Named after the hundred-eyed watchman of Greek myth, Argus watches the education landscape: spotting new opportunities, pressure-testing the ventures we're building, and tracing every read back to the real-world signals behind it.
The evidence library: the raw signals the pipeline is watching across the education ecosystem. Every idea is built from these.
arXiv:2607.06597v1 Announce Type: cross Abstract: Public chest-radiograph (CXR) datasets are typically released with small, fixed label schemas such as CheXpert-14. However, the underlying free-text reports describe far more findings -- and which findings matter depends on the task, site, and reader. We release a pipeline that converts free-text reports into multi-label matrices and then reconfigures the label schema through dictionary edits rather than new inference passes, i.e., without relabeling the corpus. After this one-time pass, reconfiguring MIMIC-CXR (223K reports) from cached annotations takes 196 seconds with no API cost, compared to \$6.6K for an equivalent relabeling pass with Claude Opus 4.7. Using a 58-label taxonomy, we show that 43\% of CXR studies contain at least one finding outside CheXpert-14. Image probes trained on these labels match CheXpert-14 probes on shared targets while also reaching 0.78 AUROC on expert-reviewed long-tail labels that CheXpert-14 cannot re
arXiv:2607.07708v1 Announce Type: new Abstract: Structure-property relationships are foundational to biology, chemistry and materials science, where function, reactivity and physical response emerge from spatial, chemical and periodic organization. Mechanistically explaining these relationships requires interpreting structural evidence through scientific principles and physical constraints, from stereochemistry and bonding to symmetry, energetics and periodic order. However, applying artificial intelligence to this process presents a joint challenge of representation and reasoning: models must preserve domain-native structural information while showing how specific evidence supports predictions under these constraints. Here we introduce SciReasoner, a multimodal scientific foundation model for native structural reasoning across proteins, small molecules and inorganic crystals. SciReasoner discretizes coordinates, topologies and periodic connectivities into a unified structure-aware voc
arXiv:2607.07707v1 Announce Type: new Abstract: Limited memory language models (LMLMs) externalize factual knowledge during pretraining to a knowledge base (KB), rather than memorizing it in their weights. During generation, the model then fetches knowledge from the KB as needed. This recently introduced paradigm provides multiple advantages, including knowledge control capabilities that remain beyond conventional LLMs. We propose continuous-query LMLM (CO-LMLM), where the KB pairs continuous keys with textual knowledge values, a significant departure from prior reliance on relational KB and queries. CO-LMLM generates flexible vector queries at minimal cost, while still integrating human-readable and attributable retrieved knowledge into its generation. We pair this design with an annotation pipeline that tags free-form factual spans in arbitrary text, removing prior work's restriction to Wikipedia. Across pretraining on Wikipedia and FineWeb-Edu and at multiple model scales, CO-LMLM o
arXiv:2607.07702v1 Announce Type: new Abstract: The optimization of long-horizon agents increasingly relies on reflection-based mechanisms, where a large language model (LLM) acts as an optimizer to diagnose agent failures and improve agent policies. However, real execution traces are difficult to use directly for optimization: large trace collections are often redundant and heterogeneous, making optimization inefficient and prone to overfitting to low-value failures; meanwhile, each individual trajectory also contains many irrelevant steps, while naive context reduction methods such as truncation or sliding windows can discard causally important evidence and produce misleading optimization signals. To resolve this dilemma, we introduce STRACE (Structural TRajectory Analysis and Causal Extraction), a framework that constructs high signal-noise optimization contexts for more precise and effective optimization. At the batch level, STRACE mines failure patterns to filter redundant traces
arXiv:2607.07670v1 Announce Type: new Abstract: Large language models hallucinate most about entities they have never seen. We ask whether a model's activations betray entity familiarity before a single answer token is generated, and whether that signal predicts the factual reliability of the answers. On four Polish Bielik models (1.5B-11B parameters), we probe four entity domains (athletes, cities, writers, musicians), each with 42 well-known, 42 obscure-but-real, and 42 fabricated entities addressed by a one-sentence question (504 prompts per model). Two unsupervised, single-forward-pass dispersion measures over post-SwiGLU MLP activations, inverse participation ratio and spectral entropy, separate known from fabricated entities at AUROC 0.95-1.00 across all domains and scales; a supervised linear probe reaches 0.99-1.00. Both clear selection-aware permutation floors of about 0.70-0.74 (empirical p<=1e-3), survive held-out layer selection (0.93-0.99), and persist on real names (known
arXiv:2607.07669v1 Announce Type: new Abstract: Large language models increasingly \emph{understand} dialectal English, yet still \emph{produce} only standard, US-leaning English, leaving dialectal generation, the harder half of the problem, largely unaddressed. We introduce \textbf{DiaLLM}, which continually pretrains three open-weight language model families on the International Corpus of English and applies implicit and explicit post-training paradigms, each combined with three model alignment strategies, giving the first controlled comparison of these components across Australian, Indian, and Northern British English. Our results reveal that dialectal robustness and generation are \emph{dissociated}: benchmarks are shaped by continual pretraining and SFT, while alignment visibly reshapes generation in ways benchmarks do not capture. Explicit variety-targeted adaptation produces output reliably recognised as dialectal and preferred over broad alignment, yet the method that most aggr
