arXiv:2607.10617v1 Announce Type: new
Abstract: The lineage graph of open-weight language models is self-reported: Hugging Face's base_model metadata field is optional and unverified, and over 60% of Hub models document no parentage at all. Methods for detecting lineage from weights exist in the research literature, but each ships as paper code tied to one signal and one experiment; when a provenance dispute breaks, the analysis is redone by hand. This report describes modelDNA, a tool that fingerprints a model from roughly 100-300 MB of ranged HTTP reads (instead of a full 15 GB download for a 7B model), compares the fingerprint against a reference database of foundation models across four published signal families, and returns one of eight verdict classes with a calibrated probability, preferring honest abstention to confident error. On a benchmark of 15 real Hub models with org-documented parentage, judged against 8 candidate bases (13 positives, 107 hard negatives), the system achieves AUROC 1.0, zero false positives at its reporting threshold, and 13/13 correct top-1 parent attribution. The report's second contribution is merge decomposition. Every mainstream weight-merging method is (near-)linear per tensor, and fingerprint sample positions are deterministic functions of tensor identity, so a merged model's fingerprint is the same linear combination of its parents' fingerprints. Mixture weights can therefore be recovered from fingerprints alone by sum-to-one constrained least squares. Against merges with published mergekit configurations as ground truth, the method recovers a slerp merge's layer-interpolation curves at r = 0.999 and a dare_ties merge's mixture weights to within 0.011 of the published values, without downloading any weights beyond the fingerprints. All fingerprints, benchmarks, and the inferred lineage graph of 55 models are public and reproducible offline.
Science Journals
arXiv:2607.11172v1 Announce Type: new
Abstract: Reinforcement learning for deep-search agents has largely focused on trajectory-level scoring -- outcome correctness, citation-aware rewards, and evidence coverage. Yet the actions that expose supporting documents receive no targeted credit, a gap we call the reward-credit mismatch. We propose STAMP, in which a reference-based verifier judges whether each cited document supports an entity or relation in a training-time evidence graph, and first-exposure attribution traces each supported citation back to the action that first surfaced it. This step credit is injected through sign-preserving advantage modulation, which redistributes advantage across steps without changing the trajectory-level reward or the relative ranking of trajectories within each group. On BrowseComp, BrowseComp-ZH, and xbench-DS, STAMP improves the GRPO baseline by +2.0/+5.5/+3.0 points under matched SFT initialization, training data, and search tools, and composes with both outcome-only and citation-rubric base rewards. Component ablations confirm that the provenance-based credit signal and the sign-preserving advantage modulation each contribute to the gains.
arXiv:2607.10528v1 Announce Type: new
Abstract: We study the nonisotropic fractional analogs of Laplace, Helmholtz and Yukawa equations. We provide a Duffin correspondence for the Yukawa equation and a Feynman--Kac reconstruction for the Helmholtz equation. The foundation of our analysis is the fact that the nonisotropic fractional Laplace equation is related to a symmetric $\alpha$-stable L\'evy process with independent identically distributed components. By using this relation we provide a Walk-on-Cubes algorithm that simulates the solutions of Helmholtz and Yukawa equations.
arXiv:2607.11024v1 Announce Type: new
Abstract: This study compares high-Reynolds-number turbulent boundary layers under zero and low-to-moderate adverse pressure gradients, showing similar scaling and energy contributions from the wall-scaled attached-eddy hierarchy and superstructures in both flows. The main differences occur in the outer/wake region, where APG-induced energisation is linked to an outer-scaled, embedded-shear-layer-type organisation that progressively penetrates the logarithmic region as the pressure-gradient strength increases. The analysis uses two complementary datasets for ZPG and APG boundary layers at matched friction Reynolds numbers of approximately 10,000, with minimal upstream pressure-gradient history: a new two-point hot-wire dataset and a previously published two-dimensional particle image velocimetry dataset. In the hot-wire experiment, one probe is fixed near the wall while the second traverses the full boundary layer, allowing estimation of the linear coherence spectrum. The results confirm the geometric self-similarity of the wall-scaled eddy hierarchy that remains coherent with the wall. Using the linear coherence spectrum as a spectral filter shows that most of the additional APG-induced energy is incoherent with the wall and is linearly superimposed on the wall-coherent component of the streamwise variance. This wall-incoherent contribution explains the departure of the variance profile from the inverse logarithmic law observed in canonical high-Reynolds-number boundary layers. Conditional averaging of the particle image velocimetry data identifies the structures responsible for this energy amplification. The results link enhanced outer-region Reynolds stresses, an outer inflection point in the mean velocity profile, and an ejection-sweep organisation of Reynolds shear stress, all characteristic of shear-layer dynamics.
