AI news archive.
10,659 articles filed under Research, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchBreaking the Mirror: Activation-Based Mitigation of Self-Preference in LLM Evaluators
arXiv:2509.03647v3 Announce Type: replace-cross Abstract: Large language models (LLMs) increasingly serve as automated evaluators, yet they suffer from "self-preference bias": a tendency to favor their own outputs over t…
- arXiv cs.AIresearchQubit-centric Transformer for Surface Code Decoding
arXiv:2510.11593v3 Announce Type: replace-cross Abstract: For reliable large-scale quantum computation, quantum error correction (QEC) is essential to protect logical information distributed across multiple physical qubi…
- arXiv cs.AIresearchPredicting kernel regression learning curves from only raw data statistics
arXiv:2510.14878v3 Announce Type: replace-cross Abstract: We study kernel regression with common rotation-invariant kernels on real datasets including CIFAR-5m, SVHN, and ImageNet. We give a theoretical framework that pr…
- arXiv cs.AIresearchSpeak to a Protein: An Interactive Multimodal Co-Scientist
arXiv:2510.17826v2 Announce Type: replace-cross Abstract: Building a working mental model of a protein typically requires weeks of reading, cross-referencing crystal and predicted structures, and inspecting ligand comple…
- arXiv cs.AIresearchDistDF: Time-Series Forecasting Needs Joint-Distribution Wasserstein Alignment
arXiv:2510.24574v3 Announce Type: replace-cross Abstract: Training time-series forecasting models requires aligning the conditional distribution of model forecasts with that of the label sequence. The standard direct for…
- arXiv cs.AIresearchQuadratic Direct Forecast for Training Multi-Step Time-Series Forecast Models
arXiv:2511.00053v2 Announce Type: replace-cross Abstract: The design of learning objectives is central to training time-series forecasting models. Existing learning objectives such as mean squared error mostly treat each…
- arXiv cs.AIresearchAligning LLMs with Biomedical Knowledge using Balanced Fine-Tuning
arXiv:2511.21075v4 Announce Type: replace-cross Abstract: Engineering LLMs to accelerate life sciences research requires a robust alignment with biomedical knowledge. We observe that biomedical text exhibits a fundamenta…
- arXiv cs.AIresearchCross-Lingual Activation Steering for Multilingual Language Models
arXiv:2601.16390v2 Announce Type: replace-cross Abstract: Large language models exhibit strong multilingual capabilities, yet significant performance gaps persist between dominant and non-dominant languages. Prior work a…
- arXiv cs.AIresearchIntersectional Fairness via Mixed-Integer Optimization
arXiv:2601.19595v2 Announce Type: replace-cross Abstract: The deployment of Artificial Intelligence in high-risk domains, such as finance and healthcare, necessitates models that are both fair and transparent. While regu…
- arXiv cs.AIresearchFast and Efficient Asynchronous Gossip Algorithm for Robust and Non-Smooth Convex Decentralized Learning
arXiv:2601.20571v3 Announce Type: replace-cross Abstract: Asynchronous primal-dual methods for decentralized non-smooth convex optimization often require each node to maintain $\mathcal{O}(d)$ auxiliary variables, where…
- arXiv cs.AIresearchRecommender system in X inadvertently profiles ideological positions of users
arXiv:2602.02624v2 Announce Type: replace-cross Abstract: Several data protection laws restrict processing that reveals political opinions, irrespective of the controller's intent. Whether recommender systems do so as a…
- arXiv cs.AIresearchSimToolReal: An Object-Centric Policy for Zero-Shot Dexterous Tool Manipulation
arXiv:2602.16863v3 Announce Type: replace-cross Abstract: The ability to manipulate tools significantly expands the set of tasks a robot can perform. Yet, tool manipulation represents a challenging class of dexterity, re…
- arXiv cs.AIresearchAdaptive Bidirectional Task Interaction for Joint Segmentation and Classification of Breast Ultrasound
arXiv:2603.01295v2 Announce Type: replace-cross Abstract: Joint lesion segmentation and tissue classification in breast ultrasound are usually trained with a shared encoder, so the two branches stop exchanging informatio…
- arXiv cs.AIresearchReal-Time Generation of Game Video Commentary with Multimodal LLMs: Pause-Aware Decoding Approaches
