AI News Today

arXiv:2610.23925v1 Announce Type: new Abstract: We introduce SpinDoctor, a method for discovering innocuous prompts for text-to-image models that result in images with a chosen target bias, while retaining the quality of the images and prompts. These prompts present a risk for user manipulation, in that a user who is given these seemingly unbiased prompts might be willing to use them and would receive biased images in return. Our method is flexible: it uses models in a black-box way only and the

arXiv:2610.23932v1 Announce Type: new Abstract: Imaging FlowCytobot (IFCB) systems generate large volumes of phytoplankton imagery that exceed the capacity of manual expert analysis. Although machine-learning approaches achieve high image-level classification performance, it remains unclear whether their predictions can provide ecologically meaningful temporal information for monitoring. This study investigates whether AI-derived phytoplankton classifications can reproduce temporal occurrence pa

arXiv:2610.23945v1 Announce Type: new Abstract: The scarcity of domain-specific annotated images remains a major limitation for developing computer-vision systems for Hajj crowd analysis. Existing crowd-counting datasets and unconstrained generative models do not capture Hajj-specific visual conditions, including sacred-site geometry, white-clothed pilgrim crowds, and indoor/outdoor illumination variation. This study presents CrowdH-Edit, a reference-guided, instruction-based framework for synth

arXiv:2610.23953v1 Announce Type: new Abstract: AI-based 3D generation models such as Hunyuan 3D and Meshy can produce visually appealing 3D shapes from an image or text prompt.However, they typically focus on an object's external appearance, often producing incomplete or implausible interior geometry. Consequently, the generated shapes are not guaranteed to be functionally valid, limiting their direct use in downstream applications such as simulation and fabrication. In this paper, we present a

arXiv:2610.23966v1 Announce Type: new Abstract: Reliable fetal brain biometry on magnetic resonance imaging (MRI) is essential for diagnosing congenital brain anomalies, but artificial intelligence models often lose accuracy under domain shifts. We developed BioTTA, a backbone-agnostic, source-free unsupervised test-time adaptation framework that adapts pretrained models online to individual unlabeled target volumes. This retrospective multicohort study included 394 reconstructed 3D fetal brain

arXiv:2610.23970v1 Announce Type: new Abstract: The global transition toward carbon-neutral energy systems is heavily dependent on the rapid deployment of solar photovoltaic (PV) infrastructure, yet the speed of this expansion has outpaced the ability of administrative registries to maintain accurate records. While high-resolution commercial imagery is often used for monitoring, its high cost and infrequent updates can create an information gap for grid operators, energy infrastructure developer

arXiv:2610.23974v1 Announce Type: new Abstract: Visual token pruning is increasingly used to reduce the memory and inference costs of vision-language models. Existing work has largely focused on designing method-specific selectors and demonstrating incremental improvements over prior methods at selected token budgets. It remains unclear whether the resulting performance reflects an inherent limit of visual token pruning or the limitations of current token-selection algorithms. We take a compleme

arXiv:2610.23857v1 Announce Type: new Abstract: Intelligent agent interactions in real-world web environments are commonly constrained by request budgets, time delays, anti-crawling restrictions, and operational failure risks. Strategies solely optimizing task success rates often exhibit unusable phenomena such as "high success but high cost" or "low risk but conservative failure." This paper proposes a constrained agentic reinforcement learning model for web agents, unifying page access, search

arXiv:2610.23923v1 Announce Type: new Abstract: Tabular data are prevalent across diverse domains such as healthcare and finance. Zero-shot tabular learning aims to make predictions without labeled data. However, existing LLM-based approaches rely on row-wise prompting, resulting in high inference cost and limited use of inter-row dependencies. In this work, we propose TABHGR+, an efficient relation-aware zero-shot framework for tabular data that leverages LLM-generated rules to label and group

arXiv:2610.23928v1 Announce Type: new Abstract: Native NVFP4 promises to accelerate reinforcement learning (RL) for large language models (LLMs), but achieving stable learning across separate training and sampling engines remains challenging. We show that matching model weights and numerical formats is insufficient to ensure consistent policy evaluation, highlighting the importance of cross-engine numerical execution. We introduce miniTE, a lightweight framework that combines execution diagnosti

