AI news archive.
10,661 articles filed under Research, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchGeometry-Aware Adaptation for Pretrained Models
arXiv:2307.12226v3 Announce Type: replace-cross Abstract: Machine learning models -- including prominent zero-shot models -- are often trained on datasets whose labels are only a small proportion of a larger label space.…
- arXiv cs.AIresearchUniGuardian: A Unified Defense for Detecting Prompt Injection, Backdoor Attacks and Adversarial Attacks in Large Language Models
arXiv:2502.13141v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) are vulnerable to attacks like prompt injection, backdoor attacks, and adversarial attacks, which manipulate prompts or models to gen…
- arXiv cs.AIresearchStructured-Noise Masked Modeling for Video, Audio and Beyond
arXiv:2503.16311v2 Announce Type: replace-cross Abstract: Masked modeling has emerged as a robust self-supervised learning framework. However, most methods rely on random masking, which disregards the structural properti…
- arXiv cs.AIresearchWaLLM -- Understanding Use and Engagement with a General-Purpose LLM on WhatsApp
arXiv:2505.08894v2 Announce Type: replace-cross Abstract: Large language model (LLM) chatbots are increasingly reaching users through messaging platforms (e.g. WhatsApp). However, these systems remain largely proprietary…
- arXiv cs.AIresearchHardening Soft Information: Evidence on Analyst Integration Costs
arXiv:2505.12269v4 Announce Type: replace-cross Abstract: We examine how the cost of transforming qualitative information into precise numerical estimates--a form of integration cost--creates a structural friction in exp…
- arXiv cs.AIresearchCOLORA: Efficient Fine-Tuning for Convolutional Models with a Study Case on Optical Coherence Tomography Image Classification
arXiv:2505.18315v5 Announce Type: replace-cross Abstract: We introduce CoLoRA (Convolutional Low-Rank Adaptation), a parameter-efficient fine-tuning method for convolutional neural networks (CNNs). CoLoRA extends LoRA to…
- arXiv cs.AIresearchIn Dialogue with Intelligence: Toward Insightful Co-Augmentation
arXiv:2505.22767v4 Announce Type: replace-cross Abstract: Dialogue with a large language model can lead a person to insight: a sudden change in how they understand a problem. This perspective asks how model activity rela…
- arXiv cs.AIresearchForward Target Propagation: A Forward-Only Approach to Global Error Credit Assignment via Local Losses
arXiv:2506.11030v2 Announce Type: replace-cross Abstract: Training neural networks has traditionally relied on backpropagation (BP), a gradient-based algorithm that, despite its widespread success, suffers from key limit…
- arXiv cs.AIresearchAre AI Coders Snitches? An Empirical Study of Pretraining Data Detection on Code Large Language Models
arXiv:2507.17389v2 Announce Type: replace-cross Abstract: Recent advances in code large language models (CodeLLMs) have made them indispensable tools in modern software engineering. However, these models occasionally pro…
- arXiv cs.AIresearchFairSSL: Fair Multimodal Self-Supervised Learning
arXiv:2508.16748v2 Announce Type: replace-cross Abstract: Prevalent multimodal self-supervised learning (SSL) methods rely on the redundancy assumption: that different views share substantial task-relevant information. W…
- arXiv cs.AIresearchWhat Drives Compositional Generalization in Visual Generative Models? The Importance of Continuous Training Objectives
arXiv:2510.03075v4 Announce Type: replace-cross Abstract: Compositional generalization, the ability to generate novel combinations of known concepts, is a key ingredient for visual generative models. Yet, not all mechani…
- arXiv cs.AIresearchIterative Topic Taxonomy Induction with LLMs: A Case Study of Electoral Advertising
arXiv:2510.15125v3 Announce Type: replace-cross Abstract: Social media platforms play a pivotal role in shaping political discourse, but the scale and rapid evolution of online content make systematic analysis difficult.…
