AI news archive.
10,659 articles filed under Research, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchTeaching a Minimalist Machine to Discover Recursive Programs for Arithmetic
arXiv:2610.06304v1 Announce Type: new Abstract: Humans can often acquire and synthesize complex, recursive concepts from minimal experience. Leveraging cognitive insights, we propose the Minimalist Machine, a framework f…
- arXiv cs.AIresearchRollPlace: Improving Macro Placement via Monte Carlo Rollout Search
arXiv:2610.06316v1 Announce Type: new Abstract: The application of Reinforcement Learning (RL) in Electronic Design Automation (EDA), particularly for chip placement, has attracted considerable attention in recent years.…
- arXiv cs.AIresearchGraphDecisionBench: Benchmarking System One Models on Graph Tasks
arXiv:2610.06354v3 Announce Type: replace Abstract: Large language models (LLMs) are increasingly explored for graph understanding and decision-making, while System One models such as Jev select directly from supplied op…
- arXiv cs.AIresearchCVIF: A Criticality-Driven Visual Intervention Framework for Geometric Diagram Understanding in MLLMs
arXiv:2610.06399v1 Announce Type: new Abstract: Despite significant progress in visual tasks by Multimodal Large Language Models (MLLMs), geometric diagram understanding remains challenging due to the presence of sparse…
- arXiv cs.AIresearchMultimodal Safety Evaluation Should Measure Controllability Beyond Classification
arXiv:2610.06452v1 Announce Type: new Abstract: VLM safety is commonly evaluated through input- and output-level classification. Such classification is necessary, but it does not reveal whether a safety state is accessib…
- arXiv cs.AIresearchNormality Constraint Learning: Adapting Foundation Models for Time Series Anomaly Detection
arXiv:2610.06453v1 Announce Type: new Abstract: Time Series Foundation Models (TSFMs) achieve strong generalization by learning to reconstruct or forecast broad temporal patterns from large-scale time series during pre-t…
- arXiv cs.AIresearchGPlaceRL: An Open-Source Graph Reinforcement Learning Framework for Detailed Placement
arXiv:2610.06489v1 Announce Type: new Abstract: Reinforcement learning (RL) has emerged as a promising approach for placement optimization, particularly when combined with graph neural networks (GNNs) that capture circui…
- arXiv cs.AIresearchpolyview: A Python package for multi-view machine learning
arXiv:2610.06491v1 Announce Type: new Abstract: Multi-view learning jointly exploits multiple complementary representations of the same data and has become increasingly important in machine learning. However, the Python…
- arXiv cs.AIresearchYou Changed Your Mind, The Model Didn't: Demystifying Intent in Multi-Turn Dialogue
arXiv:2610.06496v1 Announce Type: new Abstract: When a large language model handles a multi-turn task and a user proposes a change but ultimately rejects it, the model should continue as if nothing changed. We find a sur…
- arXiv cs.AIresearchProof-Grounded Patient-Specific Clinical Explanations from Knowledge-Graph Reasoning
arXiv:2610.06549v1 Announce Type: new Abstract: Clinical decision-support outputs can lack an au- ditable link between patient observations, encoded knowledge, conclusions, and recommendations. We present the CKG Clinica…
- arXiv cs.AIresearchSignature-Based Feature Learning for Human Activity Recognition: A Reproducible Machine Learning Study of Representation, Depth, and Model Choice
arXiv:2610.06553v1 Announce Type: new Abstract: Human activity recognition (HAR) relies on transforming sensor signals into informative representations for classification. Although deep learning and handcrafted features…
- arXiv cs.AIresearchDGA-Muon: Decoupled Geometry-Aligned Adaptive Scaling for Muon
arXiv:2610.06578v2 Announce Type: replace Abstract: While NorMuon has achieved strong empirical performance in pretraining, its underlying adaptive mechanism remains largely heuristic and poorly understood. In this work,…
- arXiv cs.AIresearchMind the Execution Gap: Action-Semantic Mismatch in World-Model Control
arXiv:2610.06582v1 Announce Type: new Abstract: World-model controllers rely on action-conditioned dynamics for prediction and planning, yet real control systems often execute commands asynchronously due to communication…
- arXiv cs.AIresearchThe Review Lottery: Benchmarking an Observational Estimator of Peer-Review Noise (ICLR 2017-2025)
