AI news archive.
10,659 articles filed under Research, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchPulseBound: Future-Beat State Forecasting Under an Explicit Information Boundary
arXiv:2610.12010v2 Announce Type: replace Abstract: Predictive representation learning from photoplethysmography (PPG) can violate causal information access even with causal attention, as normalization, nonlocal transfor…
- arXiv cs.AIresearchInterviewPlayground: A Validated Simulation Environment for Evaluating AI Interviewers
arXiv:2610.12023v2 Announce Type: replace Abstract: Increasingly, AI interviewers are being developed to elicit open-ended responses in applications like market research, public polling, preference elicitation, and socia…
- arXiv cs.AIresearchStructure Tax: How Structured Output affects LLMs Performance
arXiv:2610.12056v1 Announce Type: new Abstract: Deploying large language models in production often requires constraining outputs to structured formats such as JSON or XML, and prior work treats the resulting accuracy lo…
- arXiv cs.AIresearchIs Memorization Context-Sensitive? Prefix-Based Extraction Beyond Isolated Prefixes
arXiv:2610.12085v1 Announce Type: new Abstract: Large language models (LLMs) can expose memorized training sequences under prefix-based extraction: given a prefix from a training example, the model may assign high probab…
- arXiv cs.AIresearchRecompose and Refine Latent Reasoning Flows for Vision-Language-Action Models
arXiv:2610.12090v1 Announce Type: new Abstract: Latent reasoning enables vision-language-action (VLA) models to transform multimodal observations into task-relevant internal states before generating continuous robot acti…
- arXiv cs.AIresearchUniversal Textual Teaching for LLMs
arXiv:2610.12114v1 Announce Type: new Abstract: Knowledge distillation (KD) transfers knowledge from stronger Teacher models to weaker Student models, but most methods require training the Student parameters, thereby bin…
- arXiv cs.AIresearchAn Investigation of Model Coherence: Narrow Finetunes Contradict Themselves Under Resampling
arXiv:2610.12129v1 Announce Type: new Abstract: A large body of research measures model coherence based on output variance without adequately considering competing causes. We identify two such causes, ambiguity and indif…
- arXiv cs.AIresearchInstruction-Conditioned Electromagnetic Spectrum Understanding via Budget-Adaptive Signal Tokenization
arXiv:2610.12142v1 Announce Type: new Abstract: Electromagnetic spectrum monitoring increasingly requires flexible analysis beyond task-specific recognition and detection. Multimodal large language models offer a unified…
- arXiv cs.AIresearchLearning to Plan by Looking Back: Hindsight Hierarchies for Training Reasoning Models
arXiv:2610.12168v1 Announce Type: new Abstract: We introduce a self-improvement loop for reasoning models based on the following observation: Even when the difficulty of a problem exceeds the model's current solving abil…
- arXiv cs.AIresearchWhen Has a Bayesian Neural Network Sampled Enough? Adaptive Inference Time with Statistical Guarantees
arXiv:2610.12212v1 Announce Type: new Abstract: Bayesian neural network predictions are commonly approximated using a fixed number of Monte Carlo samples per input, without controlling the resulting error that comes from…
- arXiv cs.AIresearchLearning Probabilistic Logic Programs with Functional Gradient Guided Language Models
arXiv:2610.12303v1 Announce Type: new Abstract: Declarative logic programs offer a powerful and interpretable abstraction for encoding relational structure and neurosymbolic reasoning, by expressing dependencies as weigh…
- arXiv cs.AIresearchLooking Inside LLMs: Small-World Connectivity as a Signature of Reasoning Performance
arXiv:2610.12304v1 Announce Type: new Abstract: Understanding large language model (LLM) reasoning requires looking beyond behavioral performance to examine how reasoning ability is reflected in internal organization. In…
- arXiv cs.AIresearchA Structural Theory of Cognitive Representation and Problem Solving,Contexts, Invariance, and the Knowledge Space
