3,694 items tracked: 32 reported by two or more outlets, the rest by a single source. Most-corroborated first.
arXiv:2610.09802v1 Announce Type: cross Abstract: Concept-based vision models represent images through an intermediate layer of human-inspectable concepts, so what a model relies on can be traced to those concepts.
arXiv:2610.09892v2 Announce Type: replace-cross Abstract: Feedback from automated testing, human red teaming, and incident response can strengthen an AI system's defenses when discovered failures lead to effective repair…
arXiv:2610.09993v1 Announce Type: cross Abstract: Spatial defect signatures on wafer bin maps (WBMs) trace yield loss to specific process faults, yet supervised classifiers recognize only the defect types seen during tra…
arXiv:2610.09994v1 Announce Type: cross Abstract: Models with near-identical predictive performance can yield substantially different predictions, a phenomenon known as predictive multiplicity.
arXiv:2610.10304v1 Announce Type: cross Abstract: We study whether latent sequence compression of prompt prefixes preserves the capabilities that large language models rely on during inference.
arXiv:2610.10311v1 Announce Type: cross Abstract: Emerging computer hardware often trades reliability for energy efficiency; here we show that large-language models (LLMs) can be trained to tolerate this unreliability, a…
arXiv:2610.10320v1 Announce Type: cross Abstract: Multiphysics continuum models are powerful tools for studying electrochemical devices, enabling in silico reactor design and resolution of local pH, potential, and concen…
arXiv:2610.10411v1 Announce Type: cross Abstract: Speculative decoding accelerates large language model inference by using a low-cost draft model to propose tokens that the full-size target model verifies in parallel.
arXiv:2610.10447v1 Announce Type: cross Abstract: Reinforcement Learning (RL) from outcome rewards suffers from sparse supervision, particularly on difficult, long-horizon tasks where successful trajectories are rare and…
arXiv:2610.10462v1 Announce Type: cross Abstract: We present FoldBack, a self-correcting masked generative policy for long-horizon garment folding.
arXiv:2512.17559v2 Announce Type: replace Abstract: Healthcare systems around the world are grappling with issues such as inefficient diagnostics, rising costs, and limited access to specialists.
arXiv:2602.02639v2 Announce Type: replace Abstract: LLM self-explanations are often presented as a promising tool for AI oversight, yet their faithfulness to the model's true reasoning process is poorly understood.
arXiv:2603.22973v3 Announce Type: replace Abstract: Applying computational methods to law at scale requires separating genuine legal reasoning from surface similarity.
arXiv:2608.02365v2 Announce Type: replace Abstract: World Action Models (WAMs) build on pretrained video models, whose representations are grounded in physical dynamics and provide a natural basis for action prediction.
arXiv:2608.21567v3 Announce Type: replace Abstract: Human mobility serves as an essential proxy for understanding social, economic, and environmental dynamics in urban systems.
arXiv:2505.19912v3 Announce Type: replace-cross Abstract: We present Adjacent Possible Exploration (APE), a selective fine-tuning method for adapting large language models that systematically explores parameter modificat…
arXiv:2506.03173v3 Announce Type: replace-cross Abstract: Many physical systems do not merely move or deform; they grow, adding material and changing the geometry that a world model must represent.
arXiv:2509.14093v3 Announce Type: replace-cross Abstract: Chain-of-Thought (CoT) prompting can substantially improve the reasoning ability of large language models (LLMs), but it often comes with high inference cost due…
arXiv:2604.24197v3 Announce Type: replace-cross Abstract: Image generation systems can produce plausible photographs, readable documents, and consistent depictions of people and places.
arXiv:2605.09492v3 Announce Type: replace-cross Abstract: Reliable text generation is critical for deploying large language models (LLMs) in real-world applications, particularly in high-stakes domains such as medicine.
arXiv:2605.09504v3 Announce Type: replace-cross Abstract: We show that the instruments used to measure AI offensive capability fail in two ways: (i) they overstate harm, and (ii) they credit the model with capability tha…
arXiv:2605.10971v2 Announce Type: replace-cross Abstract: Discrete diffusion language models (DLMs) generate text by iteratively denoising all positions in parallel, offering an alternative to autoregressive models.
