AI news archive.
10,659 articles filed under Research, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchMonitor Jailbreaking: Evading Chain-of-Thought Monitoring Without Encoded Reasoning
arXiv:2609.31121v1 Announce Type: new Abstract: Chain-of-thought (CoT) monitoring is a promising safety technique for reasoning models, enabling detection of problematic reasoning before models act. A key concern is enco…
- arXiv cs.AIresearchAtomWorld-Mem: Memory-Restored World States for Long-Horizon Atomistic Evolution
arXiv:2609.31133v3 Announce Type: replace Abstract: High-fidelity atomistic evolution over long timescales requires more than observing the current crystal configuration. Instantaneous atomistic snapshots are often incom…
- arXiv cs.AIresearchCan Linguistic Reasoning Vectors Enhance Multimodal Reasoning Ability?
arXiv:2609.31140v1 Announce Type: new Abstract: Most Vision-Language Models (VLMs) are built by extending pretrained Large Language Models (LLMs) with visual modules and multimodal alignment. However, this multimodal sca…
- arXiv cs.AIresearchNeural State Prediction: Obstructing Shortcut Learning in EEG Foundation Models
arXiv:2609.31167v1 Announce Type: new Abstract: EEG foundation models increasingly use masked prediction to learn from unlabeled recordings, but optimizing this objective does not ensure transferable neural representatio…
- arXiv cs.AIresearchSPO: Discovering Adaptive Large Neighborhood Search Operators via Stackelberg Program Optimization
arXiv:2609.31179v1 Announce Type: new Abstract: Large neighborhood search (LNS) relies critically on destroy and repair operators, whose effectiveness depends on both adaptation to the evolving LNS state and interaction…
- arXiv cs.AIresearchAccounting for Bias Enables Sustainable LLM Evaluation
arXiv:2609.31184v1 Announce Type: new Abstract: LLM-as-a-judge has become the de facto standard for scalable, subjective evaluation, yet current leaderboards compensate for systematic measurement bias by running ever mor…
- arXiv cs.AIresearchSamples, Sources, Space: Decomposing Data Scale in Spatially Structured Representation Learning of Human Brain Microarchitecture
arXiv:2609.31201v1 Announce Type: new Abstract: Scaling studies typically represent training data by a single count of samples. For hierarchically and spatially structured data, however, the same number of samples can be…
- arXiv cs.AIresearchWhich Influence Are We Estimating? The Role of Counterfactual Specifications in Data Attribution
arXiv:2609.31214v1 Announce Type: new Abstract: Estimating the influence of training examples on model behavior is essential for data debugging, valuation, and attribution. Existing influence estimators often produce inc…
- arXiv cs.AIresearchDIAL: Position-Debiased LLM Judges with Adaptive Human Preference Calibration
arXiv:2609.31215v1 Announce Type: new Abstract: Large language models (LLMs) as a judge enable scalable evaluation, but their judgments can be sensitive to response order and, even after removing such position effects, c…
- arXiv cs.AIresearchPurin: A Biology-inspired Mechanism for Artificial Neural Networks
arXiv:2609.31235v1 Announce Type: new Abstract: Artificial neural networks (ANNs) usually represent neural transmission with fixed trainable weights during a training batch, which omits short-term changes in synaptic eff…
- arXiv cs.AIresearchThe Right Information Extraction Pipeline Depends on the Document: Accuracy-Energy Trade-offs for Small, Local Models
arXiv:2609.31341v1 Announce Type: new Abstract: Whether an information extraction pipeline should process page images or parsed text depends on the document, and the answer flips across the layout spectrum. We study this…
- arXiv cs.AIresearchMutable Transcripts: Mitigating Context Pollution through Editable Conversation State
arXiv:2609.31354v1 Announce Type: new Abstract: Contemporary large language model (LLM) chat systems treat conversation history as an immutable sequence of turns that defines the model's working context. However, user in…
- arXiv cs.AIresearchPrograms-of-Layers in LLMs through the Lens of Cortical Areas