arXiv:2607.09713v1 Announce Type: new
Abstract: A key step toward autonomous industrial operation is the ability to create and reconfigure control policies from natural-language requirement specifications, with minimal or no manual redesign. In this setting, policy generation by AI agents can be a credible path when paired with a plant-aware validator (e.g., a digital twin) that can check generated candidate actions before execution. However, practical deployment is constrained by inference latency and compute footprint: large cloud-based models are often too slow, opaque, or data-sensitive for edge closed-loop use. This work investigates whether a compact Small Language Model (SLM) can be retrained for control reasoning and embedded in a validator-guided correction loop. We use a Qwen2.5-1.5B model aligned via Group Relative Policy Optimization (GRPO), combined with (i) an action agent, (ii) a symbolic/digital-twin-style validation layer, and (iii) a reprompting agent that iteratively steers outputs toward valid actions. In randomized thermal-control simulations (30 experiments with 500 steps each), the framework achieves 91.5% average action-alignment accuracy (86.3%--100% across cases) at 3.84\,s mean inference latency. Under symbolic re-mapping, it maintains a 95% in-range rate, indicating robust physical regulation despite reduced token-level agreement. These results support SLM+validator architectures as a practical path toward reconfigurable autonomous control at the edge.
arXiv:2607.11684v1 Announce Type: cross
Abstract: Existing contextual multinomial logit (MNL) bandits model relevance-driven choice but ignore the potential benefits of within-assortment diversity, while submodular/combinatorial bandits encode diversity in rewards but lack structured choice probabilities. We bridge this gap with the $\textit{diversified multinomial logit}$ (DMNL) contextual bandit, which augments MNL choice probabilities with a generally submodular diversity function, thereby formalizing the relevance--diversity trade-off within a single model. Incorporating diversity renders exact MNL assortment optimization intractable. We propose a $\textit{white-box}$ UCB-based algorithm, $\texttt{OFU-DMNL}$, that constructs assortments item-wise by maximizing optimistic marginal gains, avoids black-box optimization oracles. We show that $\texttt{OFU-DMNL}$ achieves at least a $(1-\frac{1}{e+1})$-$\textit{approximate}$ regret bound $\tilde{O}\left(d \sqrt{T/K}\right)$, where $d$ is the context dimension, $K$ the maximum assortment size, and $T$ the horizon, and attains an improved approximation factor over standard submodular baselines. Experiments demonstrate consistent gains and, relative to exhaustive enumeration, comparable regret with substantially lower runtime. Overall, DMNL bandits provide a practical foundation for diversity-aware assortment optimization under uncertainty, and $\texttt{OFU-DMNL}$ offers a statistically and computationally efficient solution.
arXiv:2607.11872v1 Announce Type: cross
Abstract: A $4$-uniform $2$-cycle in a $4$-uniform hypergraph of length $t$ is a cyclic ordering of $2t$ vertices $v_1v_2\cdots v_{2t}v_1$ such that $v_{2i+1}v_{2i+2}v_{2i+3}v_{2i+4}$ are edges for $0\le i\le t-1$ while the addition is modulo $2t$.
For every $\gamma>0$ and large $n$, we characterize the $n$-vertex $4$-uniform hypergraphs such that every triple of vertices is contained in at least $(1/3+\gamma)n$ edges and admits a Hamilton $2$-cycle. Up to the error term $\gamma n$, the assumption on the minimum codegree is best possible and verifies a conjecture of Garbe and Mycroft. As a consequence, this gives a polynomial-time algorithm that decides whether an $n$-vertex $4$-uniform hypergraph with minimum codegree $(1/3+\gamma)n$ contains a Hamilton $2$-cycle. This stands as a steep contrast to the graph case where such a hardness gap has size $o(n)$.
