AI news archive.
10,659 articles filed under Research, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchDistilling Routed 3D Privilege for Spatial Reasoning in Vision-Language Models
arXiv:2610.12355v2 Announce Type: replace-cross Abstract: Spatial reasoning remains a persistent weakness of vision-language models (VLMs), because RGB inputs do not directly provide geometric evidence. Existing remedies…
- arXiv cs.AIresearchARC: A Reasoning Recipe for Robot Foundation Models
arXiv:2610.12386v1 Announce Type: cross Abstract: The prevailing approach to improving robot foundation models (RFMs) relies on larger models, more robot demonstrations, and costly training at scale. We show that there e…
- arXiv cs.AIresearchSpaceFlow: Locally Controllable 3D Generation
arXiv:2610.12399v1 Announce Type: cross Abstract: Current 3D generation methods lack explicit local control: geometric adherence is often defined by a global control strength, and appearance cannot be specified locally.…
- arXiv cs.AIresearchLeWAM: A JEPA World Action Model with Diffusion-Steering-Based MPC
arXiv:2610.12407v1 Announce Type: cross Abstract: World action models (WAMs) predict actions and future observations, typically from a reconstruction-based representation that carries noisy, redundant information which c…
- arXiv cs.AIresearchPredicting Alignment Generalization with Value Representations
arXiv:2610.12410v1 Announce Type: cross Abstract: LLM developers post-train their models to exhibit prosocial values and behavioral traits, which are enumerated in an alignment target. However, while recent post-training…
- arXiv cs.AIresearchMAMHOI: Factorizing Scene-Aware Human-Object Interaction through Affordances
arXiv:2610.12416v1 Announce Type: cross Abstract: Generating realistic human-object interactions (HOI) in complex 3D scenes requires two complementary capabilities: reasoning about interaction feasibility in the environm…
- arXiv cs.AIresearchBi-FORK: Generative Modeling of High-Dimensional Bifurcating Systems
arXiv:2610.12449v1 Announce Type: cross Abstract: Bifurcations are ubiquitous in physical systems, from structural buckling to fluid and climate dynamics, yet they remain largely unexplored in deep learning. At a symmetr…
- arXiv cs.AIresearchMachine learning and information theory concepts towards an AI Mathematician
arXiv:2403.04571v2 Announce Type: replace Abstract: The current state-of-the-art in artificial intelligence is impressive, especially in terms of mastery of language, but not so much in terms of mathematical reasoning. W…
- arXiv cs.AIresearchMissMAC-Bench: Building Solid Benchmark for Missing Modality Issue in Robust Multimodal Affective Computing
arXiv:2602.00811v2 Announce Type: replace Abstract: Current Multimodal Affective Computing (MAC) systems heavily rely on the completeness of multiple modalities to accurately understand human's affective state. However,…
- arXiv cs.AIresearchEfficient Dense Crowd Trajectory Prediction Via Dynamic Clustering
arXiv:2603.18166v2 Announce Type: replace Abstract: Crowd trajectory prediction plays a crucial role in public safety and management, where it can help prevent disasters such as stampedes. Recent works address the proble…
- arXiv cs.AIresearchSoft Tournament Equilibrium: Differentiable Set-Valued Inference for Non-Transitive Pairwise Comparisons
arXiv:2604.04328v4 Announce Type: replace Abstract: Soft Tournament Equilibrium (STE) is a differentiable layer for Top-Cycle (TC) and Uncovered-Set (UC) inference from reciprocal pair probabilities. Normalized log-sum-e…
- arXiv cs.AIresearchCan Large Language Models Reinvent Foundational Algorithms?