- arXiv cs.AIresearchUrbanVLA: A Vision-Language-Action Model for Urban Micromobility
arXiv:2510.23576v2 Announce Type: replace-cross Abstract: Urban micromobility applications, such as delivery robots, demand reliable navigation across large-scale urban environments while following long-horizon route ins…
- arXiv cs.AIresearchCausal-Aware Tabular GANs with Reinforcement Learning
arXiv:2510.24046v2 Announce Type: replace-cross Abstract: Existing tabular data generation methods primarily focus on matching statistical distributions between real and synthetic data, often overlooking the preservation…
- arXiv cs.AIresearchConstant-Time Planning for Chaining Collision-free Motion to Manipulation Behaviors
arXiv:2512.00939v3 Announce Type: replace-cross Abstract: Recent progress in contact-rich robotic manipulation has been striking, yet most deployed systems remain confined to simple, scripted routines. One of the barrier…
- arXiv cs.AIresearchECHO: A Participatory Framework for Bias-Anchored AI Harm Anticipation
arXiv:2512.03068v2 Announce Type: replace-cross Abstract: Artificial Intelligence (AI) systems increasingly shape consequential decisions, creating value but also potential harms for individuals, social groups, and socie…
- arXiv cs.AIresearchExplainability of Complex AI Models with Correlation Impact Ratio
arXiv:2601.06701v2 Announce Type: replace-cross Abstract: Complex AI systems make better predictions but often lack transparency, limiting trustworthiness, interpretability, and safe deployment. Common post hoc AI explai…
- arXiv cs.AIresearchMeasuring Iterative Temporal Reasoning with Time Puzzles
arXiv:2601.07148v4 Announce Type: replace-cross Abstract: Tool use, such as web search, has become a standard capability even in freely available large language models (LLMs). However, existing benchmarks evaluate tempor…
- arXiv cs.AIresearchMedVL-SAM2: A unified 3D medical vision-language model for multimodal reasoning and prompt-driven segmentation
arXiv:2601.09879v2 Announce Type: replace-cross Abstract: Recent progress in medical vision-language models (VLMs) has achieved strong performance on image-level text-centric tasks such as report generation and visual qu…
- arXiv cs.AIresearchVISPA: Pluralistic Alignment via Automatic Value Selection and Activation
arXiv:2601.12758v2 Announce Type: replace-cross Abstract: As large language models are increasingly used in high-stakes domains, it is essential that their outputs reflect not average} human preference, rather range of v…
- arXiv cs.AIresearchIn Vino Veritas and Vulnerabilities: Examining LLM Safety via Drunk Language Inducement
arXiv:2601.22169v2 Announce Type: replace-cross Abstract: Humans are susceptible to undesirable behaviours and privacy leaks under the influence of alcohol. This paper investigates drunk language, i.e., text written unde…
- arXiv cs.AIresearchBridging the Sim-to-Real Gap with multipanda_ros2: A Real-Time ROS2 Framework for Multimanual Systems
arXiv:2602.02269v2 Announce Type: replace-cross Abstract: We present $multipanda\_ros2$, a novel open-source ROS2 architecture for multi-robot control of Franka Robotics robots. Leveraging ros2 control, this framework pr…
- arXiv cs.AIresearchModeling The Object Representations Underlying Human Physical Reasoning
arXiv:2602.12486v2 Announce Type: replace-cross Abstract: Humans appear to represent objects when reasoning about physics with coarse, volumetric "bodies" that smooth concavities, trading fine visual detail for efficient…
- arXiv cs.AIresearchTensorCommitments: A Lightweight Verifiable Inference for Large Language Models
arXiv:2602.12630v3 Announce Type: replace-cross Abstract: Most large language models (LLMs) run on external clouds: users send a prompt, pay for inference, and must trust that the remote GPU executes the LLM without any…
- arXiv cs.AIresearchCapabilities Ain't All You Need: Measuring Propensities in AI
arXiv:2602.18182v5 Announce Type: replace-cross Abstract: AI evaluation has primarily focused on measuring capabilities, with formal approaches inspired from Item Response Theory (IRT) being increasingly applied. Yet pro…
