arXiv:2607.04141v1 Announce Type: cross Abstract: We introduce split-free cable terms and cable plays, a sequential graph-construction language whose live cables impose uniform GF(2)-row behaviour across the current cut. Every play of width w gives a birth-order layout whose cutrank is at most half of w, rounded down, so the sequential split-free width is at least twice the linear rank-width. At the first nontrivial level we prove an exact characterization: a connected graph with at least two vertices has linear rank-width at most one exactly when it admits a stream, equivalently a singleton-birth play of width at most four. We show that unrestricted term width and sequential width differ unboundedly on trees, calibrate the construction on the net graph, and formulate an affine upper-bound conjecture relating sequential split-free width to linear rank-width. For the rank-two case we prove a two-accumulator scheduling criterion that yields width-six plays under a natural future-uniformity hypothesis.
Science Journals
arXiv:2607.04984v1 Announce Type: new Abstract: Continual Generalized Category Discovery (C-GCD) aims to incrementally identify novel categories from sequential unlabeled data while preserving recognition of known classes, which is an essential capability for open-world visual learning. A major bottleneck lies in ambiguous unlabeled samples that cannot be confidently assigned to known classes nor reliably grouped as novel ones, making pseudo-labeling brittle and often biasing learning toward familiar categories. In this work, we introduce Virtual Category-Guided Continual Generalized Category Discovery by adapting Virtual Category Learning (VCL) to the continual setting. Our method identifies uncertain samples and assigns them to temporary virtual categories, enabling safe and informative learning from unlabeled streams without injecting noisy labels, while improving unlabeled data utilization and mitigating prediction bias. To further stabilize discovery across sessions and enhance class separation, we augment VCL with Expanded Neighborhood Contrastive Learning (ENCL), which exploits extended neighborhood relations and an adaptive margin to learn more discriminative and well-separated representations for both old and emerging classes. Extensive experiments on CIFAR-100, Tiny ImageNet, and ImageNet-100 demonstrate that our approach consistently outperforms state-of-the-art methods, establishing a scalable and effective solution for C-GCD.
arXiv:2607.04213v1 Announce Type: cross Abstract: We study a receding horizon game in which multiple agents drive linear systems subject to additive disturbances, private state and input constraints, and shared coupling constraints. We propose a robust game-theoretic control framework that combines tube-based constraint tightening with a finite-horizon generalized Nash equilibrium problem (GNEP), equipped with a discrete algebraic Riccati equation (DARE)-based terminal cost and a decoupled positively invariant terminal set. The framework guarantees recursive feasibility for every bounded disturbance realization. Exploiting the potential-game structure induced by tracking costs, we further establish asymptotic convergence of each agent's nominal state to a steady-state variational generalized Nash equilibrium (vGNE), and show that each agent's actual state converges to a neighborhood of the vGNE determined by the minimal robust positively invariant set.
PTCOG Treatment Efficiency Subcommittee Risk Assessment Report on Patient-Specific Quality Assurance
arXiv:2607.04446v1 Announce Type: new Abstract: Patient-specific quality assurance (PSQA) in pencil beam scanning proton therapy (PBS-PT) is often treated as a purely technical verification task. This PTCOG Treatment Efficiency Subcommittee White Paper instead frames PSQA as a workflow-embedded risk-control strategy and asks how different PSQA approaches reshape the same clinical risk landscape. Using a generic PBS-PT process-driven Failure Mode and Effects Analysis (pFMEA), 44 validated PSQA-relevant failure modes across 20 process steps were scored under a common no-PSQA baseline and three PSQA pathways: measurement-based PSQA, log file-based PSQA, and independent secondary dose calculation. A staged mathematical formalism separates preparatory data-stage effects, method-specific full-stage verification, cumulative endstate effects, and a Data-to-Cum bridge that quantifies additional verification benefit on the baseline scale. In this expert-scored, baseline-anchored model, log file-based PSQA produced the largest cumulative workflow-level risk-score reduction, followed by measurement-based PSQA and independent secondary dose calculation. The ranking is not a winner-takes-all rule or probability-calibrated risk estimate; instead, each method shows distinct risk-control strengths in different workflow regions. The White Paper therefore supports a risk-informed hybrid PSQA architecture, where log file-based PSQA, measurement-based PSQA, and independent secondary dose calculation are assigned to the workflow segments in which their signatures are strongest. It provides a transparent, semi-quantitative, stage-resolved framework for institutions seeking to evaluate, implement, or evolve PSQA in PBS-PT and emphasizes that log file-based PSQA must itself be supported by validated and governed log data and treatment records.
