AI news archive.
10,659 articles filed under Research, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchOC-GS: Gaussian Splatting for Irregular Turntable Capture
arXiv:2609.31572v1 Announce Type: cross Abstract: Uneven rotation and dropped frames make equal-angle assumptions unreliable for turntable reconstruction. We present OC-GS, an object-centric Gaussian splatting that refin…
- arXiv cs.AIresearchStatistical attribute alignment for black-box generative AI via output post-processing
arXiv:2609.31607v1 Announce Type: cross Abstract: Generative AI systems are increasingly used, but aligning their outputs with user requirements poses a continuing challenge. Here, we aim to ensure that the distribution…
- arXiv cs.AIresearchEvaluation is All You Need: Strategic Overclaiming of LLM Reasoning Capabilities Through Evaluation Design
arXiv:2506.04734v3 Announce Type: replace Abstract: Reasoning models represented by the Deepseek-R1-Distill series have been widely adopted by the open-source community due to their strong performance in mathematics, sci…
- arXiv cs.AIresearchFlow Reconstruction from Sparse Measurements in Urban Drainage Networks: An Application and Evaluation of Data-Driven Sparse Sensing
arXiv:2511.04556v3 Announce Type: replace Abstract: Urbanization and increasingly frequent intense storms are placing stress on urban drainage networks. While dense monitoring of urban drainage networks is desirable, pra…
- arXiv cs.AIresearchTesting the Utility of Using Large Language Models to Create Personalized Networks From Therapy Session Transcripts: A Proof of Concept Study
arXiv:2512.05836v2 Announce Type: replace Abstract: Recent advances in psychotherapy have focused on treatment personalization, such as by selecting treatment modules based on individual networks. However, estimating per…
- arXiv cs.AIresearchStepwise Intrinsic Rewards for Reasoning in Large Language Models
arXiv:2602.01034v2 Announce Type: replace Abstract: Reinforcement learning (RL) has become a widely used paradigm for improving the reasoning abilities of large language models (LLMs) and Vision-language models (VLMs). S…
- arXiv cs.AIresearchLatent Generative Solvers for Generalizable Long-Term Physics Simulation
arXiv:2602.11229v3 Announce Type: replace Abstract: Reliable physics simulation demands two capabilities that today's neural PDE solvers do not deliver together: generalization across heterogeneous PDE families, and stab…
- arXiv cs.AIresearchWhen to Think Fast and Slow? AMOR: Adaptive Entropy Gate for Hybrid Models
arXiv:2602.13215v3 Announce Type: replace Abstract: Recurrent-attention hybrids aim to combine the efficiency of recurrence with the contextual recall of attention, but existing approaches typically apply attention unifo…
- arXiv cs.AIresearchAttribution Bias in Large Language Models
arXiv:2604.05224v2 Announce Type: replace Abstract: As Large Language Models (LLMs) are increasingly used to support search and information retrieval, it is critical that they accurately attribute content to its original…
- arXiv cs.AIresearchReasonAudio: A Benchmark for Evaluating Reasoning Beyond Matching in Text-Audio Retrieval
arXiv:2605.03361v3 Announce Type: replace Abstract: Existing audio retrieval benchmarks primarily assess semantic matching, lacking comprehensive evaluation of the logical reasoning capabilities required by complex queri…
- arXiv cs.AIresearchThe Scaling Properties of Implicit Deductive Reasoning in Transformers
arXiv:2605.04330v3 Announce Type: replace Abstract: We investigate the scaling properties of implicit deductive reasoning over Horn clauses in depth-bounded Transformers. By discouraging the reliance on statistical short…
- arXiv cs.AIresearchReward-Decomposed Reinforcement Learning for Immersive Video Role-Playing
arXiv:2605.04733v3 Announce Type: replace Abstract: Text-based role-playing models can imitate character styles, but often fail to capture scene atmosphere and evolving tension, which are crucial for immersive applicatio…
