arXiv:2607.05518v1 Announce Type: new Abstract: AI agents issue tool calls on the basis of text they cannot verify, so any party who controls part of the context can forge the appearance of authority. I evaluate 15 contemporary language models against eight attack scenarios derived from a published corpus of real agent incidents and find that refusal varies from 100% down to 38% across fully evaluated models; the most expensive model refused only half of the attacks despite a twentyfold price spread. I present aiAuthZ, an authorization gateway that moves the safety decision off the agent's host. Before a tool call executes, the gateway verifies caller identity with a per-message HMAC-SHA256 signature bound to a single-use nonce and a timestamp window, and it evaluates a role-based and argument-level policy that the agent can neither read nor modify. Every decision joins a SHA-256 hash-chained audit log, and each accepted message yields an HMAC-authenticated QR receipt that achieves 94% mean verification across eight transmission channels, with zero forgeries accepted in 25 wrong-key trials. With the gateway in place, residual attack success falls to 0% for all 15 models at no more than 0.03 ms of added decision latency. On the AgentDojo banking suite, aiAuthZ blocks all seven attacker-directed tool calls the evaluated agents emit, at the cost of one legitimate first-time payment, while a spotlighting baseline allows two injections to succeed. Across nine in-scope case studies from the same incident corpus, aiAuthZ blocks nine of nine, against four of nine for a policy baseline without identity binding. The gateway does not prevent a model from being deceived; it prevents a deceived model from acting beyond the verified user's authority on every call routed through it. The implementation and all experiments are released at https://github.com/Sports-Vision-Inc/aiAuthZ.
Science Journals
arXiv:2607.05522v1 Announce Type: new Abstract: 3D Gaussian splatting (3DGS) is a strong representation for real-time novel-view synthesis, but its standard training pipeline relies on point estimates and hand-tuned heuristics, providing no native uncertainty or principled complexity control. This is most limiting under sparse views or fixed acquisition budgets, where a model must identify weakly supported geometry and select informative views. We introduce a rendering-aware Bayesian 3DGS framework that tracks Gaussian geometry with a Normal-Inverse-Wishart posterior over means and covariances using renderer-derived surrogate summaries. An optional Dirichlet-process extension adds a probabilistic component-usage signal, and the training schedule makes the closed-form versus approximate inference boundary explicit. Re-rendering posterior geometry samples yields native predictive uncertainty for interval calibration and active view selection. In a fixed-budget 16-to-32 active-view task, native NIW acquisition improves PSNR by +0.453 dB and LPIPS by -0.0146 over a scoring-only 3-member standard-ensemble baseline, winning 29/39 scene-seed pairs and 10/13 scene means; it also improves over PPU-style (+0.355 dB) and NIW-proxy (+0.401 dB) acquisition. NIW native intervals reduce 95% coverage error by about 17x relative to a shared proxy (0.046 vs. 0.796) and are about 10x closer to nominal coverage than a 3-member deep ensemble (0.047 vs. 0.454) at roughly one-third the training cost. As a reconstruction compatibility check, paired NIW-vs-standard analysis over 39 scene-seed runs yields +0.030 dB PSNR with 1.6% additional training time. These results position Bayesian 3DGS as a practical probabilistic scene representation for decision-facing tasks such as active view selection.
arXiv:2607.05543v1 Announce Type: new Abstract: Semantic occupancy provides a structured spatial memory for embodied indoor agents by jointly representing occupied regions, observed free space, unknown areas, and object semantics. However, existing indoor occupancy benchmarks and methods mainly focus on single-view prediction or room-level online perception, leaving long-horizon semantic mapping across connected indoor spaces underexplored. We introduce HIOcc, a hierarchical indoor occupancy benchmark that unifies ScanNet, ScanNet++, and Matterport3D under a common sparse semantic occupancy format while preserving their native observation geometries, including perspective RGB-D frames and pano-centric observation groups. HIOcc supports three complementary evaluation regimes: local semantic occupancy prediction, room-level online occupancy mapping, and building-level mapping across connected panoramic environments. We further propose GEM-Occ, a Gaussian Evidence Memory framework for semantic occupancy mapping. Rather than using pointmaps as persistent map states, GEM-Occ treats local visual geometry predictions as transient evidence, converts them into semantic Gaussian occupancy evidence and free-space ray evidence, and fuses them into a persistent hierarchical memory through visibility- and uncertainty-aware causal updates. The memory is organized into local caches, room-level submaps, and a building-level graph, and can be queried at any time through Gaussian-to-occupancy splatting. Experiments on HIOcc show that GEM-Occ improves local occupancy prediction, online map stability, free-space reasoning, revisit consistency, and building-level scalability over prior indoor occupancy and Gaussian-based mapping baselines.