arXiv:2607.07626v1 Announce Type: new Abstract: Reliable confidence estimation is essential for deploying large language models (LLMs) in confidence-aware systems, where downstream decisions such as retrieval, tool use, and adaptive computation depend on accurately estimating answer reliability. Existing approaches, however, largely treat confidence as a property of completed responses, overlooking how confidence-related information evolves throughout the answering process. In this work, we investigate confidence from a temporal perspective by comparing pre-solution Feeling-of-Knowing (FOK) and post-solution Judgement-of-Learning (JOL) confidence estimates across frontier and open-source LLMs. We show that post-solution confidence is consistently better calibrated and more discriminative than pre-solution confidence, while linear probes trained on hidden representations recover substantially richer confidence-related information than models explicitly verbalise. Building on this observ
arXiv:2607.07557v1 Announce Type: new Abstract: One-shot pruning methods like Wanda and SparseGPT apply the same sparsity ratio to every layer of a transformer, ignoring known variation in layer importance. We propose PALS (Percentile-Aware Layerwise Sparsity), which adjusts per-layer sparsity based on the 99th percentile of activation magnitudes, bounded to $\pm 5\%$ around the target ratio. On LLaMA-2-7B at 50\% sparsity, PALS achieves 10.96 WikiText-2 perplexity versus 12.92 for uniform Wanda (mean over 9 runs, $p < 0.001$). The benefit is architecture-dependent: LLaMA-3-8B shows marginal gains and Mistral-7B shows none. We also find that gradient-based allocation -- the seemingly more principled approach -- produces results worse than random, suggesting that gradient magnitude does not predict the impact of discrete weight removal. PALS adds negligible cost to the pruning pipeline and requires no fine-tuning.
arXiv:2607.07548v1 Announce Type: new Abstract: Large language model based search agents increasingly adopt multi-agent architectures in which a main agent decomposes a complex question into sub-queries and dispatches them to parallel sub-agents. However, existing systems instantiate all roles from a single model of identical scale, leaving open how model capacity should be distributed across roles. We factorize hierarchical search into three roles: a delegation role responsible for task decomposition, an execution role responsible for retrieval and evidence extraction, and an answer generation role held fixed as a confound control. We then conduct controlled capacity sweeps along the delegation and execution axes on five multi-hop QA benchmarks. The experiments yield three findings. First, role factorization consistently outperforms a single-agent baseline, improving exact match from 4.5 to 8.6 points across six model scales. Second, capacity sensitivity is asymmetric: scaling the del
arXiv:2607.07469v1 Announce Type: new Abstract: Fine-tuning large language models (LLMs) for e-commerce attribute extraction requires labeled data representative across thousands of product types, attributes, and multiple languages. This combinatorial scale translates to millions of annotations, rendering human labeling prohibitively costly. While recent work has demonstrated synthetic label generation using LLMs, deploying such approaches at industrial scale requires integrated quality control mechanisms. We present SynthAVE, a large-scale human-validated benchmark for attribute value extraction spanning 12,726 products across 229 product types, 792 attributes, and 4 languages (Spanish, French, Italian, German). To validate synthetic labels at scale, we introduce a multi-LLM arena framework where samples are independently evaluated by 21 judge configurations (7 model families $\times$ 3 prompts), with final labels determined via majority voting. The majority vote ensemble agrees with
arXiv:2607.07409v1 Announce Type: new Abstract: Speculative decoding accelerates LLM inference by drafting multiple tokens and verifying them in parallel. Block-parallel drafters such as DFlash further improve drafting efficiency by predicting an entire block in one pass, but their position-wise predictions lack explicit intra-block causal conditioning. Recent methods such as Domino and DSpark attempt to introduce such causality into block-parallel drafting, but they require training the draft model from scratch, which limits their flexibility and increases training cost. We propose DeLS-Spec, a decoupled long-short context speculative decoding method. DeLS-Spec treats the fixed DFlash model as a long-context expert and introduces a lightweight local head as a short-context expert. The local head can be trained independently with a standard next-token prediction objective, without joint training with the target model or the DFlash backbone, leading to extremely low training cost. At in
arXiv:2607.07408v1 Announce Type: new Abstract: Automatic prosodic segmentation identifies boundaries between speech units from acoustic and linguistic evidence. Although recent deep learning approaches have produced strong results for English, automatic segmentation for Brazilian Portuguese (BP) still relies mostly on rule-based or traditional machine-learning methods. This paper presents SAMPA, a Whisper-based segmenter that transcribes BP speech while inserting explicit markers for terminal prosodic boundaries. We fine-tune Whisper large-v3 on manually segmented recordings from the NURC-SP dataset and evaluate different training and test-time filtering configurations, including out-of-distribution testing on the MuPe-Diversidades dataset. SAMPA achieves competitive boundary-detection performance across settings, with the best models reaching F1=0.731 on the held-out test split and F1=0.796 on MuPe-Diversidades. Finally, through n-gram and acoustic-visual analyses, we show that our m
