Papers

Simulation can expand scarce real demonstrations for co-training, yet how world fidelity and similarity to human behavior affect policy performance remains unclear. We distinguish world grounding, which aligns simulation with the real system, and behavior grounding, which aligns simulated trajectories with human motion. We build a real2sim2real pipeline that varies these axes independently to generate data for co-training. On a dynamic dexterous pick-and-sort task, fully grounded co-training raises success from 52% to 86%; averaged across configurations, world grounding improves success by 18 percentage points and behavior grounding by 10. Deployed policies behave like a mixture of real-derived and simulation-derived policies, imitating real demonstrations in covered states and relying on simulated behavior elsewhere, which we examine through latent-space analysis. Together, these results suggest complementary roles: world grounding lets policies use simulated experience beyond real-data coverage, while behavior grounding matters mainly when world grounding is imperfect. Grounded simulation remains beneficial when co-training foundation models.

General-purpose models can adapt to many tasks from context, while specialised models can execute individual functions with less capacity. Yet obtaining such specialists requires task-specific training or adaptation. We ask whether they can instead be generated directly from a few demonstrations. Using ARC-1D as a controlled testbed, we show that individual transformations can be represented by tiny specialist models, and that a hypernetwork can generate their parameters from context. The generated parameters form a structured weight space, while the resulting specialists show partial compositional generalisation and generalisation to transformations not seen during training. In both settings, removing explicit task identifiers improves generalisation beyond the training transformations. Together, these results provide a proof of concept that few-shot task context can be compiled on-the-fly into compact executable model parameters, and that the resulting weight space can support reuse and generalisation beyond known functions.

Physiological recordings often contain nonstationary oscillatory components whose number and dynamics vary across signals. Amplitude- and frequency-modulated (AM-FM) representations are well suited to characterizing such dynamics and have shown broad utility in biomedical signal analysis. Recent approaches have incorporated neural networks to learn mode decomposition patterns from data, but component cardinality is often predefined or determined through separate stopping or selection mechanisms. We propose a permutation-invariant neural framework for variable-cardinality AM-FM mode decomposition (PI-AMFM). PI-AMFM combines a multiscale temporal encoder, Mamba backbone, and component-presence estimation, with permutation-invariant Hungarian matching during training. On synthetic AM-FM signals, PI-AMFM achieved lower decomposition, instantaneous-frequency, reconstruction, and mode-count errors than the compared methods while preserving the overall trajectory pattern in a crossing-chirp example. On photoplethysmographic recordings, recovered modes captured cardiac and respiratory dynamics despite training only on synthetic signals. These results support the feasibility of PI-AMFM for variable-cardinality decomposition of nonstationary biomedical signals.

Ambulance ramping, the delay between hospital arrival and patient handover, is a critical operational bottleneck in Emergency Medical Services (EMS), yet its systemic magnitude and dynamics remain inadequately characterised at scale. This paper quantifies the scale, trajectory, and operational correlates of ramping across an entire statewide EMS system, analysing 2,850,575 ambulance attendances in Victoria, Australia from January 2020 to March 2024 using an Exploratory Data Analysis (EDA). After systematic preprocessing, an analytical cohort of 2,026,569 Emergency Department (ED) transports across 59 hospitals with ED and 79 Local Government Areas (LGA) was examined through interval decomposition, Pareto concentration, hourly cross-correlation, hospital arrival concurrency and priority-stratified operational comparisons. Cumulative Ambulance Hours Lost (AHL) totalled 1,491,127 hours, equivalent to approximately 96 ten-hour ambulance shift lost every day of the study window. Ten of 59 hospitals account for 57.8% of lost hours from 50.9% of cases. Annual losses rose 57% to a 2022 peak while transported demand fell 3.7%, indicating deterioration in per-case handover rather than growth in demand. Handover duration varies little with patient acuity, but rises monotonically with the number of ambulances arriving at the same hospital in the preceding hour, an effect persisting within every hour of the day. Hourly demand is moderately associated with ramping two to four hours later (r = 0.365). These findings establish the empirical preconditions for hospital-state aware ambulance routing.

