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:2607.05217v1 Announce Type: new Abstract: Public institutions increasingly use large language models (LLMs) to answer citizens' questions, often pairing a curated knowledge base with live web search, yet whether the sources behind these answers can be trusted has received little empirical scrutiny. We report a pre-launch expert evaluation of Evr\'opuvefur, an independent, government-funded service run by the University of Iceland that answers questions about the European Union, conducted as Iceland prepared for its referendum of 29 August 2026 on whether to resume EU accession talks. Five domain experts produced 551 evaluations of 449 AI-generated answers, scoring each against a seven-criterion quality rubric and, separately, flagging individual cited sources. We compared two retrieval paths: a curated local corpus (RAG) and open web search. In more than a third of the reviewed web-search answers (35%, 65 of 187), at least one cited source was flagged, almost always as untrustwor
arXiv:2607.05163v1 Announce Type: new Abstract: AI systems may produce failures after deployment that pre-deployment safety assessments do not anticipate. Managing these failures requires what we refer to as adequate \textit{AI incident governance}, where having good definitions, taxonomies, monitoring practices, reporting mechanisms, and incident analysis is essential. We examine existing frameworks related to AI incident governance by regulatory bodies and independent efforts, and find that while there are frameworks that describe how individual functions can be performed, there is a lack of consistency within the aspects of definitions, classification, monitoring, and reporting. These inconsistencies apply to the types of incident data that is collected and reported, the ways in which they are categorised, and as a result, the depth, representativeness, and accuracy of analysis that can be performed.
arXiv:2607.05132v1 Announce Type: new Abstract: As large language models are deployed as autonomous agents that communicate intentions before acting, a critical safety question is whether agents that publicly commit to actions will honor those commitments. We place LLM agents in repeated $n$-player games with a three-stage protocol that separates private intent, public announcement, and final action, allowing us to identify whether each deviation from a stated announcement was already planned during private deliberation. Evaluating three frontier models across six games in homogeneous and heterogeneous groups over 10 rounds, we report two findings. First, when agents deviate from their announcements, the deviation is predominantly already stated in their private plan (exceeding 90% in the highest-deception conditions), yet this is not a fixed model property: the same model ranges from perfect honesty to near-total deviation across games. Second, different models interpret announcements
arXiv:2607.05034v1 Announce Type: new Abstract: Learning to communicate with code-generating AI models is an emerging skill for novice programmers. One recent pedagogical approach, Prompt Problems, has students solve computational tasks by writing natural-language prompts for code-generating AI models. However, little is known about the specific prompt-level mistakes novice programmers make, the kinds of computational details they fail to communicate, and what strategies they use to recover when generated code is incorrect. In a CS1 course, we studied attempts by more than 900 students to solve dialogue-based Prompt Problems. We analyzed student reflections, unsuccessful prompts, and reported debugging strategies. Compared to traditional coding tasks, students generally found prompting easier, more enjoyable, and better targeted at developing problem-solving skills. The most common mistakes are related to the omission of key details, suggesting both a failure to acknowledge their impor
arXiv:2607.04838v1 Announce Type: new Abstract: Public acceptance of artificial intelligence (AI) in legal decision-making has been primarily explained through individual differences in personality traits and general technology attitudes. However, contextual features of legal disputes themselves may systematically influence preferences for AI versus human adjudicators. Across two studies with Japanese participants (N = 1,384 and N = 596), we examined whether psychological characteristics of dispute content shape acceptability judgments for algorithmic adjudication. Study 1 employed exploratory factor analysis on acceptability ratings across 46 legal dispute vignettes, revealing a two-dimensional structure distinguishing interpersonal-relational disputes (where human adjudicators were strongly preferred) from institutional-procedural disputes (where AI acceptance was comparatively higher). Study 2 replicated this structure in an independent sample and demonstrated that experimentally ma