arXiv:2610.12306v1 Announce Type: new Abstract: Learning and problem solving depend critically on the structure of internal representations. While many modern data-driven artificial systems achieve strong predictive perf…
- arXiv cs.AIresearchVerdict Without the Rule: Diagnosing and Auditing Regulatory Rule Sensitivity in LLM Compliance Systems
arXiv:2610.12313v1 Announce Type: new Abstract: Large language model compliance systems are deployed on the assumption that a verdict depends on the regulatory rule it is given. We test this directly across five models a…
- arXiv cs.AIresearchOvercoming Prior Barriers: Supervised Fine-Tuning under Long-Tail Distribution
arXiv:2610.12345v1 Announce Type: new Abstract: Supervised fine-tuning (SFT) adapts pretrained large language models (LLMs) to downstream tasks, but the required concepts can receive substantially different levels of pre…
- arXiv cs.AIresearchCited but Not Consulted: A Counterfactual Audit of Legal Chain-of-Thought Faithfulness
arXiv:2610.12361v1 Announce Type: new Abstract: Large language models increasingly justify legal decisions by naming the statute or precedent behind a verdict, treated as evidence that the decision follows from it. We te…
- arXiv cs.AIresearchHANS: A Handwritten Answer Sheet Dataset for Noisy Hybrid Document Parsing
arXiv:2610.12363v1 Announce Type: new Abstract: Intelligent grading and automated scoring technologies constitute critical infrastructure for smart education. However, existing document parsing and handwriting recognitio…
- arXiv cs.AIresearchGeoReform: Reflective Formalization Evolution for Multimodal Geometry Problem Solving
arXiv:2610.12391v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) often struggle to identify and use geometric relations in diagrams. Recent methods address this challenge by converting geometric e…
- arXiv cs.AIresearchHRIL: Learning Multimodal Synergy via Higher-Order Tensor Modeling
arXiv:2610.12393v2 Announce Type: replace Abstract: Self-supervised multimodal representation learning has achieved remarkable success across diverse domains, yet capturing synergistic information remains challenging due…
- arXiv cs.AIresearchSearching for "Harmful Refusal": A Psychometric Audit of an AI Safety Benchmark
arXiv:2610.12409v1 Announce Type: new Abstract: Safety benchmarks typically report one overall score for a suite of datasets, each of which may target one or more safety-related attributes, so models with similar overall…
- arXiv cs.AIresearchOn the estimation and validity of AI time horizons---a statistical look at the METR plot
arXiv:2610.12466v1 Announce Type: new Abstract: METR's 50\% time horizon measures the human completion time of software tasks that an AI solves with 50\% probability, allowing AI capabilities to be expressed in interpret…
- arXiv cs.AIresearchDiscovering Global False Negatives On the Fly for Self-supervised Contrastive Learning
arXiv:2502.20612v2 Announce Type: cross Abstract: In self-supervised contrastive learning, negative pairs are typically constructed using an anchor image and a sample drawn from the entire dataset, excluding the anchor.…
- arXiv cs.AIresearchSpectralCache: Accelerating Diffusion-Based World Models via Spectral Feature Caching
arXiv:2610.02660v1 Announce Type: cross Abstract: Diffusion-based world models enable high-quality interactive environment generation but suffer from substantial inference overhead due to repeated Transformer evaluations…
- arXiv cs.AIresearchFrom Pixels, Without Pre-training: Joint Generative and Self-Supervised Representation Learning in One Model
arXiv:2610.05711v1 Announce Type: cross Abstract: Strong image generation models are conditioned on class labels, aligned to frozen pretrained encoders, or built on separately trained autoencoders. While effective, gener…
- arXiv cs.AIresearchFreeze the Decoder, Heal the Encoder: Parameter-Efficient Adaptation for SVD-Based KV-Cache Compression
arXiv:2610.10552v1 Announce Type: cross Abstract: Comparing parameter-efficient fine-tuning recipes under a single, shared learning rate is a common but flawed practice: when the arms being compared have very different t…