- arXiv cs.AIresearchHaM-World: Soft-Hamiltonian World Models with Selective Memory for Planning
arXiv:2605.05951v2 Announce Type: replace Abstract: World models support model-based planning through learned latent dynamics, but imagined rollouts can become unstable as the planning horizon grows or the dynamics distr…
- arXiv cs.AIresearchAcuityBench: Evaluating Clinical Acuity Identification and Uncertainty Alignment
arXiv:2605.11398v2 Announce Type: replace Abstract: We introduce AcuityBench, a benchmark for evaluating whether language models identify the appropriate urgency of care from user medical presentations. Existing health b…
- arXiv cs.AIresearchSelective Off-Policy Reference Tuning with Plan Guidance
arXiv:2605.11505v3 Announce Type: replace Abstract: Reinforcement learning with verifiable rewards helps reasoning, but GRPO-style methods stall on hard prompts where all sampled rollouts fail. SORT adds a repair update…
- arXiv cs.AIresearchNice Fold or Hero Call: Learning Budget-Efficient Thinking under Policy-Dependent Solvability
arXiv:2605.11625v2 Announce Type: replace Abstract: Large reasoning models (LRMs) improve problem solving through extended reasoning, but often misallocate test-time compute. Existing efficiency methods reduce cost by co…
- arXiv cs.AIresearchSciR: A Controllable Benchmark for Scientific Reasoning in LLMs
arXiv:2606.13020v3 Announce Type: replace Abstract: Three paradigmatic forms of inference recur across scientific reasoning: deduction, induction, and causal abduction. Reliably evaluating LLMs on these in scientific set…
- arXiv cs.AIresearchDo Neural Networks Preserve Case Structure? Case-Based Decomposition, Interpretation, and Decision Consistency
arXiv:2607.11347v2 Announce Type: replace Abstract: Neural networks increasingly inform consequential decisions, making their reliability increasingly important. Yet their internal mechanisms provide little evidence of w…
- arXiv cs.AIresearchEnergy Efficiency of Locally Deployed LLMs: A Preliminary Quantitative GPU Power Benchmark on Consumer Hardware
arXiv:2608.00008v2 Announce Type: replace Abstract: The local deployment of large language models (LLMs) is gaining traction due to privacy concerns and the desire for on-premise inference. However, the energy costs on c…
- arXiv cs.AIresearchState Propagation Also Satisfies: A Complex-Valued State-Space Model for Deterministic State Tracking
arXiv:2608.03425v3 Announce Type: replace Abstract: Despite the dominance of massive language models, leading paradigms like Transformers and Mamba fundamentally falter at continuous deterministic state tracking, sufferi…
- arXiv cs.AIresearchPhysElite: How Far Are LLMs from Solving Olympiad-Level Physics Problems?
arXiv:2608.25097v3 Announce Type: replace Abstract: Understanding how (multimodal) large language models perform on physics problems requires benchmarks that reflect the difficulty and breadth of expert-level physical re…
- arXiv cs.AIresearchT-LoopFormer: Token-Level Elastic-Depth Looped Transformers with Dynamic Routing
arXiv:2609.15160v3 Announce Type: replace Abstract: Looped Transformers have recently demonstrated strong performance in both reasoning and language tasks by reusing a shared set of parameters across multiple iterations,…
- arXiv cs.AIresearchLEAD: An EEG Foundation Model for Alzheimer's Disease Detection
arXiv:2502.01678v5 Announce Type: replace-cross Abstract: Electroencephalography (EEG) provides a non-invasive, highly accessible, and cost-effective approach for detecting Alzheimer's disease (AD). However, existing met…
- arXiv cs.AIresearchNaijaNLP: A Survey of Nigerian Low-Resource Languages
arXiv:2502.19784v3 Announce Type: replace-cross Abstract: With over 500 languages in Nigeria, three languages - Hausa, Yor\`ub\'a and Igbo spoken by more than 175 million people, account for about 65% of the languages. H…
- arXiv cs.AIresearchMedHal: a Synthetic Dataset for Medical Hallucination Detection
arXiv:2504.08596v4 Announce Type: replace-cross Abstract: Hallucination, the generation of non factual content by AI systems, poses serious risks in medical contexts, where errors can directly affect patient outcomes. We…
