arXiv:2602.13469v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) are changing how Blind and Low Vision (BLV) people access visual information in their daily lives. Unlike traditional visual interpretation tools that provide access through captions and OCR (text recognition through camera input), MLLM-enabled applications support access through conversational assistance, where users can ask questions to obtain goal-relevant details. However, evidence about their performance in the real-world and their implications for BLV people's everyday life remain limited. To address this, we conducted a two-week diary study, where we captured 20 BLV participants' use of an MLLM-enabled visual interpretation application. Although participants rated the visual interpretations of the application as "somewhat trustworthy" (mean=3.76 out of 5, max=very trustworthy) and "somewhat satisfying" (mean=4.13 out of 5, max=very satisfying), the AI often produced incorrect answers (22.2%) or abstained (10.8%) from responding to follow-up requests. Our work demonstrates that MLLMs can improve the accuracy of descriptive visual interpretations, but that supporting everyday use also depends on the "visual assistant" skill -- a set of behaviors for providing goal-directed, reliable assistance. We conclude by proposing the "visual assistant" skill and practical guidelines to help future MLLM-enabled visual interpretation applications better support BLV people's access to visual information.

arXiv:2602.13483v1 Announce Type: cross Abstract: Understanding the internal circuits that language models use to solve tasks remains a central challenge in mechanistic interpretability. Most prior work identifies circuits at the task level by averaging across many prompts, implicitly assuming a single stable mechanism per task. We show that this assumption can obscure a crucial source of structure: circuits are prompt-specific, even within a fixed task. Building on attention causal communication (ACC) (Franco & Crovella, 2025), we introduce ACC++, refinements that extract cleaner, lower-dimensional causal signals inside attention heads from a single forward pass. Like ACC, our approach does not require replacement models (e.g., SAEs) or activation patching; ACC++ further improves circuit precision by reducing attribution noise. Applying ACC++ to indirect object identification (IOI) in GPT-2, Pythia, and Gemma 2, we find there is no single circuit for IOI in any model: different prompt templates induce systematically different mechanisms. Despite this variation, prompts cluster into prompt families with similar circuits, and we propose a representative circuit for each family as a practical unit of analysis. Finally, we develop an automated interpretability pipeline that uses ACC++ signals to surface human-interpretable features and assemble mechanistic explanations for prompt families behavior. Together, our results recast circuits as a meaningful object of study by shifting the unit of analysis from tasks to prompts, enabling scalable circuit descriptions in the presence of prompt-specific mechanisms.

arXiv:2602.13496v1 Announce Type: cross Abstract: 1. Many ecological decisions are slowed by the gap between collecting and analysing biodiversity data. Edge computing moves processing closer to the sensor, with edge artificial intelligence (AI) enabling on-device inference, reducing reliance on data transfer and continuous connectivity. In principle, this shifts biodiversity monitoring from passive logging towards autonomous, responsive sensing systems. In practice, however, adoption remains fragmented, with key architectural trade-offs, performance constraints, and implementation challenges rarely reported systematically. 2. Here, we analyse 82 studies published between 2017 and 2025 that implement edge computing for biodiversity monitoring across acoustic, vision, tracking, and multi-modal systems. We synthesise hardware platforms, AI model optimisation, and wireless communication to critically assess how design choices shape ecological inference, deployment longevity, and operational feasibility. 3. Publications increased from 3 in 2017 to 19 in 2025. We identify four system types: (I) TinyML, low-power microcontrollers (MCUs) for single-taxon or rare-event detection; (II) Edge AI, single-board computers (SBCs) for multi-species classification and real-time alerts; (III) Distributed edge AI; and (IV) Cloud AI for retrospective processing pipelines. Each system type represents context-dependent trade-offs among power consumption, computational capability, and communication requirements. 4. Our analysis reveals the evolution of edge computing systems from proof-of-concept to robust, scalable tools. We argue that edge computing offers opportunities for responsive biodiversity management, but realising this potential requires increased collaboration between ecologists, engineers, and data scientists to align model development and system design with ecological questions, field constraints, and ethical considerations.