- arXiv cs.AIresearchInterviewSim: A Scalable Framework for Interview-Grounded Personality Simulation
arXiv:2602.20294v2 Announce Type: replace-cross Abstract: Simulating real personalities with large language models requires grounding generation in authentic personal data. Existing evaluation approaches rely on demograp…
- arXiv cs.AIresearchProtoDCS: Towards Robust and Efficient Open-Set Test-Time Adaptation for Vision-Language Models
arXiv:2602.23653v3 Announce Type: replace-cross Abstract: Large-scale Vision-Language Models (VLMs) exhibit strong zero-shot recognition, yet their real-world deployment is challenged by distribution shifts. While Test-T…
- arXiv cs.AIresearchStochastic Parrots or Singing in Harmony? Testing Five Leading LLMs for their Ability to Replicate a Human Survey with Synthetic Data
arXiv:2603.00059v4 Announce Type: replace-cross Abstract: How well can AI-derived synthetic research data replicate the responses of human participants? An emerging literature has begun to engage with this question, whic…
- arXiv cs.AIresearchMedFeat: Model-Aware and Explainability-Driven Feature Engineering with LLMs for Tabular Prediction
arXiv:2603.02221v3 Announce Type: replace-cross Abstract: In clinical tabular prediction, classical machine learning models with feature engineering often outperform neural methods. LLMs are increasingly used to automate…
- arXiv cs.AIresearchLarge Reward Models: Generalizable Online Robot Reward Generation with Vision-Language Models
arXiv:2603.16065v3 Announce Type: replace-cross Abstract: Reinforcement Learning (RL) has shown strong potential for improving robotic manipulation policies, yet its practical use remains bottlenecked by the difficulty o…
- arXiv cs.AIresearchDo Vision Language Models Understand Human Engagement in Games?
arXiv:2603.18480v2 Announce Type: replace-cross Abstract: Inferring human engagement from gameplay video is important for game design and player-experience research, yet it remains unclear whether vision--language models…
- arXiv cs.AIresearchHigh Volatility and Action Bias Distinguish LLMs from Humans in Group Coordination
arXiv:2604.02578v2 Announce Type: replace-cross Abstract: Humans exhibit remarkable abilities to coordinate in groups. As large language models (LLMs) become more capable, it remains an open question whether they can dem…
- arXiv cs.AIresearchExponential quantum advantage in processing massive classical data
arXiv:2604.07639v2 Announce Type: replace-cross Abstract: Broadly applicable quantum advantage, particularly in classical data processing and machine learning, has been a fundamental open problem. In this work, we prove…
- arXiv cs.AIresearchFrom Order to Distribution: An Exact Operator Framework for Forgetting in Continual Learning
arXiv:2604.13460v2 Announce Type: replace-cross Abstract: A central challenge in continual learning is forgetting: the loss of performance on previously learned tasks after learning new ones. Prior theory has analyzed fo…
- arXiv cs.AIresearchClinical Note Bloat Reduction for Efficient LLM Use
arXiv:2604.16364v3 Announce Type: replace-cross Abstract: Background: Clinical notes contain extensive duplicated text from templates, copy-paste, and auto-populated fields ("note bloat"), diluting clinical signal, limit…
- arXiv cs.AIresearchRewind-IL: Online Failure Detection and State Respawning for Imitation Learning
arXiv:2604.16683v2 Announce Type: replace-cross Abstract: Imitation learning has enabled robots to acquire complex visuomotor manipulation skills from demonstrations, but deployment failures remain a major obstacle, espe…
- arXiv cs.AIresearchBack into Plato's Cave: Examining Cross-modal Representational Convergence at Scale
arXiv:2604.18572v3 Announce Type: replace-cross Abstract: The Platonic Representation Hypothesis posits that neural networks trained on different modalities (e.g., text and images) converge toward a shared representation…
- arXiv cs.AIresearchVerbal tics in frontier language models: A critical review of current releases, research evidence, and public discussion
