AI news archive.
10,659 articles filed under Research, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchAnatomy of LLM Sycophancy: What a Flip Rate Hides
arXiv:2610.06522v1 Announce Type: cross Abstract: A model under pushback can correct itself, capitulate, or hold, and one flip rate counts a correction and a capitulation alike. Using SycoLens, a modular replay protocol,…
- arXiv cs.AIresearchSymmetry and AI-assisted discovery of magic-state factories
arXiv:2610.06535v1 Announce Type: cross Abstract: Magic-state distillation is a major resource cost in fault-tolerant quantum computing. The cost of a magic-state factory depends strongly on its failure rate, which grows…
- arXiv cs.AIresearchBrainTRACE: Tracing Longitudinal, Multimodal, and Volumetric Evidence in Brain MRI Clinical Reasoning
arXiv:2610.06571v1 Announce Type: cross Abstract: Brain MRI interpretation is a longitudinal clinical reasoning problem: radiologists compare serial studies, integrate information across MRI sequences, localize findings…
- arXiv cs.AIresearchSimForcing: Distilling Simulation Motion Priors into Real-Domain Robot World Models
arXiv:2610.06598v1 Announce Type: cross Abstract: Action-conditioned robot world models must respond precisely to robot trajectories while preserving realistic visual dynamics, yet learning both from heterogeneous robot…
- arXiv cs.AIresearchFrozen Factor or Spectral Band? Disentangling Two Choices in Low-Rank LoRA
arXiv:2610.06621v1 Announce Type: cross Abstract: Spectral variants of low-rank adaptation (LoRA) choose both a subspace and which factor to freeze. We separate these choices by freezing the input factor A or output fact…
- arXiv cs.AIresearchDifferentially Private Mixing of Public Datasets Improves Private Learning
arXiv:2610.06636v1 Announce Type: cross Abstract: Many machine learning applications involve sensitive data and therefore require training under differential privacy (DP). However, DP training often degrades model utilit…
- arXiv cs.AIresearchAffordCraft: Scalable Construction of Task-Ready Simulation Assets from Single Images
arXiv:2610.06643v1 Announce Type: cross Abstract: Robot learning in simulation depends on the objects the simulator offers. Many tasks need objects with separate parts, joints that allow the required motion, and physical…
- arXiv cs.AIresearchClosing the Context Gap: Activation Alignment for Tabular In-Context Learning
arXiv:2610.06679v1 Announce Type: cross Abstract: Tabular foundation models perform in-context learning (ICL) by conditioning predictions on labeled training examples provided as context. Unlike traditional models that s…
- arXiv cs.AIresearchBRANCH-MoE: Balance-Aware Tree Routing for Large Embedding Models
arXiv:2610.06725v1 Announce Type: cross Abstract: Mixture-of-experts (MoE) layers increase model capacity without a proportional increase in per-example computation. However, conventional flat routers can yield imbalance…
- arXiv cs.AIresearchBalancing Memory Pathways: Analyzing and Improving Memory Utilization in Hybrid LMs
arXiv:2610.06750v1 Announce Type: cross Abstract: Recurrent-attention hybrid language models (LMs), which interleave attention and recurrent layers, are increasingly used to combine the efficiency of the recurrent layers…
- arXiv cs.AIresearchMatrixFormer: A Foundation Model for Matrix Completion
arXiv:2610.06751v1 Announce Type: cross Abstract: Matrix completion underlies problems from tabular imputation to causal inference, yet existing tabular foundation models treat it as entry-by-entry prediction, repeating…
- arXiv cs.AIresearchIdeaLens: Detecting AI Ideas in Long-form Writing
arXiv:2610.06778v1 Announce Type: cross Abstract: While modern AI detectors identify who wrote the words, emerging policies on AI use increasingly hinge on a different question: who came up with the ideas? We introduce I…
- arXiv cs.AIresearchMC-Sparse: Deconstructing and Closing the Dense-Sparse Attention Gap in Diffusion Transformers