- arXiv cs.AIresearchStrategic Governance of AI Models in Earth Science
arXiv:2610.10560v1 Announce Type: cross Abstract: AI foundation models pretrained on weather and climate data are increasingly fine-tuned to Earth science tasks well beyond weather forecasting. Their development and adop…
- arXiv cs.AIresearchSLVR: Structured Latent Visual Reasoning via Human-like Reasoning Flows
arXiv:2610.10563v2 Announce Type: replace-cross Abstract: Multimodal large language models (MLLMs) often answer visual reasoning questions by relying on linguistic priors rather than task-relevant visual evidence. Textua…
- arXiv cs.AIresearchA Survey on LLM-Integrated Hardware Design Verification
arXiv:2610.10580v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly being integrated into hardware verification to automate specification interpretation, verification-artifact generation, debu…
- arXiv cs.AIresearchCertified Corruption Budgets: Anytime-Valid Leaderboard Claims under Adaptive Rigging
arXiv:2610.10597v1 Announce Type: cross Abstract: Public leaderboards for AI models are read continuously, and attackers can see every published standing. Vote rigging, selective disclosure of private variants, and bench…
- arXiv cs.AIresearchMRCert: Towards Post-deployment Patch Robustness Certification for Adversarially Patched Samples via Type-specific Masking
arXiv:2610.10617v1 Announce Type: cross Abstract: In post-deployment time, inputs to deep learning models may or may not be adversarially patched. Patch robustness certification on such inputs within a patch bound can ve…
- arXiv cs.AIresearchWorldBench: Evaluating LLMs on Three.js Voxel World Generation
arXiv:2610.10622v1 Announce Type: cross Abstract: Large language models can now write complete, interactive 3D worlds as code, but grading those worlds automatically is unreliable. Existing judges take one view of the ou…
- arXiv cs.AIresearchSAVU-BENCH: A Real-World Benchmark for Spatial Audio-Visual Understanding
arXiv:2610.10624v1 Announce Type: cross Abstract: Spatial audio-visual understanding requires models to recognize not only what is present, but also where events occur and how they relate across modalities. Existing benc…
- arXiv cs.AIresearchPhase-HDC: Replacing Optimizer History with Gradient Thresholds in Discrete Phase Learning
arXiv:2610.10630v1 Announce Type: cross Abstract: Training a compact model often needs far more memory than storing it, because the optimizer keeps its own records of past gradients. For a hyperdimensional classifier who…
- arXiv cs.AIresearchHas LLM Screening Performance Stalled in Software Engineering Systematic Reviews?
arXiv:2610.10633v1 Announce Type: cross Abstract: Screening in systematic reviews (SRs) is manual and time-consuming. Prior work has explored large language models (LLMs) for automating this step, but LLMs are evolving r…
- arXiv cs.AIresearchVisible Reasoning Is Not a Universal Optimizer: Persona- and Thinking-Dependent Effects in Analytics Code Generation
arXiv:2610.10639v1 Announce Type: cross Abstract: Visible Chain-of-Thought (CoT) is often treated as a broadly useful reasoning instruction, yet analytics code generation combines natural-language ambiguity, schema groun…
- arXiv cs.AIresearchCoverage-Aware Reasoning with Medical Tokens for Diagnosis Prediction
arXiv:2610.10641v1 Announce Type: cross Abstract: Large language models (LLMs) offer promising potential for next-visit diagnosis prediction, owing to their ability to integrate longitudinal clinical evidence and reason…
- arXiv cs.AIresearchFrom Log-Odds to Shapley Values: An Explanatory Geometry for the Weighted Naive Bayes Classifier
arXiv:2610.10642v1 Announce Type: cross Abstract: This paper studies the construction of an explanatory space for a weighted naive Bayes classifier from the supervised representation induced by the model. We start from t…
- arXiv cs.AIresearchMasked Generative Motion Planning with Geometry-Guided Token Search
