Academic Intelligence · Curated Daily

Explore the Frontier of Global Academia

AcademicHub aggregates real-time literature from top journals and preprint platforms. Build your personal research radar and let large language models compile cross-disciplinary analysis briefings automatically.

01.
arXiv (CS.CL) 2026-06-19

Beyond the GUI Paradigm: Do Mobile Agents Need the Phone Screen?

Recent advances in mobile agents are dominated by the GUI paradigm, in which agents perceive UI information and emit screen interactions. However, mobile platforms also expose a command-line interface (CLI) that provides direct access to device services and data. We argue CLI deserves first-class consideration alongside GUI. We evaluate three coding agents (Claude Code, Terminus-2, mini-swe-agent) across four model APIs on AndroidWorld and MobileWorld without any mobile-specific post-training, comparing against three reproducible GUI baselines (GUI-Owl-1.5-32B, MAI-UI, Qwen3-VL-32B). Claude Code (Opus 4.7) reaches 71.8\% and 51.9\%, outperforming every reproducible GUI baseline (69.3/68.1/57.8\% on AndroidWorld; 43.2/26.3/13.3\% on MobileWorld), while every other CLI configuration remains competitive. To establish the paradigm's ceiling, we provide oracle CLI solutions that reach 88.8\% on AndroidWorld (103/116 tasks CLI-solvable) and 86.3\% on MobileWorld (101/117 tasks CLI-solvable), indicating substantial room for future improvement. To cover everyday user intents beyond the GUI scope, we introduce the CLI-Advantage Task Suite, comprising 45 templates across five categories: bulk operations, multi-condition filtering, aggregation, cross-app workflows, and hidden device state. Every CLI agent outperforms every GUI baseline in all five categories, with substantially fewer steps per task (10.7 vs.\ 18.6). To support future research on mobile CLI agents, we will open-source agent implementations, oracle solutions, the CLI-Advantage suite, and evaluation infrastructure.

02.
arXiv (CS.CL) 2026-06-25

Emergent Capabilities Arise Randomly from Learning Sparse Attention Patterns

Neural scaling laws for transformer language models predict smooth improvements in pretraining loss with increasing parameters, but downstream capabilities such as in-context learning are known to emerge abruptly past a certain model scale. In this paper, we show that emergent capabilities arise stochastically throughout training, with larger models acquiring them earlier on average. We demonstrate that the emergence of capabilities such as pattern completion and indirect object identification corresponds to the abrupt learning of task-relevant attention patterns. To isolate this phenomenon, we train transformer models on synthetic linear map and cellular automata datasets, and we show that the difficulty of learning attention patterns depends on context length and pattern sparsity. Moreover, scaling the number of attention heads improves learning efficiency on our synthetic tasks, while increasing the head dimension yields diminishing returns past a minimum capacity. We additionally investigate architectures with alternative attention mechanisms, showing that MLP-Mixer outperforms a transformer on linear map tasks with complex attention patterns. Our findings provide a mechanistic insight into emergence, showing that downstream capabilities arise abruptly due to the intrinsic difficulty of learning sparse attention patterns in transformer models.

03.
arXiv (CS.AI) 2026-06-16

Scaling Adaptive Depth with Norm-Agnostic Residual Networks

arXiv:2606.16112v1 Announce Type: cross Abstract: Residual architectures are ubiquitous in deep learning, but they suffer from a subtle structural limitation: the norm of the residual stream can grow rapidly with depth. As a result, updates from later layers become small relative to the accumulated residual state. This reduces their impact on the representation and limits the benefits of scaling models in depth. To address this, we introduce NAG, a norm-agnostic residual architecture that separates magnitude from directional information in the residual stream, preserving meaningful layer contributions throughout depth and preventing later updates from being systematically suppressed by residual-norm growth. Importantly, NAG introduces only a negligible number of additional parameters and relies on simple operations that are easily kernel-fusible, preserving training efficiency in practice. We show that this architecture outperforms baseline Transformers, with gains that increase substantially as depth grows, enabling effective training of much deeper models. The norm-agnostic formulation also leads to an interpretable Mixture-of-Depths (MoD) mechanism that adaptively skips both attention and MLP layers. Beyond serving as a post-training accuracy-compute tradeoff, this mechanism can be used as a pretraining-time scaling strategy: under iso-FLOP training, compute saved by reducing per-token forward-pass cost can be reinvested into training on more tokens while keeping the total parameter count and KV-cache budget fixed. In our experiments, moderate Mixture-of-Depths rates of approximately 20%-25% match full-depth baseline performance under equal training compute while substantially reducing the number of executed layer parameters and forward-pass FLOPs. These results identify sparsity in depth as a new scaling axis for fixed-compute training, enabling very deep yet FLOP-efficient models.

