Foundation Model

Computational pathology foundation models (PFMs) have advanced whole-slide image analysis. However, their size and inference cost hinder local deployment in pathology departments. We propose MuCoDi, a pretraining framework that distills frozen tile embeddings from multiple PFMs into compact edge-oriented encoders. Instead of regressing individual teacher features, MuCoDi trains lightweight MobileOne and RepViT students with a contrastive distillation objective adapted from MoCo v3, where cached Virchow2, UNI2, and H-Optimus-1 embeddings replace momentum-encoder keys. We pretrain students on 14.3M TCGA tiles from only 11.8K WSIs and evaluate frozen encoders on 23 clinically curated downstream classification tasks. RepViT-based MuCoEdge students retain near-teacher performance while reducing model size by orders of magnitude: MuCoEdge-R2.3 and MuCoEdge-R1.5 reach 71.0% external AUROC, within 0.8 percentage points of the best teacher (Virchow2, 71.8%), while MuCoEdge-R2.3 obtains the best external F1 and the second-best AUPRC (51.8% and 53.3%). MuCoEdge-R1.0 reaches 70.9% AUROC with only 6.4M parameters and 1.12 GFLOPs. On a Raspberry Pi 5, sub-million-parameter MobileOne students achieve up to 605-fold single-tile speedup over Virchow2 while retaining 66.5% to 66.9% external AUROC, demonstrating that PFM-quality pathology representations can be moved toward practical edge deployment. Code is available at https://anonymous.4open.science/r/mucodi-6243.

Deploying a time series foundation model requires GPU infrastructure, engineering overhead, and carries no guarantee of improvement over XGBoost. We provide the first systematic break-even analysis answering when this investment pays off. Across 30 benchmark datasets, we compare zero-shot and LoRA fine-tuned foundation models (Chronos, Moirai, Lag-Llama) against classical baselines (Naive, ETS, ARIMA, XGBoost) at six training set sizes from 2% to 100% of available data. Foundation models outperform classical methods at every evaluated training fraction on 15 of 30 datasets -- GPU deployment is unconditionally justified on these regardless of data volume. On 6 datasets, classical methods surpass zero-shot foundation models with as little as 2% of training data (21-2,768 samples); on the remaining 9, break-even ranges from 24 to 8,361 samples. One robust deployment rule requires no model training: if n_train < 700 and seasonality is non-negligible, use FM zero-shot and skip fine-tuning -- this resolves 10 of 30 deployment decisions immediately. Contrary to common practice, LoRA fine-tuning can actively degrade performance on short series. We operationalise these findings as a two-step decision framework -- compute dataset length and seasonality strength, run a brief 5-10% pilot only if needed -- enabling practitioners to make the FM-versus-classical decision before committing to full infrastructure. Four dataset features motivate mechanistic hypotheses for the remaining cases, though reliable automated prediction at this benchmark scale remains an open problem. Code, benchmark, and decision tools are available at https://github.com/nicolaisi/fm-breakeven.

Given a relational database (RDB) storing heterogeneous tabular information, how can we predict missing (or future) values in some target column of interest? As the space of potential targets is vast across enterprise settings, it is preferable to avoid learning a new model from scratch each time there is a new prediction task. Frozen foundation models based on RDB-specific encoders provide a viable solution, but ideal design remains an open question. On the one hand, it has recently been argued that certain parameter-free subgraph encoders combined with single-table foundation models can achieve near SOTA performance, with no RDB-specific pre-training required. Meanwhile, other contemporary studies advocate for parameterized encoders pre-trained to exploit observable labels for learning task-specific representations. To address this ambiguity, we analyze RDB encoder properties specifically when labels are present as inputs, proving limitations on the potential efficacy of trainable encoder parameters. As empirical validation, we demonstrate that considerably simpler parameter-free encoders are still capable of strong performance across many relevant benchmarking tasks.

Learning from few labeled examples is a central challenge in tabular machine learning, and it becomes the binding constraint in domains where labeling is costly, such as crowd monitoring during Hajj and Umrah. Tabular foundation models, which predict from only a handful of examples without task-specific training, were recently introduced to address this very-few-label regime. In this study we test them on crowd-state classification to assess how much they help when labels are scarce, and we compare them against standard machine learning methods to characterize the accuracy and efficiency trade-offs between the two approaches. Using three real datasets we evaluate different machine learning models, in untuned and tuned forms, against three foundation models. Results show that no single family is best everywhere. The right choice depends on the label budget. When labels are very few, foundation models lead. As labels grow, tuned conventional models catch up and significantly surpass the foundation models on the more structural geometry target. Efficiency separates them further where tuned machine learning models incur a large tuning cost that foundation models avoid, although foundation models reprocess their context at every prediction. We summarize these results as a practical map of which approach to prefer under a given label budget and computational budget.

Pixel-wise Earth-observation (EO) foundation models are now achieving state-of-the-art performance via generated spatial embeddings. However, how these models scale and how best to spend a pretraining budget remain poorly understood. We present the largest controlled scaling study for EO to date: 395 training runs on 1,024 GH200 superchips within a fixed pixel-wise Barlow Twins family, each evaluated on 15 downstream tasks. We find that pretraining loss barely predicts downstream performance (|Pearson r| < 0.2), so selecting models by loss wastes a large share of the compute. We also find that, as the training budget grows, the encoder and the data should grow together while the projector stays fixed, which gives a simple rule for allocating compute. Using this rule, we train a family of pixel-wise models (0.5B and 1B, with a 2B model in training) and distill them into compact students for embeddings-as-data deployment. The 21-million-parameter distilled TESSERA v2-1B-M in aggregate outperforms all open and proprietary models tested, some of which are orders of magnitude larger. These students produce Matryoshka representations that are inexpensive to serve: a 16-dimensional prefix keeps 92% of the full 128-dimensional performance at 1/8 of the storage. Upon completion of training we plan to release v2 global embeddings covering 2017-2025. Together, these results give a concrete, empirically grounded recipe for scaling pixel-wise EO foundation models: train large encoders, select by downstream performance, and distil into flexible student models. All code will be released at https://github.com/ucam-eo/tessera.

EEG foundation models have shown strong potential in learning generalized representations across subjects and tasks. However, most existing approaches follow a pretraining-static deployment paradigm, which suffers from two key limitations: (1) misalignment between pretraining objectives and downstream tasks, and (2) limited adaptability to distribution shifts in online settings. We propose Online Neural Adaptation (NeuroOnline), a unified framework that enables continuous adaptation in online scenarios. NeuroOnline integrates two complementary mechanisms: (1) multi-view consistency learning, which enforces cross-view alignment to promote consistent and task-relevant representations, and (2) context-aware representation modulation, which leverages a learnable context prompt with cross-attention to dynamically adapt representations to evolving data distributions. Together, these mechanisms unify representation alignment and dynamic adaptation. Experiments on multiple EEG benchmarks show that NeuroOnline consistently outperforms strong baselines in online settings, achieving better performance under distribution shifts. Ablation and sensitivity studies further validate the necessity of each component and the effectiveness of the overall design.

Foundation models for Earth systems have so far been trained primarily on physical climate and weather data, with limited representation of the human systems that both drive and respond to environmental change. The lack of a unified global training resource that combines climate, land, ocean, cryosphere, infrastructure, hazards, and socioeconomic data on a common grid hinders progress toward truly multimodal Earth system foundation models. We present WorldTensor, a harmonised global dataset that aligns hundreds of environmental and socioeconomic variables to a standardised 0.25$^\circ$ spatial grid and annual temporal framework. WorldTensor integrates reanalysis products, remote sensing, emissions inventories, land use reconstructions, hydrological observations, infrastructure and hazard datasets, and socioeconomic indicators within a single representation designed for machine learning workflows. To build the dataset, we regridded inputs across heterogeneous native resolutions and projections, rasterised point and vector datasets into spatially meaningful gridded fields, and reconciled temporal coverages ranging from daily observations to sparse multiyear socioeconomic snapshots. All outputs are distributed as NetCDF files with standardised coordinates, variable metadata, and a common CF metadata convention. WorldTensor provides a reproducible resource for training and evaluating foundation models that learn coupled dynamics across environmental and human systems at planetary scale.

Accurate regional weather prediction requires resolving fine-scale structure while remaining consistent with global dynamics. Traditional limited area models rely on computationally expensive simulations, while many learning-based approaches frame the problem as super-resolution, overlooking statistical and physical mismatches across scales. We propose a foundation-model-driven downscaling framework that learns regional refinements of global forecasts by augmenting a pretrained weather model backbone with lightweight, multi-scale prediction heads operating directly in its latent space. Despite being trained on substantially coarser inputs, the pretrained backbone supports regional adaptation at resolutions corresponding to a two-order-of-magnitude increase in grid-cell resolution, without the need for retraining. The proposed approach uses regional numerical simulations as training targets and is evaluated not only against gridded datasets but also against ground-based weather station observations, enabling analysis of systematic biases between global reanalysis, regional simulations, and in-situ weather station observations. Our experiments show improved accuracy in comparison to NWP on most of the metrics at the fraction of computational cost. Moreover, we observe that building on a latent space of globally pre-trained weather foundation model offers better downscaling capabilities than the standard image-based super-resolution approaches.