arXiv:2605.15995v3 Announce Type: replace-cross Abstract: Learning latent representations from temporal, multimodal, and partially observed data requires specifying what information a latent state should retain, discard,…
arXiv:2605.19352v2 Announce Type: replace-cross Abstract: Understanding how humans and artificial intelligence systems predict and plan by interacting with their environment is a fundamental challenge at the intersection…
arXiv:2605.27813v2 Announce Type: replace-cross Abstract: Text-to-image diffusion models generate images by iterative denoising, so their internal layers produce trajectories of activations rather than single static repr…
arXiv:2605.29280v3 Announce Type: replace-cross Abstract: Knowledge distillation (KD) transfers a single scalar prediction from a large foundation model (FM) to compact vertical models (VMs), suffering from diminishing t…
arXiv:2606.00267v2 Announce Type: replace-cross Abstract: Video world models (WMs) have shown promise for policy evaluation and improvement by imagining realistic future observations conditioned on ego-robot actions.
arXiv:2606.06379v4 Announce Type: replace-cross Abstract: Medical vision-language models (VLMs) have shown increasing potential for clinical image interpretation, including lesion detection and report generation.
arXiv:2606.08775v2 Announce Type: replace-cross Abstract: Visual world models have shown great potential in learning complex system dynamics.
arXiv:2606.09499v2 Announce Type: replace-cross Abstract: World models have recently seen a rapid growth in both their popularity and capability as more data efficient tools for generating robot training data or simulati…
arXiv:2606.09843v4 Announce Type: replace-cross Abstract: Do large language models' (LLMs') answers to self-report questionnaires predict how they behave?
arXiv:2606.30899v2 Announce Type: replace-cross Abstract: Backdoor attacks pose a serious threat to large language models (LLMs) by causing otherwise benign systems to produce attacker-specified malicious behavior when a…
arXiv:2607.01111v2 Announce Type: replace-cross Abstract: Robot policies inevitably encounter failures when deployed in real environments.
arXiv:2607.13319v2 Announce Type: replace-cross Abstract: High-speed off-road autonomy requires precise closed-loop control for a target vehicle while remaining robust across changing terrains.
arXiv:2608.13545v2 Announce Type: replace-cross Abstract: Modern language models are trained on heterogeneous web-scale text corpora.
arXiv:2608.27402v2 Announce Type: replace-cross Abstract: How do large language models (LLMs) organize moral knowledge?
arXiv:2610.10358v2 Announce Type: replace Abstract: As multimodal large language models (MLLMs) become more capable and widely deployed, concerns about privacy and safety have become increasingly pressing.
arXiv:2610.09440v2 Announce Type: replace-cross Abstract: Pre-trained vision encoders contain layer-wise visual representations that differ in spatial granularity, semantic abstraction, and sensitivity to local details.
arXiv:2610.09513v2 Announce Type: replace-cross Abstract: Camera trajectories control viewpoint changes in video generation, scene reconstruction, and robotic perception.
arXiv:2604.08304v5 Announce Type: replace-cross Abstract: Retrieval-augmented generation (RAG) improves large language models (LLMs) with external knowledge, but this access path creates security risks distinct from inhe…
arXiv:2605.14605v4 Announce Type: replace-cross Abstract: Model providers increasingly release the weights of large language models.
arXiv:2610.08808v1 Announce Type: new Abstract: Satisfiability Modulo Theories (SMT) solvers are foundational to software verification, program analysis, and compiler testing, particularly over the theory of Quantifier-F…
arXiv:2610.08814v1 Announce Type: new Abstract: Compositional generalization remains challenging when language models must combine familiar reasoning operations in unfamiliar ways.
arXiv:2610.08878v1 Announce Type: new Abstract: This article develops a failure-mode framework for analyzing how advanced artificial intelligence could contribute to human extinction, irreversible civilizational collapse…
arXiv:2610.09013v1 Announce Type: new Abstract: Looped LMs are parameter efficient and promise dynamic computation (saving memory and FLOPs on easy tokens).
arXiv:2610.09026v1 Announce Type: new Abstract: We present BEACON-SP, an ontology-grounded Graph Retrieval-Augmented Generation (GraphRAG) framework for clinician-facing decision support in behavioral health settings suc…
arXiv:2610.09039v1 Announce Type: new Abstract: Large language models can extract useful signals from heterogeneous enterprise data, but high-recall extraction often produces outputs that are duplicated, uneven in granul…
arXiv:2610.09057v1 Announce Type: new Abstract: Objective: We investigate whether accounting for epistemic uncertainty can improve the reliability of automated defect detection in medical device manufacturing.
arXiv:2610.09144v1 Announce Type: new Abstract: Vision-language-action (VLA) policies typically feed dense visual patch tokens into a language-action backbone, preserving scene context but offering no explicit mechanism…
arXiv:2610.09188v1 Announce Type: new Abstract: Probability-only models, which TypeSafe calls System One models, return calibrated probabilities for fixed choices in milliseconds and generate no text.