04.
medRxiv (Medicine) 2026-06-24

Factors associated with the uptake of intermittent preventive treatment in pregnancy with sulfadoxine-pyrimethamine: The experiences of postpartum women attending child welfare clinics in three rural districts in the Western Region of Ghana.

Background Intermittent preventive treatment in pregnancy with sulfadoxine-pyrimethamine (IPTp-SP) is a key preventive strategy. However, optimal uptake remains inconsistent despite high antenatal care (ANC) attendance. This study assessed factors associated with IPTp-SP uptake and explored the experiences of postpartum women in rural Ghana. Methods A mixed-method study was conducted among 1,155 postpartum women attending child welfare clinics in Jomoro, Prestea-Huni Valley and Ellembelle districts of the Western Region of Ghana. Quantitative data were collected using structured questionnaires and analysed using descriptive statistics and chi-square tests. Qualitative data from in-depth interviews and focus group discussions were analysed thematically to explore womens experiences and perceptions. Results Overall, 73.5% (812/1105) of respondents received at least three doses of SP during pregnancy, in line with WHO recommendations. The most common number of doses received was three doses (31.5%, 348/1105), followed by four doses (26.4%, 292/1105), while a smaller proportion (8.1%, 90/1105) received only one dose. Knowledge of malaria in pregnancy was generally high: 92.7% (1027/1155) of respondents correctly identified its mode of transmission, while 75.1% (830/1155) and 83.5% (923/1155) were aware of the effects of malaria on pregnancy and the foetus, respectively. Uptake was not significantly associated with socio-demographic characteristics, including age, education, occupation, marital status, gravidity, and parity (p > 0.05). However, number of ANC visits was significantly associated with uptake (p = 0.006). Although not statistically significant, lower uptake was observed among peri-urban residents and uninsured women. Qualitative findings indicated that while women recognized the benefits of IPTp-SP, side effects such as nausea, dizziness, and discomfort, as well as challenges with tablet formulation and dosing negatively influenced adherence. Conclusions IPTp-SP uptake was high and largely independent of socio-demographic factors but strongly influenced by ANC attendance. Addressing experiential barriers and strengthening patient-centered counselling during ANC may further improve uptake and adherence.

05.
arXiv (CS.AI) 2026-06-18

EMORSION: Examining the Impact of Audio Parameters on Emotional Responses and Immersion in Film

arXiv:2606.18266v1 Announce Type: cross Abstract: EMORSION is an exploratory proof-of-concept study examining how film audio design shapes audience emotion and immersion in acinema setting. Four film scenes were selected across the horror (2) and drama (2) genres, balanced between mainstream and independent productions. For each scene, multiple alternative audio mixes were created by systematically manipulating three core aspects of audio design, frequency (pitch), dynamics (loudness), and directionality (spatial placement). Three audience groups viewed the scenes, with each group exposed to one manipulated mix alongside a control mix for each scene. Audience responses were assessed through a triangulated multimodal framework combining self-reported emotion and immersion via a questionnaire, physiological measures including heart rate monitoring, and video-based motion tracking. The protocol successfully captured measurable, interpretable differences across audio conditions, indicating that even subtle changes in audio design can shape emotional perception and immersion. Unconventional mixes tended to produce greater variability in audience interpretation, while conventional immersive mixes were associated with stronger cross-audience agreement. These findings establish the feasibility of the EMORSION protocol and motivate larger-scale studies to characterise the role of specific audio parameters in shaping audience experience.