arXiv:2610.23934v1 Announce Type: new Abstract: When using a large language model (LLM) to simulate a user population, how should we combine individual behavioral histories to predict the fraction of users who take a particular action? We study this question in e-commerce, predicting observed product-level conversion rates from browsing sessions without task-specific model training. We vary two design choices, each involving a bias-variance tradeoff. Summarizing a product's sessions before infer

arXiv:2610.23935v1 Announce Type: new Abstract: Speculative decoding accelerates large language model inference through parallel verification of tokens proposed by a drafter. Diffusion drafters further parallelize proposal generation, but greater proposal capacity or higher mean accepted tokens (MAT) need not yield higher throughput. Because verification accepts only a consecutive prefix, early rejections can render later correct predictions ineffective, limiting MAT gains, while even higher MAT

arXiv:2610.23937v1 Announce Type: new Abstract: Acoustic models for cough detection achieve high accuracy on curated benchmarks but fail silently in deployment, where speech, environmental noise, and audio unlike the training data induce confident misclassifications. In health monitoring, a confidently wrong prediction is worse than no answer at all. We present SECURE-AI (Self-aware Estimation of Cough Uncertainty for Reliable Evaluation of AI), a multi-signal uncertainty quantification framewor

arXiv:2610.23939v1 Announce Type: new Abstract: The size of the KV cache grows linearly with context length, making it a major memory bottleneck in LLM serving. Motivated by recent progress in identifying the functional roles of attention heads, a growing body of work compresses the KV cache non-uniformly across heads. Existing methods either fix the important heads via offline profiling or select them using attention signals from the prefill stage. In both cases, however, accuracy fluctuates su

arXiv:2610.23940v1 Announce Type: new Abstract: Collision detection for complex non-convex objects is a bottleneck in physics simulation, virtual reality, and robotics. Inner sphere trees (ISTs) answer proximity and penetration queries efficiently, but their greedy leaf-sphere construction is sequential and computationally expensive, which limits both large-scale preprocessing and runtime use. In this work, we present ML-IST, a machine-learning-based method that reformulates leaf-sphere generati

arXiv:2610.23941v1 Announce Type: new Abstract: Human Activity Recognition (HAR) using wearable or smartphone inertial sensors is commonly evaluated with both classical machine learning and deep learning methods. However, reported performance can be strongly affected by sensor modality, dataset characteristics, and data-splitting strategy. This study presents a controlled comparative evaluation of four classical machine learning models and four deep learning models on two public HAR datasets, UC

arXiv:2610.23942v1 Announce Type: new Abstract: LLM agents accumulate valuable task-specific information through their actions, observations, and environmental feedback during multi-turn task execution. When effectively used, this information can help agents refine subsequent decisions and improve task performance. However, the learning value of an interaction depends on its context and subsequent feedback, making it challenging to extract reliable, actionable lessons and revise them as the task

arXiv:2610.23946v1 Announce Type: new Abstract: Pretraining scaling laws treat training data as a one-dimensional quantity: a token count. Agentic reinforcement learning (RL) inherits this scalar abstraction, but modern synthesis pipelines now generate \textit{tasks}, \textit{environments}, and \textit{trajectories} independently and at very different costs, turning data into a structured design space. This raises a question pretraining never had to answer: given a synthesis budget, \textit{whic

arXiv:2610.23948v1 Announce Type: new Abstract: Physics-informed neural networks (PINNs) are trained to minimize the residual of a prescribed equation, so a low training loss does not indicate whether a coefficient in that equation was specified incorrectly. This study evaluates what can be inferred about the encoded parameter from the trained network alone. When the residual is linear in the parameter, written as $A - \nu B$, the least-squares estimate $\hat{\nu} = A^{\top}B/B^{\top}B$ is obtai

arXiv:2610.23950v1 Announce Type: new Abstract: Automatically generating high-performance kernels with LLM-based agents promises substantial gains in development efficiency, but two obstacles remain. First, while increasing multi-turn interaction with execution environments is crucial for refining generation quality, continuous context accumulation rapidly exceeds the model's effective context window. Second, training long-horizon tasks via GRPO inherently incurs sparse rewards due to its relian

