Papers

The evolution of machine learning has progressively changed where intelligence resides in an AI system. In conventional machine learning the task, data representation, labels and model architecture were tightly coupled, so data preparation was narrow, schema-bound and visible. Generative AI decouples the model from any single task: one foundation model serves open-ended downstream tasks, and the generality gained on the model side is matched by heterogeneity on the data side, because enterprise knowledge is authored in the formats people use (PDF, presentations, spreadsheets, scanned documents, forms, tables, diagrams and mixed-layout files) that carry textual, visual, geometric and structural information at once. A language model or retriever cannot reason reliably over information misrepresented at this interface, so content extraction becomes a lifecycle stage in its own right whose errors no downstream retriever or re-ranker can repair. This paper presents a production-ready content-extraction system that makes this stage explicit, configurable, and measurable. The system incorporates selective OCR routing, a scarcity-first curation engine with a reference-based extraction scorer that measures character, word, and table-structure accuracy, a deterministic structure-aware parent-child chunker, and a read-only retrieval evaluator that generates grounded questions from every page and reports Hit@k, mean reciprocal rank, and latency. On a 180-document corpus the best extractor scores 97.4 of 100 (character error rate 0.13%, table similarity 0.995) and the chunker reaches hit@1 of 68.6%, hit@10 of 92.8% and MRR 0.77 over 25,050 generated questions. We distil three design principles (structure before semantics, never mutate what you measure, budget your labels) and position measured content extraction as the perception layer of enterprise agentic systems.

LLM agents increasingly act in multi-actor environments, exposing them to misuse from multiple sources: decomposition attacks, where a harmful request is split into innocuous sub-requests, and prompt injection attacks, where a compromised tool delivers a malicious instruction. Existing evaluations treat these threats separately and ask whether a trajectory is harmful, rather than when it becomes harmful. We propose monitoring the agent's responses, where its actions are externalised, and ask whether the first point where monitors identify harm lands within a harm window (from the agent's first harmful commitment to goal execution). We develop a unified formalism for trace-level misuse monitoring and use it to construct a benchmark of ~6,200 conversation transcripts between a user, an LLM agent, and the external environment, spanning both threats in a shared schema, with a labelled harm window, corresponding benign controls, and matched instances of refusals to these requests. Across 17 monitor configurations, we find that our proposed action-framed monitors perform well on both threats under classical metrics (AUC: 0.95 and 0.99 respectively), while content-framed monitors collapse on injection attacks (AUC: 0.52). We also show that classical position-blind metrics paint an optimistic picture of monitor performance, since all monitors localise decomposition attacks poorly under the interval metric, which measures the ability to localise harm. Broadly, we illustrate the need for a unified study of misuse monitoring.

Modularity is a standard objective for community detection, comparing observed intra-community connectivity with its null-model expectation. Modern node embeddings capture structural and semantic proximity beyond raw topology, but replacing adjacency with representation-induced affinity while retaining the classical degree-based null model makes the observed term geometry-dependent and the expected term geometry-agnostic. This creates a null-model mismatch: the objective may reward affinity already expected from representation proximity. This paper introduces RAM, a representation-aware modularity objective with a distance-calibrated null model. RAM preserves the observed-minus-expected principle by calibrating expected affinity with both degree heterogeneity and representation distance. We analyse its relation to classical modularity and develop divisive and multi-level greedy optimisers. Experiments on seven real-world datasets and synthetic scalability tests show that RAM improves over topology-only, direct embedding-clustering, and deep learning-based baselines, remains competitive under classical modularity while improving community quality on large graphs, and scales efficiently. Ablations confirm that both degree correction and distance calibration are essential.