arXiv:2607.05791v1 Announce Type: cross Abstract: Boosting is a fundamental technique for generically improving the accuracy of learning algorithms (Schapire 1989). Existing boosting algorithms construct a strong learner using $O(\log(\frac{1}{\epsilon})/\gamma^2)$ calls to a $\gamma$-advantage weak learner, and this round complexity is known to be optimal for generic boosters that succeed on all concept classes (Freund 1995). We show that this lower bound can be circumvented for concept classes that satisfy a mild closure property. Specifically, we present a new boosting algorithm that, for any class $\mathcal{F}$ closed under $O(\log \frac{1}{\gamma})$-XOR, strong learns $\mathcal{F}$ using $O(\log \frac{1}{\epsilon})$ calls to a $\gamma$-advantage weak learner and a single batch of $\tilde{O}(\log(\frac{1}{\epsilon})/\gamma^2)$ additional samples. Our algorithm arises from a new and simple connection between boosting and list-decodable codes. Viewing the target function as a message, we run the weak learner on its encoding and view the resulting weak hypothesis as a corrupted codeword. Feeding this corrupted codeword to a list decoder, we obtain a small list of candidate hypotheses, at least one of which is a strong hypothesis for the original function. Using additional samples, we identify and output this strong hypothesis.
arXiv:2607.05712v1 Announce Type: new Abstract: Multi-hop question answering and retrieval-augmented reasoning require selecting evidence passages that are jointly useful for answering a query. However, most retrievers still score passages independently or make locally supervised sequential decisions, which can fail when evidence usefulness depends on compatibility among passages. LLM-based set selection can model such interactions, but its computational cost limits practical use. We address this gap by formulating multi-hop retrieval as query-set compatibility scoring and propose a set-level retrieval framework. Our training objective teaches retrievers to rank complete and compatible evidence sets above incomplete, noisy alternatives, making set scoring more robust to variable-length and partially noisy contexts. We instantiate the framework with two complementary set scorers: ParaSet, a lightweight late-interaction scorer that applies self-attention over precomputed bi-encoder embeddings for fast candidate-set exploration, and SetCE, a cross-encoder-based reranker trained with the same set-level objective. Experiments on various multi-hop QA benchmarks show that set-level compatibility learning improves retrieval performance and downstream QA task performance. We further show that the proposed set-level retrievers not only outperform document-level retrievers, but also exhibit complementary retrieval characteristics: combining their outputs yields stronger performance than simply retrieving more passages from a single document-level retriever.
arXiv:2606.28833v3 Announce Type: replace Abstract: Quantum kernel estimation on near-term hardware is shot-budgeted: every entry of the kernel Gram matrix is a Bernoulli expectation that must be sampled with a finite number of circuit executions. Recent work on quantum kernel classification has shown that allocating shots non-uniformly across kernel entries, weighted by their downstream task sensitivity, can reduce the shot budget required to reach a target accuracy. We extend this idea to Gaussian process (GP) regression, a setting whose downstream quantities (full-spectrum posterior variance, log-determinant, marginal likelihood) couple to kernel error more tightly than the sign-only outputs of classification. We derive three closed-form pair-level sensitivities predictive coupling $|\alpha_i\alpha_j|$, leave-one-out residual, and marginal-likelihood gradient and plug them into a Neyman-style minimum-variance allocation rule. To prevent catastrophic over-concentration when the warm-up sensitivity estimate is itself noisy, we add a high uniform coverage floor justified by a Frobenius lower bound on the missing-entry perturbation. On four UCI benchmarks and two synthetic RBF + Bernoulli controlled studies, the resulting allocator delivers $10$--$21\%$ test-RMSE improvement over uniform allocation across the moderate-budget regime. The gain transfers (i) to genuine ZZ and Pauli-Z quantum kernels on quantum-natural data ($-13$--$15\%$ at low budget, $p<0.05$ paired) and (ii) to four downstream tasks (Bayesian quadrature, heteroscedastic regression, hyperparameter learning, multi-output Cokriging). On UCI features embedded into a ZZ kernel the gain disappears, consistent with the exponential-concentration regime where shot allocation has nothing to exploit.