arXiv:2607.10846v1 Announce Type: new
Abstract: Computational social science increasingly relies on automated preprocessing pipelines -- speaker diarization, ASR transcript cleaning, sentence segmentation -- to convert raw media into analyzable text. When these pipelines produce different outputs from the same input, two distinct sources of instability can arise: the preprocessing pipeline itself (diarization method, segmentation rules) and the downstream measurement instrument (LLM annotation vs.\ keyword lexicon). Using 256 YouTube interviews across 41 public figures from five domains, we compare two speaker-diarization pipelines and two measurement methods, all targeting the coupling between affective valence and epistemic modality. We find that (1) preprocessing pipeline sensitivity is concentrated in speakers with limited video samples (N $\leq 5$); for the four best-sampled speakers (N $\geq 16$), the mean absolute pipeline-induced change in $r(\text{neg}, \text{emph})$ is only $0.13$; (2) cross-method disagreement is larger and more systematic -- the LLM and keyword-lexicon methods assign opposite coupling directions to several well-sampled speakers, even within the same preprocessing pipeline; and (3) aggregate valence proportions are highly stable ($|\Delta p(\text{neg})| < 6$pp) regardless of pipeline or method, masking both sources of instability. The contribution is a diagnostic framework that separates pipeline effects from measurement effects: researchers studying cross-dimensional relationships in interview data should verify that their conclusions are robust to both sources of variation, with particular attention to measurement method choice.
arXiv:2507.12495v3 Announce Type: replace
Abstract: Space weather events pose a growing threat to modern economies, yet their macroeconomic consequences remain underexplored. This study presents the first dedicated economic assessment of geomagnetic storm impacts on Aotearoa New Zealand, quantifying potential gross domestic product (GDP) losses across seven conservative disruption and mitigation scenarios due to an extreme coronal mass ejection (CME). The primary focus is on the damaging impacts of geomagnetically induced currents (GICs) on the electrical power transmission network. We support space weather mitigation investment decisions by providing a first-order approximation of their potential economic benefits, using best-in-class scientific models, via a coupled physics-engineering-economic spatial modelling framework. Recognising uncertainty in the economic interpretation of power outage impacts, we compare four different estimation methods. In the most severe unmitigated scenario, estimated GDP losses reach NZD3.58 billion (0.98 percent of annual GDP). Targeted GIC-informed scenarios still produce material losses, with no mitigation reaching up to NZD1.48 billion (0.41 percent of annual GDP). Mitigation substantially reduces these impacts. Operational strategies, including optimized switching and islanding, achieve benefit-cost ratios as high as 330 to 1, while physical protections such as GIC blocking devices produce returns up to 34.4 to 1. When also acknowledging additional unmodelled impacts, including multi-billion losses in capital equipment and long-term revenue, the economic rationale for pre-emptive mitigation becomes even more pertinent.
arXiv:2607.11672v1 Announce Type: new
Abstract: Industrial design in fields such as vehicle and aerospace engineering often relies on large-scale numerical simulations to evaluate fluid dynamics performance, which can incur substantial computational costs. Deep neural networks have shown promise in improving simulation efficiency, especially graph neural networks (GNNs), which demonstrate great potential due to their flexibility with unstructured data. However, GNNs face challenges when dealing with tasks involving complex geometries and large-scale meshes. In this paper, we propose the Multi-scale Feature Enhanced Graph Neural Network (ME-GNN) to tackle these challenges. ME-GNN employs a graph neural network with a two-step message-passing mechanism to capture detailed local features effectively. Additionally, it integrates an Attention U-Net with uniform grid discretization, enabling the extraction of both fine and coarse features. The model also utilizes K-hop sampling to construct subgraphs, facilitating efficient training on large datasets while preserving detailed local features. We evaluated ME-GNN on three benchmark datasets and achieved state-of-the-art results: a relative L2 error of 0.0196 for the velocity field and 0.0556 for the surface pressure on ShapeNet-Car, a normalized mean squared error of 0.0033 for the flow field on AirfRANS, and a relative L2 error of 0.1416 for the surface pressure on DrivAerNet.