arXiv:2604.05716v2 Announce Type: replace Abstract: LLMs have shown strong potential to advance scientific discovery. Whether they possess the capacity for foundational innovation, however, remains an open question. In t…
- arXiv cs.AIresearchBeyond Fixed Benchmarks and Worst-Case Attacks: Dynamic Boundary Evaluation for Language Models
arXiv:2605.06213v3 Announce Type: replace Abstract: Evaluating large language models (LLMs) today rests on fixed benchmarks that apply the same set of items to any model, producing ceiling and floor effects that mask cap…
- arXiv cs.AIresearchVLA Grounder: Language-Conditioning Space Optimization for Black-Box VLA Models
arXiv:2607.04517v2 Announce Type: replace Abstract: Vision-Language-Action (VLA) models are commonly treated as end-to-end action policies conditioned on natural-language task descriptions. In practice, however, their be…
- arXiv cs.AIresearchGLM-RAG: Graph Language Models for Graph-Based Retrieval-Augmented Generation
arXiv:2607.28397v2 Announce Type: replace Abstract: Retrieval-augmented generation (RAG) over knowledge graphs requires retrievers that can effectively capture both graph structure and semantic information. Recent approa…
- arXiv cs.AIresearchSolver-Aware Decompositions for Programming-by-Example: When Dividing Requires Knowing how to Conquer
arXiv:2608.03461v2 Announce Type: replace Abstract: Decomposition-based Programming-by-example (PBE) scales performance by splitting tasks into subtasks that a learned synthesizer solves: a decomposer predicts intermedia…
- arXiv cs.AIresearchConversational versus Dashboard Explainable AI for UAV Intrusion Detection: An Empirical Study of Operator Trust and Reliance
arXiv:2608.10434v3 Announce Type: replace Abstract: Machine learning-based Intrusion Detection Systems (IDS) have demonstrated superior performance in securing Unmanned Aerial Vehicle (UAV) networks. However, the 'black-…
- arXiv cs.AIresearchMulti2AV-Safety: Benchmarking Safety in Multimodal-to-Audio-Video Generation
arXiv:2608.26535v2 Announce Type: replace Abstract: Recent audio-video generators increasingly support joint conditioning on text, images, audio, and video. These capabilities also enable attacks that exploit cross-modal…
- arXiv cs.AIresearchMooncake: A KVCache-centric Disaggregated Architecture for LLM Serving
arXiv:2407.00079v5 Announce Type: replace-cross Abstract: Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI. It features a KVCache-centric disaggregated architecture that separates…
- arXiv cs.AIresearchBEAT: Balanced Frequency Adaptive Tuning for Long-Term Time-Series Forecasting
arXiv:2501.19065v3 Announce Type: replace-cross Abstract: Long-term time-series forecasting supports a wide range of applications, including weather prediction and electricity demand planning. Frequency-domain methods ad…
- arXiv cs.AIresearchTowards Reasonable Concept Bottleneck Models
arXiv:2506.05014v3 Announce Type: replace-cross Abstract: We propose a novel, flexible, and efficient framework for designing Concept Bottleneck Models (CBMs) that enables practitioners to explicitly encode and extend th…
- arXiv cs.AIresearchHeterogeneous-Modal Unsupervised Domain Adaptation via Latent Space Bridging
arXiv:2506.15971v2 Announce Type: replace-cross Abstract: Unsupervised domain adaptation (UDA) effectively bridges the domain gap between a labeled source domain and an unlabeled target domain, but assumes that the two d…
- arXiv cs.AIresearchAn Investigation of Robustness of LLMs in Mathematical Reasoning: Benchmarking with Mathematically-Equivalent Transformation of Advanced Mathematical Problems
arXiv:2508.08833v4 Announce Type: replace-cross Abstract: Frontier large language models (LLMs) now reach near-ceiling accuracy on standard mathematical-reasoning benchmarks and gold-medal-level performance at the Intern…
- arXiv cs.AIresearchInverse-LLaVA: Rethinking Multimodal Alignment via Text-to-Vision Mapping
arXiv:2508.12466v3 Announce Type: replace-cross Abstract: Connecting pretrained vision and language models usually involves projecting image features into the language model's input space. Inverse-LLaVA reverses this map…