arXiv:2607.04451v1 Announce Type: new Abstract: Evaluation of autonomous vehicle (AV) planners in safety-critical closed-loop simulation is essential for real-world deployment. However, generating controllable safety-critical scenarios remains challenging. Existing approaches use soft guidance that provides only probabilistic preferences and cannot guarantee the satisfaction of geometric and severity constraints associated with specific collision types. We introduce Collision-Constrained Flow Matching (CCFM), a novel framework that guarantees precise collision control through hard physical constraints. CCFM consists of three key components: (i) a heuristic collision selector that optimally identifies an adversarial agent and collision type via composite scoring; (ii) structured hard constraints that explicitly define four collision types (rear-end, side, cut-in, head-on) through contact point, heading, and severity requirements; and (iii) a collision-constrained flow matching sampler that enforces the constraints via Gauss-Newton manifold projection. CCFM achieves collision rate up to 46.4% on nuScenes and 83.1% on nuPlan, significantly outperforming baselines while preserving realistic driving behavior. By enabling controllable collision characteristics in safety-critical scenario generation, CCFM provides a reliable foundation for AV safety evaluation and sim-to-real crash data generation. The code and implementation details are available at https://github.com/KELISBU/CCFM.
arXiv:2607.04453v1 Announce Type: new Abstract: The assessment of planktonic standing stocks and microorganism structures is critical for understanding upper ocean biological processes. Currently, autonomous underwater vehicles (AUVs) equipped with in-situ optical imaging and artificial intelligence (AI) methods offer a promising solution for persistent surveillance, mapping and monitoring of planktonic life. However, current AI methods often lack robustness in dynamic, unstructured environments, where environmental noise and non-biological artifacts lead to frequent misclassifications. Standard convolutional neural network (CNN) classifiers often struggle with such conditions, leading to misclassifications that require time-consuming manual validation by marine biologists. To address this issue, we propose a novel robustness verification framework for in-situ plankton classifiers based on reachability analysis. We also introduce a continuous-time neural ordinary differential equation (neural ODE) classification model leveraging the high-resolution imaging capabilities of the SilCam particle imager. In this paper, we demonstrate the effectiveness of the proposed framework by formally verifying the robustness of the neural ODE model against environmental perturbations. We demonstrate that our verification framework acts as an automated filter providing formal guarantees of model stability against ambiguous data, thereby improving the reliability of autonomous sampling and reducing the post-processing workload.
arXiv:2607.05056v1 Announce Type: new Abstract: Recently, diffusion models have achieved considerable success in the text-guided video editing domain. However, existing works often struggle to balance the trade-off between temporal consistency and editability in video editing, with consistency and editability typically being inversely related. To address this, we propose a high-quality video editing framework enhanced for consistency and editability, named EquiEdit, which improves coordinatively the temporal consistency and editability of the edited videos while achieving a balance between the two. In terms of temporal consistency, the proposed temporal Mamba module with a tailored temporal-aware scanning scans fused video sequences following four designed directions, effectively enhancing the inter-frame consistency of edited videos. For editability, we design a noise injection strategy based on the spectral transformation to increase editing flexibility, where the Fourier transform is used to preserve the hidden structure in the initial latent noise used for editing, ensuring inter-frame consistency of the edited video and fidelity to the input video. Extensive qualitative and quantitative experiments demonstrate the effectiveness of our method in terms of temporal consistency and editability, as well as its great fidelity to the input video itself.
arXiv:2607.04215v1 Announce Type: cross Abstract: A central challenge in many mobile multi-robot applications is that communication topologies are inherently time-varying. Agents may enter or exit the network and such changes cannot generally be restricted a priori. This work introduces a distributed multi-agent control algorithm based on local communication that supports anytime agent joining and leaving the communication network without centralized coordination. The method scales efficiently with the number of agents by relying on a distance-based neighbor definition and on contracts derived from predicted trajectories. The resulting contract constraints guarantee collision avoidance and constraint satisfaction. We validate the proposed method in an autonomous multi-agent driving scenario, demonstrating effective collision avoidance in high-speed, dynamic environments with agents moving in opposite directions, in both simulated and real-world experiments.
arXiv:2607.05069v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) improves factuality by grounding LLMs in external evidence, but real-world retrieval is often polluted: semantically relevant passages may contain subtle misinformation, misleading framings, or fabrications. We introduce MIRAGE, a training-free, model-agnostic defense for long-form RAG. MIRAGE builds an NLI-based cross-document claim graph and applies a Defended-Claims Gate to either condition generation on a consistent, multi-source supported subset or to block retrieval and answer parametrically. We also release a minimal-edit pollution protocol spanning four perturbation families (Unambiguous, Conflicting, Misleading, Fabricated) to construct matched clean, mixed, and fully polluted evaluation regimes. Across four long-form QA benchmarks and multiple commercial and open-weight LLMs, pollution severely degrades vanilla RAG, while MIRAGE consistently restores factuality under mixed and fully polluted evidence and outperforms prior robust-RAG methods. Our implementation and datasets are available at https://github.com/SaadElDine/MIRAGE.