arXiv:2607.09724v1 Announce Type: new
Abstract: It has been recently argued that in semi-classical gravity, a minimal 2-sphere is not a horizon but a tiny throat of a wormhole, such as the Damour--Solodukhin wormhole (DSWH), with a free parameter $\lambda \neq 0$ separating it from a Schwarxzschild black hole (BH) ($\lambda =0$). As shown by DS, their horizonless WH can mimic many properties of a black hole (BH). Assuming that observing a BH mimicker is equivalent to observing a BH itself, we ask the question as to which identity of the object, a WH or a BH, an observer is likely to observe in a single experiment. To answer this, we introduce Tangherlini's new concept of indeterminacy in the gravitational field by portraying the field as a refractive medium. We then postulate that \textit{the identity of the observed object will depend on the probabilistic outcome of photon motion probing the object}. The probabilities will be described by Fresnel reflection ($R$) and transmission ($T$) coefficients derived by Tangherlini on the basis of a non-quantum statistical indeterminacy of photon motion in ordinary optical media. By adapting this approach to a gravitational "effective optical medium," we obtain two intriguing results: (i) The Fresnel coefficients at the DSWH throat are independent of mass $M$ but dependent solely on the parameter $\lambda \neq 0$. (ii) Depending on the location of the observer, what is a DSWH to one observer may appear as a BH to another observer for the same value of $\lambda \neq 0$.
arXiv:2607.11877v1 Announce Type: cross
Abstract: For a reversible system relaxing to equilibrium, the obvious fastest strategy is to lower all kinetic barriers (open all gates). We find that such intuition holds at three levels: the all-open-gate strategy achieves the highest local conductance, it maximizes the instantaneous speed of approach in every $f$-divergence, and it simultaneously maximizes all relaxation eigenvalues. Nevertheless, we show that a counter-intuitive finite-time optimum lies beyond this intuition and operates at a fourth level, invisible to all three: eigenvector rotation. Noncommutativity enables timed schedules to reproject residual amplitudes across relaxation modes, thereby achieving faster relaxation. Optimal schedules are bang--bang. In our illustrative example, the best-found schedule also employs counter-gating, transiently raising selected barriers, and reduces the terminal residual by a factor of $130$ relative to all-open, and by $7$ relative to the best static landscape. A no-go theorem shows that noncommutativity is necessary: commuting generators collapse every schedule to a static time-averaged landscape, worse than the intuitive static control. In the reverse problem, the dual schedule preserves nonequilibrium free energy far more effectively than intuitively keeping all barriers at maximum heights. Whether accelerating or delaying relaxation, barrier control performs no work on the reduced Markov system; it only re-times a fixed total dissipation budget.
arXiv:2607.09719v1 Announce Type: new
Abstract: We investigate a phenomenological extension of the photon sector motivated by an early-time interaction between a scalar field component and radiation. The model is described by a constant parameter $\epsilon$ which measures the departure of the photon energy density and CMB temperature-redshift relation from their standard adiabatic evolution. The standard photon sector is recovered when $\epsilon=0$. We implement the modified photon scaling in CLASS and verify that the numerical background evolution agrees with the analytic constant-$\epsilon$ prediction. We then study the diagnostic response of the recombination history, visibility function and CMB temperature spectrum. These diagnostics show that small values of $\epsilon$ can shift the recombination history and modify the acoustic peak structure of the CMB temperature anisotropy spectrum. These CMB outputs are used only as consistency and response diagnostics not as full CMB likelihood constraints. As a preliminary statistical application, we combine the modified CLASS implementation with MontePython and constrain the model using Pantheon+SH0ES supernova data together with BAO distance measurements. The late-time analysis gives $\epsilon=0.0230\pm0.0065$ and improves the best-fit likelihood relative to the fixed $\epsilon=0$ baseline with $\Delta\chi^2_{\rm eff}=-10.518$ and $\Delta{\rm AIC}=-8.518$. These results indicate that the constant-$\epsilon$ extension is favoured by this preliminary late-time data combination according to the AIC criterion.
The Individual-Targeting Assumption: A Systematic Review of Proactive Robots in Human Group Settings
arXiv:2607.09734v1 Announce Type: new
Abstract: Proactive robots are increasingly deployed in public environments where people are encountered not as isolated individuals but as members of cohesive social groups. Yet whether the prevailing design paradigm in proactive human-robot interaction (HRI) accounts for the relational structure that defines a group as a social unit remains largely unexamined. Through a systematic review of 63 proactive HRI studies in group settings from 2000 to 2025, we identify a recurring tendency, the Individual-Targeting Assumption (ITA), in which robots treat co-present people as independent engagement targets. We find that ITA is present in 60.3% of the corpus, with group-aware approaches emerging almost entirely after the robot is already embedded in an ongoing interaction. Critically, how a robot should detect and negotiate entry into a pre-formed group before initiating contact remains unaddressed across the corpus. Three failure modes, engagement misdetection, social ratification blindness, and bystander neglect, emerge as recurring patterns when proactive robots interact with human groups. These findings reframe proactive HRI in group settings not as an extension of dyadic interaction but as a qualitatively distinct design problem, and they identify the robot's approach to the group during the entry phase as a critical and understudied open challenge.
