Evolving data streams induce joint nonstationarity in continual semantic segmentation, where semantic classes, input distributions, and supervision availability change simultaneously over time. This setting reflects practical structured prediction systems, yet remains largely unexplored in prior continual learning work, which typically studies these factors in isolation. We formalize continual segmentation under coupled class, domain, and label shifts and investigate learning in heterogeneous dense prediction environments with limited annotations and abundant unlabeled data. To address instability and overfitting arising from few-shot supervision under distribution drift, we introduce gradient-adaptive stabilization, a parameter-wise regularization mechanism implemented via gradient-scaled stochastic perturbations that promotes a principled stability-plasticity tradeoff. We further leverage unlabeled data through semi-supervised learning and introduce prototype anchored supervision that validates pseudo-labels via joint confidence and prototype consistency. Together, these mechanisms enable learning under joint nonstationarity in continual segmentation. Extensive empirical evaluation across class-incremental, domain-incremental, and few-shot regimes demonstrates consistent improvements over prior methods in heterogeneous structured prediction settings. Our results expose fundamental failure modes of existing continual segmentation approaches and provide insight into learning robust dense predictors in dynamically evolving environments.

Biomedical named entity recognition (NER) and entity linking (EL) strongly depend on annotated corpora, but the utility of these resources for benchmarking is often assumed rather than characterized. We present a corpus-centric framework for diagnosing benchmark-relevant properties directly from corpus annotations, concept links, train-test splits, document metadata, and terminology mappings. The framework organizes standardized statistics into five families: (1) scale, density and label distribution, (2) lexical and conceptual structure, (3) train-test overlap, (4) metadata composition, and (5) terminology coverage where applicable. Applying the framework to nine corpora spanning diseases, chemicals, and cell types, we find that corpus properties can differ substantially, even when they address the same apparent task. We find differences in the evaluation signal they provide, the generalization demands they impose, the degree of train-test reuse they permit, and the regions of biomedical literature and concept space they represent. These differences suggest that commonly reported corpus statistics can be insufficient to characterize what biomedical NER and EL benchmarks evaluate. We argue that corpus-centric diagnostics provide a practical framework for analyzing corpora beyond surface descriptors such as corpus size and entity type, for identifying potential transfer risks, and for interpreting the scope of benchmarking conclusions. We release the framework as open-source code with an interactive dashboard to support reproducing our analyses and characterizing additional corpora.

Accurate classification of breast ultrasound images into benign, malignant, and normal categories is a critical clinical task complicated by speckle noise, acoustic shadowing, and inter-class visual ambiguity. Existing deep learning methods rely on single-stream architectures with generic augmentation that ignores ultrasound acquisition physics, and no prior method dedicates a stream to the lesion boundary features identified as the most diagnostically significant visual cue. We propose HADS-Net, a Hybrid Attention-Augmented Dual-Stream Network exploiting global texture and local boundary cues through two parallel pathways. Stream 1 applies physics-informed augmentation simulating speckle noise, acoustic shadowing, and gain variation before extracting features via pretrained EfficientNet-B3 projected to 512 dimensions. Stream 2 extracts Sobel edge maps processed by a lightweight CNN projected to the same 512-dimensional space. A cross-attention fusion module allows the texture stream to selectively query boundary features, producing a jointly optimised representation classified by an MLP trained with adaptive class-weighted focal loss. Five-fold stratified cross-validation with cosine annealing over 50 epochs is used, with the globally best checkpoint selected by lowest validation loss evaluated on a held-out test set. On the BUSI dataset, HADS-Net achieves 96.58% accuracy, macro ROC-AUC of 0.9978, macro F1 of 0.9654, and per-class F1-scores of 0.970, 0.951, and 0.976 for benign, malignant, and normal. No malignant lesion is misclassified as normal. These results confirm that modality-specific augmentation with cross-modal attention fusion is an effective strategy for ultrasound-based breast cancer diagnosis.