Join discovery aims to identify tables from large data repositories that can augment a query table with complementary information, enabling downstream tasks such as data exploration, feature engineering, and business intelligence. Although numerous join discovery methods have been proposed, existing studies rely on method-specific benchmark construction, making reproducible and fair comparison difficult. We present TabJoinBench, a benchmark for evaluating join discovery methods across semantic, relational, and hybrid data lake scenarios. TabJoinBench constructs query-candidate pairs using source-specific validation strategies, systematically introduces structural, representation, and semantic changes through composable perturbations while preserving reliable ground truth. We evaluate representative join discovery methods spanning set-based, feature-based, and learned approaches, together with general-purpose language-model embedding baselines, and publicly release the processed datasets, ground-truth annotations, and generation pipeline to facilitate reproducible evaluation and future research.

Recent studies suggest that not every token needs to pass through all Transformer layers, motivating token-level adaptive models that selectively skip layers to reduce computation. Our experiments show that these execution choices also affect safety: existing token-level adaptive reasoning models exhibit higher harmful-response rates than their reference backbones. The safety effects depend on which layers are skipped and whether skipping occurs during prompt processing or answer generation. We further find that recognizing harmful requests and producing refusals depend on different layer-wise computations. We introduce SafeDepth, a lightweight, plug-in framework that uses selective layer execution to improve both safety and efficiency. SafeDepth learns to retain computations that support safe responses and bypass those that contribute to unsafe generation. A router selects layer execution based on token representations, layer position, and inference phase, while an adapter supports the skipped paths. We jointly train these modules to reduce computation and harmful responses while preserving performance on benign tasks, targeting a better safety-efficiency trade-off. The pretrained backbone remains frozen throughout, requiring no additional pretraining. Experimental results on Llama-3-8B-Instruct show that SafeDepth reduces computation relative to full-depth inference while largely preserving task performance. Compared with FlexiDepth, it lowers unsafe-response rates across all five harmful-request benchmarks, with the largest absolute decrease on HarmBench-HJ (from 55.44% to 25.25%), while reducing the XSTest false-refusal rate from 12.0% to 4.0%.

Synthetic data are increasingly used to scale LLM training, yet more synthetic data do not necessarily produce better models. Useful synthetic data must add information relevant to the target task without introducing errors that offset their benefit, and the value of an example can change as the training set grows. We develop a linear theory that characterizes this tradeoff and determines where synthetic data are useful, how much should be added, and the marginal value of adding one example to an existing set. The analysis shows the conditions when input coverage alone is sufficient and when synthetic errors must also be considered. Guided by these results, we introduce Training-Aware Target Coverage (TATC), a synthetic data selection method for LLM fine-tuning. TATC identifies candidates whose training effects are beneficial to the target task and selects among them to expand coverage of target-relevant directions not already represented by the available data. Experiments on text and image data verify the linear theory. With mathematical reasoning tasks, TATC selects synthetic solutions for fine-tuning Qwen2.5-Math-1.5B-Instruct and outperforms alternative synthetic-data selection methods on GSM8K across selection budgets. In summary, we provide a principled approach to synthetic data selection by quantifying and maximizing its value to the target task.