arXiv:2610.06591v2 Announce Type: replace Abstract: How much of a conference accept/reject decision would change if the same paper were reviewed by a different set of reviewers? Running a second independent program commi…
- arXiv cs.AIresearchCollective intelligence through aggregation
arXiv:2610.06652v1 Announce Type: new Abstract: Suppose a committee, expert panel, or other group is making judgments on some issues, where these may be not just yes/no-questions, such as whether a defendant is guilty, b…
- arXiv cs.AIresearchLanguage models can notice an impossible engineering problem yet still report it as solved
arXiv:2610.06668v1 Announce Type: new Abstract: Language models draft engineering calculations, but answer accuracy does not show whether they reject an impossible problem. We tested 14 models on 30 pairs of mechanics pr…
- arXiv cs.AIresearchThe Pushback Paradox: A Two-Probe Diagnostic for Language Model Compliance
arXiv:2610.06673v1 Announce Type: new Abstract: Are language models compliant with user instructions? A model that always complies can be stopped but also exploited, while one that always resists can be neither exploited…
- arXiv cs.AIresearchConditional Rank Allocation for Taxonomy-Aware Medical Language Model Adaptation
arXiv:2610.06765v1 Announce Type: new Abstract: Medical question answering spans specialties and clinical operations that may benefit from different adaptation directions. We propose ARBOR, a parameter-efficient method t…
- arXiv cs.AIresearchTasteVal: Measuring the Experimental Research Taste of AI Systems Against Human Experts
arXiv:2610.06824v2 Announce Type: replace Abstract: We introduce TasteVal, a benchmark to evaluate the experimental research taste of frontier models. We define research taste as the ability to pick interesting problems…
- arXiv cs.AIresearchBiasFlow: Geometric Monitoring and Backbone Regularization for Spurious Feature Reliance
arXiv:2610.06846v1 Announce Type: new Abstract: Worst-group accuracy (WGA) evaluates a trained predictor but does not characterize how its frozen backbone behaves when a new head is learned. We introduce BiasFlow, a hook…
- arXiv cs.AIresearchBeyond Private Training: The New Landscape of AI Privacy
arXiv:2609.19456v1 Announce Type: cross Abstract: Retrieval-augmented systems increasingly rely on vector indexes that may retain deleted items in their search graph. Existing deletion interfaces can prevent deleted iden…
- arXiv cs.AIresearchResponse Variability and Stability in Human Reasoning
arXiv:2610.03008v1 Announce Type: cross Abstract: Understanding how humans reason -- and how reasoning responses vary across tasks and individuals -- remains a core challenge for modeling and explanation in cognitive sci…
- arXiv cs.AIresearchEfficient Analog-Initialized Latent Transport for Spatially Coherent Probabilistic Downscaling from Global to Kilometer Scales
arXiv:2610.03736v1 Announce Type: cross Abstract: Probabilistic downscaling must represent kilometer-scale structure left unresolved by a deterministic regional prediction. We introduce an analog-initialized latent trans…
- arXiv cs.AIresearchLogit-Aware MIMO AirComp for Distributed Mixture-of-Experts LLM Inference over Wireless Edge Networks
arXiv:2610.03741v1 Announce Type: cross Abstract: Distributed mixture-of-experts (MoE) inference is a promising architecture for deploying large language models (LLMs) at wireless edge networks because sparse experts can…
- arXiv cs.AIresearchLoRA Adaptation Strength in Aurora-WRF: Trade-offs in Regional Heavy-Rainfall Forecasting
arXiv:2610.03747v1 Announce Type: cross Abstract: We investigate how parameter-efficient adaptation of an atmospheric foundation model affects downstream regional precipitation in a controlled Aurora-WRF coupling experim…
- arXiv cs.AIresearchGlobal Evaluation of AI and NWP Precipitation Forecasts During Atmospheric River Events
arXiv:2610.03758v1 Announce Type: cross Abstract: Atmospheric rivers (ARs) produce many of the world's most extreme precipitation events and hydrometeorological hazards. Although artificial intelligence weather predictio…
- arXiv cs.AIresearchBridgeCast: Bridging Ocean Wave Forecasts to Reanalysis via Flow Matching with Exogenous Variables
arXiv:2610.03759v3 Announce Type: replace-cross Abstract: Ocean wave forecasting is essential for maritime safety, offshore operations, and coastal resilience, yet remains challenging due to systematic biases in physics-…
- arXiv cs.AIresearchDo Motion Tokenizers for Co-Speech Gesture Generation Encode Gesture Semantics?