While deep neural networks have achieved remarkable success across a wide range of domains, their underlying mechanisms remain poorly understood, and they are often regarded as black boxes. This gap between empirical performance and theoretical understanding poses a challenge analogous to the pre-axiomatic stage of classical geometry. In this work, we introduce the Pursuit of Subspaces (PoS) hypothesis, an axiomatic framework that formulates neural network behavior through a set of geometric postulates. These axioms, together with their derived consequences, provide a unified perspective on representation, computation, and generalization in both shallow and deep architectures. We show that this framework yields geometric explanations for fundamental questions in deep learning, including representation structure, architectural mechanisms, and generalization behavior, offering a principled step toward a coherent theoretical foundation.

Optimization algorithms are core methods by which machine learning models iteratively minimize loss functions, update parameters, learn from data, and improve performance. Momentum SGD and AdamW represent two important optimization paradigms. AdamW produces stable updates and usually has strong robustness across training scenarios, but its generalization performance is sometimes weaker than that of momentum methods. Momentum SGD can often obtain better generalization after careful tuning, but it is more sensitive to gradient-scale variation and hyperparameter settings. To balance the strengths and weaknesses of the two paradigms, this paper proposes Ada2MS, an optimization algorithm that achieves a smooth transition between AdamW-like behavior and momentum-SGD-like behavior through continuous exponential interpolation between elementwise second-moment estimates and global second-moment estimates. On the visual tasks evaluated in this study, Ada2MS obtains competitive results under a unified optimizer-comparison protocol. The code will be released at https://github.com/mengzhu0308/Ada2MS

In what ways might statistical signals in linguistic input assist with the acquisition of syntax? Here we hypothesize a mechanism called collocational bootstrapping, in which regularities in word co-occurrence patterns can provide cues to syntactic dependencies. We investigate whether this mechanism can support the acquisition of English subject-verb agreement. First, we simulate language acquisition by training neural networks on synthetic datasets that vary in how predictable their subject-verb pairings are. We find that there is a range of variability levels at which these statistical learners robustly learn subject-verb agreement. We then analyze the variability of subject-verb pairings in child-directed language, and we find that the variability in such data falls within the range that supported robust generalization in our computational simulations. Taken together, these results suggest that collocational bootstrapping is a viable learning strategy for the type of input that children receive.

We present NeuroQA, a large-scale benchmark for visual question answering in 3D brain magnetic resonance imaging (MRI), with 56,953 QA pairs from 12,977 subjects across 12 datasets. It spans ages 5-104 and five clinical domains: Alzheimer's, Parkinson's, tumors, white matter disease, and neurodevelopment. Unlike prior medical Visual Question Answering (VQA) efforts that operate on 2D slices or rely on narrow diagnostic labels, NeuroQA pairs every item with a full 3D volume. It evaluates 11 clinically grounded reasoning skills across Yes/No, multiple-choice, and open-ended formats. Of the 203 templates, 131 are image-grounded (answerable from a 3-plane viewer) and 72 are image-informed (ground truth from quantitative volumetry or clinical instruments). To remove text-only shortcuts, we apply answer-distribution refinement, reducing closed-format text-only accuracy from $>$80% to 44.6%; image necessity is assessed separately through an image-grounding protocol released with the benchmark. A 38-rule deterministic pipeline and two rounds of expert review verify every QA pair against FreeSurfer measurements, metadata, or radiology report fields, with zero same-subject contradictions across templates. We conduct a clinician evaluation in which two clinicians independently assess 100 frozen test items on a three-plane viewer. On closed-format (Yes/No + multiple-choice) test-public items, the best zero-shot vision-language model and a supervised 3D CNN baseline reach 47.5% and 43.7% accuracy respectively, both below the 49.4% text-only majority-template floor. NeuroQA adopts a two-tier release with public QA pairs for open-access datasets and reproducible generation scripts for datasets restricted by data use agreements (DUAs), plus subject-level splits, a held-out private test set, and an online leaderboard.