arXiv:2609.31360v1 Announce Type: new Abstract: Inference in LLMs is conventionally a fixed-depth, fixed-order forward pass through every layer, regardless of how difficult the input is. The human brain does not work thi…
- arXiv cs.AIresearchGame Arena: Strategic LLM Evaluation in Competitive Environments
arXiv:2609.31473v1 Announce Type: new Abstract: We introduce Kaggle Game Arena, an open and ever-expanding platform to evaluate large language models (LLMs) through competitive games. Different from static benchmarks, ga…
- arXiv cs.AIresearch"AI is (not) the new...": A Diagnostic Analogy Framework for Generative AI's Cultural Impacts
arXiv:2609.31482v1 Announce Type: new Abstract: Generative AI is reshaping the cultural infrastructures through which knowledge is found, synthesized, and held accountable. To make sense of this shift, scholars and polic…
- arXiv cs.AIresearchUQ-LOB: Uncertainty-Aware Limit Order Book Mid-Price Forecasting
arXiv:2609.31491v2 Announce Type: replace Abstract: Forecasting short-horizon mid-price movements from limit order book (LOB) data is central to algorithmic trading, yet most deep LOB forecasters are point predictors: th…
- arXiv cs.AIresearchPrompt Minimization: Reducing Input Redundancy Without Sacrificing Output Fidelity
arXiv:2609.31505v1 Announce Type: new Abstract: Despite the growing capabilities of large language models (LLMs), prompt design remains largely heuristic and ad hoc. This project will explore $\textit{prompt minimization…
- arXiv cs.AIresearchA Flow Matching Framework for Neural Representational Dissimilarity
arXiv:2609.31544v1 Announce Type: new Abstract: Neural representational dissimilarity quantifies differences between neural response distributions, and is essential for comparing neural codes across stimuli, brain areas,…
- arXiv cs.AIresearchLearning to Stop without Learning to Stop: Self-Supervised Confidence Training Improves Reasoning Efficiency
arXiv:2609.31619v1 Announce Type: new Abstract: Reasoning models often generate very long reasoning traces, making inference computationally expensive. Existing approaches typically improve efficiency either through infe…
- arXiv cs.AIresearchENAS: An Efficient Hardware-Aware Neural Architecture Search Framework for TinyML on Resource-Constrained Microcontrollers
arXiv:2609.30272v1 Announce Type: cross Abstract: We present \textbf{ENAS}, a hardware-aware Neural Architecture Search (NAS) framework that combines a static feasibility check, a cell-based search space supporting stand…
- arXiv cs.AIresearchWhen Does Advection-Aware Graph Nowcasting Help? A Controlled Study of Distributed Solar Ramp Forecasting with a Self-Supervised Cloud-Motion Estimator
arXiv:2609.30286v1 Announce Type: cross Abstract: Short-term forecasting of cloud-induced power ramps across a network of distributed photovoltaic (PV) or irradiance sensors is a recognised pain point for grid operators.…
- arXiv cs.AIresearchA Mechanistic Study of AI-Text Detection Neurons in Frozen BERT: Sparse Probing and Activation Patching on RAID
arXiv:2609.30287v1 Announce Type: cross Abstract: AI-generated text detectors achieve high accuracy on standard benchmarks, yet the internal representations that drive these predictions remain poorly understood. We study…
- arXiv cs.AIresearchA Survey on Fake Review Detection: From Pre-trained Language Models to Large Language Models
arXiv:2609.30292v1 Announce Type: cross Abstract: Online reviews shape consumer decisions, platform governance, and corporate reputation.Fake reviews compromise this information channel by injecting deceptive evidence in…
- arXiv cs.AIresearchSlideLab: Audience-Centered Scientific Slide Generation and Evaluation
arXiv:2609.30294v2 Announce Type: replace-cross Abstract: Scientific presentations are more than summaries of research papers. They need to present the work in a coherent sequence, explain the main ideas clearly, and hel…
- arXiv cs.AIresearchSignTrace: Describe a Sign, Find the Word