This paper introduces a fast method for high-quality 3D Gaussian Splatting (3DGS) reconstruction without traditional Structure-from-Motion (SfM). The proposed approach leverages 3D Foundation Models (3DFMs) for camera pose and point-cloud initialization, then jointly optimizes both camera poses and Gaussian primitives using a depth-guided loss function. This enables fast convergence even from rough initialization with as few as 50-60 input views. To further improve reconstruction quality in sparse-view scenarios, an MLP-based pose refinement module is introduced alongside depth-guided supervision from the foundation model. Extensive experiments on Mip-NeRF 360, Tanks and Temples, and RobustNeRF demonstrate that the proposed method achieves competitive reconstruction quality (23.61 dB PSNR, 0.19 LPIPS) while reducing training time to approximately three minutes per scene. The proposed method produces ready-to-use 3DGS models at a fraction of the time required by existing pipelines, making it suitable for near real-time applications in robotics, VR, and autonomous navigation.

Background: Foundation models (FMs) trained on large-scale unlabeled physiological data have emerged as a promising paradigm for medical artificial intelligence. Their ability to capture clinically meaningful, transferable representations for rare diseases remains largely unproven. This study investigates whether FM pre-training provides genuine clinical generalization benefits beyond improved optimization for rare electrocardiographic (ECG) phenotypes. Methods: We systematically evaluated nine publicly available ECG FMs for Brugada syndrome detection on the BrSwiss cohort (294 patients, 87 cases) and the independent external HUCA cohort (363 patients, 76 cases), under three strategies (from-scratch training, linear probing, full fine-tuning) across several configurations, including a 3% data ablation and zero-shot cross-site transfers. Results: Pre-training was necessary for high-capacity architectures unable to converge from scratch (AUC gain up to 0.411, p < 0.05), but gave no significant gain for compact architectures already converged on labeled data alone. On full BrSwiss, the best fine-tuned FM (ECG-CPC, AUC = 0.962) only marginally exceeded the strongest supervised baseline (ECG-CPC from scratch, AUC = 0.932; p = 0.091). At matched training-set size, the data-efficiency advantage on BrSwiss-3% (AUC gain = 0.055, p < 0.01) did not replicate on HUCA. Under zero-shot cross-site transfer, FM-based pipelines did not generalize better than supervised baselines, all approaching chance-level performance. Conclusion: For Brugada syndrome detection, FM pre-training is mechanical rather than semantic, providing optimization stability rather than transferable clinical knowledge. These findings challenge the assumption that large-scale pre-training inherently encodes clinically meaningful representations, highlighting the central role of model architecture and data-domain alignment.

Recent 3D foundation models, such as DUSt3R, MASt3R, VGGT, $π^3$, and Depth Anything 3, provide strong feed-forward depth and pose estimates on pinhole imagery, but degrade sharply under fisheye camera geometry. We show that this failure is partly caused by a pinhole camera bias in the positional encodings of pretrained 3D foundation models, and propose RayTun3R, a lightweight camera adaptation approach. It keeps the pretrained network fixed and adapts only lightweight components tied to token position and camera geometry. RayTun3R learns parameter-efficient residual corrections to absolute and rotary positional encodings, together with parameter-free tokenization and corrections to prediction-grid coordinates that remove residual pinhole assumptions. The resulting adapter contains only 10,752 trainable parameters and can be learned from a short temporal segment using geometric losses. Once adapted, RayTun3R transfers effectively to the remaining frames of the sequence without incurring additional runtime costs. Across diverse fisheye datasets with fields of view from $110^\circ$ to $200^\circ$, our adapter reduces rotation error by $2$-$12\times$ relative to the unadapted model, outperforms LoRA while using $\sim\!14\times$ fewer trainable parameters, improves pose over adaptation-free baselines while avoiding their multi-view inference cost, and remains competitive on depth accuracy.

Time-series forecasting supports decisions in finance, en-ergy, transportation, public health, and industrial monitoring. Recent foundation models improve transfer across forecast-ing tasks, but many depend on centralized data and Trans-former attention, which restricts their use for long, high-di-mensional, and privacy-sensitive signals. This paper presents QuantFlow, a probabilistic forecasting framework that com-bines inverted sequence embedding, bidirectional Mamba state-space decoders, quantile regression, and federated learning. Each variable is embedded over the complete ob-servation window, processed in forward and reverse direc-tions, and projected to five conditional quantiles. TSMixup expands temporal diversity through Dirichlet-weighted inter-polation while preserving sequence structure. Experiments cover cryptocurrency, traffic, electricity, Electricity Trans-former Temperature, influenza, and weather data. QuantFlow obtains mean squared errors of 0.2834 on ETTm1 and 0.2218 on Weather, and a 20-client non-IID deployment retains use-ful accuracy after three communication rounds without cen-tralizing raw records. The results indicate that selective state-space modelling is a promising basis for scalable, uncer-tainty-aware, and privacy-conscious time-series prediction, while also revealing limitations on irregular epidemiological signals and long-horizon generalization.

Foundation models are routinely released to the public, yet the data recipes used to train them -- such as domain mixture weights that determine how different sources are sampled -- are rarely disclosed. This creates an access asymmetry: researchers study the resulting models but lack visibility into the training distribution that produces them. Prior works for inferring training data, such as membership inference, detect at the level of individual samples and thus cannot characterize the global composition of the training corpus. We introduce WARP, a framework that recovers a fine-tuned model's training mixtures directly from its released weights. WARP interpolates between the base and fine-tuned models using model merging, generating pseudo-checkpoints that approximate the missing training trajectory and expose a geometric footprint of the training data in the weight space. From these simulated footprints, WARP extracts geometric features and maps them to domain proportions using either a parameter-free softmax readout or an MLP projector trained on synthetic mixtures. In controlled experiments with BERT and GPT-2, WARP recovers domain mixtures with an average MAE as low as 0.046 and 0.104 respectively, outperforming membership inference and a variant with access to the true training trajectory.

Identity document forgery has undergone a fundamental capability shift: generative AI tools now enable high-fidelity document synthesis and field-level manipulation with minimal technical expertise, while detection methods remain constrained by benchmarks that do not reflect this threat. The resulting attack surface spans physical presentation, digital injection, and fully generative synthesis, introducing distinct forensic failure modes that require a unified threat model and evaluation framework. This survey provides, to our knowledge, the first unified treatment of Presentation Attacks, Digital Injection Attacks, and GenAI-driven synthesis within a single identity verification threat model. We trace detection methodologies from rule-based heuristics through forensic localisation, injection-aware pipelines, foundation models, and few-shot frameworks. A systematic audit of public datasets from 2019--2025 exposes a persistent Reality Gap between benchmark conditions and operational deployment. We further analyse large multimodal models for identity document manipulation, identifying Script-Dependent Generative Instability (SDGI) as a recurring typographic failure mode in non-Latin script inpainting. Finally, zero-shot benchmarking on unseen synthesised ID cards shows that even the strongest publicly available models achieve APCER values above 25% under security-oriented operating conditions, highlighting substantial limits in cross-domain generalisation. We conclude by outlining future directions toward forensically grounded, privacy-preserving, and legally accountable identity verification systems.

Radiomics is the established approach for CT-based lung cancer phenotyping, yet comparisons with foundation models rarely isolate contributions of feature extractor, classification head, and segmentation choice, or test cross-cohort robustness. We benchmark five feature extractors (Curia, Curia-2, DINOv3, Radiomics2D, Radiomics3D), seven classification heads (TabPFN, TabICL, XGBoost, CatBoost, Random Forest, logistic regression, Ridge), and three segmentation regimes on five tasks: tumor volume and stage classification, 2-year survival prediction, histology classification, and age prediction. Models are trained on LUNG1 (n=338) and evaluated on an internal test set (n=84) and the external LUNG2 cohort (n=211), with worst-case cross-cohort performance as the primary metric. The dominant design factor is task-dependent: segmentation drives volume and stage classification, while classifier choice drives survival, histology, and age prediction. Radiomics is competitive for tumor volume, tumor stage and survival (partly due to label-derivation effects for the former); Curia variants reach comparable peak scores for survival; DINOv3 falls slightly short across tasks. Patch and slice aggregation have negligible impact. We recommend Curia with tumor segmentation and a CatBoost head as a safe default, achieving the best mean rank across the three primary clinical tasks, though task-specific selection consistently outperforms any cross-task default. When tumor delineations are unavailable, Curia-2 with lung segmentation and logistic regression offers a competitive alternative. All pipelines use a two-stage design suited to small cohort sizes where end-to-end fine-tuning would risk overfitting.