arXiv:2607.06442v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models are typically trained by imitation learning on large-scale robot demonstration datasets, but more data does not necessarily yield better policies due to redundancy, noise, and uneven coverage. Existing data selection methods often assess demonstrations at either the trajectory or state-action level, missing the reusable structures that compose long-horizon behaviors. In this paper, we propose SIEVE, a structure-aware data selection method for VLA imitation learning. SIEVE views demonstrations as compositions of reusable primitives and transition interfaces. It first discovers visuo-motor primitives from segmented trajectories, then allocates selection budgets to composition patterns by maximizing reuse-aware structural exposure under diminishing returns. Finally, it selects medoid trajectories within each composition-pattern bucket to retain central, stable, and imitation-friendly demonstrations. Experiments across multiple datasets, benchmarks, and VLA models show that SIEVE consistently outperforms competitive data selection baselines. Notably, SIEVE can surpass full-data training while using only 50% of demonstrations and 50% of training steps, suggesting that reusable structure, captured through primitives and transitions, is an important signal for efficient VLA imitation learning.
arXiv:2607.05729v1 Announce Type: new Abstract: Power systems consist of dynamically coupled generators, motivating the use of Graph Neural Networks (GNNs) for online transient stability prediction. Traditional GNN frameworks are often constrained by fixed admittance-based topologies that fail to capture state-dependent coupling, or by data-driven methods that neglect directional influences. This paper proposes Causal Dynamic Network Representation (C-DNR), a novel framework that fuses two complementary representations of inter-generator interactions prior to temporal modeling: a dynamic structural graph inferred from measurements and a directional causal graph obtained via nonlinear causal discovery. An end-to-end learned edge-wise fusion mechanism adaptively weights these representations for each generator pair, and the resulting graph is propagated through a Gated Recurrent Unit (GRU) to predict post-fault trajectories. Evaluated on the IEEE 39-bus system, C-DNR reduces autoregressive prediction error by 73% compared to a dynamic structural baseline. Among the evaluated causal methods, only Peter--Clark Momentary Conditional Independence (PCMCI) achieves consistent improvements, owing to its ability to isolate directional dependencies from misleading oscillatory correlations. The learned fusion weights further provide interpretable diagnostics aligned with the electrical topology, offering transparent, pairwise insight into the prediction process.
arXiv:2607.05733v1 Announce Type: new Abstract: Generating temporally continuous and socially coherent human motion from text remains a fundamental challenge, particularly in realistic streams where people act alone, enter interactions, and later disengage. Most existing methods generate fixed-length motion clips under static agent configurations, which makes them brittle to solo-social transitions and unsuitable for incremental generation over long horizons. We propose ARMS, an Anchor-Relational Motion Streaming framework that unifies solo motion and human-human interaction within a single causal generative process. ARMS introduces a dynamics-asymmetric representation that decouples per-person temporal evolution from inter-person alignment via a partner-referenced relative-translation term, enabling seamless switching of social coupling without sacrificing long-horizon stability or spatial consistency between agents. On top of a causal latent space, a causal relational diffusion model progressively refines motion segment by segment using only past context, capturing both intra-person temporal dependencies and inter-person relations. Mode-aware relational gating activates or masks cross-agent connections, allowing the same model to support both solo and interaction generation. Experiments show that ARMS improves transition smoothness and social coherence compared to interaction-centric baselines, while also achieving competitive results on human-human interaction benchmarks.