06.
arXiv (CS.AI) 2026-06-19

DynAMO:Dynamic Asset Management Orchestration via Topological Multi-Agent Scheduling

arXiv:2606.19382v1 Announce Type: cross Abstract: While LLM-powered agents offer end-to-end automation for industrial asset lifecycles, real-world Industry 4.0 deployment is hindered by latency, concurrency instability, and safety risks. We present DynAMO (Dynamic Asset Management Orchestration), a deployment-ready engine using a Plan-then-Execute architecture to generate verifiable workflow graphs. DynAMO supports both SequentialWorkflow (topological execution) and ParallelWorkflow (dependency-aware concurrency). By dynamically identifying independent tasks, DynAMO preserves structural correctness and safety while significantly improving efficiency through controlled reasoning overlap. Across six controlled experiments on the AssetOpsBench industrial benchmark, DynAMO demonstrates substantial performance and robustness gains. Parallel execution reduces end-to-end latency by a median of 1.6x over sequential orchestration, rising to 1.8x on highly parallelizable workflows. After instrumenting external tool calls with realistic latencies, a latency decomposition shows that LLM reasoning and orchestration still account for more than 90% of execution time, identifying model inference as the primary system bottleneck. Structured context pruning reduces inference latency by approximately 30%, and DynAMO maintains correct functional behaviour (task completion, agent sequencing, and output quality) while exhibiting graceful degradation under controlled fault injection. Reproducibility analysis further confirms stable execution under repeated runs, with parallel scheduling reducing latency variance. These findings establish DynAMO as a practical blueprint for scalable, safe, and latency-aware agent deployment in Industry 4.0 automation pipelines. Code is available at: https://github.com/kushwaha001/DynAMO

07.
medRxiv (Medicine) 2026-06-17

Adverse Childhood Experiences Reorganise the Brain-Personality Network Across the Psychosis Spectrum

Exposure to adverse childhood experiences is a pervasive risk factor for psychosis, exhibiting a linear relationship across the psychosis spectrum from subclinical schizotypal traits to schizophrenia spectrum disorders. While this association is often conceptualised within the vulnerability-stress framework, the systemic mechanisms through which childhood trauma reconfigures the brain-personality interactome remain poorly understood. We examined clinical, neuropsychological, and neuroimaging data from a sample of low- and high-schizotypy individuals, and patients with a diagnosis of schizophrenia spectrum disorder (N=120). Our aim was to map how trauma reconfigures interactions between neurobiology and schizotypal phenomenology. We adopted a mixed graphical model approach to jointly estimate conditional dependencies between childhood trauma, regional brain morphometry, and schizotypal traits across the psychosis spectrum. Our results show that childhood trauma reconfigures the brain-personality network, shifting it from a state driven by cognitive processes to one anchored in emotional (limbic) reactivity. This transition is marked by the increased influence of impulsive traits and a significant strengthening of connections within the salience network. These changes converge with a reduced thickness of the frontal executive regions, the brain's control centres, identified in our models. Collectively, our results suggest a structural phenomenological decoupling, where trauma conditioned affective circuits may bypass weakened top-down regulatory controls. These findings highlight the necessity of using integrative frameworks to capture how trauma fundamentally reshapes the relationship between the brain and schizotypal personality.

08.
arXiv (quant-ph) 2026-06-25

Controlling radiative dynamics of a giant $\Lambda$-type atom via interference induced by the vacuum of a waveguide

arXiv:2606.25587v1 Announce Type: new Abstract: We investigate the dynamics of a $\Lambda$-type giant atom (GA) whose both transition coupled to the guided modes of a one-dimensional (1D) waveguide at two spatially separated points with the GA initially excited and the electromagnetic (EM) modes of waveguide in vacuum. The spontaneous emission properties of this GA is investigated by solving the delay-differential equation for the amplitude of the 3GA in its excited state. Signatures of non-Markovian behavior is manifested in a population trapping in the excited state of the GA in the regime where the distance $d$ of the coupling points is smaller or comparable to the coherent length $L$ characterizing the width of the emitted wave packet. And an exact Markovian dynamics is also found when $d\geq L$ via the inference by adjusting the energy spacing and the inherent time delay besides the complex phases in the atom-light coupling, matching the behavior of a small atom coupled to a waveguide.