arXiv:2603.02655v2 Announce Type: replace-cross Abstract: Real-time video commentary generation provides textual descriptions of ongoing events in videos. It supports accessibility and engagement in domains such as sport…
- arXiv cs.AIresearchWorld Properties without World Models: Distributional Associations and the Interpretation of Decoding Results from Language Models
arXiv:2603.04317v2 Announce Type: replace-cross Abstract: A growing literature shows that variables can be linearly decoded from the activations of large language models (LLMs). These range from properties of the world,…
- arXiv cs.AIresearchUnderstanding Moral Reasoning Trajectories in Large Language Models: Toward Probing-Based Explainability
arXiv:2603.16017v2 Announce Type: replace-cross Abstract: Large language models (LLMs) increasingly participate in morally sensitive decision-making, yet how they organize ethical frameworks across reasoning steps remain…
- arXiv cs.AIresearchFederated Mixture-of-Experts Alignment on Mobile Edge Networks under Data Heterogeneity
arXiv:2603.21276v2 Announce Type: replace-cross Abstract: The growing demand for on-device large language model (LLM) services on mobile edge devices has driven the adoption of Mixture-of-Experts (MoE) architectures, whi…
- arXiv cs.AIresearchUnbiased Reward Modeling from Implicit Feedback for LLM Alignment
arXiv:2603.23184v2 Announce Type: replace-cross Abstract: Despite the success of reinforcement learning from human feedback (RLHF), existing reward modeling methods largely rely on explicit feedback, which is costly to c…
- arXiv cs.AIresearchOne-Shot Localisation of the Global Minimum of a Noisy One-Dimensional Function: A Controlled Comparison of an Iterative Neural Minimizer, Set Transformers and Classical Estimators
arXiv:2604.03614v5 Announce Type: replace-cross Abstract: We study passive global optimisation: from twenty noisy samples of an unknown one-dimensional function, with no further queries, estimate where its global minimum…
- arXiv cs.AIresearchSinkhorn doubly stochastic attention rank decay analysis
arXiv:2604.07925v2 Announce Type: replace-cross Abstract: The self-attention mechanism is central to the success of Transformer architectures. However, standard row-stochastic attention has been shown to suffer from sign…
- arXiv cs.AIresearchCross-Cultural Value Attribution in Large Vision-Language Models
arXiv:2604.09945v3 Announce Type: replace-cross Abstract: The rapid adoption of large vision-language models (LVLMs) in recent years has been accompanied by growing fairness concerns due to their propensity to reinforce…
- arXiv cs.AIresearchLearning Visual Feature-Based World Models via Residual Latent Action
arXiv:2605.07079v2 Announce Type: replace-cross Abstract: World models predict future transitions from observations and actions. Existing works predominantly focus on image generation only. Visual feature-based world mod…
- arXiv cs.AIresearchVoice "Cloning" is Style Transfer
arXiv:2605.16578v4 Announce Type: replace-cross Abstract: Artificially generated speech is increasingly embedded in everyday life. Voice cloning in particular enables applications where identity preservation is important…
- arXiv cs.AIresearchStochastic Penalty-Barrier Method for Constrained Machine Learning
arXiv:2605.18618v3 Announce Type: replace-cross Abstract: Constrained Machine Learning (CML) enables fairness-aware training, physics-informed neural networks, and integration of symbolic domain knowledge into statistica…
- arXiv cs.AIresearchReinforcement Learning over Predictive Distributions for LLM Regression
arXiv:2605.20740v2 Announce Type: replace-cross Abstract: Large language models (LLMs) have emerged as flexible regressors capable of predicting real-valued quantities from heterogeneous inputs. Yet most LLM regression o…
- arXiv cs.AIresearchD3S2: Diffusion-Guided Dataset Distillation for Semantic Segmentation
arXiv:2605.25022v2 Announce Type: replace-cross Abstract: Dataset distillation (DD) aims to compress large-scale datasets into compact synthetic sets while preserving training efficacy. However, existing studies mainly f…
- arXiv cs.AIresearchSeeing Isn't Knowing: Do VLMs Know When Not to Answer Spatial Questions (and Why)?