arXiv:2607.05736v1 Announce Type: new Abstract: Molecular property prediction often relies on isolated data modalities, where continuous 3D graph neural networks (GNNs) struggle to efficiently capture long-range topological dependencies and exact macroscopic heuristics. In this work, we introduce a parameter-efficient Tri-Branch Modular Fusion Neural Network that synthesizes three orthogonal modalities: 3D spatial geometry (SchNet), discrete topological grammar (SMILES via ChemBERTa), and explicit macroscopic physicochemical descriptors (Deep & Cross Network). By bypassing standard scalar readouts and employing a shared late-fusion architecture, the framework establishes a mathematically rigorous multimodal latent space that effectively resolves the arithmetic and oversmoothing limitations of local message passing. We evaluate the proposed architecture on the QM9 benchmark, targeting the extensive thermodynamic property of atomization energy at 0 K ($U_0^{\mathrm{atom}}$). Through systematic combinatorial ablation and latent bottleneck optimization ($d_e=64$), the tri-modal framework achieves a validation Mean Absolute Error (MAE) of 0.0207 eV. Operating with fewer than one million parameters, this architecture decisively surpasses the sub-chemical accuracy threshold and yields a substantial 20.6% error reduction over a strictly controlled geometric baseline. Ultimately, our findings demonstrate that integrating orthogonal macroscopic and topological data streams provides a synergistic, $\mathcal{O}(1)$ physical shortcut. This multimodal alignment offers a highly efficient alternative to brute-force parameter scaling, establishing a robust surrogate model for high-throughput virtual screening (HTVS) pipelines.
arXiv:2607.05800v1 Announce Type: new Abstract: Let $p$ be a prime and $R=\mathbb{Z}/p^2\mathbb{Z}$ the ring of integers modulo $p^2$. Any $A\in R^{n\times n}$ is unimodularly equivalent to its Smith form \[ S=diag\bigl(\underbrace{1,\ldots,1}_{r_0}, \underbrace{p,\ldots,p}_{r_1}, \underbrace{0,\ldots,0}_{r_2}\bigr) \in R^{n\times n}, \] i.e., there exist $U,V\in R^{n\times n}$ such that $UAV=S$, with $\det U,\det V\in R^*$ (where $R^*$ is the set of units in $R$, elements not equivalent to $0\bmod p$). Our goal in this paper is to determine $r_0,r_1,r_2$ quickly when $A$ is sparse or structured. By ``sparse'' we mean $A$ is given by a black box such that for any $v\in R^{n\times 1}$ we can compute $v\mapsto Av$ with $\tilde{O}(n)$ operations in $R$, which captures having few nonzero elements or a multiplicative structure (e.g., Hankel or Toeplitz matrices). We present a randomized algorithm which requires an expected number of \[ \tilde{O}\left(n^{3-1/(\omega-1)}\right) \] operations in $R$ to compute the Smith form, where $\omega$ is the exponent of dense matrix multiplication. Using standard cubic matrix multiplication ($\omega=3$) our algorithm thus requires $\tilde{O}(n^{2.5})$ operations in $R$, while using the current asymptotically fastest matrix multiplication, with $\omega<2.371339$, our algorithm requires $\tilde{O}(n^{2.270786})$ operations in $R$. Our algorithm is probabilistic of the Monte Carlo type, meaning it fails on any invocation with controllably small probability. We employ iterative block-Wiedemann-style matrix techniques and structured preconditioners. To our knowledge, this is the first algorithm to compute the modular Smith Normal Form modulo $p^2$ requiring fewer than $\tilde{O}(n^\omega)$ operations in $R$, i.e., faster than any dense algorithm.
arXiv:2603.11006v2 Announce Type: replace Abstract: In this paper, we present a laboratory study focused on the impact of post-quantum cryptography (PQC) algorithms on multiple layers of stateful HTTP over TLS transactions: the TCP handshake, the intermediate TCP-TLS layer, the TLS handshake, the intermediate TLS layer, and the HTTP application layer. To this end, we propose a laboratory architecture that emulates a real-world setup in which a load test of up to 100 transactions per second is sent to a load balancer, which in turn forwards them to a backend server that returns the responses. Each set of tests is executed using the TLS 1.3 key exchange groups as follows: traditional (or non-PQC), hybrid PQC and pure PQC. Each set of tests also varied the backend response size. Across more than thirty experiments, we performed data reduction and statistical analysis for each layer, to determine the specific impact of each algorithm (PQC and traditional) at every stage of the HTTP-over-TLS transaction.