Video generation has rapidly progressed from short, low-quality clips to high-resolution, long-duration sequences with complex spatiotemporal dynamics. Despite strong generative priors learned through large-scale pretraining, pretrained video models often fail to reliably follow human intent, maintain temporal coherence, or satisfy physical and safety constraints. Compared with image and text generation, alignment in video generation presents unique challenges, including error accumulation over time, motion-appearance coupling, multi-objective trade-offs, and limited supervision for temporal properties. These challenges motivate systematic post-training strategies that adapt pretrained models without retraining them from scratch. In this survey, we present the first comprehensive review of post-training and alignment in video generation models. We frame post-training as a unifying framework and distinguish between implicit alignment and explicit alignment based on how alignment signals are enforced. From this perspective, we organize existing approaches into four broad categories: supervised fine-tuning methods, self-training and distillation methods, preference- and reward-based methods, and inference-time methods. This taxonomy provides a coherent view of how alignment signals shape model behavior across both training and deployment. Beyond methodological advances, we review commonly used datasets, benchmarks, and evaluation practices, and discuss open challenges such as scalable reward design, long-horizon temporal consistency, stability-expressiveness trade-offs, and safety-aware generation. This survey aims to provide a structured conceptual foundation and practical guidance for advancing controllable and reliable video generation models.

This work introduces a hyperbolic relaxation system designed for the simulation of kinetic equations in the low-Mach number limit. The methodology is built upon a micro-macro decomposition of the scaled BGK model, which reformulates the kinetic distribution function into a coupled system consisting of a macroscopic equilibrium part and a microscopic non-equilibrium remainder. By projecting the microscopic deviations onto a set of orthogonal polynomials, we derive a closed moment relaxation system. The resulting system is a version of Grad's 13 moment system with a linear hyperbolic part and a relaxation adapted to the incompressible limit. We prove the model's structural stability in the incompressible Navier-Stokes limit. Moreover, we develop a high order Asymptotic-Preserving (AP) numerical framework using Implicit-Explicit (IMEX) Runge Kutta schemes for temporal accuracy and finite difference WENO reconstructions as well as central difference approximations for high order spatial resolution. The proposed scheme ensures uniform stability and consistency across different physical regimes, automatically degenerating into a consistent high order discretization of the incompressible thermal Navier-Stokes limit as the scaling parameter vanishes. Numerical experiments in one and two dimensions corroborate the theoretical findings, demonstrating significant reductions in computational cost and robust performance across a wide range of Knudsen and Mach numbers.

Vision-Language Models (VLMs) enable video annotation at scale, but costs accumulate quickly: processing a typical 60-second short-form video at one frame per second requires millions of tokens. To reduce costs, researchers rely on heuristics such as sampling a subset of frames, compressing videos into image grids, or using only a single modality. However, it remains unclear which heuristics save cost, and whether they preserve the downstream conclusions these annotations enable. To address this gap, we conduct a systematic evaluation of these heuristics using short-form videos, on two computational social science (CSS) tasks: sentiment and topic classification. We evaluate each configuration along three axes the literature typically treats separately: classification accuracy, validity of downstream inference, and per-video token cost. First, we find that accuracy and validity diverge: the highest-accuracy configuration can produce wrong conclusions. Second, modality value is not guaranteed: text alone can yield strong performance, indicating that adding modalities can add cost without adding signal. Finally, we find that cost can be decoupled from video length when annotating short-form videos: a single $2\times8$ image grid built via simple shot-transition detection approaches full-video understanding ($\kappa$ within~.05), at $\sim 15\%$ of the token cost. Based on these findings, we derive guidelines that can enable cost-aware VLM annotation in CSS.

Motivated by accessing crop plots in a field, where each crop plot can only be visited by a given pair of entry/exit points (we have three different types, each having four cases), we study the corresponding Minimum Spanning Tree (MST) problem of such a planar set of axis-aligned unit squares. It turns out that this crop plot distance does not satisfy triangle inequality, even though the whole setup of the problem is geometric. Hence additional care must be taken. The main results of this paper are as follows: (1) we prove that computing the MST of a set $P$ of unit squares under the crop plot distance is NP-hard, (2) the MST of $P$ can be approximated with a factor-4 approximation.