- arXiv cs.AIresearchAchieving Tokenizer Flexibility in Language Models through Heuristic Adaptation and Supertoken Learning
arXiv:2505.09738v2 Announce Type: replace-cross Abstract: Pretrained language models (LLMs) are often constrained by their fixed tokenization schemes, leading to inefficiencies and performance limitations, particularly f…
- arXiv cs.AIresearchLapDDPM: Spectral Perturbation Diffusion for Robust Single-Cell Manifold Generation
arXiv:2506.13344v2 Announce Type: replace-cross Abstract: Generating high-fidelity and biologically plausible synthetic single-cell RNA sequencing (scRNA-seq) data is a critical challenge in computational biology, driven…
- arXiv cs.AIresearchPeer Review as Structured Commentary: Immutable Identity, Public Dialogue, and Reproducible Scholarship
arXiv:2506.22497v2 Announce Type: replace-cross Abstract: This paper reconceptualises peer review as structured public commentary. Traditional academic validation is hindered by anonymity, latency, and gatekeeping. We pr…
- arXiv cs.AIresearchNeural Bridge Processes
arXiv:2508.07220v4 Announce Type: replace-cross Abstract: Learning stochastic functions from partially observed context-target pairs requires models that are expressive, uncertainty-aware, and strongly conditioned on inp…
- arXiv cs.AIresearchAUWave: A Data-Driven Model for Reconstructing Significant Wave Heights Using Sparse Observations
arXiv:2509.19384v2 Announce Type: replace-cross Abstract: Reconstructing high-resolution regional significant wave height (SWH) fields from sparse buoy observations is a critical challenge for ocean monitoring. We introd…
- arXiv cs.AIresearchProvable Speech Attributes Conversion via Latent Independence
arXiv:2510.05191v3 Announce Type: replace-cross Abstract: Conditional generation and disentangled representation learning are central to controlled generation across audio, vision, and multimodal domains. However, despit…
- arXiv cs.AIresearchModels Got Talent: Identifying High Performing Wearable Human Activity Recognition Models Without Training
arXiv:2511.06157v3 Announce Type: replace-cross Abstract: Discovering high performing model architectures for wearables-based Human Activity Recognition (HAR) applications is challenging. The astonishing diversity and va…
- arXiv cs.AIresearchStructural Enforcement of Statistical Rigor in AI-Driven Discovery: A Functional Architecture
arXiv:2511.06701v4 Announce Type: replace-cross Abstract: AI-Scientist systems risk manufacturing spurious discoveries through uncontrolled multiple testing. We present a functional architecture that enforces statistical…
- arXiv cs.AIresearchSLMFix: Leveraging Small Language Models for Domain Specific Language Error Fixing with Reinforcement Learning
arXiv:2511.19422v2 Announce Type: replace-cross Abstract: Large language models (LLMs) have shown impressive capabilities in code generation across many programming languages but even state-of-the-art LLMs generate progr…
- arXiv cs.AIresearchConsist-Retinex: One-Step Noise-Emphasized Consistency Training Accelerates High-Quality Retinex Enhancement
arXiv:2512.08982v4 Announce Type: replace-cross Abstract: Retinex-based low-light image enhancement benefits from separating reflectance and illumination, yet recent generative approaches often rely on iterative sampling…
- arXiv cs.AIresearchDemo: Generative AI helps Radiotherapy Planning with User Preference
arXiv:2512.08996v3 Announce Type: replace-cross Abstract: Radiotherapy planning is a highly complex process that often varies significantly across institutions and individual planners. Most existing deep learning approac…
- arXiv cs.AIresearchPrompt-Based Continual Compositional Zero-Shot Learning
arXiv:2512.09172v3 Announce Type: replace-cross Abstract: We tackle continual adaptation of vision-language models to new attributes, objects, and their compositions in Compositional Zero-Shot Learning (CZSL), while prev…