10.
arXiv (CS.CL) 2026-06-16

Prior over Evidence: Stereotype-Driven Diagnosis in LLM-Based L2 Pronunciation Feedback

Large language models are increasingly deployed for written pronunciation feedback in second-language (L2) English learning, under the assumption that their diagnoses are grounded in the supplied speech evidence rather than in priors from pretraining. This assumption is tested on 1,800 L2-Arctic utterances spanning six L1 backgrounds, three audio-capable LLMs, four pronunciation dimensions, and five evidence conditions ranging from a text-only baseline to numeric acoustic features and raw audio. Each (utterance x model x condition x dimension) cell is scored on three metrics: Rating Accuracy (RA) against gold labels, Evidence Coherence (EC) assessing internal consistency without ground truth, and Grounded Correctness (GC) evaluated against gold evidence. Results show three findings across models. First, rating accuracy and grounded reasoning decouple: 39.6% of judged cells contain internally coherent reasoning that supports a wrong rating, against only 15.8% where the reasoning supports a correct rating. Second, phoneme-level feedback converges to a fixed inventory of L2-English difficulty phones that recurs across all six L1 backgrounds and all evidence conditions. Third, acoustic evidence improves the rating only when the supplied feature directly probes the target dimension: textualised F0 range raises pitch-variation grounding from (0.18-0.19) to (0.45-0.62) across all three models, while stress and phoneme correctness, which require target-to-realisation alignment, remain ungrounded. The same audio waveform without textualised F0 values does not reproduce this improvement. These findings indicate that current general-purpose LLMs are more reliable as verbalisers of externally computed pronunciation evidence than as standalone diagnostic engines.

11.
arXiv (quant-ph) 2026-06-16

Neural quantum states for entanglement depth certification from randomized Pauli measurements

arXiv:2512.13121v2 Announce Type: replace Abstract: Entanglement depth quantifies how many qubits share genuine multipartite entanglement, but certification typically relies on tailored witnesses or full tomography, both of which scale poorly with system size. We recast entanglement-depth and non-$k$-separability certification as likelihood-based model selection among neural quantum states whose architecture enforces a chosen entanglement constraint. A hierarchy of separable neural quantum states is trained on finite-shot local Pauli outcomes and compared against an unconstrained reference model trained on the same data. When all constrained models are statistically disfavored, the data certify entanglement beyond the imposed limit directly from measurement statistics, without reconstructing the density matrix. We validate the method on simulated six- and ten-qubit datasets targeting GHZ, Dicke, and Bell-pair states, and demonstrate robustness for mixed states under local noise. Finally, we discuss lightweight interpretability diagnostics derived from trained parameters that expose coarse entanglement patterns and qubit groupings directly from bitstring statistics.

12.
arXiv (CS.AI) 2026-06-18

AdsMind: A Physics-Grounded Multi-Agent System for Self-Correcting Discovery of Adsorption Configurations on Heterogeneous Catalyst Surfaces

arXiv:2606.19152v1 Announce Type: cross Abstract: Identifying the lowest-energy surface-adsorbate configuration is critical for modeling heterogeneous catalysis, yet exhaustive exploration with ab initio calculations is computationally prohibitive. Machine-learning force fields (MLFFs) accelerate structural relaxation but leave the search over the vast configurational space a major bottleneck, and open-loop large language model (LLM) agents lack a physics-grounded feedback mechanism to correct erroneous initial guesses. We propose AdsMind (Adsorption configuration discovery with Machine intelligence and relaxation feedback), a closed-loop multi-agent framework that enables autonomous error correction through MLFF relaxation feedback. Across four LLM backends, AdsMind achieves consistently high search reliability, with success rates of 100% and 98.8% on the benchmarks AA20 and OCD-GMAE62. Relative to its single-pass (1-Shot) ablation it reduces cross-backend energy dispersion, and it uses only 4.11 and 4.67 MLFF relaxations per case, respectively – an approximately 14-fold reduction over heuristic enumeration baselines. Density functional theory (DFT) validation using VASP/PBE on six representative AA20 systems shows that the reported open-loop Adsorb-Agent outputs exhibit qualitative adsorption-energy sign errors for molecular adsorbates, whereas AdsMind preserves the correct sign in all tested cases with closer quantitative agreement. AdsMind thus delivers reliability, self-reflection, and interpretability simultaneously, supporting more DFT-informed autonomous chemistry workflows.