Forecasting how a newly emerged patent technology will be reused is central to technology intelligence, but reuse-pattern labels do not exist in advance: they must be constructed from the trajectories themselves, and how they are constructed determines what a forecast means. We study $201{,}710$ novel patent technologies (first-time IPC code pairings, USPTO 2002–2022). Our primary labeling applies $k$-means in the latent space of a GRU autoencoder trained on the $20$-year reuse trajectories, using no hand-crafted features; to our knowledge this is the first use of a learned sequence representation for this task. Seven emergence-time features, observable in a technology's first year, recover these labels at a one-vs-rest macro ROC-AUC of $0.914$, but the calendar year of emergence alone reaches $0.874$. A replication on technologies observed for ten full years, none of them right-censored, indicates that this calendar-year effect mainly reflects change over time in what was patented. Separately we cluster the emergence-time features themselves, after Fractal Autoencoder feature selection. That emergence-profile partition agrees with the GRU-based labels only marginally above chance (Adjusted Rand Index $\approx 0.04$), so a partition of emergence-time features is not a reuse-pattern taxonomy and should not be read as one. On a trajectory-shape task following the published construction, GBDT reaches $0.831$ with all seven features and $0.740$ with the selected subset; the published $0.728$, from a different corpus and labeling, is a reference point rather than a benchmark. Two features are additionally left-truncated for the earliest cohorts, which we quantify.

Editing a chest radiograph requires completing the requested change while preserving unrelated content. We study a latent diffusion editor with an instruction-independent source trajectory and an instruction-conditioned editing trajectory. A learned gate mixes their post-sampler candidates at each executed step, and a separate image-space mask composites the decoded proposal with the source. On 2,400 MIMIC-derived requests, 2,244 outputs met the joint target, preservation, quality, and coverage rubric (93.5%), and target completion was 97.4%. Joint validity exceeded a matched composition-only control by 1.7 percentage points (paired patient-cluster 95% interval, 0.6–2.8). At a fixed learned mask, the learned-gate proposal improved joint validity by 1.6 points (0.8–2.4); at a fixed learned proposal, the learned mask improved it by 2.6 points (1.7–3.5). Across three training seeds, mean joint validity was 93.5% with a 0.3-point sample standard deviation. A blinded 240-request assessment yielded adjudicated joint validity of 93.3% for the full editor and 91.7% for composition only. Protected-region mean absolute error decreased from 0.0190 in the raw proposal to 0.0075 after composition. These findings distinguish recurrent-gating effects on the proposal from preservation through final composition in the assessed cohort.

This paper develops a distributed adaptive neural interval observer for unknown nonlinear systems with locally incomplete measurements. Each sensor node constructs lower and upper state estimates using its local output and neighboring observer information, while unknown nonlinear dynamics are approximated by adaptive neural models. A distributed adaptation mechanism guarantees bounded estimation and weight errors, whereas a cooperative realization preserves the componentwise interval property. To enhance neural-weight convergence without requiring persistent excitation, a finite experience-replay integral concurrent-learning mechanism is incorporated into the adaptation law. For non-Metzler error dynamics, a Sylvester-based coordinate transformation is introduced to recover a Hurwitz–Metzler distributed realization. The theoretical developments are validated through a nonlinear distributed estimation example.

A robot may lose sight of an object it must later retrieve, need to recall what a person demonstrated earlier, or track which steps of a task it has already completed. Current vision-language-action (VLA) policies often fail once the information needed for action disappears from the current observation, making memory critical for long-horizon robot behavior. Existing approaches typically provide longer histories or learn implicit memory from observation-action trajectories. But action supervision tells a policy how to act, not what to remember: it does not specify which past facts should persist or how they should change as new evidence arrives. We therefore separate maintaining an evidence-grounded account of the past from learning how to act on it. This insight motivates Explicit Concept Memory (ECoMEM), which represents task-relevant history with a reusable library of grounded concepts. An evidence-based Writer selects and updates these records, while a learned Reader turns them into memory tokens that directly condition the VLA. Across 16 RoboMME tasks, ECoMEM leads the evaluated robot policies on 15 tasks. On two new real-robot tasks, the same memory library either transfers directly or requires only one new concept, achieving 86.1% success versus 8.6% for a no-memory VLA. These results show that explicit concepts provide a reusable and extensible memory interface for robot control. Project website: https://ecomem.github.io/