Advanced fibrosis is a major determinant of liver-related morbidity in metabolic dysfunction-associated steatotic liver disease (MASLD). FIB-4 is widely used as a first-line non-invasive test, but its fixed formula may underuse diagnostic information contained in age, aspartate aminotransferase, alanine aminotransferase, and platelet count. We evaluated whether machine-learning-enhanced non-invasive testing (MLE-NIT) can improve advanced fibrosis detection while preserving this FIB-4 variable space. We used three biopsy-confirmed MASLD cohorts from China, Malaysia, and India (n=784). The Chinese cohort was split into 486 training and 54 internal validation/tuning patients; final performance was reported only on the Malaysian and Indian external cohorts. Models used five variables: age, FIB-4, aspartate aminotransferase, platelet count, and alanine aminotransferase. We compared FIB-4 with a shallow-deep neural network (s-DNN), TabPFN, and gpt-4o-2024-08-06. FIB-4 achieved external ROC-AUCs of 0.75 and 0.60 in Malaysia and India, respectively. TabPFN achieved 0.69 and 0.66, fine-tuned GPT-4o achieved 0.75 and 0.63, and the s-DNN achieved 0.77 and 0.67, respectively. The s-DNN contained only 354 trainable parameters, compared with 7,244,554 for TabPFN, yet provided a more balanced external operating profile. Calibration showed s-DNN Brier scores of 0.18 and 0.22, and permutation importance identified AST and FIB-4 as dominant variables. Compact non-linear MLE-NITs may enhance FIB-4-based fibrosis assessment without increasing clinical data requirements.

Fine-tuning adapts a pretrained machine learning model to a small, sensitive dataset, but this process risks memorizing individual new data points, making the model vulnerable to adversaries who seek to extract sensitive information. In this work, we develop a randomized algorithm based on the exponential mechanism for fine-tuning while ensuring differential privacy. Our key idea is to construct a simple utility function that combines a local quadratic approximation of the pretrained model with information from the new dataset. The resulting exponential mechanism admits exact sampling from a multivariate normal distribution in closed form. We establish theoretical privacy guarantees, sensitivity bounds, and accuracy estimations for our method. We further introduce a random-projection strategy that makes the approach scalable to high-dimensional models. Numerical experiments on the MNIST benchmark and the MIMIC clinical dataset demonstrate competitive performance against existing differentially private fine-tuning techniques.

Benchmark-based evaluation remains important for tracking frontier AI progress. But it can both overstate and understate deployed capability because it privileges tasks that can be precisely specified, automatically graded, easy to optimize for, and run with low budgets and short time horizons. We advocate for a complementary class of evaluations, which we term open-world evaluations: long-horizon, messy, real-world tasks assessed through small-sample qualitative analysis rather than benchmark-scale automation. In this paper we survey recent open-world evaluations, identify their strengths and limitations, and introduce CRUX (Collaborative Research for Updating AI eXpectations), a project for conducting such evaluations regularly. As a first instance, we task an AI agent with developing and publishing a simple iOS application to the Apple App Store. The agent completed the task with only a single avoidable manual intervention, suggesting that open-world evaluations can provide early warning of capabilities that may soon become widespread. We conclude with recommendations for designing and reporting open-world evals.

Modern artificial intelligence systems require calibrated uncertainty estimates that remain reliable in sequential and non-stationary environments. Online conformal prediction (OCP) addresses this challenge through adaptively updated prediction sets that provide deterministic long-run miscoverage guarantees. These guarantees, however, hinge on the assumption of perfect feedback about the coverage of past prediction sets. In practice, the observed miscoverage indicator may be corrupted by noise, communication failures, or adversarial manipulation, which can severely degrade OCP's calibration guarantees. In this paper, we study OCP under corrupted feedback. We first model feedback corruption as an arbitrary binary flip sequence, and analyze how feedback corruption affects and degrades the miscoverage performance of standard OCP. We then propose two robust schemes: robust OCP via filtering, which leverages the structural properties of the predicted threshold to filter corrupted feedback, and robust OCP via active compensation, which incorporates an active compensation mechanism to mitigate the effect of corrupted feedback. For both methods, we establish explicit miscoverage guarantees, which are further specialized for an independent stochastic flip model and for an arbitrary error model with memory bounds. Experiments on real-world datasets validate the proposed approach, showing markedly improved calibration and significantly smaller prediction sets compared with baseline OCP methods under corrupted feedback.