arXiv:2607.07388v1 Announce Type: new Abstract: Large Language Models (LLMs) store factual knowledge and domain-specific patterns implicitly in dense Transformer parameters, making knowledge expansion costly through pretraining, fine-tuning, retrieval augmentation, or longer contexts. Engram-style memory offers a compact hidden-state injection pathway, but existing GPU-resident designs often rely on hash-based compression, causing unrelated phrases to collide in shared slots and weakening phrase-level semantic fidelity. We present TF-Engram, a train-free Engram system that constructs phrase-specific semantic memory offline from external corpora, stores large memory tables across a GPU--DRAM--SSD hierarchy, and uses Early-Exit Guided Predictive Prefetching to hide external-memory latency during autoregressive decoding. On Qwen3-0.6B, TF-Engram improves the average downstream score from 57.6 to 59.4, outperforming both the frozen backbone and a parameter-matched LoRA baseline. System eva
arXiv:2607.07318v1 Announce Type: new Abstract: Rigorous content moderation is crucial for online advertising but leads to millions of daily rejections. This scale renders manual rectification infeasible, particularly for video advertisements. However, existing safety-driven methods often suffer from aggressive over-editing, which compromises the advertiser's original semantic intent merely to satisfy compliance. In this work, we target the rectification of textual violations in video ads, covering both speech transcripts and on-screen text. We propose R^3, a novel framework designed to harmonize compliance with original semantic intent preservation. Our approach integrates three key innovations: (1) an experience-driven data synthesis framework that bootstraps high-quality supervision via a group-Relative compliance experience extractor; (2) a curriculum Reinforcement learning strategy with hierarchical rewards designed to enforce compliance while maximizing semantic consistency; and
arXiv:2607.07302v1 Announce Type: new Abstract: This paper reports an empirical study evaluating the relevance of several RAG metrics. The experiment is based on a question-answering dataset created by human annotators from business data. The generated responses and retrieved spans of a RAG system are scored using evaluation metrics from four libraries (Ragas, DeepEval, RAGChecker, Opik). These metrics are compared to scores given by two evaluators, as well as to standard metrics such as recall. An analysis of correlations is conducted. Finally, we highlight certain limitations of our methodology, compare it to those used in the literature, and suggest some avenues for future research. This paper is an English translation of a paper originally published in the French-speaking workshop EvalLLM (Brabant, 2026).
arXiv:2607.07282v1 Announce Type: new Abstract: The Prasthanatrayi -- the ten principal Upanisads, the Brahmasutra, and the Bhagavadgita, with Sankara's commentaries (bhasya) -- is the foundational corpus of Advaita Vedanta. Continuous euphonic combination (sandhi), long compounds (samasa), and dense scholastic prose make it hard to read at the word level: where one word ends, and what each word means grammatically, are both obscured. We present an open, fully offline, word-level digital reader of the entire Prasthanatrayi with Sankara's bhasya. Every word -- of both the root text (mula) and the commentary -- is clickable and resolves to a pop-up giving its split (padaccheda), morphological analysis, and gloss. Because every word carries a lemma, the reader also acts as a concordance: a search on a dictionary headword retrieves all of that word's inflected and sandhi-hidden occurrences, and its occurrences inside compounds, across both layers. The resource covers thirteen commentarial
arXiv:2607.07251v1 Announce Type: new Abstract: One of the expected abilities of vision-language models (VLMs) is spatial reasoning ability based on a given text and image. To evaluate the spatial reasoning abilities of VLMs, we focus on the use of spatial deictic expressions, which are defined as spatial expressions whose referent is determined by their situational context, such as ``this'' and ``that''. To handle spatial deictic expressions, VLMs must jointly reason over language and visual space, grounding context-dependent references in the image's spatial structure. In addition, selecting appropriate spatial deictic expressions across languages requires VLMs to understand the language-specific spatial distinctions encoded by these expressions. In this paper, we develop a benchmark to evaluate the multilingual ability of VLMs to use spatial deictic expressions in four languages. Our experiments using this benchmark reveal that the tested models use demonstratives in a manner differ
arXiv:2607.07141v1 Announce Type: new Abstract: Newly developed items must ordinarily be field tested before their psychometric properties are known, creating a cold start problem for item calibration. Predicting item parameters from features is a long standing measurement problem dating back to the Linear Logistic Test Model; modern text embeddings now automate the design matrices traditionally specified by hand. We propose an evaluation framework combining regularized regression on item text embeddings, repeated cross validated R squared reported with its resampling standard deviation, and two performance upper bounds: a reliability ceiling derived from parameter standard errors, and a design ceiling derived from simulation based power calibration. Applying this framework to a mathematics item bank (EEDI) and a medical licensure benchmark (BEA 2024), we find that item difficulty is highly predictable from text (repeated cross validated R squared = 0.53, or about 57% of its reliabilit
arXiv:2607.07050v1 Announce Type: new Abstract: Agentic language models must learn when to call tools, when to consume tool responses, and when to answer directly. This makes multi-teacher on-policy distillation a natural training strategy: one teacher can specialize in tool calls, another in direct responses, and the student can learn from both on its own generated distribution. We show that this strategy can induce a behavior shift that is invisible from aggregate losses alone. In a two-teacher tool-use setting, vanilla generalized knowledge distillation improves tool-call recall but also moves the model toward over-calling, where it calls tools on examples that should be answered directly. Aggregate explanations are insufficient: tool-call samples do not receive more token exposure, and full-sequence per-token divergence is not larger for the tool-call teacher. We instead analyze behavior leverage imbalance: local token-level signals at mode- entry and structural positions, such as