arXiv:2607.11838v1 Announce Type: new
Abstract: When a large disaster strikes, responders need a map of which buildings are damaged within hours. The models that do well on public benchmarks assume matched before-and-after imagery and a training set drawn from similar past events, and neither is usually available for a new disaster in its first day. We present HASTE (High-speed Assessment and Satellite Tracking for Emergencies), a no-code web platform that lets analysts who are not machine learning engineers produce per-building damage maps from post-disaster satellite imagery. HASTE implements two methods that share one interface. The first requires the user to label polygons over the post-disaster scene, trains a small semantic segmentation model on that single scene, runs it over the whole image, and joins the per-pixel output to existing building footprints. The second embeds every footprint with a pretrained vision model, requires the user to label a handful of buildings, and fits a logistic regression in the browser that scores the rest of the scene in seconds. We describe the platform, both methods, and the engineering that supports them. We also report preliminary experiments on xBD showing that foundation-model embeddings pooled over footprints separate damaged from intact buildings using post-disaster imagery alone, matching a fully supervised ResNet-50 baseline with a twentieth of its labels. HASTE and its predecessors have supported more than thirty real-world disaster responses since 2023, spanning earthquakes, hurricanes, cyclones, floods, wildfires, and tornadoes, delivering results to humanitarian partners within hours to days of imagery becoming available. We close with the directions we think are most promising, including vision-language assessment, active learning, and damage models for roads and other infrastructure. HASTE is open source at https://github.com/microsoft/haste.
arXiv:2607.09736v1 Announce Type: new
Abstract: The high-angle-of-attack flip maneuver of reusable launch vehicles presents significant challenges for robust trajectory optimization due to the combined effects of highly nonlinear dynamics, aerodynamic uncertainties, and actuator saturation. This paper presents a differentiable physics framework for saturation-aware robust trajectory optimization. At its core, a Differentiable Particle Tube Control (DPTC) scheme is developed to optimize uncertainty evolution through an ensemble-based distribution shaping strategy. State uncertainty is represented by a Lagrangian particle ensemble, while hard actuator projection operators are embedded directly into the computational graph, enabling the joint optimization of the nominal feedforward trajectory and a time-varying feedback policy via end-to-end backpropagation. The proposed framework is evaluated against an automatic differentiation-based Successive Convexification (AD-SCvx) baseline combined with a conventional covariance steering feedback strategy. Six-degree-of-freedom Monte Carlo simulations demonstrate that, although the baseline achieves nominal fuel-optimal solutions, its unconstrained feedback formulation becomes susceptible to actuator saturation under aerodynamic disturbances, leading to degraded closed-loop robustness. In contrast, the proposed DPTC framework proactively performs a constraint-aware performance trade-off by relaxing spatial tracking to preserve critical control authority. These results demonstrate that integrating differentiable physics with ensemble-based optimization provides an effective and practical framework for robust guidance in highly constrained aerospace flight systems.
arXiv:2607.11724v1 Announce Type: new
Abstract: A method for the control of quadrotors is presented. It is composed of a high-level reference smoothing step and a low-level reference tracking step. The high-level step leverages the Dubins airplane model for dimensionality reduction and reduced computational complexity, and exploits its structure for decoupling, spatial modeling and the formulation of a small linear program. The low-level step leverages a geometric tracking controller, which is based on the full quadrotor model. The method is designed for the tracking of references subject to lateral constraints along the path. An example is the tracking of references along obstacle contours. It is differentiated between two different setups. Either the high-level planning step is conducted once and offline, or, alternatively, the high-level planning step is conducted recedingly online in closed-loop over a limited spatial prediction horizon.