Urban heat exposure is becoming an increasingly critical challenge due to the intensifying urban heat island effect. Fine-grained shade patterns, especially those induced by urban buildings, strongly influence pedestrians' thermal exposure and outdoor activity planning. However, accurately modeling and analyzing urban shade at scale remains difficult because of the lack of large-scale datasets and systematic evaluation frameworks. To address this challenge, we present ShadeBench, a comprehensive dataset and benchmark for urban shade understanding. ShadeBench contains geographically diverse urban scenes with temporally varying simulated shade maps and textual descriptions, together with aligned satellite imagery, building skeleton representations, and 3D building meshes. Built upon this multimodal dataset, ShadeBench supports a range of downstream tasks, including shade generation, shade segmentation, and 3D building reconstruction. We further establish standardized evaluation protocols and baseline methods for these tasks. By enabling scalable and fine-grained shade analysis, ShadeBench provides a foundation for data-driven urban climate research and supports future studies in heat-resilient urban planning and decision-making. The code and dataset are publicly available at https://darl-genai.github.io/shadebench/.

Humans learn social norms and behaviors from verbal feedback (e.g., a parent saying "that was rude" or a friend explaining "here's why that hurt"). Yet, learning from feedback for LLMs has largely focused on domains like code and math, where RL rewards are directly verifiable and condensed into scalar values. As LLMs are increasingly used to simulate human behavior, e.g., standing in for users, patients, students, and other personas, there is a pressing need to make them more human-like, which requires embracing a fundamentally different kind of signal: feedback that is verbal, subjective, and multi-faceted. We present DITTO, a model trained by treating verbal feedback as a first-class signal in reinforcement learning. After each rollout, DITTO receives verbal feedback and generates a feedback-conditioned improved rollout; both outputs are jointly optimized with GRPO, distilling verbal guidance into the base policy without requiring feedback at test time. We also introduce SOUL (Simulation gym Of hUman-Like behavior), a unified benchmark and training data suite spanning 10 tasks across six categories: Theory of Mind, character role play, social skill, learner simulation, user simulation, and persona simulation. DITTO achieves an average 36% improvement over the base model and exceeds GPT-5.4 on 6 of 10 SOUL benchmarks, demonstrating that RL with verbal feedback is a promising direction for training LLMs to simulate human behavior.

We address out-of-distribution (OOD) detection across the full spectrum of distribution shifts -- global domain changes, semantic divergence, texture differences, and covariate corruptions -- through a multi-encoder fusion of per-encoder representation-space diffusion models (RDMs). We statistically identify each encoder's sensitivity to specific shift types from ID data alone and introduce EncMin2L -- an encoder-agnostic two-level $\min(\cdot)$-gate that combines and calibrates per-encoder diffusion-based likelihood detectors without OOD labels, outperforming monolithic multi-encoder baselines at $2.3\times$ lower parameter cost. Two ID-data diagnostics: $η^2$ (class-conditional F-test) and $Δμ$ (log-likelihood shift under synthetic corruptions) -- quantify encoder specialization, while a Tippett minimum $p$-value combination aggregates per-encoder scores into a single, calibration-stable OOD signal. EncMin2L achieves $\geq 0.94$ AUROC across all four shift types simultaneously, outperforming the state-of-the-art representation-space diffusion OOD detectors across overlapping benchmarks.

Deep-learning pipelines for microscopy image classification often require expensive, labor- and time-intensive expert annotation to produce high-quality ground truth for training. Recent work has shown that prompt tuning of vision-language models (VLMs) can reduce manual annotation by constructing a small prompt set of expert-verified image-caption exemplars that is reused as few-shot context to classify all remaining images at inference time. To further reduce effort, the VLM can draft captions for candidate exemplars, which experts then verify and lightly edit instead of writing text de novo. However, two practical questions remain unaddressed: (1) which unlabeled images should be prioritized for verification, and (2) how many verified exemplars are needed to reach a performance target. In this work, we address these questions by formulating prompt-set construction as a target-driven active learning problem that prioritizes which images to annotate. We study three complementary selection criteria under strict low-resource constraints with small unlabeled pools. Experiments show that our methods reach the target performance with substantially fewer expert-verified images than random selection, achieving 100% test accuracy with as few as 20 annotated images on average. More broadly, our human-in-the-loop framework demonstrates a human-centered use of generative AI in biomedical image analysis, where experts remain actively involved in verifying and refining model output while significantly reducing annotation cost. Code and data will be publicly available.