arXiv:2610.06801v1 Announce Type: cross Abstract: Sparse attention is a primary approach to reducing the latency of diffusion transformers in long-sequence generation tasks, such as video and high-resolution 3D asset gen…
- arXiv cs.AIresearchSharpen Without Search: On-Policy Distillation of Sequence-Level Power Distribution
arXiv:2610.06804v1 Announce Type: cross Abstract: A language model can give a correct answer more probability than any single incorrect answer and still usually sample an incorrect one, because the incorrect answers toge…
- arXiv cs.AIresearchTAPDreamer: Transferable Adversarial Patches for World Action Models
arXiv:2610.06814v3 Announce Type: replace-cross Abstract: World models learn to predict how their environment will evolve, making them an important foundation for general-purpose robotic control. Yet world action models…
- arXiv cs.AIresearchParadee: Distilling Kokoro-82M into an 8M-Parameter Single-Voice Text-to-Speech Model
arXiv:2610.06817v1 Announce Type: cross Abstract: We distill Kokoro-82M, a widely used open text-to-speech model with 54 voices, into Paradee, an 8.07M-parameter model that speaks one of them. Paradee keeps Kokoro's arch…
- arXiv cs.AIresearchDeep Learning for Sleep Heart Rate Estimation from Accelerometers: Toward Population-Scale Cardiac Insight Without Optical Sensors
arXiv:2610.06823v1 Announce Type: cross Abstract: Large longitudinal cohorts often contain wrist accelerometry without optical heart-rate sensing, motivating recovery of cardiac information from motion signals already co…
- arXiv cs.AIresearchUniSlider: Perceptually Uniform Sliders for Continuous Image Editing
arXiv:2610.06831v1 Announce Type: cross Abstract: Sliders provide an intuitive interface for continuous image editing. In current generative approaches, however, the slider is simply a rescaling of the method's strength…
- arXiv cs.AIresearchLearning to Read the Contextual Tokens in Diffusion Transformers
arXiv:2610.06844v1 Announce Type: cross Abstract: Multimodal Diffusion Transformers (MM-DiTs) jointly process visual and textual representations throughout generation. These models repeatedly update the text tokens throu…
- arXiv cs.AIresearchBase Models Can Reason By Taking a Cue From Training Data
arXiv:2610.06851v1 Announce Type: cross Abstract: In this paper, we study how training data creates associations between the tokens at the start of a base model's response and the reasoning behavior that follows. First,…
- arXiv cs.AIresearchGFPack++: Attention-Driven Gradient Fields for Optimizing 2D Irregular Packing
arXiv:2406.07579v2 Announce Type: replace Abstract: 2D irregular packing is a classic combinatorial optimization problem with various applications, such as material utilization and texture atlas generation. Due to its NP…
- arXiv cs.AIresearchAnswer Set Networks: Casting Answer Set Programming into Deep Learning
arXiv:2412.14814v2 Announce Type: replace Abstract: Although Answer Set Programming (ASP) allows constraining neural-symbolic (NeSy) systems, its employment is hindered by the prohibitive costs of computing stable models…
- arXiv cs.AIresearchPaTAS: A Framework for Trust Propagation in Neural Networks Using Subjective Logic
arXiv:2511.20586v5 Announce Type: replace Abstract: Trustworthiness has become a key requirement for deploying artificial intelligence in safety-critical applications, yet conventional metrics such as accuracy fail to ca…
- arXiv cs.AIresearchNeutral Substrates: A Design Constraint for Shared Records Under Persistent Interpretive Disagreement
arXiv:2601.14271v4 Announce Type: replace Abstract: Shared accountability records must often remain useful to parties who disagree about causation, responsibility, and normative interpretation. Suppressing these claims w…
- arXiv cs.AIresearchAI Mental Models: Learned Intuition and Deliberation in a Bounded Neural Architecture
arXiv:2603.22561v2 Announce Type: replace Abstract: This paper asks whether a bounded neural architecture can exhibit a meaningful division of labor between intuition and deliberation on a classic 64-item syllogistic rea…