arXiv:2602.13504v1 Announce Type: cross Abstract: The rapid integration of large language models into newsroom workflows has raised urgent questions about the prevalence of AI-generated content in online media. While computational studies have begun to quantify this phenomenon in English-language outlets, no empirical investigation exists for Turkish news media, where existing research remains limited to qualitative interviews with journalists or fake news detection. This study addresses that gap by fine-tuning a Turkish-specific BERT model (dbmdz/bert-base-turkish-cased) on a labeled dataset of 3,600 articles from three major Turkish outlets with distinct editorial orientations for binary classification of AI-rewritten content. The model achieves 0.9708 F1 score on the held-out test set with symmetric precision and recall across both classes. Subsequent deployment on over 3,500 unseen articles spanning between 2023 and 2026 reveals consistent cross-source and temporally stable classification patterns, with mean prediction confidence exceeding 0.96 and an estimated 2.5 percentage of examined news content rewritten or revised by LLMs on average. To the best of our knowledge, this is the first study to move beyond self-reported journalist perceptions toward empirical, data-driven measurement of AI usage in Turkish news media.

arXiv:2602.13524v1 Announce Type: cross Abstract: Identifying feature representations in language models is a central task in mechanistic interpretability. Several recent studies have made an implicit assumption that feature representations can be inferred in some cases from singular vectors of attention matrices. However, sound justification for this assumption is lacking. In this paper we address that question, asking: why and when do singular vectors align with features? First, we demonstrate that singular vectors robustly align with features in a model where features can be directly observed. We then show theoretically that such alignment is expected under a range of conditions. We close by asking how, operationally, alignment may be recognized in real models where feature representations are not directly observable. We identify sparse attention decomposition as a testable prediction of alignment, and show evidence that it emerges in a manner consistent with predictions in real models. Together these results suggest that alignment of singular vectors with features can be a sound and theoretically justified basis for feature identification in language models.

arXiv:2602.13562v1 Announce Type: cross Abstract: While reasoning models have achieved remarkable success in complex reasoning tasks, their increasing power necessitates stringent safety measures. For safety alignment, the core challenge lies in the inherent trade-off between safety and utility. However, prevailing alignment strategies typically construct CoT training data with explicit safety rules via context distillation. This approach inadvertently limits reasoning capabilities by creating a rigid association between rule memorization and refusal. To mitigate the safety-utility trade-off, we propose the Adaptive Safe Context Learning (ASCL) framework to improve the reasoning given proper context. ASCL formulates safety alignment as a multi-turn tool-use process, empowering the model to autonomously decide when to consult safety rules and how to generate the ongoing reasoning. Furthermore, to counteract the preference for rule consultation during RL, we introduce Inverse Frequency Policy Optimization (IFPO) to rebalance advantage estimates. By decoupling rule retrieval and subsequent reasoning, our method achieves higher overall performance compared to baselines.

arXiv:2602.13611v1 Announce Type: cross Abstract: Recently, large language models (LLMs) are extensively utilized to enhance development efficiency, leading to numerous benchmarks for evaluating their performance. However, these benchmarks predominantly focus on implementation, overlooking the equally critical aspect of software design. This gap raises two pivotal questions: (1) Can LLMs handle software design? (2) Can LLMs write code following the specific designs? To investigate these questions, this paper proposes DesBench, a design-aware benchmark for evaluating LLMs on three software design-related tasks: design-aware code generation, object-oriented modeling, and the design of acceptance test cases. DesBench comprises 30 manually crafted Java projects that include requirement documents, design models, implementations, and acceptance tests, amounting to a total of 30 design models, 194 Java classes, and 737 test cases. We evaluated seven state-of-the-art LLMs, including three DeepSeek R1, two Qwen2.5, and two GPT models, using DesBench. The results reveal that LLMs remain significantly challenged by the intricacies of software design: (1) For code generation, LLMs struggle to produce correct implementations when provided with only high-level or no designs. (2) In object-oriented modeling, while LLMs can accurately identify objects and classes, they face challenges in defining operations and inter-class relationships. (3) Acceptance test cases generated by LLMs from functional requirements achieve code coverage quality comparable to those written by humans. Our research highlights the current limitations of LLMs in managing software design and calls for further investigation into new design methodologies and languages suitable for LLM-based development.

arXiv:2602.13666v1 Announce Type: cross Abstract: In complex clinical decision-making, clinicians must often track a variety of competing metrics defined by aim (ideal) and limit (strict) thresholds. Sifting through these high-dimensional tradeoffs to infer the optimal patient-specific strategy is cognitively demanding and historically prone to variability. In this paper, we address this challenge within the context of High-Dose-Rate (HDR) brachytherapy for cervical cancer, where planning requires strictly managing radiation hot spots while balancing tumor coverage against organ sparing. We present ALMo (Aim-Limit-defined Multi-Objective system), an interactive decision support system designed to infer and operationalize clinician intent. ALMo employs a novel optimization framework that minimizes manual input through automated parameter setup and enables flexible control over toxicity risks. Crucially, the system allows clinicians to navigate the Pareto surface of dosimetric tradeoffs by directly manipulating intuitive aim and limit values. In a retrospective evaluation of 25 clinical cases, ALMo generated treatment plans that consistently met or exceeded manual planning quality, with 65% of cases demonstrating dosimetric improvements. Furthermore, the system significantly enhanced efficiency, reducing average planning time to approximately 17 minutes, compared to the conventional 30-60 minutes. While validated in brachytherapy, ALMo demonstrates a generalized framework for streamlining interaction in multi-criteria clinical decision-making.