Reliable assessment of tropical cyclone (TC) risk is limited by the brevity and spatial sparsity of the historical record, particularly for the rare, high-intensity landfalls that dominate insured loss. We present WHITS (Wind-focused Hurricane Interactive Track Simulator), a non-parametric semi-Markov track generator that extends the HITS framework of Nakamura et al. (2015) in three ways: transitions between historical track segments are conditioned on local wind speed in addition to position, age, and forward vector; the kernel selection on the comparative-vector term is sharpened to suppress dynamically inconsistent jumps; and a short smoothing window is applied across each transition to remove the position and wind discontinuities reported by downstream surge users. WHITS is fit to the full available best-track record in each of six basins in IBTrACS, extending in the North Atlantic to 1851 and in other basins to the earliest year of reliable best-track data. The resulting 10,000-yr global synthetic catalog reproduces observed track density and the annual hurricane/typhoon-force wind-hit probability across all basins. The catalog is intended for catastrophe-risk applications where a large, low-bias sample of physically plausible tracks is more useful than a small, statistically corrected one.

As autonomous agents increasingly execute end-to-end tasks under fixed monetary budgets, the pressing open question shifts from whether the budget is respected, to how to spend it effectively. Existing budget-aware methods typically control reasoning step-by-step within a single agent, or learn resource allocation policies via RL. None address how to split a budget across the composing phases of a multi-agent pipeline at inference time. We propose ZEBRA, a zero-shot framework that reduces multi-phase budget allocation to a continuous nonlinear knapsack problem: an LLM controller estimates per-phase utility curves, and a water-filling search on the Lagrange multiplier returns the per-phase split. Additive and multiplicative aggregations are unified under the same solver. On a $150$-task APPS coding benchmark, both ZEBRA variants outperform LLM-direct (budget allocation directly by an LLM) on every aggregate metric. At a budget of $α= 0.5$ of the unconstrained spend, ZEBRA recovers $94.4\%$ of unconstrained quality, versus $88.1\%$ for LLM-direct. The advantage is statistically significant and transfers beyond coding: on a $3$-phase HotpotQA pipeline, ZEBRA beats LLM-direct by $14.3$pp, with allocations empirically robust to curve-estimation noise. On HotpotQA, ZEBRA arrives at a different budget split (near-balanced) compared to the APPS one (skewed towards a refinement phase), showing adaptation to the pipeline structure. More broadly, we show that lightweight algorithmic guidance at inference time can improve the economic behavior of autonomous multi-agent systems.

Autonomous navigation in GNSS-denied environments remains a core challenge for legged robots, where exteroceptive sensors such as LiDAR are prone to elevation drift in geometrically sparse or repetitive scenes. We present a factor graph architecture that augments the LIO-SAM framework with a parallel kinematic lane driven by proprioceptive leg odometry, coupled to the main LiDAR-inertial lane via an identity relative pose constraint with a selective noise model. Applied to a Linxai D50 quadruped platform across two outdoor loops totaling over one kilometer, our approach reduces elevation drift from over 30m to under 30cm and enables convergence in a scene where the baseline pipeline fails entirely. These results suggest that proprioceptive data, already computed onboard for gait control, constitutes a lightweight and effective vertical anchor for SLAM in GNSS-denied settings.

Quadratic constraints (QCs) are widely used to characterize nonlinearities and uncertainties, but generic analytical characterizations can be conservative on bounded domains. This paper develops a framework for constructing verified quadratic characterizations of scalar relations in the two-dimensional real plane. Candidate quadratic inequalities are locally generated by solving convex quadratic programs using samples from the relation and exterior sample points. They are then verified globally using sum-of-squares certificates over an exact semialgebraic description or, in the case of nonpolynomial relations, over relaxed polynomial descriptions. The resulting verified constraints define a sound overapproximation of the scalar relations over the considered domains. These constraints are directly compatible with existing analysis frameworks based on QCs and pointwise integral quadratic constraints (IQCs) for static nonlinearities and uncertainties, and they can also be embedded in QC-based semidefinite programs for reachability and safety analysis of feedforward neural networks. For smooth activations such as $\tanh$, the method yields domain-dependent quadratic characterizations that constitute an alternative to generic sector- or slope-based descriptions. For ReLU networks, we give methods to reduce conservatism in QC-based reachability analysis of feedforward networks by exploiting dependencies between neurons and tighter local bounds. Numerical examples demonstrate improved reachability results for smooth activations, reduced conservatism for ReLU networks, and applicability beyond neural networks through an example involving saturation.