Accurate fetal birth weight (FBW) estimation shortly before delivery is clinically valuable yet challenging due to its reliance on operator expertise, particularly in low-resource settings. To reduce this reliance, we study near-term birth-weight regression from blind-sweep ultrasound (US) videos acquired within 48 hours prior to delivery, with post-delivery weighing as ground truth. Accordingly, we propose a foundation model-driven key anatomy frame selection framework that enables accurate FBW regression despite the absence of plane constraints in blind sweeps. Our highlights are as follows: (1) We believe this is the first work to estimate FBW using blind-sweep US videos, enabling operator-independent assessment. (2) An Anatomy-Guided Frame Selection module equipped with a vision-language foundation model is proposed for keyframe collection in unconstrained sweeps. (3) A Redundancy-Aware Feature Compression module is designed to compress frame features while preserving task-relevant information, alleviating temporal redundancy. Extensively validated on prospectively collected data from 839 patients, our method achieves an MAE of 161.3 g, with 90.23% and 100% of cases falling within 10% and 15% absolute percentage error, outperforming typical Hadlock estimation and strong competitors. Codes are available at https://github.com/ouleoule/BlindSweep-EBW.

Diffusion MRI probes brain microstructure with particular sensitivity to early cerebrovascular and neurodegenerative changes. Neurite Orientation Dispersion and Density Imaging (NODDI) decomposes the diffusion signal into three biophysically interpretable maps: neurite density index (NDI), orientation dispersion index (ODI), and free water fraction (FWF), capturing neurite packing, fiber coherence, and extracellular fluid. These 3D maps offer a rich substrate for transferable microstructural representations, yet integrating them is challenging: standard representation learning struggles to disentangle the unique information in each map from their shared and synergistic interactions. We present BrainFIBRE, the first foundation model for brain microstructure, pretrained on NODDI-derived maps from 55,592 UK Biobank participants. We propose Self-supervised Partial Information Decomposition (SPID), which extends PID-guided multimodal learning to the self-supervised regime for the first time. A novel Counterfactual Candidate Construction (CCC) paradigm perturbs inter-modality alignment through modality dropping and swapping, providing the contrastive signal for a Mixture-of-Experts architecture to disentangle unique, synergistic, and redundant information without any downstream label. On both Caucasian and Asian cohorts, BrainFIBRE achieves state-of-the-art performance across diverse tasks predicting age, sex, cerebrovascular and neurodegenerative markers, and cognition, while yielding neurobiologically interpretable representations that reveal task- and cohort-specific interaction patterns. BrainFIBRE establishes a versatile foundation for neuroimaging analysis at the microstructural level.

Image-guided therapies, including radiotherapy, biopsy and deep brain stimulation, rely on real-time targeting of anatomical structures. However, in the presence of motion, imaging latencies create a temporal misalignment between observed and true anatomy, compromising treatment accuracy. Artificial intelligence-based frameworks have increasingly been presented to close this latency gap, but leading personalised models can fail due to a lack of stable anatomical grounding. Foundation models can provide grounded behaviour, but they do not adapt to real-time, individual patient dynamics. Here we introduce a closed-loop coupling framework that synergises patient-specific temporal prediction with continuous segmentation-based anatomical interpretation from a foundation model. A personalised model predicts future anatomy to compensate for system latency, while a streaming foundation model provides anatomical supervision used to continuously update the temporal predictor in real time during treatment. We validate the framework using a digital phantom and intrafraction magnetic resonance imaging (MRI) from patients undergoing MRI-guided radiotherapy. For a prediction horizon of 400 ms, the proposed method improves anatomical prediction and reduces dosimetric error compared with existing approaches, within clinically relevant latency constraints. These results establish closed-loop coupling as a general strategy for real-time image-guided intervention.

In the era of satellite constellations, multi-view optical satellite imagery is pivotal for Earth Observation (EO) and high-quality Digital Surface Model (DSM) reconstruction. Although feed-forward 3D foundation models have transformed computer vision, their deployment in satellite remote sensing is inherently constrained by the structural discrepancy between implicit perspective assumptions and explicit orbital pushbroom geometry. This geometric incongruity is further compounded by pronounced view-set heterogeneity. We present EO-VGGT, a framework that adapts a frozen perspective-driven model to orbital observations via explicit physical geometry embedding.First, the Geometry-Correlation Constrained Selection (GCCS) strategy prunes sub-optimal observations by balancing geometric diversity and radiometric consistency to optimize the input sequence. Second, a Sensor-Ray Encoder (SRE) parameterizes pixel-level pushbroom lines of sight derived from the Rational Function Model (RFM) into high-dimensional space-geometric tokens, reconciling the mathematical discrepancy between central projection and orbital kinematics. Third, a lightweight Ray-Pointing-Aware Adapter (RPAA) employs gated residual blocks to integrate these tokens directly into the frozen transformer backbone. Our findings underscore that integrating explicit physical geometry with optimized view selection is essential for robust feed-forward satellite 3D reconstruction.

Accurate energy demand forecasting is essential for the reliable operation and planning of modern sustainable energy systems. Spatial-temporal graph neural networks (STGNNs) have recently achieved strong performance in point forecasting by jointly modeling temporal dynamics and relational dependencies across interconnected energy nodes. However, in real-world energy systems, accurate point forecasts alone are insufficient, as operators also require reliable uncertainty estimates to support risk-aware decision-making, grid stability, and operational planning under uncertainty. Conformal prediction provides a principled and model-agnostic framework for uncertainty quantification with statistical coverage guarantees, making it particularly attractive for safety-critical energy applications. However, existing conformal prediction approaches often fail to fully capture the complex spatial-temporal structure of energy systems. To address these limitations, we propose STOIC (Spatial-Temporal Graph Conformal Prediction with In-Context Learning), a novel framework that integrates graph-based forecasting with the zero-shot calibration capabilities of tabular foundation models. STOIC first generates point forecasts using an STGNN and subsequently reformulates spatial-temporal residuals into a tabular representation suitable for in-context learning. Leveraging a tabular foundation model, STOIC calibrates prediction intervals without task-specific retraining, effectively capturing both sequential and relational dependencies. We evaluate STOIC on five diverse benchmarks, including synthetic simulations as well as real-world electricity and district heating networks. Across all datasets, STOIC consistently outperforms existing conformal prediction baselines, delivering more reliable and robust uncertainty estimates for complex graph-structured energy time series.

The wave of AI-native applications is moving shopping beyond page- and feed-based browsing toward intent-driven experiences orchestrated by LLM agents. A common design wraps an LLM around existing search and recommendation pipelines, forcing complex intents through low-bandwidth retrieval or ranking interfaces and leaving a gap between language understanding and item-space fulfillment. Generative recommendation gives LLMs a direct item-space interface through semantic IDs (SIDs), but existing models mainly generate candidates for retrieval rather than translate flexible intents into item-space outcomes. We propose ShopX to address this bottleneck by unifying intent understanding, execution planning, and flexible SID-native item-space operations into a single foundation model. We deploy ShopX in agentic shopping workflows through a model-native item-fulfillment framework with a serving harness that defines a model-facing action protocol and exposes support surfaces for context access, catalog grounding, and state management. Within this framework, ShopX plans and composes SID-based item-space operations such as SID beam-search retrieval, listwise ranking, or product bundling. This model-centric design reduces lossy hand-offs between agent orchestration and item-space execution. To build ShopX, we design semantically recoverable, LLM-operable SIDs and a training recipe that equips a general LLM for flexible multi-turn item-space fulfillment while retaining the knowledge and instruction-following abilities needed by a shopping agent. We evaluate the ShopX framework against tool-mediated agentic systems on single- and multi-turn fulfillment tasks derived from anonymized Taobao production logs, showing that model-native fulfillment improves overall framework behavior, especially on complex or ambiguous requests.