- arXiv cs.AIresearchReLope: From Hidden-State Probing to a Decision Module for Multimodal LLM Routing
arXiv:2603.24787v3 Announce Type: replace Abstract: Routing balances performance and cost in hybrid systems by escalating selected queries from a lightweight model to a powerful but expensive one. Hidden-state probes pro…
- arXiv cs.AIresearchThe Ultimate Tutorial for AI-driven Scale Development in Generative Psychometrics: Releasing AIGENIE from its Bottle
arXiv:2603.28643v2 Announce Type: replace Abstract: Psychological scale development has traditionally required extensive expert involvement, iterative revision, and large-scale pilot testing before psychometric evaluatio…
- arXiv cs.AIresearchAI Assistance Reduces Persistence and Hurts Independent Performance
arXiv:2604.04721v5 Announce Type: replace Abstract: People often optimize for long-term goals in collaboration: A mentor or companion doesn't just answer questions, but also scaffolds learning, tracks progress, and prior…
- arXiv cs.AIresearchHigh-Precision Estimation of the State-Space Complexity of Shogi via the Monte Carlo Method
arXiv:2604.06189v2 Announce Type: replace Abstract: Determining the state-space complexity of Shogi (Japanese Chess) has been a challenging problem, with previous combinatorial estimates leaving a gap of five orders of m…
- arXiv cs.AIresearchRetrieval-Augmented Generation Must Move Beyond Factual Grounding to Represent Diverse Opinions
arXiv:2604.12138v5 Announce Type: replace Abstract: Retrieval-Augmented Generation (RAG) systems are built on an unexamined assumption - that queries have correct answers and retrieval should converge toward them. This p…
- arXiv cs.AIresearchInference-Time Amplification of Weak Reasoning Models
arXiv:2605.14163v2 Announce Type: replace Abstract: How much of the capability of a reasoning model exposed by repeated sampling can an imperfect selector recover? We study this problem as {\em inference-time amplificati…
- arXiv cs.AIresearchGrounded Continuation: A Linear-Time Runtime Verifier for LLM Conversations
arXiv:2605.14175v3 Announce Type: replace Abstract: In a long conversation, an LLM may produce a fluent continuation that rests on premises the conversation has already abandoned. Context-manipulation attacks exploit pre…
- arXiv cs.AIresearchFrom Table to Cell: Attention for Better Reasoning with TABALIGN
arXiv:2605.14465v2 Announce Type: replace Abstract: Multi-step LLM reasoning over structured tables fails because planning and execution share no explicit cell-grounding contract. Existing methods constrain the planner t…
- arXiv cs.AIresearchNudging Beyond the Comfort Zone: Efficient Strategy-Guided Exploration for RLVR
arXiv:2605.15726v2 Announce Type: replace Abstract: Reinforcement learning with verifiable rewards (RLVR) is a scalable paradigm for improving the mathematical reasoning of large language models, but it is fundamentally…
- arXiv cs.AIresearchECG-WM: A Physiology-Informed ECG World Model for Clinical Intervention Simulation
arXiv:2605.17580v2 Announce Type: replace Abstract: Electrocardiogram (ECG)-based models have achieved strong performance in diagnostic tasks, yet they remain limited in modeling how cardiac dynamics evolve under externa…
- arXiv cs.AIresearchDr-CiK: A Benchmark testing Deep Research for Context-Aided Forecasting
arXiv:2605.27904v2 Announce Type: replace Abstract: Time series forecasting in real-world settings often depends not only on historical observations, but also on external context that must be actively discovered from noi…
- arXiv cs.AIresearchMEMENTO: Leveraging Web as a Learning Signal for Low-Data Domains
arXiv:2605.29795v2 Announce Type: replace Abstract: Real-world tasks often lack large labeled datasets, motivating extensive work on learning in low-data regimes. Existing approaches such as few-shot prompting, instructi…
- arXiv cs.AIresearchBeyond Objective Equivalence: Constraint Injection for LLM-Based Optimization Modeling on Vehicle Routing Problems