Despite rapid advances in artificial intelligence, reliable real-world plant disease detection remains a persistent challenge. Visual and deep learning approaches have shown promising results, but their deployment under field conditions remains limited. A key bottleneck is the reliance on laboratory-generated datasets that lack environmental diversity, realistic backgrounds, and balanced class distributions, resulting in poor generalization. In contrast, datasets collected directly from agricultural environments capture natural variability and better reflect challenges faced by farmers across regions. This review presents a critical analysis of visual and deep learning approaches for plant disease detection, with emphasis on plant disease datasets. It establishes a taxonomy based on acquisition setting, accessibility, plant diversity, disease composition, class structure, and imbalance severity, and examines their implications for model generalization and real-world deployment. A comparative analysis of laboratory and real-field datasets identifies critical gaps that hinder disease detection. The review further analyzes how multi-level dataset imbalance, including intra-class, inter-crop, and cross-dataset imbalance, and limited environmental variability affect model performance and robustness, an area insufficiently examined in existing surveys. Beyond image-based approaches, it highlights the importance of integrating environmental parameters such as temperature, humidity, and leaf wetness with image data to improve prediction under dynamic field conditions. Finally, the review identifies key challenges, research gaps, and future directions concerning dataset construction, environmental variability, structural imbalance, standardization, and multimodal disease monitoring. It provides a foundation for developing next-generation multimodal frameworks for precision agriculture.

LLM agents interact with external systems by generating structured tool calls. Given a user request, conversational context, and a catalog of tool schemas, a tool-calling model must select tools and generate their arguments, potentially producing multiple calls in a single response. Standard autoregressive decoding generates these calls token by token, incurring substantial latency for requests involving multiple calls or many argument fields. The explicit argument structure offers opportunities for parallel generation, but later argument values may depend on preceding fields and calls, so independently generated values can differ from the target model's output. We present SchemaFill, a framework for efficient LLM tool calling through slot-parallel speculative decoding. SchemaFill generates future slot values concurrently as candidates, without requiring advance knowledge of the actual call sequence or argument values. Candidates spanning multiple fields and calls are concatenated for verification by the target model under the actual output prefix. Only verified tokens are committed, and the target supplies corrections when candidates disagree. This applies target verification while exploiting parallelism across slots and calls. On Glaive and BFCL, SchemaFill achieves up to a 4.05$\times$ improvement in end-to-end throughput over autoregressive decoding. Code is available at https://github.com/Czzzk/SchemaFill.

An inaccurate expert can still provide useful information after correction. We study online learning to defer in which the learner chooses an expert and fixes a correction function before purchasing its answer, then applies that function to the answer received. The difficulty is that observed losses reflect both expert quality and an unfinished correction: early errors can discourage queries that would be valuable after learning. We propose ORUCB, which pools shared and expert-specific polynomial responses. A bound on cumulative response-learning error calibrates confidence-weighted risk regression and exploration, allowing the router to account for this error when deciding which answers to buy. Under bounded residuals and disagreements, a fixed feasible model of optimal responses, and linear models of free and optimal queried risk, the calibrated algorithm achieves high-probability pseudo-regret $O(\sqrt T\log(T+1))$ over $T$ rounds for fixed problem parameters. The guarantee permits singular answer distributions and misspecified shared responses; optimality is relative to the bounded response class. On four test streams, the selected cubic policy has lower fee-inclusive cost than seven baselines that deploy answers unchanged. Comparisons with a common correction learner examine routing, while six-price comparisons measure cost and query rates.

Driver fatigue poses a significant challenge to railway safety, with traditional systems like the dead-man switch offering limited and basic alertness checks. This study presents a vision-based monitoring system that relies solely on a single front-facing RGB camera and a graph neural network to classify simulated train-driver states into alert, not-alert, and an emergency class comprising acted emergency-like behaviours. To optimize input representations for the model, an ablation study was performed, comparing three feature configurations: skeletal-only, facial-only, and a combination of both. Experimental results show that combining facial and skeletal features yields the highest accuracy (81%) for the three-class model under the light condition, outperforming models that use only facial or skeletal features. Furthermore, the combination of facial and skeletal features achieves 99% accuracy in the alert/not alert classification in light condition. Additionally, we introduced a controlled RGB video dataset containing alert, not alert, and acted emergency-like behaviours recorded under three illumination conditions. These contributions represent a step toward passive and non-contact train-driver state recognition based on facial and upper-body dynamics.