Joint OFDM-RIS optimization for 6G is a mixed-integer nonlinear programming (MINLP) problem covering sum-rate maximization, energy efficiency, max-min fairness, and peak-to-average power ratio (PAPR)-constrained objectives. Seventy-eight joint OFDM-RIS optimization works published between 2021 and 2026 are surveyed. No standardized benchmark exists, and cross-paper comparisons remain infeasible. This survey classifies these works into four paradigms: (I) model-based convex relaxation, (II) heuristic and metaheuristic search, (III) deep reinforcement and unsupervised learning, and (IV) emerging methods including foundation models (FM), diffusion-based generative AI, and quantum optimization. A literature synthesis of self-reported benchmarks shows that ML-based methods (Paradigm~III) report 95-99% of model-based spectral efficiency at 10^2-10^4 x faster per-inference runtime (method-pair dependent; literature values are self-reported and exclude ML pre-training cost). A companion tutorial benchmark at N=16, N=64, and N=128 reveals a critical scaling property: GPU-based neural network inference (DDQN, PPO, graph neural network (GNN), unsupervised DL) is N-invariant, with identical runtime at N=16 and N=128, while iterative solvers (AO+SCA, PSO) scale polynomially. Energy efficiency (P2) and PAPR-constrained (P4) benchmarks are deferred to future work with standardized power models and waveform generators. Six open challenges emerge from the synthesis: the cross-paradigm benchmark deficit, real-world hardware-constrained deployment, joint waveform-RIS optimization for doubly-dispersive channels, multi-objective PAPR trade-offs, LLM safety in live network control, and diminishing returns of standalone heuristics. We specify requirements for a standardized benchmark. This study serves as a roadmap for researchers and practitioners working on joint OFDM-RIS optimization in 6G networks.

Foundation models are increasingly integrated into embodied intelligence systems, but directly assigning them structured prediction tasks requires precise geometric and numerical estimation, where specialized models often remain stronger. This capability mismatch raises a key question: should foundation models replace task-specific predictors, or should they collaborate through tasks better aligned with their strengths? We propose FAT, a foundation-model-augmented task-specific reasoning framework that treats collaboration as task decomposition rather than model replacement. FAT decomposes structured prediction into specialist prediction, information-space reconstruction, and foundation-model proxy reasoning. The specialist generates geometrically and physically valid hypotheses in the native output space, while the foundation model performs a bounded proxy task, such as selection or verification, over reconstructed multimodal candidates. We instantiate this principle as ProxySelect with a vision--language model. Across 2D object detection, 3D object detection, trajectory prediction, and semantic segmentation, ProxySelect consistently improves specialized baselines and substantially outperforms direct foundation-model regression at lower computational cost. These results suggest a general collaboration principle: specialized models preserve task-specific structure, while foundation models refine their hypotheses through contextual proxy reasoning.

Text-to-3D systems can now synthesize a model from a single sentence, yet the result is a shape to render, not a design to edit. We present Arko-T, a 4B-parameter text-to-design model that maps natural-language intent directly into executable, parametric CAD programs. Rather than optimizing for code executability alone, Arko-T aligns every stage of the pipeline to a formal notion of design state, so that data curation, code normalization, and execution-grounded supervision all work to preserve the features, parameters, and construction logic that make a CAD artifact editable. Benchmarked against seven frontier LLMs across 12 metrics, Arko-T attains the best score on 8 and the second-best on 3 more, at roughly one-tenth the per-benchmark cost. The results suggest that targeted design-level training at moderate scale can match frontier general-purpose models on structured CAD generation.

Foundation models for predictive machine learning on tabular data have recently gained significant traction in academia and industry. Research communities across disciplines are increasingly evaluating tabular foundation models on diverse datasets and tasks. However, these task- and discipline-specific evaluations remain largely inaccessible to model researchers because benchmark software and evaluation protocols are fragmented. As a result, model researchers rely on standard benchmarks, which are mostly defined for tasks where tabular foundation models already excel. The most challenging scenarios are excluded, limiting meaningful progress in the field by focusing on marginal improvements on IID data rather than on broader, more demanding challenges. To overcome this, we introduce BeyondArena, the first unified holistic benchmark for tabular data that supports diverse task types (IID, temporal, grouped), across sample size and feature dimensionality scales, with diverse feature types (with text, with high cardinality) from a broad range of disciplines. To enable unified benchmarking beyond standard benchmarks, we introduce Data Foundry, a Python framework and metadata schema for curating tabular datasets for predictive machine learning. Our results across 11 models and 142 curated datasets show that existing tabular foundation models excel on tiny- to medium-sized IID data, while traditional tree-based and deep learning models still dominate on non-IID, large, and high-dimensional datasets. BeyondArena guides model research for the most demanding challenges in tabular data, enabling progress towards truly foundational tabular models.

Tabular foundation models have advanced deep learning for tabular data by delivering strong default performance across many small and medium tasks. Yet in niche domains, where data is scarce, high-dimensional, and shifted from the pretraining distribution, they may still fail to outperform carefully designed domain-specific methods. Many such domains also provide curated relational knowledge in the form of knowledge graphs and knowledge banks, but how to use this knowledge to improve and steer \textit{small} specialist tabular foundation models remains unclear. We address this problem through \textbf{Know}ledge-informed fine-tuning of \textbf{s}mall \textbf{T}abular \textbf{F}oundation \textbf{M}odels (\modelname). Specifically, we study nanoscale TabPFN- and TabICL-style variants, pretrained under controlled synthetic prior families and adapted using two complementary mechanisms: structural attention priors derived from knowledge graphs and parameter-efficient low-rank updates. We show that injecting domain-specific structural knowledge during fine-tuning yields meaningful gains over vanilla variants in specialist settings, whereas gains on general-domain tasks are marginal. We further observe that continual fine-tuning of frontier models can trigger collapse of pretrained knowledge and mechanisms.

Electroencephalography (EEG) foundation models aim to learn generalizable representations from large-scale brain recordings. However, the role of temporal feature extractors and whether pretrained time-series foundation models (TSFMs) can be effectively transferred to this setting remains underexplored. We conduct a controlled comparison of three temporal feature extraction strategies, including a linear baseline, a convolutional encoder, and a frozen pretrained TSFM (MOMENT), within a unified EEG foundation model. We evaluate their impact on representation quality using two downstream tasks: motor imagery and emotion recognition. Results reveal different trends across the evaluated benchmarks. On the motor imagery dataset, simple temporal representations perform competitively, whereas the emotion dataset benefits from richer temporal modeling. Although not specifically adapted to EEG, the pretrained TSFM serves as an effective temporal feature extractor, suggesting that general-purpose time-series representations can be transferred as frozen temporal feature extractors within EEG foundation models.

Data, as the fundamental substrate of modern intelligence, has greatly driven the development of current foundation models. Naturally, researchers aim to extend this paradigm to the domain of GUI agents, hoping to build strong GUI agents through a similar paradigm. However, GUI agent data cannot be directly harvested from the internet, making it costly and difficult to collect at scale. As a result, current GUI agents suffer from poor cross-device generalization and limited visual grounding ability for fine-grained GUI elements. As an attempt to address data challenge in GUI agents, we propose GUICrafter, a weakly-supervised GUI agent leveraging massive unannotated screenshots to substantially reduce the reliance on expensive human annotations. GUICrafter explores a curriculum learning framework for training GUI agents through two progressive stages. First, the model learns visual grounding from large-scale unannotated screenshots and webpages, leveraging the rich contextual signals inherent in GUI interactions without human annotations. Then, in Stage 2, we leverage a small amount of high-quality data to calibrate the model via reinforcement learning. Experiments show that GUICrafter achieves competitive, or even superior, performance to advanced systems like UI-TARS while using only 0.1% of its data. Furthermore, under the same amount of annotated data, GUICrafter surpasses all previous methods such as GUI-R1. Code, data, and models are available at https://github.com/fansunqi/GUICrafter.

Geospatial foundation models pretrained on satellite imagery promise broad generalization across remote sensing tasks and regions, but their geographic transferability has not been systematically tested, especially in agriculture applications. This paper presents a controlled benchmark that evaluates three models, Prithvi, SpectralGPT, and SatMAE, on multi-temporal crop segmentation and change detection across four U.S. states, Iowa, North Carolina, California, and Minnesota. By assigning each train, validation, and test split to a separate region, we measure how well each model transfers to land it has not seen. All three degrade sharply under regional distribution shift, predicting only the most common crops while missing rare ones. We further find that fitting these models to a shared input format affects each one differently, which complicates direct architectural comparison. These results expose key limitations of current geospatial foundation models for agriculture and point to region aware evaluation as a necessary standard.

While wireless foundation models (FMs) are demonstrating strong potential to enable AI-Native 6G networks, their high computational cost remains a critical barrier to deployment. The large computational cost stems from the rigid, full-depth execution of the FM backbone for every task, a process we show is not only inefficient but can also degrade performance on unseen out-of-distribution (OOD) tasks. In this paper, we propose a novel early-exit FM framework that attaches lightweight, per-task heads, at the most appropriate exit-stage of a frozen wireless FM encoder, enabling variable-depth inference tailored to each task's preferred representation depth. Our results demonstrate that these intermediate-layer features not only speed-up inference significantly (up to 93% fewer FLOPs), but also provide more transferable representations that exceed the full encoder accuracy on unseen tasks. We further demonstrate that a simple fixed-exit strategy per task is more effective than traditional early-exiting policies that route different samples to different exits based on their perceived difficulty levels.