arXiv:2605.30557v2 Announce Type: replace-cross Abstract: Spatial reasoning benchmarks typically evaluate whether vision-language models can derive the correct answer from a visual observation. Yet in real 3D environment…
- arXiv cs.AIresearchThe Terminal Representation in Reinforcement Learning
arXiv:2605.31289v3 Announce Type: replace-cross Abstract: Representation learning is a powerful tool for spatio-temporal abstraction within reinforcement learning (RL). Two well established approaches are through the suc…
- arXiv cs.AIresearchFFR: Forward-Forward Learning for Regression
arXiv:2606.03927v2 Announce Type: replace-cross Abstract: The Forward-Forward (FF) algorithm offers a computationally efficient and biologically plausible alternative to backpropagation (BP) by training neural networks t…
- arXiv cs.AIresearchCharacterize Then Distill: Mechanistic Reasoning in Large Output Spaces
arXiv:2606.06840v4 Announce Type: replace-cross Abstract: Reasoning-trained language models can select, zero-shot, a small set of relevant labels from thousands to hundreds of thousands of candidates. We ask how they do…
- arXiv cs.AIresearchSensitivity Shaping for Latent Modeling
arXiv:2606.14585v2 Announce Type: replace-cross Abstract: Generative dynamics models enable planning in challenging systems, but safe deployment requires detecting policy-induced out-of-distribution (OOD) transitions. Ex…
- arXiv cs.AIresearchSAE++: Cascaded Sparse Autoencoders Learn Multi-Level Visual Concepts in Multimodal LLMs
arXiv:2606.16193v3 Announce Type: replace-cross Abstract: Multimodal Large Language Models (MLLMs) have demonstrated strong performance on vision-language tasks, yet their internal visual representations remain difficult…
- arXiv cs.AIresearchExplaining Attention with Program Synthesis
arXiv:2606.19317v3 Announce Type: replace-cross Abstract: A longstanding goal of research on interpretable deep learning is to replace opaque neural computations with human-meaningful symbolic descriptions. In this paper…
- arXiv cs.AIresearchPrime Fourier Embeddings: A Principled Basis for Modular Arithmetic
arXiv:2606.23044v3 Announce Type: replace-cross Abstract: Numbers have algebraic structure that standard neural embeddings often fail to expose. We introduce Prime Fourier Embeddings (PFE), which encode integers as prime…
- arXiv cs.AIresearchGuided Action Flow: Value-Guided Sampling for Frozen Vision-Language-Action Policies
arXiv:2607.02092v4 Announce Type: replace-cross Abstract: Reinforcement learning can improve vision-language-action (VLA) policies beyond supervised fine-tuning, although this typically involves further updates to the po…
- arXiv cs.AIresearch3D-DefectBench: A Controlled Factorial Study of Vision-Language Model Evaluation Pipelines for Fine-Grained 3D Generation Defects
arXiv:2607.10826v2 Announce Type: replace-cross Abstract: Automated evaluation is essential for scaling generative 3D systems, where exhaustive human review is costly and slow. Yet the reliability of an automated judge d…
- arXiv cs.AIresearchRetrieval-Augmented Interpretable Learning: Towards Task-Specific Zero-Shot Models in Healthcare
arXiv:2607.17508v3 Announce Type: replace-cross Abstract: We introduce Retrieval-Augmented Interpretable Learning (RAIL), a probabilistic meta-learning framework for zero-shot generation of task-specific interpretable mo…
- arXiv cs.AIresearchVariational-Ising-Attention:Tailored Attention Matters for Science
arXiv:2607.23634v2 Announce Type: replace-cross Abstract: Attention enables context modeling via query-key scoring with softmax normalization. Driven by industrial long-context demands, mainstream research has converged…
