribut…
- arXiv cs.AIresearchRender Before Reading: Visual Rendering as a Prompt Injection Defense
arXiv:2609.36121v1 Announce Type: cross Abstract: Large language models are vulnerable to prompt injection attacks, where third-party adversarial content can hijack the model's behavior. In this paper, we study the role…
- arXiv cs.AIresearchReasoning with Neural Cellular Automata
arXiv:2609.36126v1 Announce Type: cross Abstract: Modern AI architectures used to solve visual reasoning tasks typically rely heavily on global connectivity and synchronization. As biological systems demonstrate, though,…
- arXiv cs.AIresearchAccessible, but Not Adopted: Increasing LLM Adoption among First-generation, Low-income (FGLI) College Students beyond Expanding Access
arXiv:2609.36129v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly positioned as a force to empower underserved communities, and significant efforts are being made to expand access. Yet, acce…
- arXiv cs.AIresearchEncoder-Sharing Hierarchical Federated Multi-Task Learning for VANETs
arXiv:2609.36157v1 Announce Type: cross Abstract: Most federated learning frameworks for vehicular ad hoc networks assume that all vehicles collaboratively train a single model for a common task. This assumption limits t…
- arXiv cs.AIresearchAdversarial Debiasing of Machine Learning Models for Enhanced Network Security against DDoS Attacks
arXiv:2609.36167v1 Announce Type: cross Abstract: Distributed Denial of Service attacks are a growing threat to network infrastructure, and new techniques, including the use of generative AI, make them harder to detect.…
- arXiv cs.AIresearchDraft in Parallel, Condition Through Depth: Adjacent Causal Injection for Speculative Decoding
arXiv:2609.36173v2 Announce Type: replace-cross Abstract: Parallel speculative drafting generates multiple candidates in one backbone pass, but independent token selection can produce inconsistent continuations that shor…
- arXiv cs.AIresearchPreviewDiff: Multimodal Critic-Guided Search over Diffusion Latents
arXiv:2609.36199v1 Announce Type: cross Abstract: Diffusion models can produce striking images and videos, but they still struggle with the compositional details that make a generation faithful to a prompt, such as objec…
- arXiv cs.AIresearchRepresentable but Unlearned: Encoding Rank and the Interaction-Prediction Floor
arXiv:2609.36208v1 Announce Type: cross Abstract: Input encodings can restrict which measured contrasts a predictor can jointly reproduce, even when no single contrast is forced to vanish. We compute the attainable contr…
- arXiv cs.AIresearchCineSubBench: Evaluating LLMs on Long-Form Narrative and Cultural Understanding from Multilingual Movie Subtitles
arXiv:2609.36218v1 Announce Type: cross Abstract: Large language models are increasingly evaluated in specialized domains such as law, medicine, software engineering, and cybersecurity, yet film remains comparatively und…