This paper develops an event-triggered fixed-time integral reinforcement learning framework for optimal control of unknown nonlinear systems. An integral data-driven identifier is first used to reconstruct the unknown dynamics, after which an inverse-optimal formulation is employed to construct a fixed-time running cost. A learning law satisfying the practical fixed-time property is then derived. Previously collected data, or data obtained during a finite excitation interval, are stored in an experience-replay buffer and incorporated into the weight-update law. This avoids the persistent-excitation condition, which is often difficult to satisfy in practical operation. To reduce communication and control updates, an event-triggered mechanism is introduced. The paper shows that, under the event-triggered implementation, the closed-loop system still achieves practical fixed-time stability, while the proposed triggering rule guarantees the exclusion of Zeno behavior. Finally, a nonlinear example is presented to verify the theoretical results developed in the paper.

Contextual security defenses prevent AI agents from taking rogue actions by synthesizing a task-specific policy and enforcing it on the agent's tool calls. In multi-step tasks, however, which actions are valid often depends on what the agent has already done and learned. We present Sapien, a policy engine for enforcing stateful contextual policies. A Sapien policy specifies permitted tool-call sequences using a regular expression extended with stateful predicates, deferred policy generation, and scoped semantic checks. We show that Sapien stays within a few percent of an unconstrained agent's utility. Even if the agent is fully hijacked, Sapien's policies rule out 93-95% of attacks on AgentDojo and 62-85% on Toolathlon (twice as many as tool allowlists on long-horizon tasks).

This chapter surveys terrain visibility models, algorithms, and applications. It introduces basic definitions, from line-of-sight, single-viewpoint viewsheds to cumulative and total viewsheds, on both Triangulated Irregular Network (TIN) and regular grid terrains. Reviews exact and approximate algorithms and highlights key application domains including archaeology, visual exposure to greenery, scenic route management, and land conservation.

Objective: To assess the accuracy and efficiency of a large language model (LLM) using two prompt strategies to extract structured data from ophthalmic diagnostic PDF reports. Methods: Twenty deidentified reports across four types (Visual Field, OCT Glaucoma Overview, OCT retinal nerve fiber layer Single Exam, and OCT Thickness Map; n = 5 each) were processed using two GPT-4o-assisted pipelines and compared with a reconciled manual ground truth. Schema-Constrained used Structured Output mode with a predefined JSON Schema; Prompt-Only used a detailed instruction prompt followed by Python conversion to JSON. Outcomes were value accuracy, formatting accuracy, and extraction time. Results: Schema-Constrained value accuracy was 100.00% for Visual Field and RNFL Single Exam, 97.45% for Glaucoma Overview, and 98.00% for Thickness Map; Prompt-Only achieved 100.00% across all four report types. Formatting accuracy was 100.00% for Schema-Constrained across all report types and 100.00% for Prompt-Only except RNFL Single Exam (90.14%). Mean extraction time was 56.51 s per report for manual review versus 5.04 s for Schema-Constrained and 4.70 s for Prompt-Only, an approximately 92% reduction. Conclusions: In this small proof-of-concept dataset, general-purpose LLM-assisted pipelines extracted structured data from ophthalmic diagnostic PDFs with high accuracy and substantially reduced processing time. Prompt-Only achieved the highest value accuracy, while Schema-Constrained produced schema-compliant output with 100% formatting accuracy. These complementary strengths support further evaluation of hybrid, validation-aware workflows for research and clinical data abstraction.