arXiv:2607.10131v1 Announce Type: new
Abstract: Money laundering threatens financial stability and exposes institutions to penalties, motivating automated detection. Because laundering schemes often emerge through relational patterns, graph neural networks (GNNs) are increasingly used for anti-money laundering (AML). Yet AML GNNs are typically evaluated with aggregate metrics such as overall F1 score, which hide an operational issue: high-activity recipient accounts concentrate many incoming transactions, making suspicious signals harder to isolate and costlier to investigate. We introduce a recipient-degree stratified evaluation that reports standard AML metrics across recipient-context density. Across three datasets (HI-Small, HI-Medium, and AMLSim-32k-5%), it reveals consistent degradation in dense recipient contexts, which we trace to three GNN characteristics: two known limitations that AML amplifies, i.e., (1) multiset non-discriminability and (2) cardinality blindness, and (3) an attention-specific effect: in dense neighborhoods, normalized attention attenuates weak but pattern-relevant multi-hop signals. Guided by this diagnosis, we propose SALT-GNN, a lightweight statistics-aware architecture that fuses degree-aware statistical aggregation with attention at each message-passing layer, so distributional and cardinality information shapes the node states used by subsequent attention steps. Ablations support fusion placement as a key factor in dense-context performance. On HI-Small and HI-Medium, SALT-GNN uses up to 77% fewer parameters than task-specific graph-transformer baselines while improving dense-context F1 score by 3-6 points; on AMLSim-32k-5%, it improves highest-degree F1 score by 16-20 points. The gains hold for both Transformer- and GAT-style attention, indicating that the benefit comes from where statistical and attentional evidence is fused rather than from a specific attention operator.
arXiv:2607.09790v1 Announce Type: new
Abstract: The article investigates the fundamental problem of ensuring the stability of operator control and preserving goal-targeting in hybrid human-machine decision support systems (DSS) of a new generation. Based on a two-month continuous longitudinal experiment on the joint design of a monograph-format textual array, the latent phenomenon of semantic context drift in large language models of deep logical reasoning (Reasoning LLMs) is verified and described. A mathematical model of interaction in the human-machine interface is proposed, and an original metric is introduced - the operator control stability coefficient, which takes into account the non-linear contextual pressure of hidden reasoning chains. Within the paradigm of the cognitome theory, a critical point of control functions inversion is captured. Engineering recommendations are formulated for implementing dynamic relational arbitration loops based on a modified hierarchical similarity model.
arXiv:2607.09801v1 Announce Type: new
Abstract: Governing equations provide compact descriptions of physical systems, yet the variables in which they are simple are often hidden in high-dimensional measurements. This challenge is sharper for forced systems, whose responses depend on both intrinsic dynamics and time-dependent inputs. Here we introduce FLARE, a forced latent autoencoder for response equations that learns compact response coordinates, identifies sparse input-dependent latent dynamics and decodes equation rollouts to full responses. By estimating latent dimension from data and separating state estimation from external forcing, FLARE enables forecasts to be initialized from past responses and driven by prescribed future inputs. Across known dynamical systems, application-scale forced responses and visual observations, FLARE recovers compact forced dynamics and predicts long-horizon high-dimensional responses under inputs not used for training. By turning learned coordinates into a dynamical interface, FLARE extends equation discovery to systems whose effective states are hidden within complex observations, providing a route for interpretable modelling and prediction of high-dimensional responses in forced dynamical systems.
arXiv:2607.11034v1 Announce Type: new
Abstract: There's been a surge in adoption of video conferencing applications for both personal and business use cases. However, the bandwidth limitations faced by many users worldwide may restrict the optimal use of such applications. Although deep learning offers a solution for enhancing low bit rate videos, most models today are either hard to incorporate with modern compression standards or require specialized hardware to run such as significant GPUs making these models impractical. To address these issues, we introduce the Realtime Face Video Enhancement (RTFVE) model which can be easily incorporated with any video decoder and can run in realtime on ordinary CPUs. Experiments show that our model improves perceptual quality over the compressed video baseline at multiple low bitrate settings. The source code will be made available at https://github.com/varun-jois/RTFVE.
arXiv:2607.09795v1 Announce Type: new
Abstract: Recently, large language models (LLMs) have been successfully adopted in various fields, including wireless communications, robotics, and autonomous vehicles, owing to their outstanding adaptability and reasoning abilities. Despite their huge potential, the application of LLMs for mobility management is relatively scarce since it requires not only analyzing wireless measurements but also predicting dynamic user trajectories and making real-time handover decisions across densely deployed small base stations (SBSs). In this paper, we propose an environment-aware mobility management scheme based on large multimodal models (LMMs), which extend capabilities of LLMs to process multimodal sensing data. By leveraging LMMs, the proposed scheme extracts contextual information on the surrounding environments from RGB-D images to capture user equipment (UE) mobility patterns and identify signal reflections and blockages caused by static reflectors and dynamic obstacles. Using the extracted environmental information, the proposed scheme learns the intrinsic mapping from UE and SBS positions to channel capacity, referred to as channel capacity map (CCM), from which future channel capacities along UE trajectories are predicted. Based on the predicted channel capacities, we determine proactive handover decisions maximizing the cumulative channel capacities. Simulation results demonstrate that the proposed scheme achieves substantial channel capacity improvements over conventional deep learning (DL)-based approaches.
