AI news archive.
10,660 articles filed under Research, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchStochasticity Is Not the Hard Part: Reduction and Complexity in Instructional Sequencing over Prerequisite DAGs
arXiv:2608.05455v2 Announce Type: replace Abstract: When a student must learn concepts connected by prerequisite dependencies, when does the order of instruction matter, and what does it cost to find the best one? We stu…
- arXiv cs.AIresearchFrom Behavior to Mechanism: Tracing Divergent Response Modes in Frontier Language Models
arXiv:2608.06578v2 Announce Type: replace Abstract: Frontier language models are trained with distinct data, objectives, and safety pipelines, but whether those differences produce measurably different behavior under ste…
- arXiv cs.AIresearchSDDBMs: Soft Denoising Diffusion Bridge Models
arXiv:2608.08594v3 Announce Type: replace Abstract: Diffusion bridge models leverage Doob's \(h\)-transform to construct stochastic transports between arbitrary endpoint distributions, and have shown strong potential in…
- arXiv cs.AIresearchEvaluating Large Language Model Performance on International Maritime Dangerous Goods Code Compliance
arXiv:2608.21036v2 Announce Type: replace Abstract: The transport of dangerous goods by sea is a high-consequence activity governed by the International Maritime Dangerous Goods (IMDG) Code, a complex regulatory framewor…
- arXiv cs.AIresearchFrom Solver Feedback to Faithful Plans: Multi-Role Reinforcement Learning for Symbolic Planning
arXiv:2608.21897v2 Announce Type: replace Abstract: Reliable planning requires converting natural-language instructions into executable symbolic specifications, yet large language models remain brittle without costly PDD…
- arXiv cs.AIresearchEscaping Reasoning Basin Collapse with History-Biased Search
arXiv:2609.00738v3 Announce Type: replace Abstract: Inference-time search with large language models (LLMs) often concentrates on a small set of structurally or semantically similar trajectories, leaving alternative reas…
- arXiv cs.AIresearchWhat Matters in On-Policy Distillation? A Perspective on Data Efficiency and Data Selection
arXiv:2609.05198v2 Announce Type: replace Abstract: On-Policy Distillation (OPD) has emerged as a widely adopted post-training paradigm for enhancing large language models in reasoning domains. However, the data-centric…
- arXiv cs.AIresearchRedKnot-MLA: Multi-Head Offline-Online Reuse for DeepSeek-V4 Long-Context Serving
arXiv:2609.07008v2 Announce Type: replace Abstract: Multi-head latent attention (MLA) exposes many logical query heads through one packed latent KV stream. This representation is memory efficient, but it removes the phys…
- arXiv cs.AIresearchStructural Process Supervision for Latent Chain-of-Thought Reasoning
arXiv:2609.09928v2 Announce Type: replace Abstract: Latent reasoning approaches enhance token-level efficiency and robustness by replacing verbose, explicit chain-of-thought (CoT) tokens with compact continuous-space emb…
- arXiv cs.AIresearchA Dominant Supplier Slows Recursive Drift More Than It Steers It
arXiv:2609.11146v3 Announce Type: replace Abstract: More and more of the text future language models learn from is written by a few of today's models. If one supplier writes most of a shared corpus, does it pull the mode…
- arXiv cs.AIresearchReason What Matters: Retrieval-Grounded Reasoning for Universal Multimodal Embeddings
arXiv:2609.15296v2 Announce Type: replace Abstract: Universal multimodal embedding (UME) maps multimodal inputs into a shared embedding space for diverse retrieval tasks. Recent methods improve embeddings through Chain-o…
- arXiv cs.AIresearchThe Pain Axis: LLMs Represent Self-Directed Harm and Act on It
arXiv:2609.16247v2 Announce Type: replace Abstract: LLMs sometimes behave in ways resembling human emotional responses, and recent work identified internal representations that may underlie these behaviors. We ask whethe…
- arXiv cs.AIresearchTraining-Free Uncertainty Estimation for Embedding Models