We propose the safeguarded Anderson-accelerated reflection (SAAR) method, a two-level iterative method for the continuous Sylvester matrix equation $AX+XB=C$. The core of the method is a fixed-point reformulation: at each outer iteration, the associated linear matrix equation is decomposed into independent column-wise linear systems, which are solved approximately by a reflection iteration. For nonsingular \(A\) and \(n\ge 2\), we prove the convergence of the reflection inner iteration by a spectral-radius argument and extend the result to the matrix equation setting. Since only finitely many inner iterations are used in practice, the overall scheme is analyzed as an inexact fixed-point iteration, and a sufficient condition for linear convergence of the unaccelerated inexact iteration is established in the Frobenius norm. On top of this scheme, SAAR incorporates Anderson acceleration into the outer iteration, while a residual-based safeguard rejects Anderson candidates whose Sylvester residual is larger than that of the standard inexact reflection iterate, thereby enhancing numerical stability. Numerical experiments indicate that SAAR substantially reduces the number of outer iterations and often the CPU time, and it improves empirical robustness with respect to the inner tolerance for the tested problems.

An electromagnetic (EM) digital twin gives mobile robots wireless situational awareness but depends on material conductivities that change with the environment. Online calibration faces initialization sensitivity and measurement travel costs. We demonstrate a vision-language model (VLM)-guided framework using a Unitree G1 robot and NVIDIA Sionna, with two VLM calls: material classification maps visible materials through ITU-R P.2040 to conductivity priors for Sionna's gradient descent on accumulated received signal strength (RSS) measurements; waypoint planning selects the next measurement location online using residual RSS calibration error and image coverage. In a real indoor scenario, the framework achieves a normalized mean absolute conductivity error of $1.74\times10^{-4}$ within 20 m of travel; random initialization never converges, while random waypoints require over twice the travel.

Attention maps are often interpreted as evidence of what a forecasting model uses when making predictions. In our load-forecasting model, a CLS representation of historical demand queries 24 future exogenous horizon tokens through cross-attention, inviting a temporal interpretation in which highly attended horizons may appear to explain forecast peak timing. We test this interpretation using a horizon-level attention descriptor, $\Psi_{\mathrm{out}}$. Across 31 day-aligned windows of the Panama load dataset, the forecast achieves a median peak-time error of 0 h and a 51.6% exact-match rate, whereas the argmax of $\Psi_{\mathrm{out}}$ has a median error of 5 h and 0% exact match. The forecast peak is closer to the observed peak in 27 of 31 windows. This dissociation is not merely an argmax artifact: within $\pm1$ h, attention reaches only $1.16\times$, $1.11\times$, and $1.14\times$ the uniform baseline around observed, predicted, and weekly-naive peaks, respectively, indicating weak and non-selective concentration. Yet the attention profile is structured, with cross-window consistency of 0.83. Replacing 12 future weather features with their training-set means makes the profile nearly uniform, showing sensitivity to future weather variation rather than fixed horizon position alone. The dissociation is also reproduced across three random-seed runs. These results show that structured, input-sensitive, and reproducible horizon-level cross-attention need not provide a valid peak-selective explanation of forecast behavior. The observed behavior is instead consistent with an internal horizon-reference role for integrating future exogenous information, although this functional role is not causally established.

Accurate bioactivity prediction is a central challenge in early-stage drug discovery, as individual assays often contain too few measurements to train reliable models independently. Meta-learning offers a principled approach to this few-shot setting, but assay heterogeneity may limit its effectiveness. Here, we test this hypothesis and show that meta-learning performance degrades as meta-training tasks become more heterogeneous. To address this, we introduce MetaHeta, a meta-learning framework that accounts for assay heterogeneity by conditioning predictions on auxiliary data from related assays, with relatedness defined flexibly from available assay information. The architecture of MetaHeta combines linear attention over large auxiliary datasets with exact attention over scarce task-specific context, enabling efficient scaling to the former without compromising exact attention over the latter. We demonstrate the benefits of our approach on assays from ChEMBL and BindingDB, improving few-shot bioactivity prediction and downstream compound prioritization in retrospective Bayesian optimization.