Hyperparameter prediction is a critical practical bottleneck for model-based image denoisers, ranging from classical TV/TGV variational solvers to modern diffusion-based models such as DiffPIR. While existing learned predictors can achieve near-oracle performance, this approach scales poorly: each new configuration conventionally requires its own oracle-labeled training set, and each label requires a hierarchical grid search evaluated against clean ground truth. We therefore ask whether oracle supervision collected on source configurations can transfer to target configurations with few or no target oracle labels. We propose HyperDn, a single configuration-conditioned predictor that pools oracle supervision across source configurations and predicts heterogeneous hyperparameters for new denoiser--noise configurations. In a cross-paradigm experiment, HyperDn transfers from relatively cheap TV/TGV variational sources to more expensive diffusion-based DiffPIR. With only $2$ target oracle labels, it reaches $30.23$\,dB, within $0.90$\,dB of the oracle, and outperforms the $64$-label per-configuration predictor trained from scratch, using $1/32$ as many target labels as that baseline point. Without any target oracle labels, HyperDn also reaches near-oracle PSNR on two unseen mixtures of seen noise types and on transfer from relatively cheap $96\times 96$ source images to $512\times 768$ targets. Together, these results show that expensive oracle supervision for hyperparameter prediction can be transferred from source to new target configurations, reducing the need to rebuild oracle labels for each new denoising configuration.

LLM-curated tables can appear source-grounded while containing unsupported rows: the curator may recall entries from parametric memory and retroactively attach page-level citations that are not the actual source. We study this hazard in Seed2Frontier discovery: the task of finding complement Wikipedia pages from a seed page to assemble a structured table. Stage-Audit addresses it with disjoint curator-auditor write rights, a row-level source-citation gate, and a 12-check audit taxonomy over keys, schema, source roles, cardinality, and scope. On a curated 51-instance Seed2Frontier evaluation set spanning 15 top-level domains, Stage-Audit improves source-frontier precision over a vanilla LLM curator from 0.356 to 0.505 (+42% relative) and F1 from 0.334 to 0.451 (+35%), while maintaining explicit per-row source traceability. The vanilla-LLM-vs-Stage-Audit comparison isolates the policy contribution rather than LLM-based discovery in general.

Language agents can adapt from experience in interactive environments, but current reflection-based methods can only self-correct within a single task instance. Whether such experience can be distilled into reusable lessons that improve performance on future unseen tasks remains unclear. We address this problem by introducing the In-context Training (ICT) task, a framework for evaluating cross-task self-improvement in language agents. In ICT, a reflector model observes trajectories collected by an actor model and generates system prompts intended to improve the actor's performance on future unseen tasks. We then propose an RL-based training pipeline for learning such reflections directly from experience, without human-provided examples. Across ALFWorld and MiniHack, our trained reflectors outperform an untrained baseline on most held-out task families, showing that the ability to learn from experience can itself be learned. In some cases, we observe generalisation beyond the benchmark on which the reflector was trained, to substantially different environments. Finally, we introduce MetaGym, a generic Python library for constructing meta-environments, enabling future research on self-improving language agents.

Long-horizon video generation suffers from two intertwined issues. First, there is drift, where video quality degrades over time. Second, there are continuity issues which manifest as object permanence issues, or improperly rendering transient content (e.g., an object that appears in non-consecutive frames changing color/style). Recent work has focused on autoregressive distillation techniques that attack both problems simultaneously. We instead choose to focus on drift directly and introduce \textbf{Anchored Tree Sampling (ATS)}: a training-free inference-time scheduler that replaces left-to-right rollout with sparse-to-dense, anchor-bounded imputation organized as a tree. A root call produces sparse anchors over the full horizon, recursive refinement generates intermediate anchors, and final leaf spans are synthesized between neighboring anchors. This reduces the critical path from $K$ sequential rollout steps to $L+1$ tree-hierarchical steps and converts horizon-compounding drift into anchor-bounded drift. We focus on V2V generation in the \emph{static-camera} regime, where sparse anchors over the horizon are well approximated by the dense conditioning signal, and the base model can produce them without retraining. We evaluate ATS against two contemporary autoregressive baselines on Wan $2.1$ $+$ VACE, across five conditioning modalities (inpainting, outpainting, edge, pose, depth). We show that ATS outperforms both competitors in overall quality, as well as in drift prevention. We additionally demonstrate stable $\geq 40$-minute generation on LTX-$2.3$ across the same five modalities. We conclude by proposing a path forward to extend ATS to arbitrarily long T2V generation, as well as the dynamic-camera and multi-shot regimes.