13.
arXiv (CS.AI) 2026-06-16

The Reservoir Attention Network: Cross-Pass State in Pretrained Transformers via Content-Addressable Reservoir Injection

Authors:

arXiv:2606.15678v1 Announce Type: cross Abstract: A feasibility and dynamics study of the Reservoir Attention Network (RAN), an architecture that injects a fixed, randomly-initialized reservoir into the mid-layer attention of a pretrained transformer to carry state across forward passes. Experiments span GPT-2 (124M, 355M) to Qwen2.5 (0.5B, 1.5B) on a single consumer GPU. The tasks are minimal probes chosen to isolate individual mechanisms; the broader always-alive agent vision is treated throughout as compute-limited future work, not a claim of this paper. The reservoir is left untrained (fixed random) by design: this isolates whether untrained recurrent dynamics alone suffice to carry usable cross-pass state, leaving trained recurrence as a complementary, more expensive direction.

14.
arXiv (CS.AI) 2026-06-19

Simulation of Language Evolution under Regulated Social Media Platforms: A Synergistic Approach of Large Language Models and Genetic Algorithms

arXiv:2502.19193v2 Announce Type: replace-cross Abstract: Social media platforms frequently impose restrictive policies to moderate user content, prompting the emergence of creative evasion language strategies. This paper presents a multi-agent framework based on Large Language Models (LLMs) to simulate the iterative evolution of language strategies under regulatory constraints. In this framework, participant agents, as social media users, continuously evolve their language expression, while supervisory agents emulate platform-level regulation by assessing policy violations. To achieve a more faithful simulation, we employ a dual design of language strategies (constraint and expression) to differentiate conflicting goals and utilize an LLM-driven GA (Genetic Algorithm) for the selection, mutation, and crossover of language strategies. The framework is evaluated using two distinct scenarios: an abstract password game and a realistic simulated illegal pet trade scenario. Experimental results demonstrate that as the number of dialogue rounds increases, both the number of uninterrupted dialogue turns and the accuracy of information transmission improve significantly. Furthermore, a user study with 40 participants validates the real-world relevance of the generated dialogues and strategies. Moreover, ablation studies validate the importance of the GA, emphasizing its contribution to long-term adaptability and improved overall results.

15.
arXiv (math.PR) 2026-06-18

The FBSDE approach to sine-Gordon up to $6\pi$

arXiv:2401.13648v3 Announce Type: replace-cross Abstract: We develop a stochastic analysis of the sine-Gordon Euclidean quantum field $(\cos (\beta \varphi))_2$ on the full space up to the second threshold, i.e. for $\beta^2 < 6 \pi$. The basis of our method is a forward-backward stochastic differential equation (FBSDE) for a decomposition $(X_t)_{t \geqslant 0}$ of the interacting Euclidean field $X_{\infty}$ along a scale parameter $t \geqslant 0$. This FBSDE describes the optimiser of the stochastic control representation of the Euclidean QFT introduced by Barashkov and one of the authors. We show that the FBSDE provides a description of the interacting field without cut-offs and that it can be used effectively to study the sine-Gordon measure to obtain results about large deviations, integrability, decay of correlations for local observables, singularity with respect to the free field, Osterwalder-Schrader axioms and other properties.

16.
arXiv (math.PR) 2026-06-24

History estimation in random recursive trees: Pointwise approach via iterated Jordan centralities

arXiv:2606.24465v1 Announce Type: new Abstract: We study the problem of estimating the arrival times of vertices in a uniform random recursive tree from its unlabeled structure. We adopt a pointwise perspective and analyze the distribution of the relative estimation error, and derive tail bounds that are uniform in both the vertex and the tree size. For the ranking induced by Jordan centrality, the probability that the estimate exceeds the true arrival time by a factor $S$ decays on the order of $1/S$, while the probability of underestimating the arrival time by a factor $1/S$ decays exponentially in $S$. We introduce a refined centrality measure whose overestimation tail decays on the order of $(\log S)/S^{2}$, at the cost of a heavier lower tail of order $1/S^{2}$. These results reveal a tradeoff between upper- and lower-tail performance in arrival-time estimation that is invisible to the previously studied risk functional. Nevertheless, the refined centrality measure attains the optimal order of the risk for all its parameter values.