arXiv:2607.04601v1 Announce Type: new Abstract: We investigate how banning generative artificial intelligence-generated content (AIGC) affects knowledge seeking, knowledge contribution, and contribution efficiency in online question-and-answer communities. After the launch of ChatGPT in late November 2022, several Stack Exchange communities implemented official bans on AIGC over concerns such as less reliable and socially engaged content. Leveraging data from the full network of Stack Exchange communities, we employ a difference-in-differences (DID) approach to examine the impacts of these bans. Our results reveal a double-edged impact: while the AIGC ban increases knowledge seeking, as evidenced by a higher volume of posted questions, it simultaneously reduces contribution efficiency, reflected in a lower proportion of questions receiving satisfactory answers within the expected time frame. Notably, these impacts are only evident in non-STEM communities. We take a socio-technical pers
arXiv:2607.04543v1 Announce Type: new Abstract: Governments are important actors in frontier AI governance, but many facts about their adoption and use of AI systems are difficult to observe directly. Procurement disclosures and official statements are useful, but can also be delayed, selective, and better suited to measuring formal adoption than actual day-to-day use. We propose a complementary monitoring primitive: measuring traces of language-model assistance in public government documents. The approach is lightweight, externally reproducible, and based on revealed behavior rather than stated intent. In a pilot study of ten public document streams from U.S. and PRC government-related sources, we find that, while 2021 baselines are consistently near zero, by 2026, four of our ten sources show statistically significant signs of AI-assisted writing. In our sample, the U.S. signal concentrates in publications downstream of policy work; the PRC signal concentrates closer to it. We close
arXiv:2607.04503v1 Announce Type: new Abstract: This article examines the institutional conditions under which artificial intelligence systems in U.S. welfare administration come to operate as instruments of support or as instruments of control. Rather than asking what welfare algorithms "really" are (tools of proactive assistance or infrastructures of surveillance) the article starts from the premise that support and control are co-present within the same system, while their relative balance shifts over time. This movement is conceptualized through the notion of support-control convergence and the model of an institutional ratchet. Routine budgetary and political pressures make control-oriented effects easily measurable and politically capitalizable, whereas a return toward support requires external intervention of disproportionate force, such as judicial compulsion, legislative prohibition, or public scandal. Empirically, the article draws on process tracing of six state- and county-
arXiv:2607.03906v1 Announce Type: new Abstract: To whom do the fruits of advanced technological innovation belong? To their inventors, to the organizations and individuals involved in making such discoveries possible, or to still larger groups of people, potentially encompassing all of humanity? This question sits at the heart of the present investigation. The arguments developed here focus on an expansive reading of the entitlement to benefit from technological breakthroughs: we argue that they should be designed, developed, and distributed in ways that benefit everyone. This central claim, which encompasses technologies such as advanced forms of artificial intelligence, is grounded in an exploration of five moral arguments that involve human rights, beneficence, contingencies of birth, the global tree of knowledge, and global economic justice. Taken together, they underpin the argument for globally beneficial technologies.
arXiv:2607.03700v1 Announce Type: new Abstract: Public Scratch projects are reused in computing education as classroom examples, remix sources, open-exploration materials, and research data. Curation often begins with titles, thumbnails, descriptions, tags, and remix links, but Scratch projects are executable learning artifacts. Content affecting age appropriateness can appear only after execution, gameplay progression, a failure state, user interaction, costume switching, audio playback, or a hidden event trigger. We study "runtime-revealed sensitive content" as a computing education curation challenge: educators and researchers need runtime evidence about what students may encounter when Scratch projects are used in these settings. We introduce a runtime-aware annotation scheme that separates content category, risk level, evidence channel, reveal mechanism, and annotation confidence. Using this scheme, we conducted an audit of 500 public Scratch projects sampled from curated candidat
arXiv:2607.03607v1 Announce Type: new Abstract: A routing algorithm for Se\~noritas Courier, a bicycle delivery cooperative in S\~ao Paulo, Brazil, composed exclusively of cis women and trans people, is presented in this paper. Unlike conventional logistics optimization, which typically focuses on cost or distance minimization, this cooperative operates under principles of solidarity, care, and equitable income distribution. The algorithm was developed through a participatory process involving cooperative members as co-designers. The classical Vehicle Routing Problem proved inadequate for this context, as it disregards individual constraints and fairness. We formulate a new variant, the Se\~noritas Routing Problem, which incorporates biker-specific constraints on weight, volume, and maximum distance, alongside a solidarity objective that balances route lengths. A genetic algorithm is employed as the solution method. Three fitness formulations are compared: a baseline distance-minimizat