- arXiv cs.AIresearchGeometric-Photometric Event-based 3D Gaussian Ray Tracing
arXiv:2512.18640v3 Announce Type: replace-cross Abstract: Event cameras offer a high temporal resolution over traditional frame-based cameras, which makes them suitable for motion and structure estimation. However, it ha…
- arXiv cs.AIresearchInitial results of the Digital Consciousness Model
arXiv:2601.17060v3 Announce Type: replace-cross Abstract: Artificially intelligent systems have become remarkably sophisticated. They hold conversations, write essays, and seem to understand context in ways that surprise…
- arXiv cs.AIresearchRAPTOR: Ridge-Adaptive Logistic Probes
arXiv:2602.00158v3 Announce Type: replace-cross Abstract: Probing studies what information is encoded in a frozen LLM's layer representations by training a lightweight predictor on top of them. Beyond analysis, probes ar…
- arXiv cs.AIresearchHuPER: A Human-Inspired Framework for Phonetic Perception
arXiv:2602.01634v2 Announce Type: replace-cross Abstract: We propose HuPER, a human-inspired framework that models phonetic perception as adaptive inference over acoustic-phonetics evidence and linguistic knowledge. With…
- arXiv cs.AIresearchBeyond Bag-of-Words: Diagnosing Compositional Binding Failures in Vision-Language Models
arXiv:2602.02043v2 Announce Type: replace-cross Abstract: Modern vision-language models struggle with basic compositional reasoning, failing to bind attributes to objects or relations to their referents. Existing benchma…
- arXiv cs.AIresearchAffective Flow Language Model for Emotional Support Conversation
arXiv:2602.08826v3 Announce Type: replace-cross Abstract: Large language models (LLMs) have advanced emotional support conversation, but existing alignment methods rely mainly on sparse preferences at the response level…
- arXiv cs.AIresearchSpectral-Sphere-Constrained Hyper-Connections
arXiv:2603.20896v2 Announce Type: replace-cross Abstract: Hyper-Connections (HC) extend residual connections into multiple streams, employing residual matrices for cross-stream mixing to enrich model expressivity. Howeve…
- arXiv cs.AIresearchGVCC: Zero-Shot Video Compression via Codebook-Driven Stochastic Rectified Flow
arXiv:2603.26571v4 Announce Type: replace-cross Abstract: At ultra-low bitrates, high-fidelity reconstruction requires sampling plausible videos from the posterior rather than regressing to oversmoothed conditional means…
- arXiv cs.AIresearchThe Shrinking Lifespan of LLMs in Science
arXiv:2604.07530v3 Announce Type: replace-cross Abstract: Scaling laws describe how language model capabilities grow with compute and data, but say nothing about how long a model matters once released. We introduce time-…
- arXiv cs.AIresearchEndogenous Information in Routing Games: Memory-Constrained Equilibria, Recall Braess Paradoxes, and Memory Design
arXiv:2604.11733v2 Announce Type: replace-cross Abstract: We study routing games in which travelers optimize over routes that are remembered or surfaced, rather than over a fixed exogenous action set. The paper develops…
- arXiv cs.AIresearchHuman-1 by Josh Talks: A Full-Duplex Conversational Modeling Framework in Hindi using Real-World Conversations
arXiv:2604.23295v3 Announce Type: replace-cross Abstract: Full-duplex spoken dialogue systems can model natural conversational behaviours such as interruptions, overlaps, and backchannels, yet such systems remain largely…
- arXiv cs.AIresearchTopology-Driven Anti-Entanglement Control for Soft Robots
arXiv:2605.05236v2 Announce Type: replace-cross Abstract: In the field of precision manufacturing in complex constrained environments, the role of soft robots is increasingly prominent, and the realization of anti-windin…
- arXiv cs.AIresearchTransformers Can Implement Preconditioned Richardson Iteration for In-Context Gaussian Kernel Regression
arXiv:2605.08475v3 Announce Type: replace-cross Abstract: In this paper, we study in-context kernel ridge regression (KRR) with Gaussian kernels and show, both theoretically and empirically, that a standard softmax-atten…