arXiv:2604.19139v4 Announce Type: replace-cross Abstract: Repeated praise, canned reassurance, familiar contrasts, and conspicuous vocabulary are recurring subjects in discussions of large language models. Their interpre…
- arXiv cs.AIresearchCompute Aligned Training: Optimizing for Test Time Inference
arXiv:2604.24957v3 Announce Type: replace-cross Abstract: Scaling test-time compute has emerged as a powerful mechanism for enhancing Large Language Model (LLM) performance. However, standard post-training paradigms, Sup…
- arXiv cs.AIresearchDomain-Adapted Small Language Models for Reliable Clinical Triage
arXiv:2604.26766v2 Announce Type: replace-cross Abstract: Accurate and consistent Emergency Severity Index (ESI) assignment remains a persistent challenge in emergency departments, where highly variable free-text triage…
- arXiv cs.AIresearchVIDA: A Dataset for Visually Dependent Ambiguity in Multimodal Machine Translation
arXiv:2605.02035v4 Announce Type: replace-cross Abstract: Ambiguity resolution is a key challenge in multimodal machine translation (MMT), where models must genuinely leverage visual input to map an ambiguous expression…
- arXiv cs.AIresearchLensVLM: Selective Context Expansion for Compressed Visual Representation of Text
arXiv:2605.07019v4 Announce Type: replace-cross Abstract: Vision Language Models (VLMs) offer the exciting possibility of processing text as rendered images, bypassing the need for tokenizing the text into long token seq…
- arXiv cs.AIresearchYour Language Model is Its Own Critic: Reinforcement Learning with Value Estimation from Actor's Internal States
arXiv:2605.07579v4 Announce Type: replace-cross Abstract: Reinforcement learning with verifiable rewards (RLVR) for Large Reasoning Models rests on variance reduction, which requires both a reliable baseline and high pro…
- arXiv cs.AIresearchDynGhost: Temporally-Modelled Transformer for Dynamic Ghost Imagings
arXiv:2605.10185v3 Announce Type: replace-cross Abstract: Ghost imaging reconstructs spatial information from a single-pixel bucket detector by correlating structured illumination patterns with scalar intensity measureme…
- arXiv cs.AIresearchReForge: Refining Merged Models with Anchor-Regularized Regression
arXiv:2605.12843v3 Announce Type: replace-cross Abstract: Model merging aims to combine multiple task-specific expert models into a single model without joint retraining, offering a practical alternative to multi-task le…
- arXiv cs.AIresearchProbing Persona-Dependent Preferences in Language Models
arXiv:2605.13339v4 Announce Type: replace-cross Abstract: Large language models (LLMs) can be said to have preferences: they reliably pick certain tasks and outputs over others, and preferences shaped by post-training an…
- arXiv cs.AIresearchGPart: End-to-End Isometric Fine-Tuning via Global Parameter Partitioning
arXiv:2605.14841v3 Announce Type: replace-cross Abstract: Low-rank adaptation (LoRA) has become a dominant paradigm for parameter-efficient fine-tuning (PEFT) of large-scale deep learning models. However, its bilinear pa…
- arXiv cs.AIresearchREALM: Retrospective Encoder Alignment for LFP Modeling
arXiv:2605.14867v4 Announce Type: replace-cross Abstract: Spike activity has been the dominant neural signal for behavior decoding because its high spatiotemporal resolution supports accurate decoding. However, as intrac…
- arXiv cs.AIresearchUniversal Approximation of Nonlinear Operators and Their Derivatives
arXiv:2605.15285v4 Announce Type: replace-cross Abstract: We show that Universal Approximation (UA) of nonlinear operators and their derivatives via Operator Learning (OL) architectures fails in ${C^k_F}$ (Fr\'echet) com…
- arXiv cs.AIresearchReshape and Recur: Improving SSMs with Input Reshaping and Depth Recurrence
arXiv:2605.16048v2 Announce Type: replace-cross Abstract: State Space Models (SSMs) are increasingly deployed in the Edge because they offer, at comparable performance, a smaller memory/training/inference footprint, comp…