Vector processors exploit data-level parallelism to provide high computational throughput, but very long vectors can make the Vector Register File (VRF) a significant source of area, energy, and register pressure. This cost is exacerbated when vector instructions operate on values with scalar semantics: although such values are architecturally represented using vector registers, they do not require full-width storage. This paper proposes the Scalarized Vector Register File (SVRF), a microarchitectural enhancement that redirects scalar-semantics vector values to a dedicated scalar register file, avoiding unnecessary allocation and access of full-width physical vector registers. The SVRF integrates with vector register renaming while preserving compatibility with the supported vector ISA. We implement and evaluate SVRF in an Register Transfer Level (RTL)-based RISC-V Vector Extension (RVV)-compliant vector processing unit supporting very long vectors. Across representative HPC and AI/ML workloads, the SVRF reduces vector-register pressure and VRF activity without degrading performance. By exploiting the resulting reduction in VRF demand, the proposed design achieves up to 15.8% VRF area reduction and up to 6% total area reduction, while reducing total power by up to 12% in evaluated configurations. Some workloads also achieve up to 1.12X speedup.

Class-incremental learning must recognize all classes seen so far without task labels. Logit replay methods such as DER and DER++ mitigate forgetting by matching the model's past predictions on stored examples. Deleting this matching reveals its benefit, but the resulting accuracy cost cannot show whether the stored scores themselves are needed, or whether the cost survives correction of the classifier's bias toward recent classes. We propose a diagnostic framework that treats a cached prediction as temporally heterogeneous supervision: it separates classes known when an example was stored from classes learned afterward, edits each group, and evaluates every model before and after a task-level offset that leaves within-task predictions unchanged. On CIFAR-100 with DER++, suitable fixed constants replace the unrefreshed stored scores of later-learned classes within an equivalence margin of 1 percentage point, and the offset reduces the cost of deleting their matching from 14.9 to 1.8 points. Reassigning the non-gold scores of classes known at storage, which preserves their values and each task's target probability, costs 4.3 points before and 4.0 after the offset, and a parallel cost persists in image distillation. In the tested fixed-head setting, the large cost of deleting later-class matching is thus mostly correctable by this offset, whereas the smaller cost of disrupting class correspondence persists. Code and data are available at anonymous.4open.science/r/replay-preserve-E22B.

High-quality datasets are essential for reliable machine learning, but dataset curation remains costly and hard to generalize across domains. Existing methods typically rely on manually designed heuristics or model-dependent signals, limiting their applicability across tasks and user queries. To address these limitations and automate data curation, we propose CuratorMAS, a multi-agent collaboration framework that orchestrates agents to evaluate and curate high-quality datasets. To achieve the goal of flexible curation, CuratorMAS decomposes the complex curation process into five programmable execution stages and forms a parallelizable workflow. Specifically, CuratorMAS first performs dataset exploration to collect contextual information such as file structures and constraint cues, thereby developing a comprehensive understanding of the given task. In order to acquire up-to-date information, CuratorMAS retrieves domain knowledge from online sources to augment the evaluation process. Next, CuratorMAS derives the necessary evaluation criteria and computes the corresponding metrics. Based on these results, CuratorMAS executes filtering accordingly. Finally, an evolution module summarizes the evaluation outcomes and updates the relevant skills. Extensive and comprehensive experiments demonstrate that CuratorMAS significantly reduces the noise rate by up to 36.03 percentage points (pp) while also improving the F1 score of downstream models by up to 8.88 pp.

Estimating a decision threshold requires locating observations near an unknown boundary. We study how gradient-based pretraining learns this statistical rule in a two-parameter softmax-attention model with a fixed feature and inequality direction. Pretraining uses labeled contexts and their true thresholds; a fresh threshold must be inferred from context alone. Under a large-resolution initialization, constant-step gradient descent on $m$ tasks with $n$ examples each produces a frozen estimator with error $\widetilde O((m\wedge n)^{-1}+N^{-1})$ for each fixed interior threshold and every fresh-context size $N$. The two terms separate finite-pretraining accuracy from fresh-context localization. The mechanism is coordinated parameter divergence: population training calibrates the relative label and feature scores, then increases the attention scale as $t^{1/4}$, giving population threshold error $O(t^{-1/4})$. To transfer this mechanism to a fixed finite corpus, we control gradient errors relative to the shrinking directions of progress at successive parameter scales. This certifies a growing training interval without requiring long-time tracking of the population trajectory. We also identify the boundary limitation of the one-head model and explain statistically what a reflected symmetrization could achieve.