A faithful 3D world representation should account for layered geometry, where a single camera ray may contain multiple visible and geometrically valid surfaces. Monocular depth estimation, however, reduces this structure to one scalar depth per pixel. Transparent scenes make this ambiguity measurable: the same ray can pass through foreground glass and observe the background, turning the supervised target into a convention of annotation, data, and training rather than a scene-intrinsic truth. A learned predictor exposes this convention as its depth-layer preference. We introduce MultiDepth-3k (MD-3k), a sparse two-layer ordinal benchmark for measuring depth-layer preference and multi-layer spatial relationship accuracy (ML-SRA). On MD-3k, leading depth foundation models exhibit diverse layer preferences under standard RGB input, showing that the same layered geometry can be resolved differently across models. We further find that Laplacian Visual Prompting (LVP), a training-free spectral input transformation, can substantially change the reported layer for certain frozen models. The strongest RGB/LVP pair, DAv2-L, reaches 75.5% ML-SRA. These results suggest that depth foundation models may express complementary geometric hypotheses that standard RGB inference leaves unexpressed. We invite the community to rethink depth supervision and evaluation through an ambiguity-aware lens, where multiple valid 3D interpretations are treated as geometric structure to be measured, preserved, and expressed.

This work examines perturbation generalization in spatial foundation-model embeddings derived from fluorescence microscopy images. Although these models can discriminate drug conditions accurately, it remains unclear whether the learned representations reflect patterns consistent with expected perturbation axes that transfer across drugs. We introduce SVC-Probe, a perturbation-aware framework that combines Subcellular Embedding Atlas Stability, Mondrian Neighborhood Graphs, and a Foundation Model Perturbation Probe to assess embedding stability, neighborhood rewiring, and centroid prediction under drug treatment. Applied to the CM4AI MDA-MB-468 chemical-perturbation atlas comprising 462 antibody labels and SubCell 1536-dimensional embeddings, SVC-Probe demonstrates that 98.6% three-way condition accuracy does not correlate with reliable cross-drug prediction, with cosine similarity diminishing from 0.944 in-domain to 0.30 under leave-one-drug-out evaluation, constituting a two-drug stress test rather than a general benchmark. Null calibration indicates that raw residual-turnover coupling is largely influenced by generic embedding structure, whereas a drug-specific signal emerges under vorinostat and is consistent with chromatin-related reorganization. In contrast, the paclitaxel axis is not robustly reconstructed, likely due to sparse coverage of microtubule-associated proteins. Together, these results introduce and demonstrate a reusable diagnostic framework for stress-testing spatial virtual-cell representations and indicate that perturbation generalization may serve as a stricter and more informative benchmark than baseline condition discrimination.

Since its initial release in 2020, Darts has become a widely used open-source Python library for time series analysis. A series of foundation models have recently claimed accuracy improvements in zero-shot forecasting, promising a paradigm shift from training custom models to harnessing pre-trained general-purpose forecasters. Foundation models, however, are often released as isolated packages with fragmented interfaces and limited interoperability with common tooling, making joint evaluation and integration within complete pipelines difficult. In Darts, we developed a unified $\texttt{FoundationModel}$ class collection (Chronos-2, TimesFM 2.5, TiRex, PatchTST-FM) that provides standardized, full-cycle forecasting interfaces with minimal external dependencies for integrating foundation models into the ecosystem. Existing Darts pipelines can now use foundation models with only a name change; new pipelines can use them for zero-shot or fine-tuned forecasting, uncertainty estimation, and backtesting, combined with data processing and evaluation tooling, all within a unified framework.

Remote Sensing Foundation Models (RSFMs) have emerged as a powerful alternative to supervised models for Earth Observation, allowing satellites to autonomously trigger high-resolution captures or adjust tasking parameters upon detecting an anomaly, thereby maximizing the utility of the mission's limited power and computational resources. RSFMs are versatile, unified encoders that optimize onboard storage for multiple orbital applications while ensuring high-fidelity feature extraction. In particular, unsupervised change detection with RSFMs offers a well-informed and transformative path for disaster monitoring without expensive labels. In this paper, we present a novel unsupervised detection method based on ResNet (RSFM) + FPN which identifies a wide spectrum of anomalies by detecting subtle semantic shifts in the latent space between successive orbital passes. By relying on an untrained FPN architecture and its intrinsic priors, the system achieves efficient image-level generation and higher resolution mapping with minimal effort (training-free) compared to previous proposals (patch-based, trained). And by replacing tailored models with RSFMs, we can achieve comparable results through an approach that eliminates the need for bespoke training and extensive development effort and adds customization, while ensuring high-performance generalization across diverse terrains and sensors.

Tabular foundation models achieve strong accuracy on choice prediction tasks, but their predictions often violate the economic logic those tasks require: raising a price can increase predicted demand, implied willingness-to-pay estimates are frequently negative or implausible, and unavailable alternatives receive nonzero probability. We propose a two-stage adapter that takes a foundation model's predicted choice probabilities as a precomputed feature and embeds them inside a multinomial logit's utility. In Stage 1, we fit the multinomial logit's structural coefficients by maximum likelihood with sign constraints; in Stage 2, we freeze those coefficients and fit a small neural correction operating on the foundation model's predictions. We prove that this composition exactly preserves the multinomial logit's marginal rate of substitution, so analytically computable value-of-time becomes a mathematical guarantee rather than an empirical accident. Across three datasets and two foundation models, the adapter gains 6.4 percentage points (pp) of test accuracy on average over the multinomial logit and up to 12.8 pp, maintains 100% cost monotonicity, and produces values of time within the published transportation-economics range on the transportation datasets. Performance degrades gracefully under foundation-model context restriction, retaining at least 6 pp of accuracy gain even at 10% of the original foundation-model context.

Artificial intelligence increasingly drives automated scientific discovery, yet contemporary generalist agents lack physical grounding, frequently hallucinating hardware-incompatible designs. Here, we present a physically grounded, multi-agent discovery engine that autonomously architects hardware-compliant computing systems. Anchored by an Evolutionary Knowledge Graph structuring past scientific innovations, the framework extracts an "algorithmic Chain-of-Thought" to transform blind stochastic search into directed structural evolution. Applied to the extreme testbed of foundation model deployment, the engine evolved two hardware-aware compression methodologies surpassing human-engineered heuristics: Q-Enhance mitigates long-context accuracy loss in dense models, and MoE-Salient-AQ outperforms state-of-the-art manual sparse Mixture-of-Experts designs by 3.7% at sub-3-bit regimes. Utilizing a bandwidth-efficient Sensitivity Profile, we successfully deployed a massive 235-billion-parameter model onto a constrained dual-A100 server, reducing memory requirements by 75% with a marginal 0.64% accuracy degradation. By transforming unconstrained combinatorial search into knowledge-driven autonomy, this establishes a scalable hardware-software co-design paradigm for machine-driven discovery within strict physical boundaries.

Online reinforcement learning (RL) agents increasingly depend on knowledge acquired offline to achieve practical efficiency. Originally studied in offline-to-online RL, this paradigm now spans foundation model post-training and embodied intelligence, with prior types expanding from offline datasets and pre-trained policies to increasingly diverse knowledge sources such as multimodal foundation models and generative world models. Offline priors have become central to how deep RL is developed and deployed. However, this reliance introduces a challenge that the prevailing benchmark-driven paradigm cannot resolve: because prior validity varies across deployments and shifts during training, no single approach to managing it is universally optimal, and benchmark rankings offer limited guidance for real-world deployments. Rather than pursuing universal solutions, we argue that the field should shift to diagnosis-driven tension management, in which deployment-specific evidence guides how the learner relates to its priors throughout training, enabling both flexible and adaptive deployment. We support this position with a framework characterizing how priors reshape online optimization through three functional roles, controlled experiments demonstrating help-or-hurt reversals, cross-domain evidence from foundation model post-training to embodied intelligence, and engagement with five substantive counterarguments.

Remote sensing object detection has advanced rapidly with the development of large-scale benchmarks and modern detection architectures. However, existing datasets and detectors remain fragmented. Most benchmarks focus on limited categories, fixed spatial resolutions, or a single sensor, while detectors still struggle to work across different sensors and categorical systems. In this paper, we introduce LEVIRDet-159, the largest and most comprehensive remote sensing object detection dataset to date, with 159 categories, 2.56 million bounding boxes, and 700k fine-grained annotations under a multi-level taxonomy. In each key scale dimension, LEVIRDet-159 exceeds the corresponding largest existing remote sensing object detection dataset, containing approximately (7x) more images, (6x) more object instances, and (4x) more categories. Based on this dataset, we design LEVIRDetNet, a scale-hierarchy-aware detection foundation model for universal remote sensing object detection. LEVIRDetNet couples online visual Ground Sampling Distance (GSD) prediction, GSD-conditioned query modulation and allocation, and a hierarchy-aware detection head for mixed-granularity remote sensing supervision. Under stringent evaluation settings, LEVIRDetNet demonstrates strong cross-domain generalization. Even without target-domain training or fine-tuning, it achieves state-of-the-art detection performance on 9 external benchmarks, improving the strongest fully supervised competing methods by 5.02 mAP on average under each benchmark's primary metric. We hope this study will facilitate the development of strongly generalizable remote sensing object detection across diverse category systems, spatial resolutions, and sensor platforms. The dataset and trained models will be released at https://qinzheyang.github.io/LEVIRDet/, accompanying the final paper.