arXiv:2607.03542v1 Announce Type: new Abstract: Frontier-AI governance today faces a problem structurally analogous to the one banking regulation faced pre-2008, and which post-2008 reforms (Basel III, Dodd-Frank) have since addressed. Two gaps recur: discovering a risk is not tantamount to acting on it, and individual-model review is unlike managing correlated build-up across the sector. Drawing on the Basel III framework and the U.S. financial-stability architecture, I propose a macro-prudential early warning and response system ("MEWRS") for internal frontier AI. These are systems deployed for labs' own internal research, testing, and production workflows, as distinct from externally released products. Layer A adapts the finder-coordinator-defender early-warning model to route structured reports on dual-use capabilities, autonomy indicators, and security compromises through a government clearinghouse to domain-specific defender working groups. Layer B calibrates operational controls
arXiv:2607.03427v1 Announce Type: new Abstract: AI systems are increasingly being positioned as potential Digital Public Goods (DPGs) to accelerate progress towards the Sustainable Development Goals (SDGs). Yet, despite major global commitments, most notably the Global Digital Compact's call to "develop, disseminate and maintain safe and secure open-source software, open data, open artificial intelligence models and open standards that benefit society as a whole", very few AI systems currently meet the DPG Standard in practice. This report explains why, and what must change for "AI as Digital Public Goods" (AIDPGs) to become a credible, implementable pathway rather than an aspirational label. Commissioned by the Asian Development Bank (ADB) and produced by United Nations University (UNU) in partnership with UN Office of Digital and Emergent Technologies (UN ODET), this assessment combines: (i) a structured desk review of policy, legal, and technical frameworks on DPGs, openness, and AI
arXiv:2607.03419v1 Announce Type: new Abstract: This research paper examines how Knowledge Components (KCs) - fine-grained concepts or skills required to solve programming tasks - can be used as interpretable signals for understanding assignment difficulty and student struggle in introductory programming courses. While prior work has focused on predictive models based on programming behavior, such models are often difficult to interpret and therefore hard to use for instructional decisions. We analyze KC-based metrics, including the number of KCs per assignment and changes in KC coverage between consecutive assignments. We examine correlations between the number of KCs and student performance on the assignment, and analyze changes in KCs across assignments to identify cases where performance declines without new concepts being introduced. Selected assignments are then qualitatively inspected to understand potential design issues. Our results on data from three introductory programming
arXiv:2607.02972v1 Announce Type: new Abstract: Moral sensitivity is the ability to identify the morally relevant features of a decision situation and use them as the basis for action. It is the foundation of broader moral competence: any other moral reasoning capabilities will be irrelevant if an agent lacks sensitivity to the relevant facts. In this paper, we offer a new evaluation of LLM moral sensitivity and in doing so, we address and resolve a central problem in AI alignment research: how to scale behavioural evaluations beyond expensive and sometimes metaethically dubious comparisons with a human baseline, without adopting an LLM judge that must be assumed to have the very capability that you are attempting to evaluate. Our central question is this: can LLMs successfully identify the morally relevant features of noisy cases, in which various kinds of morally irrelevant information have been introduced to distract the respondent? To explore this, we introduce \textbf{MORPH-1K (MO
arXiv:2607.02955v1 Announce Type: new Abstract: We argue that AI systems used in conducting foreign policy tasks - broadly enacting 'statecraft' - should be a priority test case for technical AI governance research. In enacting foreign policy, we refer to the formulation and implementation of external objectives by political actors. Statecraft is a high-consequence deployment domain, with extreme downside risks and structural properties that standard evaluation practices handle poorly. These features include partial observability, unbounded action spaces, contested ground truth, and multidimensional objectives. This paper advocates for a literature-grounded research agenda. Our contribution is threefold: (i) a claim about the structural conditions of foreign policy that combine catastrophic tail risk with technical evaluation complexities, (ii) an ECOSYSTEM review that highlights the asymmetric focus on ASSESSMENT features over ACCESS, VERIFICATION, SECURITY, and OPERATIONALIZATION, an