Cone-beam CT (CBCT) is routinely acquired during radiotherapy for patient setup, but its quantitative reliability is degraded by scatter, noise, and reconstruction artifacts, limiting Hounsfield Unit (HU) accuracy. We propose EPC-3D-Diff, a novel conditional 3D latent diffusion framework for volumetric CBCT to CT synthesis that introduces a projection domain equivariance loss derived from acquisition physics. Unlike common image domain equivariance, we exploit the fact that an in plane rotation of the volume corresponds to an angular shift in its projections. During training, we enforce this relationship by forward projecting rotated synthesized CT volumes and matching them to appropriately angle shifted projections of the paired target CT, yielding a physics consistent equivariance constraint integrated into the diffusion objective. To capture full 3D context efficiently, conditional diffusion is performed in a compact latent space learnt by a lightweight 3D autoencoder, preserving axial depth while downsampling in plane resolution for stable training. We validate on a paired head CBCT/CT phantom dataset, including repeat scans, and paired clinical data using patient wise splits, and perform single and mixed domain training, ablations, and comparisons with diffusion and CycleGAN. EPC-3D-Diff generalizes well and achieved substantial improvements, +7.4 dB (phantom) and +1.8 dB (clinical data) in PSNR compared to state of the art methods, alongside improved SSIM and HU accuracy, within tissue boundaries. Overall, EPC-3D-Diff improves robustness and physics consistency, supporting HU aware synthesis for downstream radiotherapy workflows.

Vision-language models (VLMs) are increasingly used for medical image interpretation, yet they frequently hallucinate, generating clinically plausible but factually incorrect findings that pose direct patient safety risks. We introduce HalluCXR, a benchmark evaluating six architecturally diverse VLMs across 856 stratified MIMIC-CXR chest radiographs and three query types, yielding 15,408 model evaluations. An eight-category hallucination taxonomy with clinical severity ratings and a two-layer detection pipeline are validated against 250 human annotations (auto-detection F1=0.959; LLM judge F1=0.907). We find that 61.9--82.3% of outputs contain hallucinations, with clinically dangerous errors in up to 80.2%. Three key patterns emerge: normal radiographs paradoxically attract the most severe hallucinations, common findings are systematically over-fabricated while rare findings go under-detected, and response length alone predicts hallucination risk (AUC up to 0.908). A six-model ensemble reduces fabrication by up to 84.8% at the cost of increased omission; a three-model subset retains comparable performance at half the cost. These results establish that hallucination auditing, verbosity-based risk monitoring, and ensemble-based safety layers are prerequisites for clinical deployment.

Neural networks can be trained to rank the choices made by logical reasoners, resulting in more efficient searches for answers. A key step in this process is creating useful embeddings, i.e., numeric representations of logical statements. This paper introduces and evaluates several approaches to creating embeddings that result in better downstream results. We train embeddings using triplet loss, which requires examples consisting of an anchor, a positive example, and a negative example. We introduce three ideas: generating anchors that are more likely to have repeated terms, generating positive and negative examples in a way that ensures a good balance between easy, medium, and hard examples, and periodically emphasizing the hardest examples during training. We conduct several experiments to evaluate this approach, including a comparison of different embeddings across different knowledge bases, in an attempt to identify what characteristics make an embedding well-suited to a particular reasoning task.