Variational autoencoders (VAEs) are a key part of modern text-to-image models, which generate images within their latent space. VAEs are known to disentangle the main factors of variation in the data, and color is known to be one of the most structured of these in natural images: decorrelating it yields one luminance axis and two opponent-color axes. Color should therefore be expected to emerge as a distinct factor in the VAE latent space. Yet how these latent spaces represent color remains largely unexplored. In this work, we show that the VAEs of text-to-image models share a color subspace aligned with brightness and opponent-colors. Through a linear approximation of the encoder and targeted latent steering, we find this subspace consistently across a broad range of VAEs, from SD1.5 to FLUX.2 and Z-Image. Building on this characterization, we propose three applications: ColorTuning, which achieves state-of-the-art in precise numerical color generation on the fine-grained CSS3/X11 system of GenColorBench, saturation control, to adjust the global chromatic intensity, and color transfer, to change the palette to match a reference. The code and models are publicly available at https://julian075.github.io/Color_Subspace/

The quality of computed tomography (CT) images is significantly affected by the selection of reconstruction kernels: sharp kernels improve spatial resolution but increase noise, whereas soft kernels diminish noise at the expense of edge clarity. This study presents an innovative enhancement framework utilising Bidimensional Empirical Mode Decomposition in conjunction with Quaternion Bilateral Filtering (BEMD–QBF) to convert sharp-kernel CT images into representations resembling soft-kernels, while maintaining critical anatomical structures. The technique disaggregates each image into intrinsic mode functions via BEMD and analyzes them inside a cohesive quaternion framework to attain efficient noise reduction and structural integrity. The proposed methodology is evaluated using several reconstruction kernels (B50, B46, B41, B36, B35, B31) and compared with recognised filtering strategies, including Non-Local Means, Anisotropic Diffusion, Bilateral Filtering, and Quaternion Bilateral Filtering. Quantitative evaluations of the Structural Similarity Index (SSIM) and Peak Signal-to-Noise Ratio (PSNR) indicate that BEMD-QBF consistently attains superior structural fidelity and competitive noise reduction across all evaluated kernels. The results underscore the efficacy of the proposed strategy as a viable approach to enhancing post-reconstruction CT images, yielding superior image quality without requiring access to raw projection data.

Small language models are inexpensive to serve and can run on private infrastructure, but base models are often not good enough at multi-turn tool calling, and fine-tuning them needs per-API data that rarely exists. Existing synthesis methods are too expensive for high-scale fine-tuning, as they often require mock operational environments for different domains and multiple LLM calls per generated conversation turn. We introduce a fully automated, lightweight synthesis framework that models each API as a finite-state machine, representing the system as abstract states that determine when each tool may be called, producing state-valid sequences of tools; sequences are translated into complete examples with a single LLM call. Rather than optimize diversity, we set a target distribution over the number of turns, the tool sequence and task complexity. We measure data quality by fine-tuning SLMs on generated trajectories, showing that our FSM-based generation significantly improves downstream accuracy over an unmutated baseline and, against existing works, reaches 70.7% full accuracy over 63.4% and 53.7% with 3.6-6.6$\times$ fewer tokens.

Image denoising is a crucial task in image processing, focused on improving image quality by minimizing noise while maintaining essential structural elements. This study presents a hybrid denoising framework that combines several decomposition techniques, including empirical mode decomposition (EMD), variational mode decomposition (VMD), multichannel EMD (MEMD), and bidimensional EMD (BEMD), with curvelet transform thresholding. Each decomposition mode undergoes processing through both soft and hard thresholding, and the denoised modes are combined to rebuild the final image. Comprehensive evaluations of standard CT image datasets reconstructed with various kernels (B50, B46, B41, B36) reveal substantial enhancements in denoising efficacy. VMD consistently achieves the highest peak signal-to-noise ratio (PSNR) and structural similarity index (SSIM), signifying exceptional noise reduction and feature preservation. The study analyses the trade-offs between soft and hard thresholding: soft thresholding maintains intricate visual details, whilst harsh thresholding provides enhanced noise reduction. The suggested method surpasses traditional techniques in both reference and non-reference quality criteria, indicating its potential for broader application in medical imaging and future incorporation with adaptive thresholding algorithms.