arXiv:2610.23955v1 Announce Type: new Abstract: Raman spectroscopy generates large volumes of unlabeled data that are difficult to exploit with conventional supervised learning. This work introduces a multi-domain self-supervised learning framework based on a masked autoencoder (MAE) for learning transferable Raman spectral representations from heterogeneous biological, chemical, forensic, and materials datasets. The proposed pretraining strategy incorporates physics-aware objectives by combinin

arXiv:2610.23960v1 Announce Type: new Abstract: Code generation has become a core capability of large language models (LLMs), and code data is central to the pre-training process that develops it. As obtaining public code of sufficient quality becomes more difficult, further progress cannot rely on corpus expansion alone. Tiered data management instead applies increasingly targeted processing to smaller data pools, producing data states suited to different training objectives. Following this per

arXiv:2610.24013v1 Announce Type: new Abstract: Peer-to-peer collaborative learning is an emerging distributed deep learning paradigm that eliminates the need for a central aggregator and disseminator, avoiding the single-point-of-failure and bottleneck issues they can bring. Many such approaches use parameter averaging, requiring clients to have homogeneous model architectures, whereas others use knowledge distillation as an alternative while leaning on shared public data or centralized control

arXiv:2610.24029v1 Announce Type: new Abstract: Internal signatures could support monitoring, adaptive computation, and mechanistic analysis, but benchmark prompts can be separable without any shared computational distinction. We test whether a prespecified knowledge/reasoning label defines a reusable internal signature in five contemporary 7B to 31B models. We treat the \textbf{task} as the unit of inference probes hold out complete tasks, labels are permuted across tasks, and the best layer an

arXiv:2610.24032v1 Announce Type: new Abstract: RL agents trained on a single trajectory-level return face a credit-assignment problem: when a reward arrives many steps after the decision that caused it, every action gets the same signal regardless of causal responsibility. This paper studies Visual Causal-chain Bookmarking (VCBM), which concentrates credit on the decision points that determine an episode's return, via two instantiations. The first targets a fully observed, low-dimensional MDP (

arXiv:2610.24036v1 Announce Type: new Abstract: Federated learning (FL) trains a shared model across data-owning clients without centralizing raw data, but client data difficulty and compute budgets can differ. We study local early-exit Vision Transformer (ViT) inference, where an intermediate classifier may return a prediction before the final Transformer stage. The proposed method replaces one global acceptance threshold with a client-specific base threshold from label entropy and shallow-exit

arXiv:2610.24112v1 Announce Type: new Abstract: Generalizing from small graphs to larger ones can require computation beyond the depth of a neural model used during training. We study target tasks that admit a common local iterative computation and whose effective dependency radius grows with graph size. The central idea is to learn a local update rule through GNN pretraining, then repeatedly apply the same learned processor beyond the training depth to extend information reach on larger graphs

arXiv:2610.23860v1 Announce Type: new Abstract: The Prisoner's Dilemma has long served as a foundational framework for studying human decision-making and cooperative outcomes across social scenarios, yet human behavior consistently deviates from predictions of fully rational economic theory. Previous works have studied human and LLM outcomes in the Prisoner's Dilemma; however, these studies have lacked at least one key feature: a memory component for LLM agents, accessible open-source models, or

arXiv:2610.23867v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used as simulated respondents in computational social science, yet accurately reproducing population-specific heterogeneous response distributions remains challenging. Existing methods such as demographic prompting are sensitive to prompt design and increase inference overhead, while parameter-based methods struggle to reuse demographic information efficiently, limiting generalization to unseen combinat

arXiv:2610.23868v1 Announce Type: new Abstract: Machine translation systems often preserve meaning but systematically flatten linguistic style, a failure that is most acute when translating into non-Western languages. The RASTA framework of Havaldar et al. (2025a) addresses this through retrieval-augmented stylistic alignment, but relies on GPT-4, a closed, proprietary model. We investigate whether an open-weight translation specialist, Hunyuan-MT-7B, can serve as an open-weight alternative. We