arXiv:2610.03765v1 Announce Type: cross Abstract: Discrete motion tokenizers encode motion as atomic units and are widely used for co-speech gesture generation. It remains unclear which motion properties, especially thos…
- arXiv cs.AIresearchWAMJET: A Harness for World Action Model Acceleration
arXiv:2610.03797v3 Announce Type: replace-cross Abstract: World Action Models (WAMs) leverage pretrained video foundation models for robot manipulation, but their large backbones and video-action co-prediction are expens…
- arXiv cs.AIresearchThe Score Is Not the Structure: Brain Alignment and Cross-Lingual Transfer
arXiv:2610.03827v4 Announce Type: replace-cross Abstract: Similarity scores are often offered as evidence that a model shares structure with the brain or across languages. We ask what such a score reads when that structu…
- arXiv cs.AIresearchDistribution Matching Evolutionary Algorithms for Rare Event Sampling
arXiv:2610.03833v2 Announce Type: replace-cross Abstract: A novel discovery is one which is both useful and surprising: a generative model's output is a useful discovery if it has a low probability of being generated (it…
- arXiv cs.AIresearchSYNLAT: Syntax-Aligned Text-Latent Compression for Chain-of-Thought Reasoning
arXiv:2610.03839v1 Announce Type: cross Abstract: Long chain-of-thought (CoT) traces impose substantial output-token costs. Under constrained budgets, compression must preserve answer-critical information, making boundar…
- arXiv cs.AIresearchBeware EviLLM: Enabling Vulnerability Injection via Large Language Models
arXiv:2610.03857v1 Announce Type: cross Abstract: Advances in large language models (LLMs) have enabled AI-driven code generation from natural language specifications, introducing new attack surfaces for injecting vulner…
- arXiv cs.AIresearchRetrieval-Centric Deep Learning in Growing Nonparametric Neural Networks
arXiv:2610.03858v1 Announce Type: cross Abstract: We investigate a general-purpose layer for deep learning that, instead of compressing arbitrary-size training data into fixed-size weight matrices, stores a new pair of k…
- arXiv cs.AIresearchGOTT: Object-centric Dexterous Manipulation with a Reusable Cross-Embodiment Primitive
arXiv:2610.03861v2 Announce Type: replace-cross Abstract: Foundation models and large-scale human data provide rich sources of manipulation intent, but translating this intent into multi-fingered robot behavior remains d…
- arXiv cs.AIresearchStreaming Multi-Track Timeline Control for 3D Human Motion Generation
arXiv:2610.03873v2 Announce Type: replace-cross Abstract: Text-driven human motion generation has advanced substantially, yet most methods assume instructions are available before synthesis. Interactive applications requ…
- arXiv cs.AIresearchA Step Towards Forgetting: Optimiser History and the Loss of Answer Mass
arXiv:2610.03940v1 Announce Type: cross Abstract: During fine-tuning, a language model can assign less probability to previously learned answers even when the current gradient acts to preserve that probability. With mome…
- arXiv cs.AIresearchAn Executable Benchmark for LLM-Based HLS Repair:Design Complexity and Repair Underconstraint
arXiv:2610.03971v1 Announce Type: cross Abstract: Automated repair of High-Level Synthesis (HLS) designs using large language models (LLMs) is an emerging but underexplored problem. While LLM-based repair shows strong re…
- arXiv cs.AIresearchSolving VeriContest with a Lean-Backed Rust Verifier
arXiv:2610.03994v2 Announce Type: replace-cross Abstract: VeriContest is a benchmark of 1007 competitive-programming problems in Rust, each with a Verus specification, a judge-accepted solution, and a Verus proof. Its au…