arXiv:2607.02531v1 Announce Type: new Abstract: Water use by data centers is routinely reported as a single footprint, but water is consumed through two physically distinct pathways: at the site for cooling and in the power system that generates electricity. We mapped both pathways for 472 U.S. hyperscale facilities by linking facility locations to electricity regions, hydrologic basins, and water-stress data. Under baseline assumptions, operational water consumption totals approximately 300 GL yr^-1 (range 205-451 across scenarios), with electricity-related water contributing three-quarters of the total. The two pathways produce different hotspot geographies: direct cooling burdens concentrate in stressed western and south-central basins, whereas electricity-related burdens concentrate in a few eastern grid regions with fossil-heavy supply. Just 3 of 24 hosting balancing authorities account for 59% of electricity-related water. Separating pathways identifies which decisions matter whe
arXiv:2607.02530v1 Announce Type: new Abstract: Cybercrime victimization among young adult males aged 18--20 has become an increasingly urgent public safety concern in the post-pandemic digital environment. From 2022 to 2024, individuals aged 20--29 submitted 191,787 complaints to the FBI Internet Crime Complaint Center (IC3), reporting combined losses of more than $1.28 billion. Although this population represents a substantial share of cybercrime victims, the 18--20 male sub-cohort remains insufficiently examined as a distinct demographic group within cybercrime victimization research. This study presents an original risk factor analysis and theoretical synthesis, representing the first integration of criminological, neurological, and behavioral evidence for this specific demographic sub-cohort. Drawing on FBI IC3 and FTC Consumer Sentinel Network data from 2022--2024 alongside European cybersecurity threat intelligence from ENISA, the study develops a unified risk profile centered o
arXiv:2607.02520v1 Announce Type: new Abstract: Automated research agents increasingly generate code, retrieve literature, and draft scientific artifacts, but they often fail to verify whether generated experiments execute correctly or whether cited sources support generated claims. We present AutoResearch, an execution-grounded multi-agent framework for reliable research workflow automation. AutoResearch couples sandboxed Python/PyTorch execution, iterative code repair, citation verification, claim-support auditing, decision control, and structured \LaTeX{} artifact generation. The system treats runtime errors, citation-verification failures, and review-agent feedback as practical filtering signals for generated research artifacts. In controlled evaluations on HumanEval, MBPP, a SciCode subset, citation-validation tasks, claim-support auditing, and small end-to-end workflow stress tests, AutoResearch improves execution success, citation validity, local claim support, and workflow comp
Conversations with Kevin Hogan: Author and educator Andrew Marcinek argues that the Meta lawsuit is the inevitable outcome of 20 years of algorithmic manipulation — and that schools have a narrow window to get AI right before history repeats itself.
Where the AFT's new 10-point plan gets it right, where it falls short, and why “devices down” is not the path to meaningful learning.
Conversations with Kevin Hogan: CoSN Board Member Kris Hagel downloads on the state of edtech in US schools.
Researchers looked at more than 150,000 prompts from more than 4,400 K-12 teachers interacting with AI. Here's what they found.
Article URL: https://techcabal.com/2025/05/28/rethinking-african-edtech/ Comments URL: https://news.ycombinator.com/item?id=44123628 Points: 1 # Comments: 0
Vibe coding can feel instant, but it is not simply pressing a button and getting a finished app.
We've been promised that AI will introduce personalised tutoring, that it will replace traditional schooling, etc. However, I see fewer and fewer edtech startups these days... Chegg, Udemy, Busuu and many others are on the decline. What's happening to Edtech? Comments URL: https://news.ycombinator.com/item?id=43495666 Points: 2 # Comments: 0
Article URL: https://www.scientificamerican.com/article/medical-education-needs-rethinking/ Comments URL: https://news.ycombinator.com/item?id=24293391 Points: 2 # Comments: 0
In May, a cybercriminal group executed the largest educational data breach on record, targeting Instructure, the company behind the Canvas learning management system. The breach impacted 275 million students, teachers and staff across approximately 9,000 education institutions. Many took quick action. The University of Wisconsin-Madison, for example, issued real-time alerts warning faculty and students: “If Canvas prompts you to perform any action — such as clicking a link, logging in, resetting your password or completing any tasks — do not proceed.” For universities, the incident…
The conversation around AI in schools is changing almost as rapidly as the technology. Here are some recent trends.