arXiv:2306.00206v3 Announce Type: replace-cross Abstract: Embedding models, often obtained via self-supervised learning, extract general-purpose representations from data. Quantifying the reliability of these representat…
- arXiv cs.AIresearchTowards More Trustworthy and Interpretable LLMs for Code through Syntax-Grounded Explanations
arXiv:2407.08983v2 Announce Type: replace-cross Abstract: Trustworthiness and interpretability are inextricably linked concepts for LLMs. The more interpretable an LLM is, the more trustworthy it becomes. However, curren…
- arXiv cs.AIresearchDetection and Characterization of Coordinated Online Behavior: A Survey
arXiv:2408.01257v3 Announce Type: replace-cross Abstract: Coordination is a fundamental aspect of life. The advent of social media has made it integral also to online human interactions, such as those that characterize t…
- arXiv cs.AIresearchHelp Me Help You: The Aggregate Value of Source and Target Data in Transfer Learning
arXiv:2408.16189v4 Announce Type: replace-cross Abstract: Transfer learning, in regression or classification, concerns problems where one aims to use imperfect data from a source distribution P to improve prediction w.r.…
- arXiv cs.AIresearchGoal-Conditioned Supervised Learning for Multi-Objective Recommendation
arXiv:2412.08911v4 Announce Type: replace-cross Abstract: Multi-objective learning endeavors to concurrently optimize multiple objectives using a single model, aiming to achieve high and balanced performance across diver…
- arXiv cs.AIresearchEasier Said Than Done: Unpacking Intent-Behavior Gap in Jailbreaking LLM-Based Robots
arXiv:2412.16633v5 Announce Type: replace-cross Abstract: LLM-based robots use Large Language Models (LLMs) as planners to translate natural language instructions into policies such as grasp(), move_to(), and open_grippe…
- arXiv cs.AIresearchLocalized time-frequency representation learning for bioacoustic classification in complex soundscapes
arXiv:2502.13440v2 Announce Type: replace-cross Abstract: Prevailing bioacoustic classifiers assign species labels to fixed time-frequency windows rather than to individual vocalizations. When multiple vocalizations occu…
- arXiv cs.AIresearchLearning Where and What to Restore for Composite Image Restoration
arXiv:2503.17915v2 Announce Type: replace-cross Abstract: Real-world degraded images often contain multiple co-occurring degradation types, making composite image restoration fundamentally different from the single-degra…
- arXiv cs.AIresearchEmergence of psychopathological computations in large language models
arXiv:2504.08016v3 Announce Type: replace-cross Abstract: Can large language models (LLMs) instantiate computations of psychopathology? In this work, we establish a computational-theoretical framework to provide an accou…
- arXiv cs.AIresearchFocus on Likely Classes for Test-Time Prediction
arXiv:2505.03819v4 Announce Type: replace-cross Abstract: We ask: Can focusing on likely classes of a single, in-domain sample improve accuracy? Prior work argued "no", we answer "yes" on average. Standard entropy minimi…
- arXiv cs.AIresearchTags for DAGs: Graph Refinement with Meta-Informed Relations
arXiv:2506.19459v2 Announce Type: replace-cross Abstract: Causal discovery has shifted from data-centric methods to hybrid strategies that integrate semantic knowledge from experts or large language models (LLMs). Such e…
- arXiv cs.AIresearchAudio-JEPA: Joint-Embedding Predictive Architecture for Audio Representation Learning
arXiv:2507.02915v2 Announce Type: replace-cross Abstract: Building on the Joint-Embedding Predictive Architecture (JEPA) paradigm, a recent self-supervised learning framework that predicts latent representations of maske…
- arXiv cs.AIresearchLLM Bidders Preserve the Mechanism-Level Orderings of Human Bidders
arXiv:2507.09083v2 Announce Type: replace-cross Abstract: Training on vast amounts of human-generated data has motivated growing interest in using large language models (LLMs) to simulate human behavior. We ask which fea…