arXiv:2607.03137v1 Announce Type: cross Abstract: Carbon-supported single-atom catalysts maximize metal utilization, but how metal nanoparticles transform into isolated atoms within carbon remains unclear. We show that metal nanoparticles can undergo a self-driven dispersion process under hydrocarbon oxidation conditions, transforming into single atoms that are confined in carbon matrix. Using Pt-catalysed hydrocarbon oxidation as a model, we combine operando electron microscopy, near-ambient-pressure X-ray photoelectron spectroscopy and mass spectrometry to track coupled structural and chemical evolution. Graphitic carbon grows at step edges of Pt nanoparticle, continuously reconstructing Pt surface and generating undercoordinated sites for atom release. In-situ generated CO accumulates at the metal-carbon interface, weakening bonding and facilitating self-amplified atom release and migration. Defective carbon overlayers then trap, stabilize and transport liberated atoms, while oxidative etching preserves interfacial access of reaction-gas. Similar behaviour across other metals suggests a general atomization pathway for single-atom catalyst synthesis, yielding products with electrocatalytic hydrogen production activity beyond standard commercial benchmarks.
arXiv:2607.05135v1 Announce Type: new Abstract: Fully developed isotropic turbulence exhibits a dual nature: a continuous, scale-invariant energy cascade coexists with discrete, intense vortex filaments. We show that this duality arises from a spontaneously broken SO(3) gauge symmetry. By identifying the specific angular momentum $\mathbf{L} = \mathbf{r}\times\mathbf{u}$ as a non-Abelian gauge connection and the radial velocity $u_r$ as a Higgs field, the turbulent vacuum is described by the SO(3) Georgi-Glashow model. When the radial strain condenses, the symmetry breaks SO(3) $\to$ U(1), generating a topological mass gap $M_W = gv$. This gap partitions the energy into a massless U(1) sector (the solenoidal background) that sustains the Kolmogorov cascade, and a massive SO(3)/U(1) sector that is confined to vortex filaments. Using high-resolution DNS data (JHTDB, $Re_\lambda\approx433$), we empirically verify three key predictions: (i) the energy spectra obey a strict 1:2 equipartition over the inertial range, with a sharp divergence at $M_W \approx 40$; (ii) the radial Higgs field extracted around isolated vortex cores follows the exact BPS monopole profile $H(r)=\coth(r/\eta)-\eta/r$ with $\eta = 0.0093$ domain units and the VEV $v = 0.338$, identifying the ubiquitous "worms" as macroscopic 't Hooft-Polyakov monopoles; (iii) the Wilson loop computed from the velocity field exhibits a clean area law $\langle W_C \rangle \sim e^{-\sigma A}$ with string tension $\sigma = 0.303 \pm 0.009$, directly confirming the confining nature of the turbulent vacuum.
arXiv:2607.05142v1 Announce Type: new Abstract: Standard Pancharatnam-Berry and linear-birefringent media convert optical spin into orbital angular momentum (OAM) through an anisotropy \emph{director}, a rank-two, headless field, and therefore obey the selection rule $\Delta\ell=2q$ per unit texture charge $q$. We show that a medium with geometric \emph{torsion}, the continuum limit of a screw-dislocation array, can convert spin to OAM through the \emph{contortion} of its material connection, which enters the effective paraxial dynamics as a rank-one vector field. The resulting selection rule is $\Delta\ell=q$. Its winding is fixed by geometry and symmetry, not by a Pancharatnam--Berry director, and the process conserves the screw charge $\tilde J_z=L_z+(q/2)\sigma_z$ while exchanging $(2-q)\hbar$ of angular momentum per converted photon with the defect lattice. Paraxial simulations confirm the rule: a circular Gaussian input develops a stable, topologically quantized $\ell=+q$ vortex in the reversed helicity, with $83\%$ conversion over three Rayleigh ranges and no fine-tuning. We propose a polarization-resolved photonic-lattice discriminator in which the slope of the measured OAM versus the independently written texture charge, one for torsion, two for birefringence, separates the two mechanisms.
arXiv:2607.05188v1 Announce Type: new Abstract: A coding agent solving a software-engineering task spends dozens of steps reasoning, editing code, and running tests, yet little is known about what the underlying language model internally represents about the program it is working on. We show that the residual streams of language models under coding agents linearly encode properties of the evolving program: a logistic-regression probe on hidden states is able to decode whether the current code parses, passes its test suite, reduces the number of failing tests, and introduces regressions, reaching AUC up to 0.83 for correctness across two models and two benchmarks. Our second finding is more surprising: these representations run ahead of the agent's own edits. Probes trained to predict the outcome of future edits (before they are materialized and written on disk) achieve performance above chance up to roughly 25 steps in advance. We call this the agent's latent programming horizon. As a proof of external validity, we show that the probes transfer across benchmarks without retraining. Our positive results open calls for more research in mechanistic interpretability of coding agents.