arXiv:2607.07047v1 Announce Type: new Abstract: Understanding the geometric structure of pre-trained language model embeddings matters for interpretability and safety. We ask whether sentence-level classification signal lives in the Riemannian geometry of contextual token embeddings, and probe it by extracting per-token pullback metrics from a learned encoder's analytical Jacobian and aggregating them with the Fr\'echet mean on the symmetric positive definite (SPD) manifold; we call this procedure Riemannian Mean Pooling (RMP). Across three datasets with non-trivial linguistic structure (CoLA, CREAK, RTE), RMP outperforms Euclidean mean pooling, while on FEVER-Symmetric, a benchmark constructed to remove annotation-driven lexical artifacts, the method correctly stays at chance. Ablations show that a randomly initialised encoder combined with Fr\'echet aggregation already beats Euclidean pooling on two of the three signal-bearing datasets, localising the source of the gain to the geomet
arXiv:2607.06974v1 Announce Type: new Abstract: Large language models (LLMs) increasingly improve their reasoning at test time via additional computation, yet most existing works treat each problem in isolation. When problems arrive sequentially, accumulating reusable experience across them can further improve performance. Existing memory-based methods either store whole-solution templates that generalize poorly to novel problems or use heuristic step-level selection that is not optimized for final-answer correctness. Learning selection policies requires large-scale training data and fixed action spaces, making such approaches unsuitable for test-time settings where memory expands incrementally and only limited supervision is available. We propose MILES (Modular Instruction Memory with LEarnable Selection for self-improving LLM reasoning), a framework that dynamically expands step-wise memory and applies correctness-optimized memory composition under realistic test-time constraints. MI
arXiv:2607.06940v1 Announce Type: new Abstract: The remarkable performance of large language models (LLMs) in linguistic tasks underscores an urgent need for comprehensive evaluation of their response quality. Prevailing methods, often confined to singular dimensions, fall short of capturing the full spectrum of model capabilities. This study introduces a multifactor scoring paradigm, integrating accuracy, conciseness, factual consistency, readability, and coherence, complemented by a graphical user interface (GUI) for visualizing outcomes. Evaluations on the TruthfulQA dataset unveil mainstream LLMs' strengths in reasoning tasks (peaking at a composite score of 0.6104) alongside pervasive limitations in navigating complex facts and ambiguities. Transcending the narrow lens of traditional metrics, this framework offers a transparent, adaptable avenue to illuminate model potential and deficiencies. Though presently focused on English tasks, its horizons beckon toward multilingual domain
arXiv:2607.06845v1 Announce Type: new Abstract: African American English (AAE), a rule-governed dialect spoken by over 30 million people, is routinely misinterpreted and "corrected" by large language models (LLMs). Across six instruction-tuned LLMs (14B to 70B), we show that state-of-the-art models systematically prefer Standard American English (SAE) continuations even when the preceding context is in AAE, effectively rewriting AAE into SAE. We present an end-to-end framework to audit and mitigate this bias. For auditing, we introduce conditional Dialect Group Invariance (cDGI), which isolates true model bias from translator-induced artifacts, and a feature-level localization analysis that identifies which AAE markers most strongly trigger bias; we find that syntactic constructions, especially negative concord (e.g., "ain't nobody"), are universal triggers across all models. For mitigation, we introduce, to our knowledge, the first application of activation steering to dialect bias: a
arXiv:2607.06831v1 Announce Type: new Abstract: Speech-to-text alignment means finding the temporal boundaries of each word in the audio. Some models provide such an alignment directly and others do not. Connectionist temporal classification (CTC) and transducer models have an alignment by construction, whereas attention-based encoder-decoders (AED) and speech large language models (LLMs) do not, and their word timings are usually read off the attention weights instead. All of these signals live on the encoder frame grid, which bounds their temporal precision. We study a generic gradient-based alignment that applies to any differentiable ASR model. We take the gradient of each teacher-forced token log probability with respect to the input, reduce it to a per-frame saliency, and decode the resulting matrix into word boundaries with a single dynamic-programming pass. The method needs no training, no model modification and no alignment heads, works across all model families including the
arXiv:2607.06818v1 Announce Type: new Abstract: For any E-commerce website it is a nontrivial problem to build enduring advertisements that attract shoppers. It is hard to pass the creative quality bar of the website, especially at a large scale. We thus propose a programmatic solution to generate product advertising headlines using retail content. We propose a state of the art application of Reinforcement Learning (RL) Policy gradient methods on Transformer based Masked Language Models. Our method creates the advertising headline by jointly conditioning on multiple products that a seller wishes to advertise. We demonstrate that our method outperforms existing Transformer and LSTM + RL methods in overlap metrics and quality audits. We also show that our model-generated headlines outperform human submitted headlines in terms of both grammar and creative quality as determined by audits.