We consider the estimation of drift, diffusion, and noise covariance from discrete observations of stochastic differential equations driven by Gaussian processes. For a fixed observation horizon $T>0$ and a known initial state $x_0\in\mathbb R$, we study \begin{equation*} dX_t=a(X_t)\,dt+\sigma(X_t)\,dZ_t^{\beta,f}, \qquad X_0=x_0,\quad 0\leq t\leq T. \end{equation*} \smallskip\noindent Here $a:\mathbb R\to\mathbb R$ is the drift coefficient, $\sigma:\mathbb R\to(0,\infty)$ is the diffusion coefficient, and $Z^{\beta,f}$ is a centered Gaussian process from the weighted sub-fractional Brownian family, with covariance \begin{equation*} \operatorname{Cov}(Z_s^{\beta,f},Z_t^{\beta,f}) =\int_0^{s\wedge t} f(r)q_\beta(s-r,t-r)\,dr, \qquad 0\leq s,t\leq T. \end{equation*} \smallskip\noindent Here $s\wedge t=\min\{s,t\}$. The temporal weight $f:[0,T]\to[0,\infty)$ is measurable, bounded, and positive almost everywhere, and $\beta\in(0,2)$ is the covariance exponent. For $u,v\geq0$, the kernel is $q_\beta(u,v)=[u^\beta+v^\beta-(u+v)^\beta]/(1-\beta)$ when $\beta\ne1$. Its continuous extension at $\beta=1$ is $q_1(u,v)=(u+v)\log(u+v)-u\log u-v\log v$, with $0\log0=0$. Using the Euler approximation, we reconstruct the Gaussian driving increments from observed transitions and use their joint density to obtain a trajectory likelihood. Neural and radial-basis representations model the drift, diffusion, and normalized temporal weight, while a likelihood profile estimates the covariance exponent and diffusion scale. We compare the method with two neural alternatives on the same simulated trajectories in twenty coefficient settings.

Enterprise information is represented through artifacts shaped by applications, projects, technologies, organizational boundaries, and local requirements. These structures accumulate over time, creating representational complexity that must be maintained by the enterprise and interpreted by information consumers and AI systems. This paper introduces Enterprise Representation Simplification (ERS) as reducing unnecessary representational complexity while preserving required information within a defined scope, and Enterprise Representation Complexity (ERC), a representation-neutral model for comparing complexity across representation states. ERC characterizes representational extent through four dimensions: Representation Objects, Interactions, Behaviors, and Supporting Sources. Objects, Interactions, and Behaviors form dependent categories, while Supporting Sources characterize representation exposure. ERC is defined at representation and task levels, enabling comparison and distinguishing architectural simplification from retrieval optimization. The paper develops two consequences of ERS. First, representational structures create lifecycle obligations for maintenance, governance, dependencies, change, enhancement, and operation. An economic model distinguishes recurring global representation cost, recurring task-level cost, and one-time transformation cost, enabling evaluation over a defined time horizon. Second, reductions in task-level ERC reduce the representational extent an AI system must identify, relate, and interpret. Text-to-SQL research provides evidence that reduced schema and reasoning complexity can improve reasoning accuracy. ERC is not a universal complexity, performance, or cost metric. It provides measurable architectural variables for comparing representational alternatives, transformation effects, economic outcomes, and AI reasoning performance.

A correctly governed LLM agent can reach a state in which neither continuing execution nor automatically halting is admissible: the system has detected a persistent failure of its observability or drift-detection layer, but cannot itself decide who has the authority to resume, deny, or recalibrate the deployment. We call this an identity-bound governance event and formalise the mechanism that resolves it. We introduce the Accountability Proof Block (APB): a system-constructed evidence block, a human-supplied decision block, and an ed25519 signature binding both to a registered principal. The system cannot forge the signature, and the principal cannot alter the evidence undetected. We prove four theorems: Protocol-Bounded Governance Completeness, Non-Repudiability, Impossibility of Anonymous Re-Authorization, and Finite-Time APB Construction Termination. The implementation uses RFC 8785 JSON canonicalization and a UUID4-based replay predicate. Empirically, governance completeness holds over 3,812 halt events with zero unresolved cases; the verifier detects 100% of 1,800 attacks across 9 adversarial vectors; a k-of-n multi-principal variant shows 0 false acceptances in 2,000 single-key capture attempts. A study of six open LLMs finds the drift threshold T* stable within model (sigma/T* < 2%) but varying across models, refuting size-monotonicity: the largest model did not drift. T* must therefore be measured per deployment, and the APB is the vehicle by which that threshold yields accountable authority transfer.