- arXiv cs.AIresearchBridging MOOCs, Smart Teaching, and AI-Assisted Learning: A Unified Quantitative Model
arXiv:2507.14266v4 Announce Type: replace-cross Abstract: MOOCs, Smart Teaching (ST), and AI-assisted learning support different stages of higher education, yet a unified quantitative basis for analyzing their contributi…
- arXiv cs.AIresearchOn the Interaction of Compressibility and Adversarial Robustness
arXiv:2507.17725v3 Announce Type: replace-cross Abstract: As demands for resource efficiency and safety in modern neural networks intensify, substantial research effort has gone into model compression and adversarial rob…
- arXiv cs.AIresearchRooseBERT: A New Deal For Political Language Modelling
arXiv:2508.03250v5 Announce Type: replace-cross Abstract: The increasing amount of political debates and politics-related discussions calls for the definition of novel computational methods to automatically analyse such…
- arXiv cs.AIresearchGraph Structure Learning with Temporal Graph Information Bottleneck for Inductive Representation Learning
arXiv:2508.14859v2 Announce Type: replace-cross Abstract: Temporal graph learning is crucial for dynamic networks where nodes and edges evolve over time and new nodes continuously join the system. Inductive representatio…
- arXiv cs.AIresearchLearning Domain- and Class-Disentangled Prototypes for Domain-Generalized EEG Emotion Recognition
arXiv:2509.01135v3 Announce Type: replace-cross Abstract: Electroencephalography (EEG)-based emotion recognition plays a critical role in affective Brain-Computer Interfaces (aBCIs), yet its practical deployment remains…
- arXiv cs.AIresearchOne Model, Many Morals: Uncovering Cross-Linguistic Misalignments in Computational Moral Reasoning
arXiv:2509.21443v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) are increasingly deployed across multilingual and multicultural settings, yet it remains unclear whether changing language leads mode…
- arXiv cs.AIresearchPushing Toward the Simplex Vertices: A Simple Remedy for Code Collapse in Smoothed Vector Quantization
arXiv:2509.22161v4 Announce Type: replace-cross Abstract: Vector quantization, which discretizes a continuous vector space into a finite set of representative vectors (a codebook), has been widely adopted in modern machi…
- arXiv cs.AIresearchDynamic Buffers: Cost-Efficient Planning for Tabletop Rearrangement with Stacking
arXiv:2509.22828v2 Announce Type: replace-cross Abstract: Rearranging objects in cluttered tabletop environments remains a long-standing challenge in robotics. Classical planners often generate inefficient, high-cost pla…
- arXiv cs.AIresearchPatch Rebirth: Fast and Transferable Model Inversion of Vision Transformers
arXiv:2509.23235v3 Announce Type: replace-cross Abstract: Model inversion is a widely adopted technique in data-free learning that reconstructs synthetic inputs from a pretrained model through iterative optimization, wit…
- arXiv cs.AIresearchGraph Your Own Prompt
arXiv:2509.23373v3 Announce Type: replace-cross Abstract: We propose Graph Consistency Regularization (GCR), a novel framework that injects relational graph structures, derived from model predictions, into the learning p…
- arXiv cs.AIresearchQuantifying How Training Gradient Sparsity Affect Spiking Neural Network Accuracy And Robustness
arXiv:2509.23762v4 Announce Type: replace-cross Abstract: Spiking Neural Networks (SNNs) have recently received increasing attention in both computational neuroscience and artificial intelligence owing to their potential…
- arXiv cs.AIresearchAttentionViG: Cross-Attention-Based Dynamic Neighbor Aggregation in Vision GNNs
arXiv:2509.25570v2 Announce Type: replace-cross Abstract: Vision Graph Neural Networks (ViGs) have demonstrated promising performance in image recognition tasks against Convolutional Neural Networks (CNNs) and Vision Tra…
- arXiv cs.AIresearchLearning to Generate Rigid Body Interactions with Video Diffusion Models