The development of efficient iterative schemes for approximating the inverse and generalized inverse matrices is important in my research fields. To this end, a family of fourth-order matrix iterative schemes for approximating the inverse and generalized inverse matrices is established by incorporating an appropriate weight function into the scalar Heun method. Moreover, a fifth-order matrix iterative scheme is obtained as a particular member of the proposed family. Under suitable conditions, the theoretical order of convergence is determined for the proposed family, whose stable members are identified through dynamical analysis. To assess their performance and verify the consistency of the theoretical results, some numerical tests are performed on matrices of different sizes.

Large language models are increasingly used to simulate how individuals respond to new situations, yet the behavioral reasoning behind these responses is either inherited from pretraining or learned from individual-level annotations, which offer limited behavioral diversity and little supervision of the reasoning itself. We propose to learn behavioral reasoning from prediction markets, whose price trajectories record how populations respond to real-world events at scale. We introduce macro2mind, which trains a language model with GRPO using market signals. A social behavioral decomposition makes behavioral reasoning an explicit step of forecasting: the model infers representative groups of market participants, predicts how each interprets the news and updates its beliefs, reasons about their interactions, and aggregates these responses into a price. A hindsight-regret curriculum with difficulty-aware sampling focuses training on transitions where hindsight-identified groups substantially improve the forecast while prioritizing examples that remain learnable for the current policy. The learned reasoning applies to user simulation without further training. On SWM-Bench, macro2mind achieves state-of-the-art directional accuracy and correlation on Polymarket. Trained on market data, it transfers zero-shot to four user-simulation benchmarks (Humanual, OvertonBench, PRISM, and CAD) and has competitive performance among zero-shot methods. Used as a data generator, macro2mind also raises a downstream simulator's accuracy on unseen users by 15.5 points, outperforming data generated by its backbone by 13.2 points.

Impact sound rendering synthesizes the sound produced when a 3D object is struck, but practical renderers often rely on fixed material presets such as wood, plastic, or steel. These presets limit the range of impact sounds a renderer can express, while manually adjusting the underlying material parameters remains difficult without expertise in material acoustics. We therefore study inverse impact sound rendering: predicting material parameters from a reference impact sound so that a simulator can recreate a similar material response. To support this task, we introduce ImpactMat, a dataset and benchmark of single and blended material impact sounds paired with ground-truth material parameters. We further propose a feed-forward model that predicts these parameters from one or more recordings, using blended materials to learn smooth transitions between material types. Experiments show that our method outperforms competitive baselines and enables re-rendering from real recordings without manual parameter tuning. The project page is available https://material-from-impact.github.io/material-from-impact/.

Despite substantial progress in short-to-medium-range weather forecasting, predicting high-impact events such as flash droughts remains a key challenge for both early warning operations and physically-based subseasonal-to-seasonal (S2S) prediction systems. Here we demonstrate that, for S2S soil-moisture forecasting over Europe, forecast skill depends as much on how the prediction problem is formulated as on the forecasting model itself. Using a Vision Transformer-based architecture with dual-pathway temporal and spatial attention, we show that residual learning is essential to outperform persistence. This advantage is realized only when forecasting root-zone soil moisture in physical units rather than standardized anomalies, revealing that the target representation itself constrains predictability. A probabilistic extension via quantile-head fine-tuning further provides well-calibrated predictive distributions. Benchmarked against deep-learning and operational ECMWF S2S baselines over 2021-2022, our model achieves the highest deterministic and probabilistic skill at all lead times and reliably detects anomalously dry root-zone states (below the 20th percentile). Yet flash drought onset, defined by multi-pentad intensification criteria, remains a fundamental challenge shared across all current S2S systems. These findings advance data-driven S2S soil-moisture forecasting while highlighting the remaining challenge of predicting rapid drought development.