Flow matching (FM) learns generative transport by fitting continuous-time motion from a simple source distribution to the data distribution. Most existing methods use first-order bridges: once a source and a target sample are paired, the path is a straight motion with constant velocity. FM with optimal transport (OT) improves the pairing, but the bridge itself remains linear, limiting its ability to model curved motion, acceleration, and changing directions. A natural remedy is to use second-order phase-space dynamics; however, learning the bridge requires target-side terminal-velocity information that static datasets do not provide. We propose Variational Terminal-Velocity Flow Matching (VTV-FM), a second-order FM framework that derives the missing velocity by minimizing acceleration energy, yielding a closed-form closure for static data. The same minimum-acceleration variational construction also defines the OT pairing cost and the acceleration targets used for training. Experiments on low-dimensional datasets, PDE-governed physical fields, and CIFAR-10 show that VTV-FM improves transport geometry and generation quality over first-order and high-order FM baselines.

Teleoperated demonstrations are a primary source of data for robot manipulation, and teleoperated interventions are a primary mechanism for correcting policies at deployment. Yet most teleoperation systems close the loop through vision alone and are built around parallel-jaw grippers, limiting both what the robot can execute and what the operator can express through it. This is most damaging in shared autonomy, where the operator sees the scene only through occluded cameras and must take over a dexterous hand mid-task, often with an object already grasped. We present DITTO-X, a hand-agnostic dexterous teleoperation interface that renders joint-level force and fingertip contact events from sensing already on the robot hand, and drives three commercial dexterous hands (Sharpa, Wuji, and Inspire) without per-hand redesign. Because the exoskeleton is actuated, DITTO-X also supports reverse teleoperation, in which the robot back-drives the operator's fingers into its own configuration before control is transferred, so the human enters the loop already matched to the state they inherit. Our results show that DITTO-X improves demonstration quality and throughput over a commercial hand-tracking glove, both in regular data collection and in human intervention during policy deployment for contact-rich manipulation tasks. More information can be found from our website: https://tml.stanford.edu/ditto-x/.

Image watermarking supports provenance and attribution by embedding verifiable identity information into images. Practical deployments, however, must jointly satisfy requirements for attack resistance, false-positive rate (FPR), image quality, and latency. Existing watermarking methods are robust to different classes of transformations, so combining complementary methods can provide broader protection than any single watermark. Such composition is challenging, as additional fragments increase distortion and decoding cost and must share the same FPR budget. Therefore, we propose **TAILOR**, a request-conditioned watermark composition framework with three stages: (1) *offline characterization* measures fragment recovery, distortion, and runtime as response curves over embedding strength; (2) *joint configuration selection* encodes the request as an SMT model over these curves and solves for the lowest-distortion composition of fragments, strengths, order, and geometric recovery; and (3) *live calibration* validates the selected configuration on the user's images and refines predictions that fail to transfer. Experimental results across 7,321 distinct requests spanning five scenarios and 20 attack settings show that **TAILOR** achieves **96.21%** scenario-averaged request satisfaction with a mean PSNR of **41.02 dB**, outperforming existing methods in robustness while achieving consistently better image quality. Code is available at [https://github.com/aaFrostnova/Tailor](https://github.com/aaFrostnova/Tailor).