17.
arXiv (CS.LG) 2026-06-19

Quantum ring all-reduce: communication and privacy advantages for distributed learning

arXiv:2606.20344v1 Announce Type: cross Abstract: Machine learning models have scaled to unprecedented sizes, making training across distributed devices the de facto standard in the field. In this work, we explore how quantum communications can make distributed training both more communication-efficient and information-theoretically private, for both classical and quantum learning models. Ring all-reduce is the foundational communication primitive for large-scale distributed training. We present a quantum version that reduces per-link online communication by a provably optimal factor of two using pre-shared entanglement and superdense coding, without requiring the learning model or gradient computation to change. Beyond bandwidth, the primitive enables privacy guarantees that are information-theoretically impossible for any classical protocol, achieving composable {\epsilon}-secure aggregation, via verified entanglement, at a 2x overhead in GHZ copies. Our hybrid quantum-classical communication architecture yields simultaneous communication and security advantages for large scale distributed training, regardless of whether the learning itself is quantum or classical. Finally, we characterise quantum advantages in gradient conflict detection for server-to-client communication under bandwidth constraints, a setting that arises after ring all-reduce is completed, when full gradient broadcast to external clients is infeasible. Two variants of the problem admit different separations. For margin-based alignment testing (\textsc{GapIP}_{\tau}), the quantum advantage is quadratic in the margin parameter: \widetilde{O}({\tau}^{-1}\log P) qubits versus \widetilde{O}(\min(\{\tau}^{-2},P)) bits. For sign-consistency auditing against a private parameter matching (\textsc{TieAudit}_{\epsilon}), the advantage represents an exponential separation in communication complexity: \Omega(\sqrt{P}) bits whereas O({\epsilon}^{-2}\log P) qubits suffice.

18.
arXiv (CS.AI) 2026-06-11

An XAI View on Explainable ASP: Methods, Systems, and Perspectives

arXiv:2601.14764v2 Announce Type: replace Abstract: Answer Set Programming (ASP) is a popular declarative reasoning and problem solving approach in symbolic AI. Its rule-based formalism makes it inherently attractive for explainable and interpretive reasoning, which is gaining importance with the surge of Explainable AI (XAI). A number of explanation approaches and tools for ASP have been developed, which often tackle specific explanatory settings and may not cover all scenarios that ASP users encounter. In this survey, we provide, guided by an XAI perspective, an overview of types of ASP explanations in connection with user questions for explanation, and describe their coverage by current theory and tools. Furthermore, we pinpoint gaps in existing ASP explanations approaches and identify research directions for future work.

19.
medRxiv (Medicine) 2026-06-24

Cortisol Stress Response is Associated with Iron Status in Pregnancy

Background: Iron deficiency (ID) affects up to 40% of pregnant women in the third trimester, even in highly resourced and iron-supplemented populations, with adverse consequences for maternal health and long-term offspring development. Psychological stress may compromise iron status through hypothalamic-pituitary-adrenocortical (HPA) axis dysregulation and inflammation, but no study has directly examined cortisol in relation to iron status across human pregnancy. Objective: This longitudinal study examined associations between HPA function and maternal iron status across pregnancy and tested whether IL-6 and CRP mediated the relationship between cortisol and ferritin across gestation. Methods: One hundred sixty-eight pregnant Black women with Medicaid insurance completed up to four laboratory assessments across pregnancy. Salivary cortisol was measured before and in response to the Trier Social Stress Test, yielding basal and reactive cortisol indices. Serum ferritin, IL-6, and CRP were collected at each visit. Trimester-specific regression models examined cortisol reactivity in relation to ferritin; linear mixed-effects models with moderated mediation tested whether basal cortisol predicted ferritin via inflammation. Results: Higher cortisol reactivity was associated with lower ferritin specifically in the third trimester (std. {beta} = -0.197, p = .004). Higher basal cortisol predicted a steeper IL-6 rise across gestation (p = .002), and IL-6 was positively associated with ferritin (b = 0.236, p = .006), consistent with inflammatory iron sequestration. The indirect effect of basal cortisol on ferritin via IL-6 was statistically significant, and higher basal cortisol was negatively associated with cortisol reactivity in the third trimester. No pathway was observed through CRP. Conclusion: Greater cortisol reactivity predicted lower third-trimester ferritin, a pattern that suggests cumulative iron depletion, atypically sustained HPA reactivity in late pregnancy, or both. To our knowledge, this is the first prospective study linking cortisol reactivity to iron status across human pregnancy, identifying maternal stress physiology as a novel target for understanding and addressing gestational iron deficiency.