arXiv:2607.06528v1 Announce Type: new Abstract: Citation-based systems usually treat each citation as an equal signal of scholarly influence, although citations can express very different relationships: direct method use, result comparison, broad background, or weak ceremonial acknowledgement. This distinction is crucial for citation-cartel analysis because dense internal citation alone is not suspicious; legitimate research communities are also densely connected. We present a trust-aware pipeline that combines citation graph structure with semantic citation intent to rank suspicious paper-level communities for audit. On a DBLP-derived graph with 500,000 papers and 4.87M citation edges, we use an LLM teacher to label 205,897 citation pairs, train a SciBERT student, and scale citation-intent typing to 2.04M unique graph edges. We then compute a Composite Cartel Index (CCI) that integrates internal density, citation inflation, reciprocity, semantic superficiality, degree assortativity, and trust-weighted PageRank shift. The highest-ranked community contains 1,079 papers and 8,603 internal citations, with 254.3x more internal citations than expected and 64.2% of them superficial. Comparisons against density-only, inflation-only, semantic-only, and random baselines show that CCI cannot be reduced to a single heuristic. Edge excision validation further shows that CCI-selected communities behave differently from matched random removals. The result is a reproducible, curator-facing ranking framework for prioritising communities that warrant closer inspection.
arXiv:2607.06529v1 Announce Type: new Abstract: Fine-scale socioeconomic information is often unavailable across rapidly ur-banizing regions of the developing world, like India, limiting the ability to delineate intra-urban variations in affluence and deprivation. This study pro-poses a scalable, grid-based urban delineation framework using building morphology derived from open-source satellite imagery. Urban areas across 59 Indian cities and towns are partitioned into high-resolution spatial grids and characterized using interpretable morphological indicators, which are combined into a transparent, rule-based scoring framework to delineate areas with contrasting levels of urban affluence. The resulting classifications are validated through ground-level Google Street View observations, revealing a sharp contrast between the grid classes which are consistent with the ex-pected effects of the lifestyle affluence indicators. We further investigate density-based clustering of building footprints in Mumbai to identify dense urban settlements, demonstrating that the resulting clusters exhibit substan-tial spatial overlap with known informal settlements across the city. Finally, we conduct an exploratory analysis mapping consumer loan delinquency across the derived affluence classes. By relying entirely on publicly available geospatial data, the proposed framework provides a scalable, interpretable, and cost-effective approach for granular urban affluence mapping across In-dian cities.
arXiv:2607.05851v1 Announce Type: new Abstract: To address the need for time-frequency analysis (TFA) of broadband microwave signals and to overcome the reliance of existing schemes on large-bandwidth swept microwave sources, we propose a broadband microwave signal TFA approach based on stabilized period-one (P1) oscillation and recirculating frequency shifting (RFS). By employing a feedback loop, a stable swept optical signal is generated from the stabilized P1 oscillation of a semiconductor laser, and its sweep bandwidth is further extended by an RFS loop to achieve multi-fold bandwidth expansion. For system compactness, the feedback loop and RFS loop share a common long fiber. The combined operation produces a broadband swept optical signal, which, through stimulated Brillouin scattering-based frequency-to-time mapping, enables TFA and frequency measurement of broadband microwave signals. Experimental results demonstrate an instantaneous analysis bandwidth of up to 57 GHz, a frequency resolution of 60 MHz, and a maximum mean absolute frequency measurement error of 38.16 MHz.