arXiv:2609.30295v1 Announce Type: cross Abstract: Identifying an unfamiliar sign is difficult when a learner remembers its movement but does not know its meaning or formal feature codes. SignTrace addresses this longstan…
- arXiv cs.AIresearchAdaptive multi-resolution Gaussian processes: Scalable exact inference with naturally data-sparse covariance matrices
arXiv:2609.30348v1 Announce Type: cross Abstract: Gaussian processes constitute a cornerstone of probabilistic machine learning, yet scaling them to large datasets typically forces a trade-off between computational effic…
- arXiv cs.AIresearchStrategic Self-Consistency
arXiv:2609.30352v1 Announce Type: cross Abstract: Self-consistency has become a popular technique for enhancing the reasoning abilities of large language models by generating multiple reasoning paths and selecting the fi…
- arXiv cs.AIresearchCost-Aware Best-LLM Identification using Dueling Feedback
arXiv:2609.30360v1 Announce Type: cross Abstract: Inspired by the problem of identifying the best model from a collection of large language models (LLMs) with heterogeneous querying costs, we formulate and analyse a vari…
- arXiv cs.AIresearchDanLing NestedTensor: Composable Multi-Ragged Tensors for Deep Learning
arXiv:2609.30379v1 Announce Type: cross Abstract: Variable-size inputs are common in deep learning, but dense batching allocates a shared envelope and spends computation on padding. The cost multiplies across varying axe…
- arXiv cs.AIresearchWhat Improves Multimodal Misinformation Detection? Answers from a Large-Scale Empirical Study
arXiv:2609.30402v1 Announce Type: cross Abstract: Multimodal misinformation is increasingly crafted to look convincing by pairing a textual claim with an image that appears to "prove" it. Yet in practice, building effect…
- arXiv cs.AIresearchA Unified Account of Concepts and Chunks
arXiv:2609.30414v2 Announce Type: replace-cross Abstract: Cognitive psychology has studied how people encode, use, and learn concepts that describe categories, and how they represent, recognize, and acquire chunks for fa…
- arXiv cs.AIresearchUnderstanding Perturbed Parameter Ensemble Sensitivities Using A Contrastive Learning Approach
arXiv:2609.30420v1 Announce Type: cross Abstract: Perturbed parameter ensembles (PPEs) reveal how physics parameters affect climate simulations, but interpreting parameter sensitivities across multivariate, spatially str…
- arXiv cs.AIresearchActively Resolving Contextual Uncertainty for Underspecified Tasks in Natural Language
arXiv:2609.30428v1 Announce Type: cross Abstract: Foundation models provide robots with the ability to interpret natural language and reason about environmental context, yet most language-conditioned policies assume that…
- arXiv cs.AIresearchA Benchmarking Framework for Context-aware XR Interfaces
arXiv:2609.30466v1 Announce Type: cross Abstract: Everyday Extended Reality (XR) systems aim to provide context-aware access to the right functionalities at the right time and place, with minimal manual reconfiguration a…
- arXiv cs.AIresearchBreaking Homogeneity: Diversifying Persona Sets for Creative LLM Outputs
arXiv:2609.30492v1 Announce Type: cross Abstract: Language models often produce homogeneous responses to open-ended tasks; such homogeneity can spawn groupthink-the convergence of ideas toward a singular and potentially…
- arXiv cs.AIresearchPolicyAttention: Softmax Attention Implements Policy Mirror Descent for Closed-Loop Control
arXiv:2609.30500v1 Announce Type: cross Abstract: Can causal softmax attention implement policy mirror descent as a repeated controller rather than a one-step algebraic identity? Negative-entropy policy mirror descent (P…
- arXiv cs.AIresearchConvergence guarantees for Muon: New parameter regimes and generalizations
arXiv:2609.30546v1 Announce Type: cross Abstract: In this paper, we establish the first asymptotic convergence guarantees for the Muon algorithm through a more accurate proxy for the Newton-Schultz iteration than the typ…
- arXiv cs.AIresearchProportional Representation in Temporal Voting with Ranked Preferences