arXiv:2602.13685v1 Announce Type: cross Abstract: Large Audio Language Models (LALMs) excel at perception but struggle with complex reasoning requiring precise acoustic measurements. While external tools can extract fine-grained features like exact tempo or pitch, effective integration remains challenging: naively using all tools causes information overload, while prompt-based selection fails to assess context-dependent utility. To address this, we propose AuTAgent (Audio Tool Agent), a reinforcement learning framework that learns when and which tools to invoke. By employing a sparse-feedback training strategy with a novel Differential Reward mechanism, the agent learns to filter out irrelevant tools and invokes external assistance only when it yields a net performance gain over the base model. Experimental results confirm that AuTAgent complements the representation bottleneck of LALMs by providing verifiable acoustic evidence. It improves accuracy by 4.20% / 6.20% and 9.80% / 8.00% for open-source and closed-source backbones on the MMAU Test-mini and the MMAR benchmarks, respectively. In addition, further experiments demonstrate exceptional transferability. We highlight the complementary role of external tools in augmenting audio model reasoning.

arXiv:2602.13813v1 Announce Type: cross Abstract: We introduce Pawsterior, a variational flow-matching framework for improved and extended simulation-based inference (SBI). Many SBI problems involve posteriors constrained by structured domains, such as bounded physical parameters or hybrid discrete-continuous variables, yet standard flow-matching methods typically operate in unconstrained spaces. This mismatch leads to inefficient learning and difficulty respecting physical constraints. Our contributions are twofold. First, generalizing the geometric inductive bias of CatFlow, we formalize endpoint-induced affine geometric confinement, a principle that incorporates domain geometry directly into the inference process via a two-sided variational model. This formulation improves numerical stability during sampling and leads to consistently better posterior fidelity, as demonstrated by improved classifier two-sample test performance across standard SBI benchmarks. Second, and more importantly, our variational parameterization enables SBI tasks involving discrete latent structure (e.g., switching systems) that are fundamentally incompatible with conventional flow-matching approaches. By addressing both geometric constraints and discrete latent structure, Pawsterior extends flow-matching to a broader class of structured SBI problems that were previously inaccessible.

arXiv:2602.13817v1 Announce Type: cross Abstract: AI is reshaping academic research, yet its role in peer review remains polarising and contentious. Advocates see its potential to reduce reviewer burden and improve quality, while critics warn of risks to fairness, accountability, and trust. At ICLR 2025, an official AI feedback tool was deployed to provide reviewers with post-review suggestions. We studied this deployment through surveys and interviews, investigating how reviewers engaged with the tool and perceived its usability and impact. Our findings surface both opportunities and tensions when AI augments in peer review. This work contributes the first empirical evidence of such an AI tool in a live review process, documenting how reviewers respond to AI-generated feedback in a high-stakes review context. We further offer design implications for AI-assisted reviewing that aim to enhance quality while safeguarding human expertise, agency, and responsibility.

arXiv:2602.13842v1 Announce Type: cross Abstract: Severe aortic stenosis is a common and life-threatening condition in elderly patients, often treated with Transcatheter Aortic Valve Implantation (TAVI). Despite procedural advances, paravalvular aortic regurgitation (PVR) remains one of the most frequent post-TAVI complications, with a proven impact on long-term prognosis. In this work, we investigate the potential of deep learning to predict the occurrence of PVR from preoperative cardiac CT. To this end, a dataset of preoperative TAVI patients was collected, and 3D convolutional neural networks were trained on isotropic CT volumes. The results achieved suggest that volumetric deep learning can capture subtle anatomical features from pre-TAVI imaging, opening new perspectives for personalized risk assessment and procedural optimization. Source code is available at https://github.com/EIDOSLAB/tavi.