20.
arXiv (CS.CV) 2026-06-19

Rethinking Robust Adversarial Concept Erasure in Diffusion Models

Concept erasure aims to selectively unlearning undesirable content in diffusion models (DMs) to reduce the risk of sensitive content generation. As a novel paradigm in concept erasure, most existing methods employ adversarial training to identify and suppress target concepts, thus reducing the likelihood of sensitive outputs. However, these methods often neglect the specificity of adversarial training in DMs, resulting in only partial mitigation. In this work, we investigate and quantify this specificity from the perspective of concept space, i.e., can adversarial samples truly fit the target concept space? We observe that existing methods neglect the role of conceptual semantics when generating adversarial samples, resulting in ineffective fitting of concept spaces. This oversight leads to the following issues: 1) when there are few adversarial samples, they fail to comprehensively cover the object concept; 2) conversely, they will disrupt other target concept spaces. Motivated by the analysis of these findings, we introduce S-GRACE (Semantics-Guided Robust Adversarial Concept Erasure), which grace leveraging semantic guidance within the concept space to generate adversarial samples and perform erasure training. Experiments conducted with seven state-of-the-art methods and three adversarial prompt generation strategies across various DM unlearning scenarios demonstrate that S-GRACE significantly improves erasure performance 26%, better preserves non-target concepts, and reduces training time by 90%. Our code is available at https://github.com/Qhong-522/S-GRACE.

21.
arXiv (CS.CL) 2026-06-17

When Tables Go Crazy: Evaluating Multimodal Models on French Financial Documents

Vision-language models (VLMs) perform well on many document understanding tasks, yet their reliability in specialized, non-English domains remains underexplored. This gap is especially critical in finance, where documents mix dense regulatory text, numerical tables, and visual charts, and where extraction errors can have real-world consequences. We introduce Scribe Finance, the first multimodal benchmark for evaluating French financial document understanding. The dataset contains 1,204 expert-validated questions spanning text extraction, table comprehension, chart interpretation, and multi-turn conversational reasoning, drawn from real investment prospectuses, KIDs, and PRIIPs. We evaluate six open-weight VLMs (8B-124B parameters) using an LLM-as-judge protocol. While models achieve strong performance on text and table tasks (85-90% accuracy), they struggle with chart interpretation (34-62%). Most notably, multi-turn dialogue reveals a sharp failure mode: early mistakes propagate across turns, driving accuracy down to roughly 50% regardless of model size. These results show that current VLMs are effective for well-defined extraction tasks but remain brittle in interactive, multi-step financial analysis. Scribe Finance offers a challenging benchmark to measure and drive progress in this high-stakes setting.

22.
arXiv (CS.CV) 2026-06-25

GeoRanker: Distance-Aware Ranking for Worldwide Image Geolocalization

Worldwide image geolocalization-the task of predicting GPS coordinates from images taken anywhere on Earth-poses a fundamental challenge due to the vast diversity in visual content across regions. While recent approaches adopt a two-stage pipeline of retrieving candidates and selecting the best match, they typically rely on simplistic similarity heuristics and point-wise supervision, failing to model spatial relationships among candidates. In this paper, we propose GeoRanker, a distance-aware ranking framework that leverages large vision-language models to jointly encode query-candidate interactions and predict geographic proximity. In addition, we introduce a multi-order distance loss that ranks both absolute and relative distances, enabling the model to reason over structured spatial relationships. To support this, we curate GeoRanking, the first dataset explicitly designed for geographic ranking tasks with multimodal candidate information. GeoRanker achieves state-of-the-art results on two well-established benchmarks (IM2GPS3K and YFCC4K), significantly outperforming current best methods.