arXiv:2609.30555v1 Announce Type: cross Abstract: We study proportional representation in temporal voting, where one candidate is selected in each round. While prior work has focused on approval ballots, we consider rank…
- arXiv cs.AIresearchAction Forcing: Training World Models on Unsupervised Video by Recovering Underlying Egomotion Bases
arXiv:2609.30595v1 Announce Type: cross Abstract: Synchronised action annotations are needed to train controllable world models and these datasets remain elusive. Existing approaches make use of instrumented platforms wi…
- arXiv cs.AIresearchMedTokenBudget: Lesion-Preserving Token Routing for Dermoscopic Image Classification
arXiv:2609.30613v1 Announce Type: cross Abstract: Dermoscopy classifiers built on Vision Transformers process all image patches uniformly, although diagnostic evidence is concentrated in the lesion region. Existing token…
- arXiv cs.AIresearchSAGE: Source-Anchored Guidance via Frequency Equalization for Hierarchical RGB-T Alignment and Fusion
arXiv:2609.30703v1 Announce Type: cross Abstract: Spatial misregistration and cross-modal discrepancies often cause ghosting, structural blurring, and content imbalance in RGB-T fusion. Existing methods typically decoupl…
- arXiv cs.AIresearchCombining General and Domain-Specific Pretext Tasks for Brain MR Image Segmentation
arXiv:2609.30708v1 Announce Type: cross Abstract: A key challenge in medical image analysis is the scarcity of large annotated datasets for specific populations and diseases. As deep learning models rely heavily on label…
- arXiv cs.AIresearchVLALight: Lightweight Vision-Language-Action Models for Emergency-Aware Traffic Signal Control
arXiv:2609.30709v1 Announce Type: cross Abstract: Traffic signal control (TSC) is essential for mitigating urban congestion. Recent advances in vision-language models (VLMs) enable richer interpretation of intersection s…
- arXiv cs.AIresearchWords Speak Louder Than Order: A Behavioral Evaluation of Gemma 4
arXiv:2609.30716v1 Announce Type: cross Abstract: When a language model receives two conflicting documents as input, how does it decide which one to prioritize? Does it rely on how the sources are framed or the presentat…
- arXiv cs.AIresearchWerracle: Sub-Cent Intra-Block AI Reflex Oracles and Flash-Loan Circuit Breakers for EVM Smart Contracts
arXiv:2609.30719v1 Announce Type: cross Abstract: Contemporary on-chain artificial intelligence (AI) encounters an intractable Von Neumann memory and latency wall. Storing static floating-point neural weight matrices ins…
- arXiv cs.AIresearchTrafficImag: A Benchmark for Counterfactual Roadside Traffic Video Generation
arXiv:2609.30722v1 Announce Type: cross Abstract: Existing roadside traffic datasets support perception, forecasting, and visual question answering, but they do not evaluate counterfactual video generation, in which a se…
- arXiv cs.AIresearchAnatomy-Aware Dexterity-Driven Design Optimization of Surgical Continuum Robots
arXiv:2609.30745v1 Announce Type: cross Abstract: Performing complex medical procedures with continuum robots requires careful selection of their geometric design parameters. The robot should have high dexterity in the s…
- arXiv cs.AIresearchBeyond the Last Truffula Tree: SustainAI - A Water-Aware, Closed-Loop Framework for Environmentally Accountable AI
arXiv:2609.30747v1 Announce Type: cross Abstract: As artificial intelligence (AI) becomes embedded in everyday life, its environmental footprint, particularly water consumption remains largely invisible. While energy and…
- arXiv cs.AIresearchNavGen: Visual Generative Models as a Scalable Data Engine for Embodied 3D Navigation
arXiv:2609.30770v1 Announce Type: cross Abstract: General-purpose robot models increasingly rely on large and diverse datasets. For embodied 3D navigation, however, existing data sources face a fundamental trade-off: sim…
- arXiv cs.AIresearchXPhysICS: Cross-Physical-Domain Threat Grounding for Industrial Control Systems Security
arXiv:2609.30805v2 Announce Type: replace-cross Abstract: Industrial control system attacks are usually documented in terms of the plant where they occurred: its sensors, actuators, process stages, and control logic. Yet…