arXiv:2607.06641v1 Announce Type: new Abstract: Large language models (LLMs) achieve promising results on medical question answering benchmarks, yet their use in public health is constrained by hallucinations and the rapid evolution of official guidance. Retrieval-Augmented Generation (RAG) mitigates these risks by grounding responses in an explicitly maintained corpus, but end-to-end performance depends critically on retrieval configuration and on evaluation beyond multiple-choice formats. We extend PubHealthBench, a question answering (QA) benchmark of 7,929 questions derived from UK Government public health guidance, into a retrieval-augmented setting and systematically evaluate retrieval and generation choices. We compare dense, sparse, and hybrid retrieval across multiple embedding models and corpus variants, and show that hybrid retrieval consistently improves recall and ranking quality, with chunk length and topic interacting with ranking performance. Providing retrieved context
arXiv:2607.06611v1 Announce Type: new Abstract: Automatically recognizing the sentiment, positive or negative, from speech is a challenging task, requiring both the analysis of vocal inflections and the interpretation of uttered words. Recent solutions rely on audio foundation models to solve the task, but it remains unclear if such models can take all aspects into account. To this end, we propose a multimodal solution that integrates audio and text information via cross-modal transformers, where text transcripts are automatically generated via an automatic speech recognition (ASR) tool. Moreover, we create multiple text modalities by automatically translating the transcripts into multiple languages via machine translation tools. Audio and multilingual text features are combined via a cascaded architecture comprising cross-modal transformer blocks that integrate modalities one by one. We further distill knowledge from the multimodal model, called teacher, into a unimodal (audio only) m
arXiv:2604.20711v2 Announce Type: replace-cross Abstract: Artificial intelligence is increasingly deployed to synthesize large-scale public input in policy consultations and participatory processes. Yet no formal framework exists for auditing whether these summaries faithfully represent the source population, an accountability gap that existing approaches to AI explainability, grounding and hallucination detection do not address because they focus on output quality rather than input fidelity. Here, participatory provenance is introduced: a measurement framework grounded in optimal transport theory, causal inference and semantic analysis that tracks how individual public submissions are transformed, filtered or lost through AI-mediated summarization. Applied to Canada's 2025-2026 national AI Strategy consultation ($n = 5{,}253$ respondents across two independent policy topics), the framework reveals that both official government summaries underperform a random-participant baseline ($-9.
arXiv:2603.15245v2 Announce Type: replace-cross Abstract: Empathy is central to human connection, yet people often struggle to express it effectively. In blinded evaluations, large language models (LLMs) generate responses that are often judged more empathic than human-written ones. Yet when a response is attributed to AI, recipients feel less heard than when comparable responses are attributed to a human. We built a conversation platform in which participants are asked to offer empathic support to an LLM expressing realistic troubles and conducted a randomized experiment collecting 33,938 messages spanning 2,904 text-based conversations between 968 participants and their LLM conversational partners. We find participants report feeling empathy but systematically fail to express it, but an LLM coaching intervention offering personalized feedback on effective empathic communication significantly boosts it without homogenizing participants' responses. Moreover, we derive a data-driven tax
arXiv:2602.17588v4 Announce Type: replace-cross Abstract: Despite rapid progress in autonomous web agents, human involvement remains essential for shaping preferences and correcting agent behavior as tasks unfold. However, current agentic systems lack a principled understanding of when and why humans intervene, often proceeding autonomously past critical decision points or requesting unnecessary confirmation. In this work, we introduce the task of modeling human intervention to support collaborative web task execution. We collect CowCorpus, a dataset of 400 real-user web navigation trajectories containing over 4,200 interleaved human and agent actions. We identify four distinct patterns of user interaction with agents -- hands-off supervision, hands-on oversight, collaborative task-solving, and full user takeover. Leveraging these insights, we train language models (LMs) to anticipate when users are likely to intervene based on their interaction styles, yielding a 61.4-63.4% improvemen
arXiv:2605.08630v3 Announce Type: replace Abstract: Evaluating visualization systems in niche domains such as genomics is challenging due to scarcity of domain experts and difficulty recruiting a representative user base. While LLM-based synthetic personas are increasingly used to ease evaluation bottlenecks, they face well-founded skepticism. Rather than weighing synthetic personas as substitutes for real users, we ask a fundamental open question: when synthetic personas evaluate a real visualization system, what do they actually produce, and how does that output change when grounded in documented human contexts? We present Sycamore, an exploratory three-condition probe design using Geranium, a search engine for multimodal genomics visualization, as a case study. Sycamore evaluates Geranium using: (1) ungrounded synthetic personas from generic LLM priors; (2) grounded synthetic personas constrained by voice-of-customer artifacts from a prior interview study; and (3) a published baseli