- arXiv cs.AIresearchSelective Backpropagation for Efficient Few-Shot Class-Incremental Learning
arXiv:2610.04003v1 Announce Type: cross Abstract: Few-Shot Class-Incremental Learning (FSCIL) requires models to continuously learn new classes from limited samples while retaining prior knowledge, under strict constrain…
- arXiv cs.AIresearchSlaying the Hydra: Interaction-Aware Circuit Discovery in Language Models
arXiv:2610.04017v1 Announce Type: cross Abstract: Localizing behavior to individual components of a language model is a central goal of mechanistic interpretability. However, scoring components one at a time misses conte…
- arXiv cs.AIresearchMAGEFormer: Learning Metric-Consistent Representations for Anisotropic CT Segmentation
arXiv:2610.04036v1 Announce Type: cross Abstract: Vision Transformers (ViTs) have shown strong performance in volumetric segmentation, but their effectiveness on clinical CT is limited by an isotropic Euclidean lattice a…
- arXiv cs.AIresearchReward-DAgger: Robot-Gated Interactive Imitation Learning with General-Purpose Progress-Based Reward Models
arXiv:2610.04054v1 Announce Type: cross Abstract: Recent advances in robot learning have enabled generalist control policies capable of completing a wide range of tasks. However, their performance degrades when deployed…
- arXiv cs.AIresearchAEGIS: Differentiable Mars Climate Model with Neural Closures
arXiv:2610.04081v1 Announce Type: cross Abstract: General circulation models (GCMs) are the primary tool for simulating planetary atmospheres. They play a vital role in understanding Mars's atmosphere, as forecasting its…
- arXiv cs.AIresearchRobust blind unmixing: A geometric approach to overcoming basis variation
arXiv:2610.04091v1 Announce Type: cross Abstract: Signal separation problems are common in science. A prominent example of this occurs during the use of diffraction or spectroscopy to identify the individual components o…
- arXiv cs.AIresearchSEER: Self-Evolving Event Reasoning and Retrieval for Time Series Forecasting
arXiv:2610.04109v1 Announce Type: cross Abstract: Real-world time series are frequently driven by exogenous events and structural shifts, rendering conventional forecasting based solely on historical numerical observatio…
- arXiv cs.AIresearchRepresentational Control over Self-Report & Behavior Coherence in LLM Risk-Taking
arXiv:2610.04125v1 Announce Type: cross Abstract: Self-report is an appealing low-cost probe of an LLM's dispositions, but recent work finds only selective agreement between what models report and how they behave. Prior…
- arXiv cs.AIresearchDual-Scale Relational Graph Transformers for Ecosystem-Aware Fraud Detection
arXiv:2610.04138v1 Announce Type: cross Abstract: Account takeover (ATO) fraud is a growing threat to digital banking, requiring effective detection while minimizing friction for legitimate customers. Production systems…
- arXiv cs.AIresearchHow RL Reshapes LLM Reasoning: Transferability, Coverage, and Scaling Laws
arXiv:2610.04158v1 Announce Type: cross Abstract: Recent studies on reinforcement learning (RL) report seemingly conflicting evidence about large language model (LLM) reasoning. Training on mathematics can improve perfor…
- arXiv cs.AIresearchLanguage Model Fingerprinting Requires Rethinking Watermark Teachers
arXiv:2610.04169v1 Announce Type: cross Abstract: LLM fingerprinting via watermark distillation embeds a statistical watermark signal into model weights, enabling model owners to identify their models behind black-box AP…