arXiv:2610.10646v1 Announce Type: cross Abstract: Generative motion planners typically use learned trajectory priors for initial generation, while leaving test-time repair to local continuous refinement. We introduce Mas…
- arXiv cs.AIresearchBeyond the Ergodic Wall: A Discrete Geometric Physics Sandbox for Analysing AI Scaling Limits and Complexity Collapse
arXiv:2610.10651v1 Announce Type: cross Abstract: This paper exposes the ergodic ceiling and thermodynamic inefficiency of current deep learning, which converges to a statistical average of historic human knowledge. True…
- arXiv cs.AIresearchNullify: Null-Space Activation Steering for Training-Free LLM Unlearning
arXiv:2610.10655v1 Announce Type: cross Abstract: Large Language Models (LLMs) inevitably internalize substantial amounts of sensitive or private information during pre-training, while LLM unlearning aims to selectively…
- arXiv cs.AIresearchBeyond Owls: Subliminal Learning Can Transfer Learned Capabilities and Backdoors
arXiv:2610.10657v1 Announce Type: cross Abstract: In subliminal learning (SL), a teacher model passes on a trait to a student model by distillation on data semantically unrelated to the trait. So far, SL has been demonst…
- arXiv cs.AIresearchLinSlot: Exploiting Linear Representation hypothesis for unsupervised attribute discovery from slot based object representation
arXiv:2610.10722v2 Announce Type: replace-cross Abstract: This paper studies the problem of learning disentangled representations of objects and their attributes from raw, unstructured image data. Slot-based methods have…
- arXiv cs.AIresearchConversational Task Disambiguation over Tabular Data: Leakage-Aware Formulation, Benchmark Suite, and Training
arXiv:2610.10740v1 Announce Type: cross Abstract: Conversational task disambiguation over tabular data uses dialogue to resolve missing information about a user's intended task before producing a solution over tables or…
- arXiv cs.AIresearchBRANCH: Bypassing Multi-Scanner AI Guardrails
arXiv:2610.10742v1 Announce Type: cross Abstract: AI systems increasingly rely on Large Language Models (LLMs) as core reasoning engines, making them targets for prompt injection and jailbreaks. Guardrails monitor and va…
- arXiv cs.AIresearchClarify, Then Focus: Statement Normalization for Conversation Analytics at Scale
arXiv:2610.10758v1 Announce Type: cross Abstract: Enterprise conversation analytics asks many questions of millions of interactions. Each question can require reconstructing what people mean and identifying which informa…
- arXiv cs.AIresearchAI-Mediated Self: How HCI Defines and Relates to the Self
arXiv:2610.10770v1 Announce Type: cross Abstract: How might AI alter how we understand and experience the self? This scoping review analyzes 102 papers to examine how the self is defined in the field of human-computer in…
- arXiv cs.AIresearchVICO: Visual Environments Co-Evolving for Vision-Language Model Reasoning
arXiv:2610.10782v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) has become a standard recipe for post-training vision-language models (VLMs), but it typically assumes a static trai…
- arXiv cs.AIresearchGrammar Concept Annotation at Scale: Deployed Fine-Tuned Small Language Models Outperform Prompted Frontier Models
arXiv:2610.10827v2 Announce Type: replace-cross Abstract: Corrective feedback is among the best-evidenced drivers of second-language acquisition, yet corrections delivered during lessons rarely accumulate into an actiona…
- arXiv cs.AIresearchReal Long-Term Memory for AI: A 50-Million-Token Window That Is Faster and Cheaper Than Recompute
arXiv:2610.10845v1 Announce Type: cross Abstract: A large language model can only use the text that fits in its context window, and it recomputes its internal key-value (KV) state for a prompt every time the prompt is se…
- arXiv cs.AIresearchThe Missing Fourth Term for the Emulation Tensor Memory Equilibrium (TME) Model: The Residue Deconstruction Cost
arXiv:2610.10924v1 Announce Type: cross Abstract: The Tensor-Memory Equilibrium (TME) model of "FP8 is All You Need (Part 1)" calculates the execution time of Ozaki Scheme II emulation of fp64 as the maximum of a tensor-…