arXiv:2607.09806v1 Announce Type: new
Abstract: Artificial intelligence (AI) is transforming scientific discovery, but its effectiveness is fundamentally limited by the availability of structured scientific knowledge. Although existing databases have accelerated data-driven materials research, much of the knowledge needed for predictive modeling and inverse design remains embedded in unstructured scientific literature. We present an Autonomous Scientific Knowledge Generation Framework that transforms scientific publications into a Unified AI-Ready Scientific Knowledge Base. The framework integrates ontology-guided literature acquisition, hybrid scientific knowledge extraction, semantic harmonization, knowledge fusion, and validation within a unified workflow. Rather than treating literature retrieval, information extraction, and database construction as separate tasks, the framework progressively converts scientific publications into structured, semantically consistent, and provenance-preserving knowledge suitable for AI-driven reasoning. As a proof of concept, the framework was applied to electro-optic materials. Autonomous literature acquisition retrieved and validated about 1,000 publications from multiple scholarly repositories. A representative subset of eight publications was processed through the complete workflow, generating 29 structured scientific records that were harmonized into 7 canonical scientific records. The results demonstrate the complete transformation from scientific literature to an AI-ready scientific knowledge base while preserving quantitative measurements, operating conditions, provenance, and scientific context. The proposed framework provides a scalable, domain-independent foundation for predictive AI, generative AI, and closed-loop AI-driven scientific discovery.
arXiv:2607.09825v1 Announce Type: new
Abstract: Robotic manipulation policies rely on pre-trained vision models that give either a global scene embedding or a dense patch grid. Both mix task-relevant and task-irrelevant features. Object-centric slot representations are a structured alternative: they group features into a few per-object slots. We test what this structure buys on ManiSkill3 PickCube-v1, with a frozen encoder and a held-out-seed evaluation. Holding the policy, goal token, rendering, and calibration fixed and changing only the encoder, a frozen object-centric SPOT representation (DINO ViT-B/16 + Slot Attention) reaches 55.0$\pm$2.9% success, 22.4% above a dense DINO global-feature baseline (32.6 $\pm$ 1.5%), with the same trainable policy and no encoder fine-tuning. More tokens alone do not help: a dense patch grid with 16x the tokens performs no better than the global feature. Adding an explicit 2D spatial goal and native-resolution rendering raises the full system to 68.7$\pm$4.2%, just below a privileged 3D-oracle upper bound (71.7$\pm$4.1%). An automated kinematic failure taxonomy then separates spatial-precision (Near-Miss) failures from object-tracking (No-Grasp) failures: spatial grounding reduces Near-Miss while leaving No- Grasp unchanged. The same taxonomy transfers to the harder StackCube-v1 and points to occlusion as the main bottleneck.
arXiv:2607.09839v1 Announce Type: new
Abstract: Mathematical diagrams play a crucial role in K 12 education, both as problem components and as scaffolding for student comprehension. However, current AI tools, including Large Language Models (LLMs), struggle to reliably generate accurate and pedagogically sound visual diagrams, even when provided with detailed descriptions. A significant gap therefore remains in the reliable generation of diagrams for middle school mathematics. To address this, we introduce an agentic workflow that enables LLM agents to evaluate the quality of generated visuals and use this feedback to iteratively improve their outputs. This self improvement loop aims to enhance the accuracy and educational appropriateness of AI generated diagrams. Our research investigates two questions. First, can LLMs accurately generate quality assurance questions for a visual aid given specific criteria for visual quality? Second, given valid quality assurance questions, can Vision Language Models effectively evaluate generated K 12 visual aids and use the resulting feedback to improve them iteratively? We conduct an exploratory evaluation of our agentic workflow and identify key areas for improvement, including stronger spatial reasoning and more comprehensive coverage of diagram features in the generated quality assurance questions. Our results provide preliminary evidence that this approach can improve the reliability and educational value of AI generated mathematical diagrams.