- arXiv cs.AIresearchCAF\'E: Causal Black-Box Testing of Machine Unlearning
arXiv:2509.16525v2 Announce Type: replace-cross Abstract: Machine learning models are increasingly deployed as software components that must evolve as requirements change. When specific training records or features must…
- arXiv cs.AIresearchAyurParam: A State-of-the-Art Bilingual Language Model for Ayurveda
arXiv:2511.02374v2 Announce Type: replace-cross Abstract: Current large language models excel at broad, general-purpose tasks, but consistently underperform when exposed to highly specialized domains that require deep cu…
- arXiv cs.AIresearchTowards Scalable Meta-Learning of near-optimal Interpretable Models via Synthetic Model Generations
arXiv:2511.04000v2 Announce Type: replace-cross Abstract: Decision trees are widely used in high-stakes fields like finance and healthcare due to their interpretability. This work introduces an efficient, scalable method…
- arXiv cs.AIresearchA PDE Perspective on Generative Diffusion Models
arXiv:2511.05940v3 Announce Type: replace-cross Abstract: Score-based diffusion models have emerged as a powerful class of generative methods, with successful applications across diverse domains. Despite their empirical…
- arXiv cs.AIresearchOne Permutation Is All You Need: Fast, Deterministic Feature Importance and Model Stress-Testing
arXiv:2512.13892v3 Announce Type: replace-cross Abstract: Reliable estimation of feature contributions in machine learning models is essential for transparency, algorithmic fairness, and regulatory compliance. While perm…
- arXiv cs.AIresearchGPF-Net: Gated Progressive Fusion Learning for Polyp Re-Identification
arXiv:2512.21476v2 Announce Type: replace-cross Abstract: Colonoscopic Polyp Re-Identification (ReID) aims to match the same polyp across a large gallery of images captured from different viewpoints and with different ca…
- arXiv cs.AIresearchSRUG: A Fusion-Driven Generator Network for Medical Image Translation
arXiv:2601.04785v2 Announce Type: replace-cross Abstract: MRI sequence synthesis aims to recover missing image contrast while preserving patient-specific anatomy. The choice of generation mechanism affects both optimizat…
- arXiv cs.AIresearchExplanation Multiplicity in SHAP: Characterization and Assessment
arXiv:2601.12654v3 Announce Type: replace-cross Abstract: SHAP explanations are widely used in high-stakes settings to justify decisions, yet they can differ substantially across repeated runs, even when the model, the i…
- arXiv cs.AIresearchObscuring Data Contamination Through Translation: Evidence from Arabic Corpora
arXiv:2601.14994v2 Announce Type: replace-cross Abstract: Data contamination can invalidate benchmark evaluation when a model benefits from memorized evaluation content rather than genuine generalization. Yet contaminati…
- arXiv cs.AIresearchTrust, Don't Trust, or Flip: Robust Preference-Based Reinforcement Learning with Multi-Expert Feedback
arXiv:2601.18751v2 Announce Type: replace-cross Abstract: Preference-based reinforcement learning (PBRL) offers a promising alternative to explicit reward engineering by learning from pairwise trajectory comparisons. How…
- arXiv cs.AIresearchFreshMem: Brain-Inspired Frequency-Space Hybrid Memory for Streaming Video Understanding
arXiv:2602.01683v2 Announce Type: replace-cross Abstract: Transitioning Multimodal Large Language Models (MLLMs) from offline to online streaming video understanding is essential for continuous perception. However, exist…
- arXiv cs.AIresearchPhantom Transfer: Data Poisoning can Survive Data-Level Defences
arXiv:2602.04899v3 Announce Type: replace-cross Abstract: We present a data poisoning attack -- Phantom Transfer -- with the property that, even if you know precisely how the poison was placed into an otherwise benign da…
- arXiv cs.AIresearchBi-temporal Image-driven Acute Stroke Evolution Analysis
arXiv:2602.07535v2 Announce Type: replace-cross Abstract: Acute ischemic stroke requires rapid treatment decisions that are strongly guided by emergency imaging. Admission computed tomography perfusion (CTP) is commonly…
- arXiv cs.AIresearchRethinking Latency Denial-of-Service: Attacking the LLM Serving Framework, Not the Model