Yield forecasts help planners and farmers decide on inputs, storage and imports, but small agricultural tables can make reported accuracy fail on a new season. We built a crop-yield prototype for Punjab, Pakistan that combines Random Forest, XGBoost, support vector regression and a Ridge-stacked ensemble with a MobileNetV2 leaf-health classifier, and deployed it as a web application with SHAP explanations. A random 80/20 split of a merged Kaggle-derived table (414 rows) gives the ensemble an R2 of 0.991. An audit showed that the table contains only 46 independent observations: a join with nine temperature records per year copied every crop-year nine times. Holding out whole years takes XGBoost on the same rows from R2 = 0.994 to -0.20. On deduplicated data, and on a longer FAOSTAT table (1990-2024, 70 observations), a per-crop linear trend (leave-one-year-out RMSE 0.29 Ton/Ha) beats every model not given the year (0.84-1.06). Neither pesticide use nor national temperature change explains the trend residuals. An apparent pesticide gain in the Kaggle table disappears on FAOSTAT, where the pesticide series is mostly imputed and the two releases disagree. An independent district-level wheat panel (36 districts, 13 seasons) shows that most variation in Punjab is spatial and that a district mean with a common trend matches the learned models. The leaf classifier reaches 99.87% accuracy on held-out PlantVillage images and recalls 96.4% of 336 unseen diseased leaves after near-duplicates were removed. However, no leaf image is paired with a yield record, so the health score used in the yield models had to be constructed and adds nothing. We report these negative findings together with the prototype.

We introduce sHAIL-Causal, the causal specialization of the Saturated Hierarchical Atomic Incremental Learning (sHAIL) paradigm: a sequential staircase procedure that ascends a nested hierarchy of hypothesis classes H_0 < H_1 < ... < H_K once a saturation signal indicates that mastery of the current stage has plateaued. Where general sHAIL leaves the saturation criterion open, sHAIL-Causal instantiates it with a joint criterion of goodness-of-fit saturation and cross-environment invariance, replacing the complexity control of Structural Risk Minimization. We show, theoretically and by simulation, that complexity-only staircases are seduced by confounded predictors that lower empirical risk without reflecting stable causal structure, whereas an invariance-gated staircase provably halts at the true causal predictor set under a per-variable Richness condition. We show that naive greedy search fails to recover the causal set even under Richness, trace the failure to non-monotonicity of the invariance statistic along single-variable paths, and validate a fix combining bounded-exhaustive block-seeding with a calibrated acceptance threshold. We then extend the guarantee to environments arriving sequentially, yielding a confidence guarantee that stays valid at every arrival, which one-shot exhaustive search cannot offer without repeating its full combinatorial search. We close by formalizing the intervention of a wise teacher who lifts a saturated learner off a plateau of boredom.

Behavioral cloning (BC), despite its simplicity, exhibits many counterintuitive phenomena in the real world. For example, the performance of BC often keeps increasing as the model overfits more to the dataset, and fully closed-loop policies often completely fail without action chunking. Unfortunately, properly studying these anecdotal phenomena ("behavioral cloning mysteries") is challenging: in the real world, datasets and experiments are costly and not fully controllable; in simulation with synthetic data, these phenomena are often not easily observed partly due to the discrepancy between scripted policies and human demonstrations. In this work, we propose OCBench, a robotic manipulation benchmark with controllable scripted policies that have similar properties to human demonstrations. We show that, by mimicking key properties of human demonstrations, OCBench reproduces many anecdotal BC-related phenomena in controlled settings. With its GPU-accelerated environments and scripted policies, we demonstrate how OCBench enables scientific studies of previously reported BC-related phenomena by analyzing and refuting various hypotheses. Project page: https://seohong.me/projects/ocbench

We study the query complexity of finding a Tarski fixed point over $[n]^k$. Previous work has left a large gap between $\smash{{\Omega}(\log^2 n)}$ and $\smash{\log^{O(k)}n}$. We show that both of the previous upper and lower bounds were far from tight: for every $k\geq 3$, \[ \Omega\left((\log n)^{\frac{1}{2}\lceil \log k\rceil}\right)\le \operatorname{Tarski}(n,k)\le O\left(5^k(\log n)^{\lceil \log k\rceil}\right). \] Succinctly, up to the fixed-parameter factor of $5^k$, the complexity is settled at $(\log n)^{\Theta(\log k )}$. In particular, we obtain the first super-polynomial query lower bound for this problem.