Respiratory acoustic foundation models (FMs) are benchmarked exclusively on smartphone recordings, yet clinical deployment increasingly targets body-coupled (BC) wearables whose sensors attenuate high-frequency content through tissue and bone, leaving FM reliability uncharacterised. We introduce BCoughBench, evaluating five FMs (OPERA-CT/CE/GT, HeAR, M2D+Resp) on nine classification tasks (AUROC, sensitivity at 95% specificity, Expected Calibration Error) and three age regression tasks (MAE vs. a mean-predictor baseline) across five EBEN-simulated BC sensor conditions on five labeled cough datasets. Mean AUROC declines from 0.785 (smartphone) to 0.689-0.723, degrading most under temple vibration pickup ($Δ$ = -0.096) and least under the soft in-ear ($Δ$ = -0.062). No FM meets the clinical sensitivity threshold (Se@Sp95 $\geq$ 0.20) on most disease tasks under any BC sensor. Sex classification on the CIDRZ cohort collapses (AUROC 0.954 to 0.596-0.628, $Δ$ = -0.341) while COVID detection is nearly unaffected ($Δ$ = -0.004). Age regression is robust, improving under the forehead accelerometer on CoughVID (MAE 9.61 to 8.97 yr); HeAR leads on regression and demographic tasks, M2D+Resp on disease and characteristic tasks. BCoughBench provides a reproducible framework for FM evaluation under wearable conditions.

Personalization in wearable-based stress detection remains challenging due to substantial inter-individual variability in physiological and behavioral responses. While traditional approaches rely on user-specific fine-tuning or costly self-supervised pre-training on large datasets, we propose a lightweight alternative based on retrieval-augmented personalization. Our method leverages frozen, out-of-domain foundation models to retrieve similar patterns from a target user's history and encode them into a compact personalized embedding that modulates representations extracted by a lightweight transformer network. We evaluate our approach on the WESAD stress detection dataset with N=15 users, comprising wrist-worn physiological (EDA, BVP, temperature) and activity (accelerometer) signals, and report gains of +3.92% in accuracy and +4.76% in macro F1-score over a non-personalized transformer baseline, approaching supervised fine-tuning performance without requiring any labeled user data. We further show that temporal retrieval, where only prior user samples are available, achieves performance close to full intra-user retrieval, demonstrating robustness to limited user history. Finally, we explore personalization in a cross-dataset retrieval setting, leveraging embeddings from the K-Emocon dataset to personalize representations for stress detection on the WESAD dataset.

Due to the wide use of graph-structured data in different fields of industry and science, the development of Graph Foundation Models (GFMs) has recently attracted a lot of attention. While many different types of models are called GFMs, particular interest has been paid to GFMs designed for node property prediction tasks, which is one of the most popular settings in Graph ML with lots of real-world applications from fraud detection in financial and social networks to recommendation systems for e-commerce and user-generated content platforms. While a number of GFMs for this task have been recently proposed, the field has not converged to a unified evaluation setting, and different works evaluate their models in widely different ways, preventing reliable comparison of GFMs with each other and with other types of models. In this work, we conduct a fair and rigorous reevaluation of 9 recent GFMs for node property prediction, comparing them to strong Graph Neural Network (GNN) baselines. We find that, among these GFMs, only the most recent ones based on the Prior-data Fitted Networks paradigm outperform well-tuned GNNs in predictive performance, although at a higher inference cost.

Operating in complex real-world environments requires robots to understand their surroundings on a functional semantic level. This demands a detailed multi-layer world model capturing the complex relations of its surroundings. Hierarchical 3D scene graphs address this challenge by integrating geometric, semantic, and relational data within a unified spatial framework. However, current 3D scene graph approaches often restrict themselves to rigid structures of pre-determined relationship classes, mostly neglecting important semantic connections, like causal connections or environmental contexts. This paper explores the potential of foundation models to build forests of 3D scene graphs with open semantic relationships to improve scene understanding and robotic task execution. We propose a method where instance-specific concept-nodes and relationships are first identified by a VLM and extended upon by a LLM, inferring broader, more abstract concept-nodes and relationships through reasoning. These object-nodes, concept-nodes, and relationships are then assembled into a forest of hierarchical 3D scene graphs, enhanced with concept-nodes to represent abstract concepts. Evaluations were conducted on the uHumans2 and ScanNet indoor dataset, validating the accuracy and relevance of the generated relationships. Downstream suitability of scene-graph forests for robotics applications is demonstrated in an open-vocabulary object-retrieval task utilizing both ScanNet data and a real-world indoor deployment using a Boston Dynamics Spot. This paper leverages foundation models to create more expressive, semantically deep 3D hierarchical scene graphs and demonstrates their potential to advance semantic and environmental understanding in robotics.

Data scarcity is a fundamental challenge in developing AI and foundation models for agricultural robots. Existing open-source data platforms do not provide sufficient incentives for data providers so long-term data collection remains difficult. Furthermore, advances in generative AI have introduced a new challenge of verifying that collected data genuinely originates from real farm environments. We propose an ecosystem for the sustainable collection and distribution of real farm data, integrating automatic pricing driven by demand and rarity, revenue sharing that distributes earnings to farmers as an incentive to keep providing data, and data authenticity guarantees through authenticated device uploads. To demonstrate the economic sustainability for all three parties among farmers, AI companies, and the platform, we estimate the economic value that agricultural robots stand to generate.

Accurate identification of the epileptogenic zone (EZ) is essential for seizure freedom after resective surgery in drug-resistant epilepsy, yet seizure freedom rates remain below 50%. We developed EpiiSLM, a dual foundation model system for EZ identification with stereo-electroencephalography (sEEG), by training a signal foundation model on 104,990 minutes of sEEG recordings from the Montreal Neurological Institute & Hospital, while leveraging all recordings regardless of surgical outcome and anchoring EZ biomarker extraction on non-epileptic signals. A language foundation model then integrates sEEG-derived outputs with multimodal clinical information to produce interpretable predictions. Under leave-one-patient-out evaluation, EpiiSLM achieved 0.978 contact-level positive predictive value (PPV), outperforming the seizure onset zone(SOZ)-as-EZ baseline by 15.1% (p < 0.05), and 100% region-level accuracy; on an external dataset, EpiiSLM achieved 0.857 contact-level PPV. EpiiSLM requires only one night of interictal sleep data, suggesting potential to reduce invasive sEEG monitoring duration and improve surgical outcomes.

Accurate recognition of anatomical structures is essential for safe and effective minimally invasive surgery (MIS), yet it remains underexplored in surgical computer vision due to limited annotated data and methods tailored primarily to natural scenes. In this work, we present a combined dataset and model framework to advance anatomy-aware perception in MIS. First, we introduce ATLAS-120k, a large-scale clip-level semantic segmentation dataset comprising over 120,000 annotated frames from 100 surgical videos spanning 14 procedures and multiple modalities, including laparoscopic and robot-assisted surgery. The dataset captures substantial procedural variability and was created using a scalable annotation pipeline that integrates expert manual labeling, automated propagation, iterative refinement, and surgeon verification to ensure high-quality annotations. Second, we propose ATLAS (Anatomy Recognition with Context Learning using Foundation Representations), a video semantic segmentation model specifically designed for surgical anatomy recognition. Unlike conventional approaches that emphasize object tracking, ATLAS leverages foundation-model embeddings together with lightweight temporal reasoning to incorporate contextual cues such as procedure type, surgical phase, and short-term visual memory. This design enables temporally consistent and accurate predictions while maintaining real-time feasibility. Together, the dataset and model establish a practical foundation for robust surgical scene understanding and support the development of clinically applicable guidance systems for minimally invasive surgery. The models, dataset annotations and annotation platform are publicly available at: https://github.com/TimJaspers0801/ATLAS.