arXiv:2602.13910v1 Announce Type: cross Abstract: Algorithmic stability is a classical framework for analyzing the generalization error of learning algorithms. It predicts that an algorithm has small generalization error if it is insensitive to small perturbations in the training set such as the removal or replacement of a training point. While stability has been demonstrated for numerous well-known algorithms, this framework has had limited success in analyses of deep neural networks. In this paper we study the algorithmic stability of deep ReLU homogeneous neural networks that achieve zero training error using parameters with the smallest $L_2$ norm, also known as the minimum-norm interpolation, a phenomenon that can be observed in overparameterized models trained by gradient-based algorithms. We investigate sufficient conditions for such networks to be stable. We find that 1) such networks are stable when they contain a (possibly small) stable sub-network, followed by a layer with a low-rank weight matrix, and 2) such networks are not guaranteed to be stable even when they contain a stable sub-network, if the following layer is not low-rank. The low-rank assumption is inspired by recent empirical and theoretical results which demonstrate that training deep neural networks is biased towards low-rank weight matrices, for minimum-norm interpolation and weight-decay regularization.

arXiv:2602.13971v1 Announce Type: cross Abstract: Recommendation systems are essential for personalizing e-commerce shopping experiences. Among these, Trigger-Induced Recommendation (TIR) has emerged as a key scenario, which utilizes a trigger item (explicitly represents a user's instantaneous interest), enabling precise, real-time recommendations. Although several trigger-based techniques have been proposed, most of them struggle to address the intent myopia issue, that is, a recommendation system overemphasizes the role of trigger items and narrowly focuses on suggesting commodities that are highly relevant to trigger items. Meanwhile, existing methods rely on collaborative behavior patterns between trigger and recommended items to identify the user's preferences, yet the sparsity of ID-based interaction restricts their effectiveness. To this end, we propose the Deep Adaptive Intent-Aware Network (DAIAN) that dynamically adapts to users' intent preferences. In general, we first extract the users' personalized intent representations by analyzing the correlation between a user's click and the trigger item, and accordingly retrieve the user's related historical behaviors to mine the user's diverse intent. Besides, sparse collaborative behaviors constrain the performance in capturing items associated with user intent. Hence, we reinforce similarity by leveraging a hybrid enhancer with ID and semantic information, followed by adaptive selection based on varying intents. Experimental results on public datasets and our industrial e-commerce datasets demonstrate the effectiveness of DAIAN.

arXiv:2602.14010v1 Announce Type: cross Abstract: Pathology foundation models (PFMs) have enabled robust generalization in computational pathology through large-scale datasets and expansive architectures, but their substantial computational cost, particularly for gigapixel whole slide images, limits clinical accessibility and scalability. Here, we present LitePath, a deployment-friendly foundational framework designed to mitigate model over-parameterization and patch level redundancy. LitePath integrates LiteFM, a compact model distilled from three large PFMs (Virchow2, H-Optimus-1 and UNI2) using 190 million patches, and the Adaptive Patch Selector (APS), a lightweight component for task-specific patch selection. The framework reduces model parameters by 28x and lowers FLOPs by 403.5x relative to Virchow2, enabling deployment on low-power edge hardware such as the NVIDIA Jetson Orin Nano Super. On this device, LitePath processes 208 slides per hour, 104.5x faster than Virchow2, and consumes 0.36 kWh per 3,000 slides, 171x lower than Virchow2 on an RTX3090 GPU. We validated accuracy using 37 cohorts across four organs and 26 tasks (26 internal, 9 external, and 2 prospective), comprising 15,672 slides from 9,808 patients disjoint from the pretraining data. LitePath ranks second among 19 evaluated models and outperforms larger models including H-Optimus-1, mSTAR, UNI2 and GPFM, while retaining 99.71% of the AUC of Virchow2 on average. To quantify the balance between accuracy and efficiency, we propose the Deployability Score (D-Score), defined as the weighted geometric mean of normalized AUC and normalized FLOP, where LitePath achieves the highest value, surpassing Virchow2 by 10.64%. These results demonstrate that LitePath enables rapid, cost-effective and energy-efficient pathology image analysis on accessible hardware while maintaining accuracy comparable to state-of-the-art PFMs and reducing the carbon footprint of AI deployment.