arXiv:2607.07650v1 Announce Type: cross Abstract: Time-constrained interactive systems such as USSD (Unstructured Supplementary Service Data)-based financial services operate under strict session limits and sequential user interaction. While stronger authentication mechanisms improve security, they also increase interaction complexity and time burden, potentially reducing transaction completion. In this work, we model the failure dynamics of such systems and investigate how authentication complexity interacts with user response time and network round-trip time to influence session success rate. We propose and implement a simulation-based framework to investigate these failure dynamics and formally define a non-linear failure phenomenon, termed the \textit{Success Cliff}, where session success rates sharply decline beyond a critical complexity threshold. Through controlled experiments, we quantify the trade-off between security and usability and identify conditions under which secure au
arXiv:2607.07420v1 Announce Type: cross Abstract: Safety for generalist robots is usually discussed in terms of motion or dialogue. We argue a third question is missing: should the robot take its first hard-to-undo social action at all, such as a greeting, an uninvited grasp, or stepping into someone's space? We call this initiation authorization. Current frameworks rarely treat it as a separate safety layer. Today's stacks often skip this step: a high engagement score or a confident VLA rollout is treated as permission to act. But seeing a person is not the same as having their consent to be addressed. We frame initiation authorization within generalist-robot safety and contrast it with post-plan VLA guardrails, implementing PAS (probe-authorize-speak) on a doorway humanoid, comparing it with direct-init on logged traces, and proposing a three-condition user study, with open questions on metrics, governance, and where initiation ends and foundation-model generation begins.
arXiv:2607.07370v1 Announce Type: cross Abstract: In embodied intelligence systems, the motion controller serves as the critical bridge between semantic reasoning and physical execution. Humanoid control has progressed rapidly through large-scale human motion-capture data and motion-tracking paradigm. However, producing quadruped robots motion corpora with scalability and physical feasibility faces more fundamental obstacles: animal motion data is scarce, and cross-embodiment retargeting remains fragile. We present ABot-C0, a generalist motion-control system for quadruped robots that establishes three complementary behavior foundations: a scalable multi-source motion-data pipeline, robust policy learning across motion tracking, locomotion, and scene interaction, and a unified deployment stack for reliable real-world operation. Fundamentally, we construct a data pyramid through conditional video-generation synthesis, annotated motion capture, teleoperation and human design, producing 16
arXiv:2607.07099v1 Announce Type: cross Abstract: Squint and cataract are major ocular disorders that majorly affect visual perception and interaction capability. This paper proposes a real-time video-based automated detection system for squint and cataract detection based on computer vision and image processing methods. The proposed system uses a media-pipe face-mesh (a 478-point facial landmark detection model) to extract geometric ocular features for multi-class squint classification. Simultaneously, The presence and severity cataract is estimated through grayscale intensity and histogram-based lens opacity analysis. The system records short video sequences with standard laptop or mobile cameras, which can be deployed at low costs and on a large scale. The experimental performance has shown great accuracy in the detection of squint (98.39%) and classification of cataract (96.90%). Besides automatic ocular analysis, the proposed framework is also made accessible for visual impairment
arXiv:2607.07021v1 Announce Type: cross Abstract: Humans continuously coordinate with others in dynamic interactions, often through implicit, hard-to-quantify social norms that act as shared tacit expectations among interacting agents. As AI agents, including large language models (LLMs), become embedded in daily life, they increasingly participate in such interactions and reshape social interaction structures. Yet they often fail to coordinate with humans in an effective, considerate, and natural manner. We hypothesize that this gap arises because existing approaches align model behavior with human demonstrations without explicitly quantifying the underlying norms that generate such behavior. We selected pedestrian-vehicle interaction as a representative dynamic interaction and developed a simplified experimental platform that captures its key interactive features. From 3,456 dynamic human interactions collected via this platform, we identified three principles underlying human social
arXiv:2607.06608v1 Announce Type: cross Abstract: We present key challenges and future research directions in the security and privacy of agentic AI, based on a horizon-scanning exercise that brought together thirty leading international experts from academia, industry, and government to engage in focused discussions and collaborative exercises on the emerging risks associated with the growing agency of AI.