Community colleges serve as a bridge between education and employment, helping students gain the skills needed for local and regional jobs. But with workforce needs evolving more rapidly, these institutions are under pressure to ensure programs remain aligned with labor market demand. Data analytics and artificial intelligence (AI) are helping community colleges leverage labor market intelligence (LMI) to make more informed decisions about program creation, student success initiatives and workforce development strategies. However, overcoming organizational challenges, fragmented systems, data…
arXiv:2606.23870v2 Announce Type: replace-cross Abstract: PLCverif is the most mature open-source platform for PLC formal verification, developed at CERN and in production use since 2019. Yet it has two fundamental limitations: no support for Ladder Diagram (LD) programs, the dominant PLC notation, and reliance on CBMC as its primary backend, which restricts verification to bounded proofs. The PLCverif authors themselves identified ESBMC as the appropriate backend improvement. Prior work established ESBMC-PLC (a textual LD frontend with k-induction) and ESBMC-GraphPLC (graphical PLCopen XML support); together, they cover LD with unbounded proofs but not Structured Text (ST), and graphical LD with timer/counter function blocks remains unverifiable. This paper presents ESBMC-PLC+, a unified framework that closes both gaps: (1) an ST/SCL frontend via the MATIEC IEC 61131-3 compiler, routing C-compiled ST to ESBMC with nondeterministic input modeling and YAML property injection; (2) functi
arXiv:2606.23195v2 Announce Type: replace-cross Abstract: Large Language Model (LLM) agents increasingly rely on memory systems to maintain long-term coherence. Recent work shows that agent memories degrade during continuous consolidation. However, existing research assumes memories are derived from unbiased experiences. In this work, we identify and formalize a novel phenomenon: Memory Contagion -- the cross-temporal propagation of evaluator bias through agent memory. We show that when agents are trained or guided by biased evaluators, their experiences become biased; when these trajectories are stored and consolidated into memory, the bias propagates to future agents retrieving from the same memory store, even when consolidation is perfect (oracle). Across two bias types (length preference, authority bias) and four experimental phases, we demonstrate: (1) Memory Contagion occurs for length bias even with perfect consolidation on older models (Gamma_A = 13.18, DeepSeek V4-Chat), while
arXiv:2606.22873v2 Announce Type: replace-cross Abstract: Vision-language models (VLMs) are increasingly deployed in consumer, medical, financial, and enterprise applications. This broad deployment expands the safety surface: risks can arise from multimodal question answering, assistant responses, and cross-modal composition, while moderation policies may vary across products, regions, and deployment stages. Most existing guardrails either rely on fixed taxonomies or target only a narrow set of interaction settings, which limits their adaptability when safety rules change at deployment time. We present \textbf{SingGuard}, a policy-adaptive multimodal guardrail model family for safety assessment in multimodal conversations. SingGuard treats the active policy as a runtime input: given natural-language rules, it checks the target content against the active policy rule by rule and predicts both the safety label and the triggered rule. To balance efficiency and interpretability, SingGuard s
arXiv:2606.22485v2 Announce Type: replace-cross Abstract: Decision-making in real-world settings rarely follows a fixed script. Instead, it unfolds as a dynamic reasoning process in which the appropriate course of action evolves as new context and data become available. Traditional Business Process Management systems provide rigor, determinism, and auditability, yet they generally struggle to adapt their execution at runtime. Conversely, agentic systems based on Large Language Models (LLMs) bring flexibility to decision-making, but they are inherently opaque, often unreliable, and suffer from significant scalability constraints when operating over large datasets. To combine these complementary paradigms, we introduce VADAOrchestra, a neurosymbolic framework that models complex workflows as evolving reasoning processes. The framework adopts a hybrid approach: given a user query and a collection of data sources, an LLM-based orchestrator incrementally plans and adapts the workflow. This
arXiv:2606.19626v2 Announce Type: replace-cross Abstract: AI pipelines that reason quantitatively over technical text depend on input where physical quantities, numbers, units, and symbolic expressions arrive intact; when these entities fragment at tokenization, errors propagate downstream. Byte-Pair Encoding, optimized for vocabulary compression, is blind to such entities and fragments them into arbitrary subwords -- a problem aggravated in technical Brazilian Portuguese. We present TOTEN, a knowledge-based system whose input representation preserves each technical entity as a whole, typed unit: vocabulary is not derived statistically but classified declaratively under a formal ontology of engineering entities (OEE). The core is the triple : types, principles, and invariants; a classifier mapping raw text into typed regions; and instantiators yielding a self-descriptive representation. Integrity rests on deterministic coupling to three external authorities: Pint (dimensional), Unicode