23.
arXiv (CS.CL) 2026-06-16

Calibrated Triage, Not Autonomy: Confidence Estimation for Medical Vision-Language Models

A vision-language model can answer a question about a medical image fluently and confidently while barely using the image, leaning instead on language priors. In medicine this is the failure that matters most, because the answer looks trustworthy and is not, and the only protection is a confidence score reliable enough to tell the system when to abstain. We ask a deployment question rather than an accuracy one: how much imaging work a model can safely handle alone, and which confidence signal makes that possible. We evaluate seven confidence estimators across five open-weight LVLMs and three medical visual-question-answering datasets spanning broad clinical imaging, radiology, and pathology, with every probe trained only on natural images and applied without adaptation. Recast as bounded selective prediction (automate a case only when confidence clears a threshold, defer the rest), the comparison is cautionary. The standard metrics are poor guides: discrimination barely separates the methods, and the weak calibration of a cheap self-report is cheaply removed by off-domain temperature scaling without changing deployable yield. What distinguishes a usable estimator is the high-confidence region a clinician acts on: the weakest baselines are confidently wrong on 41 to 45 percent of their errors against 1 to 4 percent for the best probe, and no estimator is reliably best across domains or models. Safe handoff is governed at two levels: base-model competence sets a ceiling, so a well-calibrated score recovers roughly a third of radiology cases at a 20 percent error tolerance but almost none of pathology; the confidence layer then decides how much of that ceiling is reachable. The usable role today is calibrated triage, not autonomy: automate the cases a calibrated score marks safe, route the rest to a clinician. We release all outputs, correctness judgments, and confidence scores, with code.

24.
arXiv (CS.AI) 2026-06-25

Internal Data Repetition Destroys Language Models

arXiv:2606.24998v1 Announce Type: cross Abstract: Language models are running out of high-quality training data, and even aggressively deduplicated corpora retain some amount of repetition. Earlier controlled studies predated Chinchilla-style scaling laws and could only measure the cost of repetition indirectly. We revisit repetition in the Chinchilla era, using a fitted no-repetition scaling law to report Compute-Equivalent Gain and Compute-Equivalent Loss. We show that under this modernized paradigm, repetition damage is systematic in three ways. First, holding compute allocated to repeated data constant, eval loss peaks at an intermediate repeat count $\Rep$; repeating a moderately sized subset a moderate number of times damages performance more than repeating a large subset a few times or a small subset many times. Second, the location of this peak is well-fit by a power law in model size; this scaling law reveals that the most damaging number of repeated data grows more quickly than compute. Finally, when repeated documents consume 10\% of the FLOPs budget in a controlled exact-document repetition setting, the compute-equivalent loss can be large: on FineWeb-Edu-Dedup, the most damaging repeat count for a Qwen3-style 344M-parameter model at $\operatorname{OT}=1$ matches the loss of a no-repetition run using 67% of the FLOPs. We demonstrate that these phenomena are not language-model-specific, and can be analytically understood in a simple statistical model: a misspecified linear regression with verbatim duplicates reproduces the same qualitative loss peak, quantifying how such peaks can arise from a statistical tradeoff between memorization and generalization. Our findings add precision to the study of duplication in language models, allowing practitioners to quantify the wasted compute incurred by the presence and repeat structure of duplicates in pretraining corpora.

25.
arXiv (CS.AI) 2026-06-19

ORAgentBench: Can LLM Agents Solve Challenging Operations Research Tasks End to End?

arXiv:2606.19787v1 Announce Type: new Abstract: Large language models are increasingly deployed as autonomous agents for multi-step tasks in executable environments, yet their ability to perform realistic operations research (OR) work remains unclear. Existing OR evaluations often decouple modeling from solving, rely on pre-formalized or text-only instances, and rarely test the full workflow from operational artifacts to validated decisions. In this work, we introduce ORAgentBench, an execution-grounded benchmark for evaluating autonomous agents on challenging end-to-end operations research tasks. It contains 107 human-reviewed tasks across diverse operational scenarios, each packaged in an isolated environment with a natural-language brief, multi-file data, configuration artifacts, and a required submission schema. Agents must write and run solution code, and their submissions are evaluated by hidden validators for schema validity, hard-constraint feasibility, and normalized objective quality. Experiments with fourteen frontier agent-model configurations show that current agents remain far from reliable OR practice. The best agent passes only 35.51% of all tasks and 20.59% of hard tasks, and many feasible submissions still fall below the required quality threshold. Failure analysis further shows that errors are dominated by strategic weaknesses, including missed operational rules, brittle formulations, weak feasible-solution construction, and insufficient solution improvement. OR-specific procedural skills increase hard-task feasibility, but do not reliably improve solution quality or pass rate. These results suggest that progress in OR agents requires moving beyond plausible optimization code toward dependable, high-quality operational decision-making.