arXiv:2610.24048v1 Announce Type: new Abstract: LLM agents that read untrusted content can be hijacked by prompt injections. Runtime monitors that try to catch a hijack before the agent acts, and benchmarks that score each task with a single run, share an assumption: whether an agent follows an injection is settled when the injection is read. We test this assumption with branching rollouts that replay an episode exactly up to the step at which the agent reads an injection and then resample the r

arXiv:2610.24087v1 Announce Type: new Abstract: Can large language model (LLM) agents deliver expert-level operations research (OR) solutions directly from original client materials, without prior expert reformulation? Existing OR benchmarks typically begin with self-contained descriptions or predefined optimization tasks, underrepresenting the translation of original business materials into professionally validated solutions. We introduce OR-License, an end-to-end benchmark of 31 instances acro

arXiv:2610.24118v1 Announce Type: new Abstract: Variable roles describe recurring behaviors such as accumulation, traversal, and retaining the best candidate encountered. We use Sajaniemi's independently defined taxonomy to study which role distinctions can be recovered from large language models, how sparse autoencoders (SAEs) retain those distinctions, and whether associated directions support control of generation. We introduce static annotation rules for all eleven roles and a corpus of 126,

arXiv:2610.24123v1 Announce Type: new Abstract: Prefix-tuning is a parameter-efficient fine-tuning method for large language models (LLMs) that steers model outputs by prepending task-specific prefix representations to the input sequence. Despite its practical success, the theoretical understanding of the expressiveness of prefixes remains incomplete. In particular, the following question remains open: Given a pretrained autoregressive Transformer, for any input-output sequence pair $(\mathtt{x}

arXiv:2610.24150v1 Announce Type: new Abstract: Everyday norms of social interaction - e.g. norms of sharing space, taking turns, or queuing - are essential to large societies, offering structured procedures for common interactions. However, it remains unclear how the underlying algorithms of these implicit joint plans evolve as they diffuse through populations. Here we show that this process of diffusion can select against complex algorithms in the earliest stages. We conducted a large-scale st

arXiv:2610.24164v1 Announce Type: new Abstract: Voice agents built as cascaded automatic speech recognition (ASR)->large language model (LLM)-> text-to-speech (TTS) pipelines increasingly rely on conversational TTS: streaming, context conditioned models that adapt delivery to dialogue history. Such models are natural and expressive but offer little explicit control over how rare, trust-critical drug names are pronounced, because these entities are too infrequent, and their vocabulary too fast-gr

arXiv:2610.24172v1 Announce Type: new Abstract: Human children learn language from continuous, prosodically structured speech long before they can read, yet almost all language models train on orthographic text. Building on previous phonemic BabyLM training (Goriely et al., 2024; arXiv:2410.22906), we ask whether supplying an estimate of the prosody infants exploit improves phonemic language modelling at BabyLM scale. We compare an orthographic baseline to three conditions forming a ladder of ph

arXiv:2610.24184v1 Announce Type: new Abstract: We investigate the use of Large Language Models (LLMs) in multi-author style change detection. Using off-the-shelf LLMs or supervised fine-tuning solely within the target domain fails to yield effective features; for this reason, we propose cross-domain transfer learning with LLM-based embeddings fine-tuned for authorship verification. We fine-tune Mistral-7B embedding model and compare it with DeBERTa, used in the state-of-the-art (SOTA) systems i

arXiv:2610.24223v1 Announce Type: new Abstract: While aligned large language models (LLMs) can successfully complete many creative tasks, their outputs tend to be highly self-similar. Though solutions to this problem of "mode collapse" have been proposed, comprehensive large-scale surveys of the phenomenon in specific textual genres are still lacking. We address this gap through an extensive treatment of LLM mode collapse in poetry. Across 15 poetic forms, 248 subject matter tags, and 16 open-we

arXiv:2610.24232v1 Announce Type: new Abstract: User simulators can help evaluate and train AI systems to interact with humans at scale. To do so, evaluation of user simulators must measure behavioral parity with people. We evaluate whether memory-constrained user simulators are sensitive to two factors known to affect human information retention: repetition of a fact and interference from competing information. We find that some simulators achieve human-like overall accuracy, and replicate the