Cell segmentation is critical for computational pathology and biomedical discovery. While recent Vision Foundation Models (VFMs) have demonstrated remarkable universal feature representations, unlocking their full potential for cellular imaging is currently bottlenecked by resource-intensive adaptation paradigms. Existing methods typically rely on fine-tuning heavy visual encoders, leading to extensive computational overhead and a dependency on large-scale annotations. To address this, we propose the EffiCell-Seg framework for highly efficient cell segmentation without re-training the visual encoder. Our core insight is that pretrained VFMs intrinsically encode complementary structural priors: global saliency for localizing potential cells, and local morphological patterns for delineating cellular structures. To harness these priors, we devise a Cell Structure Prompt Encoder (CSP-Encoder) that synthesizes semantic-aware saliency and principal morphological features from frozen VFM representations into explicit structural prior maps. Moreover, we propose a Synergistic Mask Decoder (SM-Decoder) that enforces contextual consistency by jointly predicting geometric distance fields and semantic maps via mutual cross-guidance. Extensive experiments demonstrate that EffiCell-Seg outperforms state-of-the-art methods across diverse cell imaging modalities while requiring only ~5M trainable parameters, over 130x fewer than fully fine-tuned VFM counterparts. The code is available at https://github.com/xq141839/EffiCell-Seg.

Recent speech research involves increasingly large datasets, complex models, and diverse experimental workflows. However, existing frameworks require substantial engineering effort to support such experiments. We present ESPnet3, a speech and audio research framework built on a modular system architecture with configuration-driven dataset composition and unified Python-based workflows. ESPnet3 introduces a DataOrganizer abstraction for flexible dataset integration and dataset sharding for memory-efficient large-scale training, while allowing recipe-specific logic through lightweight stage overrides. In OWSM pre-training experiments, ESPnet3 reduces per-epoch training time by \emph{21.1 minutes} compared to ESPnet2 and achieves \emph{>80% GPU utilization} in multi-node training. Fine-tuning experiments show that new models and datasets can be integrated with around \emph{46 lines of additional code}. ESPnet3 will be publicly released with model checkpoints and training logs.

Vision foundation models have substantially advanced computer vision, enabling state-of-the-art performance in zero- and few-shot settings. They have been successfully applied to biomedical imaging tasks ranging from organ segmentation in computed tomography to cell segmentation in light microscopy. Electron microscopy (EM) is a central modality for analyzing cellular ultrastructure due to its nanometer-scale resolution. However, the application of foundation models in EM has so far been limited to specific organelles, such as mitochondria, largely due to the diversity of segmentation tasks and the scarcity of comprehensively annotated data. As a result, EM segmentation still predominantly relies on supervised learning, requiring extensive manual annotation and limiting ultrastructural analysis. To address this gap, we propose $μ$Match, a framework for semi-supervised learning and domain adaptation that leverages foundation models. We implement state-of-the-art student-teacher-based methods and evaluate multiple foundation models (SAM, SAM2, $μ$SAM, DINOv2/v3) on challenging EM tasks, including mitochondrion, nucleus, and neurite segmentation. Our results demonstrate consistent improvements over strong baselines and highlight a path toward substantially reducing the annotation effort in EM.

Evaluating generalist robot manipulation policies in the real world is expensive, slow, and difficult to scale. Action-conditioned video world models offer a scalable alternative by simulating policy rollouts. Autoregressive rollouts accumulate compounding errors, observations across multiple camera views must remain mutually consistent, and the evaluator must generalize to policies whose behaviors lie outside the training distribution. We address these challenges with SC3-Eval, a self-consistent video generation recipe that adapts a pre-trained video foundation model into an accurate policy evaluator by enforcing three complementary forms of consistency. First, forward-inverse dynamics consistency jointly trains the model to predict frames from actions and to recover actions from frames, anchoring generated rollouts to a physically plausible action manifold and counteracting the drift a forward-only model cannot penalize. Second, cross-view consistency trains the model to inpaint each camera view from the other, keeping the multi-camera observation coherent over long rollouts without any explicit memory mechanism. Third, test-time consistency reuses the inverse dynamics mode at inference as a per-action-chunk uncertainty signal that terminates rollouts whose generated frames drift away from the requested actions. We also demonstrate SC3-Eval rollouts reproduce the failure modes that policies exhibit in real-world rollouts, supporting fine-grained diagnostic comparison rather than aggregate ranking alone. Across seven real-world vision-language-action policies, SC3-Eval attains a closed-loop Pearson correlation of $0.929$ and MMRV of $0.119$, outperforming three strong prior video-model-based baselines, and generalizes to new tasks.

A rule-based logic solver resolves every instance in our benchmark in under 50 microseconds with 100% accuracy; the best frontier language model reaches 65% at best and drops to 23.5% under rendering-robust evaluation (worst case over four surface renderings). We introduce DeFAb (Defeasible Abduction Benchmark), a dataset and generation pipeline that converts four decades of publicly funded knowledge bases into formally grounded instances for defeasible abduction: constructing hypotheses that explain anomalies by overriding defaults while preserving unrelated expectations. Because every hypothesis must pass polynomial-time checks for valid derivation, conservativity, and minimality, DeFAb makes logical rigor the instrument for measuring creativity and theoretical reasoning, scoring the disciplined construction of theory revisions rather than fluent but theory-destroying prose. The pipeline pairs taxonomic hierarchies (OpenCyc, YAGO, Wikidata) with behavioral property graphs (ConceptNet, UMLS) to produce 372,648+ instances across 33.75M materialized rules from 18 sources, in three levels with polynomial-time verifiable gold standards. Four frontier models do not reliably internalize defeasible reasoning: rendering-robust Level 2 accuracy is 7.8-23.5%; chain-of-thought variance (~36 pp) exceeds any inter-model gap; and a matched contamination control isolates a +19.4 pp Level 3 gap. We further release DeFAb-Hard (a 235-instance Level 3 difficulty variant; best model 53.3% vs 100% symbolic) and CONJURE (a kernel-verified transformative-creativity variant of 560 Lean 4/Mathlib instances whose gold answers are definitions the proof kernel did not previously contain, judge-free verifier; a pilot finds zero novel concepts). The same verifier doubles as an exact reward for preference optimization (DPO, RLVR/GRPO). Released under MIT at https://huggingface.co/datasets/PatrickAllenCooper/DeFAb.

Knowledge graph (KG) foundation models (KGFMs) are zero-shot generalizers: trained once, they can predict links on unseen graphs without retraining. However, understanding when and how they can robustly generalize across KGs is still an open question. In this paper, we shed some light on their generalization mechanisms highlighting how their performance on unseen KGs is not uniform when it comes to partially seen links, which we call half-links. In fact, we show that to predict a test triple $(h,r,t)$ it might suffice in practice to have observed the half-link $(h,r)$ or $(r,t)$ in the inference graph. This yields a taxonomy of four scenarios when combinations of these half-links are observed or not. In a rigorous stratified analysis over these scenarios, we reveal that SoTA KGFMs use seen half links for predictions, while unseen half-links pose different challenges. As such, our finer-grained taxonomy can be a diagnostic protocol for robust KGFM generalization and highlights where novel KGFMs can improve.

Foundation models in language and multimodality achieve strong generalization by aligning heterogeneous data under a unified formulation and training at scale. In this report, we investigate whether this scaling recipe can be applied to robotic manipulation to achieve genuine generalization. This is challenging because, unlike text, manipulation data is heterogeneous by nature, expensive to collect, and narrow in diversity, making alignment and scale simultaneously difficult. We present Qwen-RobotManip, a generalizable Vision-Language-Action foundation model built on Qwen-VL. Qwen-RobotManip introduces a unified alignment framework across the representation, motion, and behavioral dimensions of manipulation, making large-scale multi-source training coherent rather than conflicting. This alignment capability in turn enables Qwen-RobotManip to absorb manipulation data at a scale that prior training regimes could not sustain. A human-to-robot synthesis pipeline converts egocentric hand demonstrations into robot trajectories across 15 platforms, and a rigorous curation pipeline harmonizes heterogeneous datasets. Using only open-source datasets and human videos without proprietary data collection, Qwen-RobotManip constructs a ~38,100-hour pretraining corpus and exhibits emergent generalization capabilities, including zero-shot instruction following, robustness to perturbations, reactive error recovery, and cross-embodiment transfer. We find that standard benchmarks fail to capture pretraining quality and instead adopt OOD settings including RoboCasa365, LIBERO-Plus, EBench, RoboTwin-Clean2Rand, RoboTwin-IF, and RoboTwin-XE. Qwen-RobotManip substantially outperforms prior state-of-the-art models, including $π$0.5, across all OOD settings, ranks 1st in RoboChallenge with a 20% relative improvement, and is validated on real-robot platforms including AgileX ALOHA, Franka, UR, and ARX.