- arXiv cs.AIresearchMulti-Scale Structural Features for Continual, Comprehensible Visual Recognition in a Developmental Learning Framework
arXiv:2607.25531v2 Announce Type: replace-cross Abstract: Contemporary machine learning struggles to learn continually, reuse prior knowledge, and expose a comprehensible internal structure. A recently proposed developme…
- arXiv cs.AIresearchDiagnosing Fine-Grained Inconsistency Classification in Financial Disclosure Text
arXiv:2607.26368v3 Announce Type: replace-cross Abstract: Financial disclosures may contain numerical, temporal, referential, factual, and policy inconsistencies that require different evidence and reasoning to diagnose.…
- arXiv cs.AIresearchDo AI weather models miss extremes?
arXiv:2608.09972v2 Announce Type: replace-cross Abstract: AI weather models are often reported to underestimate extremes, but most evidence concerns deterministic regression models verified against reanalysis. We evaluat…
- arXiv cs.AIresearchPertMind: Eliciting Emergent Biological Reasoning in LLM via Reinforcement Learning on Cellular Perturbation Data
arXiv:2608.16419v3 Announce Type: replace-cross Abstract: Large language models can describe mechanisms, yet scalable post-training still depends on costly, manually curated biological reasoning traces. Here we show that…
- arXiv cs.AIresearchThe Latent Diagnostic Taxonomy: A Framework for Constructing Classifiers and Diagnosing Their Decisions, Applied to Prompt Injection Detection
arXiv:2608.26423v2 Announce Type: replace-cross Abstract: This paper proposes a framework for constructing a classifier as a safeguard layer, and for developing a complementary diagnostic that identifies which of the cla…
- LessWrongresearchChallenging the unawareness argument with third actions and mixed actions
[ x-posted from the EA Forum ] 1. Introduction Here’s Anthony DiGiovanni’s unawareness argument, quoted from his summary post (footnotes omitted): Let’s say that we c-prefer A over B if the reason we prefer A is an impar…
- Engadget AIresearchOpenAI just posted hundreds more results on major math problems
The company said that most results were produced in a response to a single prompt given to a single AI agent.
- The Verge AIresearchOpenAI drops another batch of mathematical breakthroughs
OpenAI has revealed solutions to a number of long-standing mathematics problems produced by an unreleased frontier model in a batch of 722 manuscripts, covering 372 result families that group related papers. It extends a…
- Google ResearchresearchAsk a Scientist: How are researchers using AI to help pregnant women access ultrasounds?
By pairing AI with “blind sweep” ultrasounds, Google researchers found a way to get more people the prenatal ultrasounds they need.
- The DecoderresearchMicrosoft publishes Nobel economist's bearish AI forecast of just 1.5% GDP growth over a decade
Microsoft published a bearish AI outlook from Nobel economist Daron Acemoglu. He predicts about 1.5 percent GDP growth over ten years and at most five percent of jobs replaced. Bigger models won't move the needle, he arg…
- WIRED AIresearchOpenAI Is Pissing Off a Bunch of Mathematicians—Again
“There’s a perception of mobster behavior” from leading AI companies, one mathematician tells WIRED as OpenAI prepares to release more than 100 new solutions to unsolved problems.
- Microsoft ResearchresearchWhat AI gets wrong and what failure teaches us
Jennifer Neville did not want to go into computer science—but that’s exactly where she landed. Neville discusses the starts and stops that led to her professional sweet spot and her work identifying “surprising failures”…