arXiv:2602.14080v1 Announce Type: cross Abstract: Standard factuality evaluations of LLMs treat all errors alike, obscuring whether failures arise from missing knowledge (empty shelves) or from limited access to encoded facts (lost keys). We propose a behavioral framework that profiles factual knowledge at the level of facts rather than questions, characterizing each fact by whether it is encoded, and then by how accessible it is: cannot be recalled, can be directly recalled, or can only be recalled with inference-time computation (thinking). To support such profiling, we introduce WikiProfile, a new benchmark constructed via an automated pipeline with a prompted LLM grounded in web search. Across 4 million responses from 13 LLMs, we find that encoding is nearly saturated in frontier models on our benchmark, with GPT-5 and Gemini-3 encoding 95--98% of facts. However, recall remains a major bottleneck: many errors previously attributed to missing knowledge instead stem from failures to access it. These failures are systematic and disproportionately affect long-tail facts and reverse questions. Finally, we show that thinking improves recall and can recover a substantial fraction of failures, indicating that future gains may rely less on scaling and more on methods that improve how models utilize what they already encode.

arXiv:2602.14099v1 Announce Type: cross Abstract: As robots become increasingly integrated into everyday tasks, their ability to perceive both the shape and properties of objects during in-hand manipulation becomes critical for adaptive and intelligent behavior. We present SemanticFeels, an extension of the NeuralFeels framework that integrates semantic labeling with neural implicit shape representation, from vision and touch. To illustrate its application, we focus on material classification: high-resolution Digit tactile readings are processed by a fine-tuned EfficientNet-B0 convolutional neural network (CNN) to generate local material predictions, which are then embedded into an augmented signed distance field (SDF) network that jointly predicts geometry and continuous material regions. Experimental results show that the system achieves a high correspondence between predicted and actual materials on both single- and multi-material objects, with an average matching accuracy of 79.87% across multiple manipulation trials on a multi-material object.

arXiv:2602.14106v1 Announce Type: cross Abstract: The most valuable asset of any cloud-based organization is data, which is increasingly exposed to sophisticated cyberattacks. Until recently, the implementation of security measures in DevOps environments was often considered optional by many government entities and critical national services operating in the cloud. This includes systems managing sensitive information, such as electoral processes or military operations, which have historically been valuable targets for cybercriminals. Resistance to security implementation is often driven by concerns over losing agility in software development, increasing the risk of accumulated vulnerabilities. Nowadays, patching software is no longer enough; adopting a proactive cyber defense strategy, supported by Artificial Intelligence (AI), is crucial to anticipating and mitigating threats. Thus, this work proposes integrating the Security Chaos Engineering (SCE) methodology with a new LLM-based flow to automate the creation of attack defense trees that represent adversary behavior and facilitate the construction of SCE experiments based on these graphical models, enabling teams to stay one step ahead of attackers and implement previously unconsidered defenses. Further detailed information about the experiment performed, along with the steps to replicate it, can be found in the following repository: https://github.com/mariomc14/devsecops-adversary-llm.git.

arXiv:2602.14211v1 Announce Type: cross Abstract: Agent skills are becoming a core abstraction in coding agents, packaging long-form instructions and auxiliary scripts to extend tool-augmented behaviors. This abstraction introduces an under-measured attack surface: skill-based prompt injection, where poisoned skills can steer agents away from user intent and safety policies. In practice, naive injections often fail because the malicious intent is too explicit or drifts too far from the original skill, leading agents to ignore or refuse them; existing attacks are also largely hand-crafted. We propose the first automated framework for stealthy prompt injection tailored to agent skills. The framework forms a closed loop with three agents: an Attack Agent that synthesizes injection skills under explicit stealth constraints, a Code Agent that executes tasks using the injected skills in a realistic tool environment, and an Evaluate Agent that logs action traces (e.g., tool calls and file operations) and verifies whether targeted malicious behaviors occurred. We also propose a malicious payload hiding strategy that conceals adversarial operations in auxiliary scripts while injecting optimized inducement prompts to trigger tool execution. Extensive experiments across diverse coding-agent settings and real-world software engineering tasks show that our method consistently achieves high attack success rates under realistic settings.

arXiv:2602.14358v1 Announce Type: cross Abstract: Airbnb search must balance a worldwide, highly varied supply of homes with guests whose location, amenity, style, and price expectations differ widely. Meeting those expectations hinges on an efficient retrieval stage that surfaces only the listings a guest might realistically book, before resource intensive ranking models are applied to determine the best results. Unlike many recommendation engines, our system faces a distinctive challenge, location retrieval, that sits upstream of ranking and determines which geographic areas are queried in order to filter inventory to a candidate set. The preexisting approach employs a deep bayesian bandit based system to predict a rectangular retrieval bounds area that can be used for filtering. The purpose of this paper is to demonstrate the methodology, challenges, and impact of rearchitecting search to retrieve from the subset of most bookable high precision rectangular map cells defined by dividing the world into 25M uniform cells.