arXiv:2607.06549v1 Announce Type: new Abstract: Deep learning-based computer-aided diagnosis (CAD) systems have shown strong performance in breast cancer diagnosis, particularly for classification tasks in mammography. However, domain shifts across multi-site datasets remain a challenge, especially when models are applied to unseen domains. In this work, we proposed a calcification classification framework to improve malignant versus benign breast disease classification across multi-site mammography datasets. The framework consisted of two components: (1) an unsupervised domain adaptation module based on style transfer models (AdaIN and CycleGAN) to generate vendor-specific and technique-specific training samples without additional annotations, and (2) a supervised classification module using Swin Transformer V2 as the backbone. We evaluated the proposed method on three datasets: cross-validation on OPTIMAM (National Health Service, United Kingdom; n=2994), followed by external validation on EMBED (Emory University; n=125), and Duke Calcification Dataset v1 (n=788). These datasets cover multiple vendors and include both full-field digital mammography and synthetic 2D images derived from digital breast tomosynthesis. The proposed framework improved cross-site performance for both EMBED (AUC 0.68 to 0.72) and the Duke Calcification Dataset (AUC 0.68 to 0.73). These findings indicate that domain adaptation can reduce domain shifts and improve the generalization for calcification classification across multi-site datasets.
arXiv:2607.06552v1 Announce Type: new Abstract: Infrared remote-sensing imagery captures intensity structure, object-background contrast, and illumination-invariant cues often invisible in RGB imagery. Yet, most remote-sensing vision-language resources and models focus on visible-band semantics, leaving infrared vision-language understanding underexplored. We introduce MonoIR-RS, a large-scale infrared remote-sensing vision-language dataset and benchmark that couples IR-aware data construction with CLIP-style contrastive adaptation and VLM instruction tuning. Built from the same source pool and split as FusionRS, MonoIR-RS retains the infrared image as the model-facing modality, yielding 600,000 synthesized infrared images and 59,032 retained IR-aware caption records. The model experiments use this retained language-supervision subset, whose captions rewrite supervision around grayscale structure and infrared-style contrast instead of RGB appearance. We show that the synthesized infrared imagery is markedly closer to real thermal imagery than a grayscale conversion on the AVIID benchmark. We fine-tune five CLIP backbones and six VLM backbones, and calibrate them against zero-shot behavior: IR-aware adaptation lifts CLIP mean recall by up to 12.8 points and drives VLM captioning IR-cue coverage to 100% while reducing residual RGB-color leakage to near zero. By isolating the infrared modality from RGB-IR dual-modal learning, MonoIR-RS offers a controlled, reproducible testbed for aligning infrared remote-sensing evidence with language.
arXiv:2607.06560v1 Announce Type: new Abstract: We formulate computer vision as unified multimodal generation, where heterogeneous visual tasks are expressed in the native text and image generation spaces of a unified multimodal model, without task-specific architectures. Under this formulation, SenseNova-Vision uses natural-language instructions and optional visual prompts to specify tasks, target regions or views, and decoding conventions, and generates responses as text for symbolic outputs, images for dense spatial predictions, or mixed text-and-image outputs for compositional tasks. To support large-scale training, we convert diverse computer vision annotations into instruction-response examples compatible with these generation spaces, resulting in the SenseNova-Vision Corpus, a computer-vision instruction-response corpus spanning text, image, and mixed targets. Starting from an off-the-shelf pretrained unified multimodal model, SenseNova-Vision is trained primarily on this corpus, with auxiliary multimodal data used as a capability-preserving mixture, and requires no task-specific prediction heads or architectural modifications. The resulting model covers a broad range of vision tasks, including detection, OCR, keypoint estimation, segmentation, depth estimation, surface normal prediction, point maps, and camera pose estimation, while supporting language-defined variants that combine category, color, region, and other visual cues. Experiments show that a single unified model can match leading task-specialized systems across structured visual understanding, dense geometric prediction, segmentation, and multi-view visual geometry. These results suggest unified multimodal generation as a scalable route for integrating computer vision capabilities into general-purpose foundation models. The model and corpus are publicly available.