Accurate polyp size stratification guides surveillance decisions, with lesions larger than 5 mm typically requiring closer follow-up. However, monocular colonoscopy lacks a reliable metric reference. We present a diagnostic audit of binary polyp size classification (<=5 mm vs. >5 mm) across multiple public multi-center datasets, model families, and patient-stratified cross-validation. Across architectures and input modalities, including RGB appearance, relative depth, and photometry, model performance is moderately consistent, suggesting reliance on cues correlated with examination behavior rather than true metric scales. By providing ground-truth scale at varying granularities, we quantify the potential improvement from perfect scale information and show that current depth estimation and global calibration offer limited gains. We further demonstrate that segmentation errors under distribution shift eliminate most of this potential, with oracle scale under predicted masks recovering only baseline performance. These results highlight metric scale and mask robustness as two independent bottlenecks and provide reusable evaluation tools such as oracle scale ladders, shortcut partitions, and mask substitution for auditing future polyp sizing pipelines. Our code is publicly accessible at https://github.com/anaxqx/polyp-sizing-audit.

In recent years, there has been a notable increase in the level of attention that is given to algorithms based on deep learning in the context of medical image segmentation. Nevertheless, the reliability of the field has been hindered due to the absence of a standardized methodology for performance analysis and the utilization of different datasets in previous research. The primary objective of the research is to comprehensively evaluate contemporary segmentation frameworks combined with state-of-the-art pre-trained backbones in order to accurately predict COVID-19 lesions in CT images. Moreover, this evaluation can serve as a point of reference for the segmentation of images in various other imaging scenarios. In order to accomplish this, we integrate four distinct deep learning architectures, namely Unet, PSPNet, Linknet, and FPN, with six pre-trained encoders, including VGG 19, DenseNet 121, Inception ResNet V2, MobileNet V2, SeresNet 101, and EfficientNet B0. This approach enables the development of diverse testing architectures. In the context of image segmentation, our research encompassed both binary and multi-class experimentation. The findings derived from our analysis of three distinct COVID-19 CT segmentation datasets indicate that deep learning architectures yield precise and efficient segmentation outcomes. Significantly, a maximum F1-Score of 98% was attained for binary class segmentation, while multi-class segmentation yielded F1-Scores of 75% and 77% across two separate datasets. The utilization of artificial intelligence and deep learning enhances the diagnostic process for pandemic diseases across multiple dimensions.

Differentially private stochastic gradient descent (DP-SGD) enables private deep learning through per-example clipping and calibrated Gaussian noise, but its high-variance updates can reduce utility on challenging datasets. We propose \textbf{SMA-DP-SGD}, a \textbf{Spectral Memory-Aware Differentially Private Stochastic Gradient Descent} method that augments DP-SGD with a fractional memory branch built only from previously privatized noisy releases. WeightWatcher-inspired power-law spectral exponents provide group-wise reliability signals, instantiated layer-wise in our experiments, to adapt the decay and effective memory depth. Private-history alignment, norm matching, and warm-up activation stabilize the memory contribution. Privacy remains transparent: conditioned on the private release history, the memory branch is fixed, and the only newly data-dependent term is the current clipped sum scaled by a fixed coefficient \(β\). Hence, SMA-DP-SGD preserves a clean conditional sensitivity structure and exactly recovers group-wise DP-SGD when \(β=1\). Experiments on CIFAR-100, CIFAR-10, and MNIST show competitive or superior accuracy over several DP optimization baselines, with the largest gains on CIFAR-100 and CIFAR-10. CIFAR-10 ablations show that \(β\) controls the privacy--utility trajectory, while spectral and memory diagnostics confirm a controlled short-to-moderate effective memory depth and a small memory-branch ratio. Runtime analysis shows that the mechanism incurs additional overhead, about \(2.94\times\) DP-SGD in our CIFAR-10 implementation, revealing a practical trade-off between adaptive private memory and computational cost.

Can language-pretrained transformers become effective time-series forecasters, and why? In this paper, we show that cross-modal transfer arises because language pretraining preconditions time series training with a reusable manifold. A linear probe on frozen LLM states decodes realistic time-series trajectories without paired supervision, and retrieval in this projected space yields competitive forecasts, showing that structure and dynamics exist before finetuning. Pretrained initialization also improves optimization, producing coherent gradients and a highly anisotropic loss landscape unlike random initialization. Finetuning then acts as low-dimensional alignment, reusing existing directions rather than learning temporal primitives from scratch, as evidenced by low-rank updates, subspace alignment, and shared features for periodicity, trend, and repetition. Together, these results support a geometric account of LLM-to-time-series transfer: language pretraining builds the manifold, and finetuning projects numerical dynamics onto task-relevant directions.