arXiv:2607.06577v1 Announce Type: cross Abstract: Physiological tremor of the upper limb is a sensitive neuromuscular indicator that may be modulated by cognitive load and competitive stress, yet its behaviour in real esports conditions remains uncharacterised. We measured wrist accelerometer-based tremor in 16 healthy adult male StarCraft~2 players across two tournament days, computing log power spectral density ($log(PSD)$) and dominant frequency in four bands (2--4, 8--14, 10--20, and 1--25Hz) and comparing them to published population norms using linear mixed models. Players deviated significantly from the reference in all bands: $log(PSD)$ was elevated at 2--4~Hz and substantially reduced at higher frequencies (Cohen's $d = 1.6$--$2.3$), suggesting long-term neuromuscular adaptation to the fine-motor demands of esports. Tremor indicators declined systematically over the tournament day. Contrary to the fatigue-related increases typical of traditional motor tasks. Neither game outco
arXiv:2607.07522v1 Announce Type: new Abstract: Controlled research on AI ideation typically compares independent agents, while field studies of human-AI collaboration sacrifice experimental control. We introduce a controlled, two-player extension of the Alternate Uses Test (AUT) that enables comparison of human-human and human-AI co-creation under matched interactive conditions, alongside calibrated non-interactive baselines. The platform supports decomposition of performance into three typically confounded factors: participant traits, partner perceptions, and content dynamics. An in-person pilot (N = 62) demonstrates its utility. Under matched time limits, originality with a GPT-4 partner is statistically equivalent to that with a human partner. Approach motivation (BAS Drive) moderates whether interactive partnership benefits originality, and self-reported cognitive outsourcing predicts lower originality specifically in human-human dyads. Prior exposure to highly creative ideas impr
arXiv:2607.07521v1 Announce Type: new Abstract: AI agents that generate final answers based on user input often do not meet the needs of creative fields. Fields such as structural design and architecture need interactive systems that help users externalise and develop ideas, explore alternatives, and refine partial solutions. The final product of such designs needs to comply with many constraints concerning, e.g., spatial configuration, mechanical behaviour, material quantities, and costs. These constraints create friction in the design process, which can stimulate novel and creative solutions. In this paper, we discuss the misalignment between current generative AI goals to remove friction and provide final solutions and the needs of creators, such as structural designers, who develop ideas through iterative work. We present the design dimensions of systems allowing for constrained human-AI co-creation that rely on vision-language models making structural exploration conversational, m
arXiv:2607.07463v1 Announce Type: new Abstract: A perennial research question in visualization involves identifying which visual encodings for a particular dataset are most effective for users in performing a specific task. The relative effectiveness of the different encodings are commonly identified through controlled experiments. However, designing an experiment involves making many, often ad hoc, decisions about the experimental setup such as whether to include a training module, whether to provide performance-based incentives to participants, etc. Yet, there is limited guidance on how these decisions should be made, and we do not fully understand the impact of these subjective decisions on empirical results. In this paper, we investigate the impact of one such key design decision: monetary rewards. Specifically, we ask: does providing or not providing participants with performance-based financial incentives affect the results and the conclusions that we draw from visualization stud
arXiv:2607.07185v1 Announce Type: new Abstract: Neurological injury affects hundreds of millions of people worldwide, yet the loss of motor or communication functions resulting from stroke, spinal cord injury, and neurodegenerative disease remains largely irreversible with existing therapies. Brain-computer interfaces (BCIs) offer a promising pathway for restoring these functions by decoding neural activity into commands that control an external device. Here, we present the first quantitative analysis of China's BCI translational ecosystem, integrating evidence from three pillars: investigator-initiated trials (IITs), registered clinical trials, and regulatory-approved products. We analyzed 134 clinical trials from the Chinese Clinical Trial Registry (ChiCTR), 26 IITs, and five BCI-related products approved by the National Medical Products Administration as of June 2026. Results demonstrate that clinical trial registration has increased rapidly since 2020, with research centers concent
arXiv:2607.07116v1 Announce Type: new Abstract: In some cases, end-user programming allows the design of stand-alone applications. But none of the existing approaches is concerned by safety aspects of programming. Heavy techniques exist to develop safe applications, particularly in non-interactive domains. They involve software engineering techniques, and sometimes, formal methods. All these techniques are very far from end-users. Our idea is to let this part to experts, and to connect end-user programming onto this safe conventional development. Starting from an existing functional core, we built an interactive end-user programming environment called GenBuild, which allows designing interactive stand-alone applications. GenBuild is composed of two distinct modules. The Generator is the first one. It is a specialized tool developed for a domain expert who sets out a safe functional core. The Builder is the second module. It is a purely interactive tool that allows an end-user to develo