arXiv:2607.05968v1 Announce Type: new Abstract: Matching influencers (KOLs) to free-form, multi-part Thai marketing criteria is today served either by keyword search over structured profiles, which misses semantic fit, or by prompting frontier LLMs over every candidate, which is accurate but slow and expensive. We present InfluMatch, a low-cost three-stage cascade -- retrieval $\rightarrow$ rerank $\rightarrow$ reason -- built entirely from small open-weight models: dense retrieval returns 50 candidates, a 4B pointwise reranker scores each by the log-probability of a single Yes token and keeps 10, and a 4B reasoner grades the shortlist per criterion on a rubric with a Thai rationale. The cascade is designed for cost: reasoning over a filtered top-10 halves token spend versus reasoning over all 50 while scoring 14 points higher. End-to-end against human relevance labels on an 11-query set with all 50 candidates labeled, the full cascade reaches 94.1% P@5, versus a retrieval-only baseline near random; it matches the frontier model Kimi-K2.6 (91.8%) while emitting ${\sim}35\times$ fewer output tokens and serving a 50-KOL query in ${\sim}20$ s on one A100. Notably, the only fine-tuning that pays off is pairwise: a SimPO-tuned reranker matches the frontier baseline's best-pick accuracy (78.0 EM), whereas fine-tuning the reasoner on pointwise per-criterion labels improves offline scores yet degrades end-to-end ranking -- an inversion we trace to the design of the absolute labeling task -- leaving the untuned base model as the strongest deployed reasoner. The result is a deployable, explainable KOL search system at a small fraction of frontier serving cost.
arXiv:2509.23876v3 Announce Type: replace Abstract: Autoregressive (AR) models based on next-scale prediction have emerged as a powerful tool for image generation, but they face a critical weakness: information inconsistencies between patches across timesteps introduced by progressive resolution scaling. These inconsistencies scatter guidance signals, causing them to drift away from salient regions within the image and leaving behind ambiguous, unfaithful features during sampling. We tackle this challenge with Information-Grounding Guidance (IGG), a novel framework that anchors guidance to semantically important tokens via an attention-based dynamic weighting formulation, consequently ensuring that guidance and semantic contents remain tightly aligned. Across both class-conditioned and text-to-image generation tasks, IGG delivers sharper, more coherent, and semantically grounded images, demonstrating its efficacy for correcting AR-based methods. Our code is available at https://github.com/dnngky/infoground-guidance.
arXiv:2607.05880v1 Announce Type: new Abstract: Imaging demand is growing faster than the radiology workforce can expand, and reporting backlogs cannot be resolved through training and recruitment alone. The most direct opportunity is reducing the time and effort radiologists spend producing reports, a task that requires interpreting images, integrating clinical history and prior studies, and drafting structured findings. We present Harrison.Rad 1.5 (HR1.5), a radiology-specific multimodal large language model that accepts interleaved text and visual inputs and generates structured and unstructured text across plain-film radiology, spanning computed radiography, chest, musculoskeletal, abdominal, spine, and pelvic x-rays, and mammography. HR1.5 is trained through a three-stage pipeline: domain adaptation of a base language model on radiology reports, contrastive vision-encoder training with curriculum-based hard negatives on ~6 million image-report instances, and visual-question-answering fine-tuning on multi-turn conversations. We evaluate it with a Findings-Diagnosis scoring framework that extends RadGraph-XL entity extraction with ontology-based synonym matching and polarity-contradiction detection, benchmarked on RadBench, a simulated FRCR 2B Short Case examination scored against Angoff-method thresholds, ReXGradient, and internal multi-modality datasets. HR1.5 is the only system evaluated to meet the simulated FRCR passing standard and achieves the highest accuracy on closed-format clinical questions, across anatomical regions, on internal multi-body-part and mammography reporting, and on the primary clinically-aligned score for public chest reporting. We further examine explainability and model behaviour, including question-sensitive Grad-CAM heatmaps, attention analysis, and confidence estimation, to support responsible future evaluation toward clinical use, and a framework for clinically grounded assessment of report quality.
arXiv:2607.05975v1 Announce Type: new Abstract: This demo presents an MCP-enabled agentic AI architecture for autonomous control of vendor-agnostic IPoDWDM networks. We demonstrate live end-to-end lifecycle multi-layer automation and closed-loop control using GNPy and telemetry, validated on a real testbed.