arXiv:2602.07878v2 Announce Type: replace-cross Abstract: LLM inference is inherently expensive, even a modest slowdown can translate into substantial operating costs and severe availability risks. Recently, a growing bo…
- arXiv cs.AIresearchActionCodec: What Makes for Good Action Tokenizers
arXiv:2602.15397v2 Announce Type: replace-cross Abstract: Vision-Language-Action (VLA) models leveraging the native autoregressive paradigm of Vision-Language Models (VLMs) have demonstrated superior instruction-followin…
- arXiv cs.AIresearchHistCAD: Constraint-Aware Parametric CAD Histories for Evaluating Editability
arXiv:2602.19171v4 Announce Type: replace-cross Abstract: Sketch constraints specify geometric conditions for constructing and modifying parametric CAD models. We study whether predicted constraints allow a given history…
- arXiv cs.AIresearchTest-Time Scaling with Diffusion Language Models via Reward-Guided Stitching
arXiv:2602.22871v3 Announce Type: replace-cross Abstract: Reasoning with large language models often benefits from generating multiple chains-of-thought, but existing aggregation strategies are typically trajectory-level…
- arXiv cs.AIresearchmAVE: A Watermark for Joint Audio-Visual Generation Models
arXiv:2603.07090v2 Announce Type: replace-cross Abstract: Watermarking joint audio-visual generation supports vendor copyright protection and content provenance. However, independently valid audio and video watermarks do…
- arXiv cs.AIresearchJailbreak Scaling Laws for Large Language Models: Polynomial-Exponential Crossover
arXiv:2603.11331v4 Announce Type: replace-cross Abstract: Adversarial attacks can reliably steer safety-aligned large language models toward unsafe behavior. Empirically, we find that adversarial prompt-injection attacks…
- arXiv cs.AIresearchPhysMoDPO: Physically-Plausible Humanoid Motion with Preference Optimization
arXiv:2603.13228v3 Announce Type: replace-cross Abstract: Recent progress in text-conditioned human motion generation has been largely driven by diffusion models trained on large-scale human motion data. Building on this…
- arXiv cs.AIresearchExecVLA: Following Fine-Grained Execution Constraints in Vision-Language-Action Models with Bi-Level Action Representation
arXiv:2603.17524v2 Announce Type: replace-cross Abstract: We study fine-grained execution-constraint following in vision-language-action (VLA) models. Given an invariant task goal, the policy must follow instruction-spec…
- arXiv cs.AIresearchImperative Interference: Social Register Shapes Instruction Topology in Large Language Models
arXiv:2603.25015v2 Announce Type: replace-cross Abstract: System prompt instructions that cooperate in English compete in Spanish, with the same semantic content, but opposite interaction topology. We present instruction…
- arXiv cs.AIresearchDecidable By Construction: Design-Time Verification for Truly Fearless Systems
arXiv:2603.25414v5 Announce Type: replace-cross Abstract: Concurrency, parallelism and distributed execution become truly fearless when the compiler tracks wait-for edges, proves multi-threaded work is sound and preserve…
- arXiv cs.AIresearchTask-Centric Personalized Federated Fine-Tuning of Language Models
arXiv:2604.00050v3 Announce Type: replace-cross Abstract: Federated Learning (FL) has emerged as a promising technique for training language models on distributed and private datasets of diverse tasks. However, aggregati…
- arXiv cs.AIresearchAI Appeals Processor: A Deep Learning Approach to Automated Classification of Citizen Appeals in Government Services
arXiv:2604.03672v2 Announce Type: replace-cross Abstract: Government agencies must register, classify and route every citizen appeal within statutory time limits, and much of this work is still done by hand. We describe…
- arXiv cs.AIresearchVirtual Smart Metering in District Heating Networks via Heterogeneous Spatial-Temporal Graph Neural Networks
arXiv:2604.10166v2 Announce Type: replace-cross Abstract: Intelligent operation of thermal energy networks aims to improve energy efficiency, reliability, and operational flexibility through data-driven control, predicti…