Standardized evaluation protocols are indispensable for robust benchmarking in remote sensing, particularly as foundation features are increasingly transferred across diverse sensors and complex imaging geometries. In satellite multi-view reconstruction, conventional evaluations relying on unconstrained 2D global matching are often misleading. The Rational Function Model (RFM) and its Rational Polynomial Coefficients (RPC) dictate a curved, height-dependent epipolar geometry that render flat 2D search spaces physically inconsistent. We propose a geometry-faithful and reproducible protocol tailored for the RPC framework. Our approach integrates an RPC-projected 3D consistency metric with a geometry-constrained dense matching proxy, specifically evaluating whether similarity responses remain localized and unique under physically plausible search manifolds. A pivotal finding of our joint reporting strategy is the decoupling of semantic agreement and geometric localization: high cross-view similarity at a projected 3D point does not guarantee reliable matchability in practical inference. Our benchmark demonstrates that incorporating geometric constraints is fundamental to the problem definition in satellite imagery. Furthermore, we show that state-of-the-art 2D backbones remain remarkably competitive against specialized 3D-aware models when subjected to this RPC-consistent evaluation.

Foundation models (FMs) have emerged as powerful representation extractors for medical data, yet their generalizability to datasets under distribution shift remains underexplored. This work systematically evaluates FM-based representations on a suite of computational pathology tasks across two real-world commercial cohorts, IH-BC and IH-NSCLC, drawn from the licensed in-house (IH) oncology dataset. The analysis focuses on two modalities, whole-slide images and transcriptomic profiles, drawn from the IH multimodal data. We first benchmark unimodal probing performance across five FMs on eight downstream classification tasks, and find that image and omics representations carry complementary predictive signals. Then we investigate whether multimodal fusion can yield additional gains over unimodal baselines by comparing three image-omics fusion strategies built on paired representations. The trustworthiness of selected unimodal and multimodal pipelines is further assessed through conformal prediction. Our results show that FM representations achieve competitive performance on out-of-distribution data and that multimodal fusion helps mainly when no single modality dominates the signal. Conformal prediction reveals that in the majority of cases where a point prediction fails, the true diagnosis remains recoverable within the prediction set, reinforcing the value of uncertainty-aware inference for clinical support.

Foundation models are now used in settings where the prompts they receive can change quickly. Users change, topics change, policies change, and the model may suddenly face a kind of request that was rare in the calibration data. This makes fixed calibration risky. Conformal prediction and conformal risk control give model-agnostic ways to control error, but they work best when the calibration data still look like the future data. This paper develops PromptShift CRC, a drift-aware conformal risk control method for foundation-model outputs under prompt and domain shift. The method embeds prompts and responses, measures how far the current prompt stream has moved from the calibration pool, gives more weight to relevant or recent calibration examples, and updates the risk level online after observed violations. It reports three practical diagnostics: realized risk error, prompt drift, and effective calibration size. We give conditions under which the method controls risk up to terms for distribution mismatch and weighted quantile uncertainty. In a synthetic prompt-shift benchmark, static conformal risk control fails sharply after drift, while PromptShift-CRC gives the best coverage among the adaptive baselines considered. We then evaluate the same calibration layer on public benchmark derived streams for question answering, toxicity, summarization factuality, and long-context hallucination risk

Vision foundation models (VFMs) have demonstrated strong robustness and transferability across a wide range of visual tasks. However, each model typically encodes strong inductive biases shaped by its pre-training objective and data domain, resulting in fragmented yet complementary visual knowledge. As a result, a single model often struggles to capture the diverse visual representations required across multiple dense prediction tasks. To address this limitation, we propose TIGER (Task-Instruction-Guided Expert Routing), a framework that coordinates multiple heterogeneous VFMs for multi-task dense prediction. Instead of naively aggregating expert features, TIGER leverages natural-language task instructions to guide a routing network that assigns token-level expert weights conditioned on task semantics, enabling adaptive integration of complementary expert features. TIGER further introduces a counterfactual loss that aligns routing decisions with each expert's causal contribution by measuring prediction changes when experts are excluded, encouraging more reliable and interpretable routing. We evaluate TIGER on two multi-task dense prediction benchmarks, NYUD-v2 and Pascal Context, where it consistently outperforms recent multi-task learning baselines while keeping all VFMs frozen. These results demonstrate that combining instruction-guided expert routing with counterfactual causal alignment enables effective coordination of heterogeneous vision foundation models.

Electronic health record foundation models typically treat ICD diagnosis codes as flat tokens, overlooking the clinically meaningful hierarchical structure that captures disease families, subcategories, and fine-grained diagnostic detail. As a result, existing EHR representation learning methods do not explicitly exploit the hierarchical structure already present in the coding system. In this work, we study ICD-10-CM hierarchy as a general inductive bias for clinical representation learning. We investigate two complementary mechanisms for incorporating hierarchy: first, by augmenting diagnosis sequences in a BERT-style transformer with tokens corresponding to different levels of the ICD hierarchy, and second, by injecting hierarchy into graph-based code representations through hierarchy-aware edges combined with diagnosis co-occurrence structure. Across these settings, we evaluate whether explicit hierarchy improves downstream prediction, which levels of the hierarchy are most useful, whether hierarchy encoding improves transfer across datasets, and how hierarchy reshapes embedding similarity structure. We conduct experiments on two large-scale real-world clinical datasets: MIMIC-IV, used for pretraining and in-domain evaluation, and eICU, used to assess cross-dataset transfer via frozen encoder probing. Our findings show that explicitly encoding ICD hierarchy improves over flat code representations in both in-domain and cross-dataset settings, while revealing that the most useful level of hierarchy depends on both the task and the modeling approach. More broadly, we focus on hierarchy-aware EHR representation learning and show that the benefits of encoding hierarchy are generalizable across modeling settings and hierarchy levels.

Respiratory acoustic foundation models (FMs) excel at cough classification, yet their ability to predict continuous health quantities from cough audio remains largely unexplored, despite the clinical value of passive age, BMI, and disease probability estimation in settings where physical measurements are unavailable. We introduce the multi-model, multi-target cough regression benchmark evaluating five FMs (OPERA-CT, OPERA-CE, OPERA-GT, HeAR, M2D+Resp) across six targets on three datasets under subject-disjoint protocols, comparing linear, MLP-small, and full MLP regression heads. MLP-small beats the mean-predictor baseline on all tasks and linear probing in 23 of 30 model x task cases, with full MLP overfitting on small clinical data but recovering on larger sets, revealing a dataset size x head-capacity trade-off. HeAR leads within-dataset age regression on Coswara (9.12 yr MAE); its CIDRZ result is excluded from headline claims owing to possible HeAR-CIDRZ pretraining overlap. OPERA-GT is favored over OPERA-CT on age in all three datasets, with the CIDRZ margin within seed variance, extending a generative-pretraining advantage from breath to cough. HeAR and M2D+Resp reach near-full performance at N = 50 samples while OPERA models require N = 400. Cross-dataset transfer is strongly asymmetric as large diverse data generalises to small clinical populations (CoughVID to CIDRZ: -0.17 yr) but not vice versa (CIDRZ to Coswara: +2.43 yr, +26.6%).

Foundation models (FMs) trained on large datasets and fine-tuned on downstream tasks have emerged as a powerful paradigm in AI for science. Industrial FMs are typically trained using self-supervision with masking due to the lack of labels. In many scientific domains, accurate simulations are plentiful and facilitate large, labeled datasets. This opens up new possibilities for pre-training. We present a systematic comparison of pre-training methods using the OmniLearned High Energy Physics FM framework. We test supervised classification, flow-matching generation, and self-supervised masked particle modeling. All models are pre-trained on the JetClass dataset and fine-tuned on two representative downstream tasks, top jet classification and JetNet conditional generation. Among other observations, for classification tasks, we find that pure classifier pre-training is optimal when downstream labels and model capacity are plentiful, but combining it with self-supervised masked particle modeling (MPM) is uniquely powerful in the low-finetuning label regime. Flow matching-based generative pre-training seems to provide little benefit for downstream classification, and interestingly, for downstream generation, we find that flow matching must be in the pre-training objective to see a significant finetuning advantage, hinting at the orthogonality of classification and generation tasks. That is, for a model to transfer to both generative and classification downstream tasks, it must be pre-trained on both. This study provides a template for controlled scaling analysis of pre-training objectives for foundation models in simulation-based sciences.

The workflow from particle collision to physics analysis passes through a series of reconstruction steps that are traditionally modular and disconnected, with no shared representation linking low-level detector data to high-level analysis tasks. We show that casting event reconstruction as a machine learning problem naturally produces such a shared representation. We repurpose a machine learning model trained for particle-flow reconstruction (MLPF) to perform three distinct analysis tasks: jet flavor identification, jet energy regression, and missing momentum regression. By appending the per-particle latent representations learned during reconstruction as additional input features, we substantially improve over baselines that use kinematic features alone. We further demonstrate that a single linear layer trained using only the latent representations achieves competitive performance against state-of-the-art baseline architectures, and outperforms the baseline for missing momentum regression with approximately 35 times fewer parameters. These results demonstrate that the latent representations learned during reconstruction encode essential physics information needed for downstream analysis, establishing MLPF as a foundation model and offering a concrete step toward an end-to-end pipeline from detector data to physics analysis.