arXiv:2510.16165v2 Announce Type: replace Abstract: A key question in benchmarking generative crystal reconstruction models is how the amount and type of crystallographic information provided to a generative model affects its ability to reconstruct atomic structures. Yet such comparisons often overlook the fact that models receive unequal information about the target during reconstruction, thereby confounding architectural conclusions. We present AtomBench, an extensible, model-agnostic framework for comparing generative models on a well-defined crystal reconstruction task (rather than \textit{de novo} generation), which we here apply to conventional superconductors. We train and evaluate four models, AtomGPT, CDVAE, FlowMM, and MatterGen, on the JARVIS Supercon-3D and Alexandria DS-A/B datasets, grouping them by the information each accesses at inference. Reconstruction fidelity is measured by the Kullback-Leibler divergence (KLD) and mean absolute error (MAE) of lattice parameters and the root-mean-squared displacement (RMSD) of atomic coordinates. We further introduce the continuous corrected RMSD (ccRMSD), a continuous measure of local geometric fidelity defined for every structure in the test set. MatterGen achieves the best atomic-coordinate reconstruction, followed by AtomGPT, while CDVAE reconstructs lattices most accurately, and FlowMM is the least accurate but fastest overall. We find that conditioning on critical temperature T$_c$ does not consistently improve fidelity. We also release AtomBench as an open-source Python package that reproduces all reported reconstruction metrics, figures, and tables from one or more benchmark files and supports direct submission to the JARVIS-Leaderboard. Any inverse model emitting crystal reconstructions can be benchmarked with \texttt{atombench}, and we encourage community use. https://github.com/atomgptlab/atombench
arXiv:2607.05925v1 Announce Type: new Abstract: The refractive index (RI) is an intrinsic, label-free marker of a living cell's dry mass and subcellular morphology, and hence of its physiological state. Its three-dimensional (3D) reconstruction has become a powerful way to study cells and tissues in their native state, spanning cell growth, drug response and disease diagnosis. Yet this capability rests on a fundamental constraint: the RI can be recovered only from light transmitted through the specimen, which demands optical access to both sides. The cells that matter most -- those within thick tissues, intact organs and living animals -- are therefore out of reach. A tissue, however, can illuminate its own cells from behind: light backscattered by intrinsic tissue structures beneath a cell carries the same transmission information a microscope would collect from the far side. Here we develop a divide-and-conquer inverse-scattering framework that recovers this transmission from the backscattering and reconstructs a cell's 3D RI. We demonstrate label-free, quantitative imaging of cells within an engineered tissue, and a living mouse through its intact skull, where we further quantify the dry mass of individual osteocytes in vivo. By removing the need for two-sided access, this reflection-only approach extends RI tomography into living tissue, enabling non-destructive, longitudinal imaging of cells in their native environment.
arXiv:2607.05930v1 Announce Type: new Abstract: We present a multiconfigurational binary-encounter (MC-BE) framework for direct analytical evaluation of electron-impact electronic-excitation cross sections for dipole-allowed transitions from ab initio excited-state data. The method combines the threshold-modified Mott-Massey (TMMM) approximation with binary-encounter (BE/BE$f$) scaling. The effective binding energy in the BE/BE$f$ prefactor is obtained from amplitude-weighted occupied-orbital contributions computed by linear-response time-dependent density functional theory (LR-TDDFT), without system-specific fitting parameters. For benzene, MC-BE/TMMM cross sections for the dominant $1{}^{1}\!E_{\mathrm{1u}}$ ($\pi\!\to\!\pi^{\ast}$) band agree well with experiment at incident energies $T=10$-$20$ eV and improve on the Schwinger multichannel/truncated configuration-interaction singles results of Falkowski et al. [J. Chem. Phys. 159, 194301 (2023)] for this band and energy range. For naphthalene, the calculated total excitation cross section reproduces the onset and principal maximum of the gas-phase apparent fluorescence cross section, used as an emission-based proxy under dipole-dominated conditions, without empirical energy shifts or intensity scaling. Analytic peak-position and peak-height expressions, parameterized by $r=\langle B\rangle/\Delta E$, show that typical valence excitations peak at incident energies $T\simeq 1.5$-$1.6\Delta E$ with substantial BE attenuation, providing a diagnostic for relating measured cross-section profiles to excitation energies. Although demonstrated with LR-TDDFT, the framework is transferable to other excited-state theories that provide compatible amplitudes and well-defined orbital energies. These results support MC-BE/TMMM as a practical, inexpensive route for modeling electron-impact excitation of polyatomic molecules with finite oscillator strength.