Whole-body tracking has become the interface through which operators drive humanoid robots, yet the references it consumes are recorded on level ground and carrying nothing, so the tracker is aware of neither the forces the robot must exchange with objects nor the terrain it must stand on. Existing controllers address one side of this gap: force-capable policies command an end-effector force but prescribe no whole-body pose, while terrain-adaptive trackers treat loads as disturbances to reject rather than wrenches to command. We present BRACE, a whole-body tracker that exerts and compensates commanded hand forces from diverse poses while following a flat-ground reference on sloped terrain. Rather than leaving the tracker to absorb the load and the slope, BRACE folds both into the reference it follows: terrain conformance lifts footholds and root onto the local surface, and a wrench transformation resolves the hand displacement that produces a force jointly with the center-of-mass and center- of-pressure shifts it induces, bounded by teacher-specific arm-effort limits. Separate exertion and compensation teachers are distilled by DAgger into one flow-matching student that runs on proprioception alone, without a height map or measured wrench, so a teleoperator (even in remote locations) can supply a flat- ground trajectory and the robot resolves slope and load onboard. We extensive experiments on the Unitree-G1 to demonstrate the ability of BRACE to exert, compensate force and handle diverse terrain in simulation and real robot experiments.

We study errors-in-variables problems in which a target study contains only a single error-prone surrogate of an unobserved exposure, while an external source study provides repeated surrogate measurements from a different population. The measurement error distribution is allowed to depend on the observed error-free variables, and the error-free variable distribution itself may differ between studies. We introduce a conditional transportability assumption that enables the use of external repeated measurements under source-target heterogeneity. Together with additional replicate-error conditions, it identifies the target conditional measurement-error distribution. Building on this identification result, we develop a data-fusion estimator for a broad class of target functionals. The estimator combines conditional deconvolution, flexible nuisance estimation, and orthogonal correction that reduces first-order sensitivity to nuisance estimation. For the proposed estimator, we develop a unified spectral theory covering both diffuse-spectrum and finite atomic-spectrum target functionals, derive a general asymptotic expansion, and establish consistency and target-specific convergence-rate bounds. The resulting convergence-rate bounds depend jointly on the spectral properties of the measurement error, the latent exposure, and the target functional. For finite atomic-spectrum targets, we further establish joint Gaussian and bootstrap limits, yielding inference for smooth moment transformations under an additional centering condition. In the reported simulations, Fuse-EIV has small bias for the primary exposure-related coefficient. Applications to the National Health and Nutrition Examination Survey illustrate how accounting for population heterogeneity and error heteroscedasticity can change empirical conclusions.

Compact time-frequency separators that mask the mixture and refine through a shared cell face two limits. First, a bounded multiplicative mask only scales a mixture bin, so where overlapping components cancel, the estimate stays small. Second, a shared cell applies the same weights to every time-frequency token at every step, so enlarging it adds compute everywhere. We present SEAL (Sparse Expert routing with Additive Latent reconstruction) to address both. For reconstruction, a zero-sum additive residual bounded by the local mixture amplitude lets estimates be nonzero where components cancel yet still sum to the mixture. For routing, a query built from acoustic and inter-step evidence sends each token to one of six residual experts, and a norm cap keeps the step cue from overriding clear acoustic evidence. On EchoSet, SEAL (small) surpasses TIGER (small) by 0.31 dB SI-SDRi with 28% fewer parameters and 2.9 times fewer MACs, and SEAL (large) is within 0.07 dB SI-SDRi of TIGER (large) at 3.1 times fewer MACs.