arXiv:2606.19157v2 Announce Type: replace-cross Abstract: AudioLLMs enable speech recognition conditioned on textual prompts such as domain descriptions or entity lists. However, it remains unclear whether these models genuinely utilise such context or rely on parametric knowledge learned during pretraining. Existing benchmarks cannot answer this question because they evaluate transcription under fixed prompting conditions and rarely include explicit contextual inputs. We introduce IndicContextEval, a 56-hour multilingual benchmark of natural speech from 555 speakers across 8 Indian languages and 23 professional domains. We design a 7-level prompting framework that progressively introduces contextual signals, including metadata, natural-language descriptions, entity lists in English and native script, and adversarial prompts with incorrect entities. Evaluating five models reveals substantial differences in context utilisation behaviour, highlighting the need for explicit evaluation of
arXiv:2606.16497v2 Announce Type: replace-cross Abstract: GPU kernel optimization represents a paradigm where functional correctness is assumed and execution efficiency is the objective. We present daVinci-kernel, a reinforcement learning framework that couples skill discovery with skill exploitation through a dynamically evolving skill library. daVinci-kernel jointly trains three agents sharing one LLM backbone: a Skill Selection Agent that retrieves relevant techniques via BM25 and LLM reranking, a Policy Agent that generates multi-turn CUDA/Triton kernels conditioned on selected skills, and a Skill Summary Agent that distills successful rollouts into reusable skills. Candidate skills are added only after execution-based verification confirms reproducible speedups. All three agents share a single LLM backbone, are initialized via a structured SFT cold start on diversity-filtered data, and are then jointly optimized end-to-end with multi-turn REINFORCE and per-agent advantage estimati
arXiv:2606.07512v2 Announce Type: replace-cross Abstract: Current Vision-Language Models struggle with hours-long videos because processing full-length visual sequences induces prohibitive token explosion and attention dilution. To overcome this, we introduce MemDreamer to decouple perception and reasoning, shifting long-video understanding into an agentic exploration process. As a plug-and-play framework, it incrementally streams videos to construct a Hierarchical Graph Memory, a top-down three-tier architecture for semantic abstraction, anchored by a foundational graph capturing spatiotemporal and causal relations. During inference, the reasoning model employs agentic tool-augmented retrieval, navigating hierarchies, searching nodes, and traversing logical edges via an Observation-Reason-Action loop. Experiments show MemDreamer achieves SOTA results across four mainstream benchmarks, narrowing the gap with human experts to only 3.7 points. It constrains the reasoning context window t
arXiv:2605.05097v3 Announce Type: replace-cross Abstract: LLMs are trained once, then deployed into a world that never stops changing. External memory compensates for this, but most systems manage it explicitly rather than letting it adapt on its own. Biological memory works differently: coupled multi-timescale dynamics make new associations immediately usable, strengthen what repetition confirms, and let the rest fade. We argue that external memory should follow a similar principle. In Memini, this view takes the form of an associative memory that organizes knowledge as a directed graph. Each edge carries two coupled internal variables, one fast and one slow, following the Benna-Fusi model of synaptic consolidation. From this coupling, episodic sensitivity, gradual consolidation, and selective forgetting are expected to emerge as facets of a single mechanism, reframing external memory as a learning substrate that reorganizes through its own dynamics. This workshop article describes an
arXiv:2604.03314v2 Announce Type: replace-cross Abstract: Foundation models have revolutionized AI, but adapting them efficiently for multimodal tasks, particularly in dual-stream architectures composed of unimodal encoders, such as DINO and BERT, remains a significant challenge. ParameterEfficient Fine-Tuning (PEFT) methods like LowRank Adaptation (LoRA) enable lightweight adaptation, yet they operate in isolation within each modality, limiting their ability in capturing cross-modal interactions. In this paper, we take a step in bridging this gap with Cross-Modal LowRank Adaptation (CoLA), a novel PEFT framework that extends LoRA by introducing a dedicated inter-modal adaptation pathway alongside the standard intra-modal one. This dual-path design enables CoLA to adapt unimodal foundation models to multimodal tasks effectively, without interference between modality-specific and crossmodal learning. We evaluate CoLA across a range of vision-language (RefCOCO, RefCOCO+, RefCOCOg) and au
arXiv:2603.10371v2 Announce Type: replace-cross Abstract: Speech tokenizers are essential for connecting speech to large language models (LLMs) in multimodal systems. Speech tokenizers are expected to preserve both semantic and acoustic information for downstream understanding and generation tasks. However, emerging evidence suggests that the term "semantic" in speech processing does not align with linguistic lexical-semantic, leading to a mismatch between speech and text modality. In this paper, we systematically analyze the information encoded by several widely used speech tokenizers, evaluating their lexical-semantic and phonetic content through three tasks. Our results show that current tokenizers primarily capture phonetic rather than lexical-semantic structure, deriving practical implications for the design of next-generation speech tokenization methods. Code is released to public at https://github.com/Alexuan/codec_probing_release.