Synthetic data now is essential to LLM training, used to strengthen advanced capabilities such as autonomous and long-horizon task execution. Yet recent work shows that training on it at scale can degrade model generation, making it important to decide what synthetic data is worth training on. While current data curation practices do so with individual-level signals (i.e., estimates of each data sample's training utility in isolation), across pre-training and post-training settings we show that this is insufficient for synthetic data, and that group-level signals (i.e., estimates of utility that account for interactions among data samples) are necessary for effective data curation. First, we show that individual-level signals are blind to how samples jointly affect training: synthetic datasets with different compositions can be indistinguishable under individual-level influence yet differ sharply under group-level influence, and curating by the latter yields better downstream performance, particularly in generative capability. Second, we find that group-level signals matter more as training pipelines become increasingly synthetic: among widely used data curation methods, only those incorporating them improve over baseline, with gains increasing when weights capturing relations among samples are amplified. Finally, we translate these findings into practice – for model developers under a compute budget, we offer a cheap diagnostic that prioritizes which groups of synthetic data most need group-level estimation, recovering much of the benefit of full group-level scoring at a fraction of the compute cost.

In goal-conditioned reinforcement learning (GCRL), quasimetric learning models goal-reaching costs as quasimetric distances, connecting local constraints to global value geometry. Its local constraints, however, should reflect the direction- dependent effects of control composition over a finite horizon together with environmental feasibility. We propose ReQRL, which constrains the critic's value gradients through finite-horizon reachability. Drawing on state-constrained optimal control, we decouple dynamical reachability from boundary geometry, estimating both from data. On OGBench, our method outperforms or rivals existing quasimetric approaches and other offline GCRL methods.

A $k$-arrangement of pseudolines is a set of bi-infinite curves in the plane such that any two of them intersect each other in exactly $k$ points, at which they cross, and it is simple if no three curves meet at a common point. Cyclic arrangements are the only simple $1$-arrangements of pseudolines that are unavoidable, in the Ramsey spirit: for each fixed $m\ge 1$, every sufficiently large simple $1$-arrangement of pseudolines has a cyclic subarrangement of size $m$. We show that, for every $m\ge 3$, the number of unavoidable simple $k$-arrangements of pseudolines of size $m$ grows exponentially with $k$, independently of $m$. For even $k$, we prove an analogous result for $k$-arrangements of pseudocircles.

A central puzzle in transfer learning is why pre-training on one task can accelerate training or improve performance on another task, and what mechanisms underlie this transfer. In this work, we examine the transfer between memorization tasks of random input-output mappings. We find two surprising transfer patterns: equivalent transfer, where each additional pre-training epoch saves approximately one downstream fine-tuning epoch; and non-equivalent transfer, where pre-training on a mismatched task can be even more efficient than directly training on the downstream task itself. Through ablation experiments, we decompose and localize the transfer into two separate effects: a "trivial" magnitude-driven transfer in the last layer, and a "non-trivial" structure-driven transfer, partially attributable to the covariance of the other layers. These results advance our understanding of the underlying mechanisms of transfer learning and have the potential to lead to principled pre-training strategies.

Pre-training interventions are critical to alignment research, since beliefs formed during pre-training shape how a model generalizes from later training. One recently popular technique for such interventions is synthetic document fine-tuning (SDF), which aims to alter what the model believes. Ideally, synthetic documents would be mixed into pre- or mid-training, but every change to a pre-training corpus must be followed by a full post-training run before its effect can be measured, making iteration slow and expensive. Common practice instead applies SDF to an already post-trained model. This is known to leave artifacts and degrade capabilities, and, as we show, it makes the model treat fabricated entities unrelated to the documents as real, a failure we call reality drift. We propose grafting: train the SDF adapter on the pre-trained checkpoint, then add the learned weight update to the post-trained model, which approximates the faithful approach while reusing the existing post-training. We demonstrate this by installing false facts, training misaligned model organisms and applying a constitutional mid-training intervention, across model families up to 284B parameters. Grafting installs the target belief as strongly as SDF on the post-trained model while reducing both reality drift and the loss of preference coherence by more than half on average, and it stays closer to a faithful mid-training run. Because grafting requires no post-training, the same adapter can be applied to any later checkpoint, enabling researchers to iterate quickly on pre-training interventions at the cost of a single fine-tuning run.