arXiv:2510.02284v4 Announce Type: replace-cross Abstract: Recent video generation models have achieved remarkable progress and are now deployed in film, social media production, and advertising. Beyond their creative pot…
- arXiv cs.AIresearchInvestigating The Smells of LLM Generated Code
arXiv:2510.03029v2 Announce Type: replace-cross Abstract: Context: Large Language Models (LLMs) are increasingly being used to generate program code. Much research has been reported on the functional correctness of gener…
- arXiv cs.AIresearchAI Adoption Across Mission-Driven Organizations
arXiv:2510.03868v2 Announce Type: replace-cross Abstract: Despite AI's promise, little is known about how mission-driven organizations (MDOs) adopt AI. We conducted semi-structured interviews with 15 experts and leaders…
- arXiv cs.AIresearchNOSA: Native and Offloadable Sparse Attention
arXiv:2510.13602v3 Announce Type: replace-cross Abstract: Decoding throughput improvements from larger inference batches are limited by GPU memory, which is largely consumed by the key-value (KV) cache. Prior training-fr…
- arXiv cs.AIresearchScaling Vision Transformers for Functional MRI with Flat Maps
arXiv:2510.13768v3 Announce Type: replace-cross Abstract: We study the problem of training self-supervised foundation models for functional MRI. Our main contributions are: (1) we introduce a new model family (CortexMAE)…
- arXiv cs.AIresearchAlignBeat: A Latent Variable Model for Multi-Class Beat Tracking from Partially Labeled Data
arXiv:2510.14391v3 Announce Type: replace-cross Abstract: Recent neural beat trackers predict beats and downbeats with two independent frame-wise binary classification heads, a convention adopted because a single multi-c…
- arXiv cs.AIresearchA Survey on Efficient Vision-Language-Action Models
arXiv:2510.24795v3 Announce Type: replace-cross Abstract: Vision-Language-Action models (VLAs) represent a significant frontier in embodied intelligence, aiming to bridge digital knowledge with physical-world interaction…
- arXiv cs.AIresearchSparse, self-organizing ensembles of local kernels detect rare statistical anomalies
arXiv:2511.03095v2 Announce Type: replace-cross Abstract: Modern artificial intelligence has revolutionized how we extract representations from scientific data, yet the statistical properties of these representations rem…
- arXiv cs.AIresearchCOGNOS: Universal Enhancement for Time Series Anomaly Detection via Constrained Gaussian-Noise Optimization and Smoothing
arXiv:2511.06894v4 Announce Type: replace-cross Abstract: Reconstruction-based methods are a dominant paradigm in time series anomaly detection (TSAD), however, their near-universal reliance on Mean Squared Error (MSE) l…
- arXiv cs.AIresearchD-GAP: Improving Out-of-Domain Robustness via Dataset-Agnostic and Gradient-Guided Augmentation in Frequency and Pixel Spaces
arXiv:2511.11286v4 Announce Type: replace-cross Abstract: Out-of-domain (OOD) robustness is challenging to achieve in real-world computer vision, especially in unsupervised domain adaptation scenarios, where shifts in im…
- arXiv cs.AIresearchServer-Enforced Watermarking in U-Shaped Split Federated Learning
arXiv:2511.14422v2 Announce Type: replace-cross Abstract: U-shaped split federated learning (U-SFL) enables resource-constrained Internet of Things devices to collaboratively train models with an edge server while retain…
- arXiv cs.AIresearchThe Devil in the Details: Emergent Misalignment, Format and Coherence in Open-Weights LLMs
arXiv:2511.20104v2 Announce Type: replace-cross Abstract: Prior work has shown that fine-tuning models on a narrow domain with misaligned data can lead to broad misalignment - a phenomenon termed "emergent misalignment"…
- arXiv cs.AIresearchWhy They Disagree: Decoding Differences in Opinions about AI Risk
arXiv:2512.06350v2 Announce Type: replace-cross Abstract: Identifying the reasons for disagreements between influential points of view on issues that affect the public can help produce informed policy responses, even if…