arXiv:2602.17663v2 Announce Type: replace-cross Abstract: HIPE-2026 is a CLEF evaluation lab dedicated to person-place relation extraction from noisy, multilingual historical texts. Building on the HIPE-2020 and HIPE-2022 campaigns, it extends the series toward semantic relation extraction by targeting the task of identifying person-place associations in multiple languages and time periods. Systems are asked to classify relations of two types -- $at$ ("Has the person ever been at this place?") and $isAt$ ("Is the person located at this place around publication time?") -- requiring reasoning over temporal and geographical cues. The lab introduces a three-fold evaluation profile that jointly assesses accuracy, computational efficiency, and domain generalization. By linking relation extraction to large-scale historical data processing, HIPE-2026 aims to support downstream applications in knowledge-graph construction, historical biography reconstruction, and spatial analysis in digital hum
arXiv:2602.06566v3 Announce Type: replace-cross Abstract: Despite recent successes, test-time scaling -- i.e., dynamically expanding the token budget during inference as needed -- remains brittle for vision-language models (VLMs). Unstructured visual reasoning chains entangle perception and reasoning, leading to long, disorganized contexts where small perceptual mistakes may cascade into completely wrong answers. Reasoning also requires expensive reinforcement learning with hand-crafted rewards. Here, we introduce SPARC (Separating Perception And Reasoning Circuits), a modular framework that explicitly decouples visual perception from reasoning. Inspired by sequential sensory-to-cognitive processing in the brain, SPARC implements a two-stage pipeline where the model first performs explicit visual search to localize question-relevant regions, then conditions its reasoning on those regions to produce the final answer. This separation enables independent test-time scaling with asymmetric
arXiv:2601.17917v3 Announce Type: replace-cross Abstract: Diffusion Large Language Models (dLLMs) offer a compelling paradigm for natural language generation, leveraging parallel decoding and bidirectional attention to achieve superior global coherence compared to autoregressive models. While recent works have accelerated inference via KV cache reuse or heuristic decoding, they overlook the intrinsic inefficiencies within the block-wise diffusion process. Specifically, they suffer from spatial redundancy by modeling informative-sparse suffix regions uniformly and temporal inefficiency by applying fixed denoising schedules across all the decoding process. To address this, we propose Streaming-dLLM, a training-free framework that streamlines inference across both spatial and temporal dimensions. Spatially, we introduce attenuation guided suffix modeling to approximate the full context by pruning redundant mask tokens. Temporally, we employ a dynamic confidence aware strategy with an earl
arXiv:2512.01085v3 Announce Type: replace-cross Abstract: Medical phrase grounding (MPG) maps textual descriptions of radiological findings to corresponding image regions. These grounded reports are easier to interpret, especially for non-experts. Existing MPG systems mostly follow the referring expression comprehension (REC) paradigm and return exactly one bounding box per phrase. Real reports often violate this assumption. They contain multi-region findings, non-diagnostic text, and non-groundable phrases, such as negations or descriptions of normal anatomy. Motivated by this, we reformulate the task as generalised medical phrase grounding (GMPG), where each sentence is mapped to zero, one, or multiple scored regions. To realise this formulation, we introduce the first GMPG model: MedGrounder. We adopted a two-stage training regime: pre-training on report sentence--anatomy box alignment datasets and fine-tuning on report sentence--human annotated box datasets. Experiments on PadChest