arXiv:2606.04816v2 Announce Type: replace Abstract: Large language models (LLMs) can generate executable solver code from natural-language descriptions of optimization problems. However, existing verification signals foc…
- arXiv cs.AIresearchScaling Participation in Modular AI Systems
arXiv:2606.07812v2 Announce Type: replace Abstract: Humanity is a mosaic of multifaceted talents and needs, and any truly intelligent AI must reflect that richness. Yet the LLMs used by all are built by the few -- a cent…
- arXiv cs.AIresearchSafety is Contextual, LLM-Judges Are Not: Navigating the Rigid Priors of Evaluators
arXiv:2606.07874v2 Announce Type: replace Abstract: LLMs-as-judges are the primary way to evaluate safety at scale. Despite their importance, LLM-judges themselves are rarely evaluated beyond human agreement in simple, s…
- arXiv cs.AIresearchCIAware-Bench: Benchmarking Control Intervention Awareness Across Frontier LLMs
arXiv:2606.11063v2 Announce Type: replace Abstract: AI control protocols oversee untrusted models by monitoring their actions and modifying potentially unsafe steps, often using a trusted model. This partially tampers wi…
- arXiv cs.AIresearchDART: Draft-Agreement Routing for Training-Free Adaptive Thinking Budgets in Hybrid Reasoning Models
arXiv:2606.23181v4 Announce Type: replace Abstract: Hybrid reasoning models can answer directly or spend extra tokens on extended thinking. A practical router should choose between these modes for each query, so easy pro…
- arXiv cs.AIresearchTIPS: Topological Ill-Posedness Probing and Steering in Large Language Models
arXiv:2606.23590v2 Announce Type: replace Abstract: Ill-posed questions, including those involving ambiguity, under-specification, or conflicting statements, may admit no valid answer or multiple plausible answers, posin…
- arXiv cs.AIresearchMORPH: Generative Retrieval via Diffusion Transformer with Metric-Ordered Sequence Training and Hybrid-Policy Preference Optimization
arXiv:2606.26899v2 Announce Type: replace Abstract: Embedding-based retrieval typically returns highest-scoring items, but many production scenarios require items that satisfy a target attribute while preserving a fine-g…
- arXiv cs.AIresearchLook-Before-Move: Narrative-Grounded World Visual Attention in Dynamic 3D Story Worlds
arXiv:2606.26964v3 Announce Type: replace Abstract: As embodied AI and world models increasingly operate in dynamic 3D environments, visual perception must move beyond passively interpreting given observations toward act…
- arXiv cs.AIresearchBeyond Compilation: Evaluating Faithful Natural-Language-to-Lean Statement Formalization
arXiv:2606.31002v4 Announce Type: replace Abstract: Lean verifies that a generated declaration is well typed, but cannot check whether it states what the user intended. We measure how far compilation overstates faithfuln…
- arXiv cs.AIresearchSubliminal Clocks: Latent Time Modelling in Diffusion Language Models
arXiv:2607.01774v3 Announce Type: replace Abstract: Diffusion Language Models (DLMs) have recently emerged as a promising alternative to autoregressive models. Unlike standard diffusion-based approaches, DLMs are not exp…
- arXiv cs.AIresearchMeasuring Intelligence Beyond Human Scale
arXiv:2607.07040v2 Announce Type: replace Abstract: How can we measure intelligence beyond human capability? Human-authored benchmarks saturate, and above human capability, examiners may not know which tasks are both har…
- arXiv cs.AIresearchWhat Keeps Vision-Language Models Looking at the Image?
arXiv:2607.12815v3 Announce Type: replace Abstract: When do vision-language models need direct access to the image while generating an answer? We study image dependence during answer generation by examining how the visua…
- arXiv cs.AIresearchA Dual-Hypothesis Reasoning Framework for LLM Guardrails
arXiv:2607.17575v3 Announce Type: replace Abstract: We propose ARBITER, a novel LLM guardrail framework that introduces two key ideas: (i) dual-hypothesis reasoning, a reasoning method for LLM guardrails that explicitly…