arXiv:2607.07105v1 Announce Type: new Abstract: Composition in Traditional Chinese Paintings (TCPs) carries spatial, narrative, and cultural-aesthetic meaning. Systematic compositional analysis is therefore important for understanding their visual language and artistic meaning. Traditional compositional analysis is mainly qualitative and interpretation-driven. It supports close reading of individual paintings, but it is difficult to discover, compare, and verify compositional patterns across large painting collections. To better understand these challenges, we conducted a literature review and in-depth interviews with two art historians. Based on these findings, we introduce the Composition Graph, a scene-graph-based representation for TCP composition. It models a painting through four layers: entities, relations, void space, and context. Based on this representation, we develop CompoVista, a canvas-based visual analytics system for composition-oriented exploration of TCPs. CompoVista
arXiv:2607.07073v1 Announce Type: new Abstract: Searching for time-series segments that match user-defined patterns is important in domains such as finance, climate science, and healthcare. However, existing visual query tools often struggle to support vague, composite, or fuzzy pattern descriptions, often requiring users to express their intent through precise sketches or rigid structured filters. We present ShapeTalk, a coordinated natural-language and sketch-based querying system for univariate time-series pattern search. Rather than treating text and sketch as a fused input stream, ShapeTalk uses them as complementary representations of analytic intent: natural language supports semantic and compositional pattern descriptions, while sketching supports direct geometric refinement. The two modalities are linked through a shared visual context, editable feature representations, and synchronized result views, enabling users to move between text and sketch during iterative query formula
arXiv:2607.06996v1 Announce Type: new Abstract: Sign language recognition technologies can improve communication between deaf individuals and the broader community, but many existing systems face challenges in real-world deployment. This paper presents a deployable smart glove system for sign language recognition that integrates wearable sensing and deep learning. The glove incorporates flex sensors and an inertial measurement unit (IMU) to capture finger articulation and hand motion, while facial cues are obtained through a camera. Sensor data are transmitted via an ESP32-C6 microcontroller and processed using a long short-term memory (LSTM) network to model temporal gesture dynamics. Experimental results show that the proposed model achieves an overall recognition accuracy of approximately 95%. The trained model is further converted to TensorFlow Lite for real-time inference. This demonstrates the feasibility of the system for practical sign language translation applications.
arXiv:2607.06901v1 Announce Type: new Abstract: Virtual reality (VR) nature immersion is an increasingly popular field of research due to its potential to help people who do not have access to real nature. There are many questions surrounding how virtual forests can be designed to effectively reduce stress and restore attention. Many of these questions relate solely to visual aspects, but more recent literature has started exploring multisensory experiences. In these experiences, senses are treated as additive; however, certain results from the current literature may indicate that there are more complex, cross-sensory interactions occurring. For example, adding sound to visuals can increase stress reduction potential, but certain natural sounds can feel threatening if they are out of place within the virtual nature scene. Overall, cross-sensory interactions in VR nature environments (VNEs) are underexplored and challenge our current understanding of multisensory VNEs, and future explor
arXiv:2607.06778v1 Announce Type: new Abstract: Augmented reality (AR) can enhance visual perception for people with low vision (PLV) by overlaying multimodal information. Selection-based augmentation further allows users to flexibly choose and augment relevant information while reducing distraction and visual clutter. However, little is known about the ability and preferences of PLV in performing object selection techniques in AR, considering their potential visual and gaze control challenges. To understand what selection techniques are suitable for PLV to support selection-based AR augmentations, we conducted a mixed-methods study with 20 PLV and 18 sighted controls who performed target selection tasks using three input techniques -- head, gaze, and finger pointing with dwell-based confirmation -- in two real-world scenarios (sitting vs. on the go). We found that for PLV, gaze-based selection enabled the fastest initial pointing when sitting and comparable overall selection time to h
arXiv:2607.06761v1 Announce Type: new Abstract: We present a rehearsal-oriented system for creating responsive built environments during theatre devising workshops. The system connects bespoke sensing modules for gesture, position, and speech recognition to light and sound outputs through a visual no-code programming layer. It was developed, used, and refined across six workshops with eight professional performance-makers, where participants created light-and-sound scores, gesture- and position-triggered scenes, responsive architectures, participatory prototypes, and a multi-room scratch performance. Rather than presenting a production-ready show-control platform, this demo focuses on how sensing and actuation can be made available as compositional materials during early-stage creative experimentation for immersive theatrical compositions. The system is designed to support quick configuration, visible mappings, and in-room testing, allowing performers to experiment with responsive spac
arXiv:2607.06754v1 Announce Type: new Abstract: Co-designing with families for environmental sustainability relies on participatory imagination, yet habitual family roles and uneven participation, especially between adults and young children, often constrain it. A second challenge is continuity: workshop relationships and embodied ways of working do not easily survive into the final design, where artefacts travel more readily than roles or interactional dynamics. We report on a nationally toured mixed-reality installation developed through applied-theatre-led co-design with families. Across three workshops and user testing, applied theatre methods supported families to co-create narratives, artefacts, and interactional roles that shaped the public event. We show how theatrical co-design can rebalance child-adult participation through playful status shifts, and how selected workshop dynamics can be re-staged within a public mixed-reality installation. We contribute a theatrical account