arXiv:2507.16863v2 Announce Type: replace-cross Abstract: A common belief in multimodal research is that the perceptual weaknesses of vision--language models can be compensated by stronger language reasoning (e.g., chain-of-thought, in-context learning, or external tools). We challenge this assumption. We argue that for a broad class of visual tasks hard to specify in language, failures stem from a structural fatality where the temporal decision of \textit{when} to reason strictly dictates the spatial constraint of \textit{where} reasoning takes place. When visual reasoning is deferred to language generation, current architectures do not merely delay computation; they displace it from the continuous visual representation to a discrete textual space. Consequently, the sequential ``Perception-then-Reasoning'' paradigm degenerates perception into a passive, one-off feature encoding process, rendering it functionally equivalent to ``Reasoning-in-Text-Space'', where task-critical spatial si
arXiv:2507.16518v3 Announce Type: replace-cross Abstract: Recent advances in multimodal large language models (MLLMs) have shown impressive reasoning capabilities. However, further enhancing existing MLLMs necessitates high-quality vision-language datasets with carefully curated task complexities, which are both costly and challenging to scale. Although recent self-improving models that iteratively refine themselves offer a feasible solution, they still suffer from two core challenges: (i) most existing methods augment visual or textual data separately, resulting in discrepancies in data complexity (e.g., over-simplified diagrams paired with redundant textual descriptions); and (ii) the evolution of data and models is also separated, leading to scenarios where models are exposed to tasks with mismatched difficulty levels. To address these issues, we propose C2-Evo, an automatic, closed-loop self-improving framework that jointly evolves both training data and model capabilities. Specifi
arXiv:2501.02211v2 Announce Type: replace-cross Abstract: Large language models (LLMs) reproduce homogeneity bias -- the tendency to portray marginalized groups as more internally similar than dominant groups -- but whether this bias is stable or an artifact of inference settings has only been studied in single proprietary models. We map homogeneity bias across a 5x5 temperature-by-top-p grid in seven open-weight instruction-tuned LLMs (7-20B parameters). Hispanic and Asian Americans are portrayed as more homogeneous than White Americans in at least 18 of 20 hyperparameter configurations across six of seven models, including at extreme sampling settings. African American and gender bias show model-specific variation in direction. A conservative cell-level re-analysis confirms Hispanic and Asian homogeneity as robust, while weaker African American and gender signals largely do not survive, establishing group-specific robustness. We also apply the same grid to a names-based paradigm in w
arXiv:2405.17423v4 Announce Type: replace-cross Abstract: As Visual Language Models (VLMs) become increasingly embedded in everyday applications, ensuring they can recognise and appropriately handle privacy-sensitive content is thus essential to protect users. To this end, we conduct a comprehensive evaluation of twelve state-of-the-art VLMs and identify limitations in their understanding of visual privacy. However, existing privacy-related datasets often suffer from label inconsistencies, limiting their reliability. To address this, we introduce two compact, high-quality benchmarks, PrivBench and PrivBench-H, that focus on commonly recognised visual privacy categories aligned with the General Data Protection Regulation (GDPR). Additionally, we present PrivTune, an instruction-tuning dataset specifically curated to improve privacy sensitivity. We obtain multiple Privacy VLMs by fine-tuning off-the-shelf VLMs on only a few hundred samples from PrivTune, which leads to substantial gains
arXiv:2403.11425v4 Announce Type: replace-cross Abstract: Cancer treatments are known to introduce cardiotoxicity, negatively impacting outcomes and survivorship. Identifying cancer patients at risk of heart failure (HF) is critical to improving cancer treatment outcomes and safety. This study examined machine learning (ML) models to identify cancer patients at risk of HF using electronic health records (EHRs), including traditional ML, Time-Aware long short-term memory (T-LSTM), and large language models (LLMs) using novel narrative features derived from the structured medical codes. We identified a cancer cohort of 12,806 patients from the University of Florida Health, diagnosed with lung, breast, and colorectal cancers, among which 1,602 individuals developed HF after cancer. The LLM, GatorTron-3.9B, achieved the best F1 scores, outperforming the traditional support vector machines by 39%, the T-LSTM deep learning model by 7%, and a widely used transformer model, BERT, by 5.6%. The