arXiv:2607.05160v1 Announce Type: new Abstract: We present a new algebraic modeling of the Supersingular Isogeny Problem as a system of multivariate polynomial equations, in the case where the elliptic curves are connected by an isogeny whose degree is a power of $2$ or $3$. This modeling relies on Renes formulas for elliptic curves in Montgomery form (degree $2$) or triangular form (degree $3$). We investigate several algebraic properties of these systems: we prove that they are zero-dimensional, compute the dimension of their highest degree part, and show that they are not in generic coordinates. Experimental results show that solving these systems via Gr\"obner basis techniques is significantly faster than solving the algebraic modeling with modular polynomials.
arXiv:2607.05230v1 Announce Type: new Abstract: Pre-term infants are susceptible to potentially harmful apnoea-related cessations of breathing due to immature respiratory control. However, reliable respiratory monitoring in the neonatal intensive care unit (NICU) remains challenging because motion artefacts, sensor displacement, and skin fragility can compromise contact-based measurements. Non-contact video monitoring offers a complementary approach that does not depend on adhesive sensors while providing additional respiratory information. We investigated whether camera-based signals can detect apnoea-related cessation of breathing (COBE) and provide complementary information to routinely acquired physiological signals. Using video and clinical recordings from 30 pre-term infants, respiratory motion was extracted from dynamically tracked torso regions to generate camera-derived time-series signals. Camera-only models were trained using residual network (ResNet) architectures, while hybrid models combined video-derived signals with impedance pneumography (IP), ECG-derived respiration (EDR), and the PPG-derived respiratory envelope. Camera-only models achieved a balanced accuracy of 76.9%, demonstrating the feasibility of non-contact COBE detection. Combining video-derived features with IP improved balanced accuracy to 90.6%, outperforming either modality alone and indicating that video provides respiratory information beyond standard physiological signals. These findings show that video-derived signals contain clinically relevant respiratory features and enhance COBE detection when combined with conventional physiological signals. This supports non-contact video as a complementary modality for automated COBE detection and highlights its potential to improve the robustness of neonatal respiratory monitoring.
arXiv:2605.09018v3 Announce Type: replace Abstract: We introduce Evolutionary Ensemble (EvE), a decentralized framework that organizes existing, highly capable coding agents into a live, co-evolving system for algorithmic discovery. Rather than reinventing the wheel within the "LLMs as optimizers" paradigm, EvE fixes the base agent substrate and focuses entirely on evolving the cumulative guidance and skills that dictate agent behaviors. By maintaining two co-evolving populations, namely functional code solvers and agent guidance states, the system evaluates agents through a synchronous race, updating their empirical Elo ratings based on the marginal gains they contribute to the current solver state. When applied to a research bottleneck in In-Context Operator Networks (ICON), EvE autonomously discovered a robust rescale-then-interpolate mechanism that enables reliable example-count generalization. Crucially, controlled ablations reveal the absolute necessity of stage-dependent agent adaptation to navigate the shifting search landscapes of complex codebases. Compared to variants driven by a fixed initial agent or even a frozen "best-evolved" agent, EvE uniquely avoids phase mismatch, demonstrating that organizing agents into a self-revising ensemble is the fundamental driver for breaking through static performance ceilings.
arXiv:2607.05227v1 Announce Type: new Abstract: The reliance on software as a distinguishing factor in the automotive industry is increasing. With a combined reliance on vendor-supplied software and cost-effective implementation, the AUTOSAR consortium was initialized to provide standardized platform specifications that enable re-use. Specifically, the AUTOSAR Adaptive Platform (AP) specification aims to provide a high-performance service-oriented architecture. Objective: The goal of this study is to investigate what pain-points emerge when developing AUTOSAR Adaptive applications and whether they originate from the platform specification, its vendor-implementation, or its local usage. Methods: We conduct a Design Science Research study, developing a minimal AP that serves as an experimental prototype for our investigation. Results: We find that a combination of specification-inherent, implementation-based, and local practices contributes to the emergence of pain-points. Conclusions: We conclude that there are AUTOSAR specification-inherent reasons for pain-points, resulting from architectural choices and re-use goals. The implication for development organizations is the need to mitigate these effects through tooling that better supports configuration file management and reduces developer training time to properly understand the adaptive application runtime life-cycle.
arXiv:2607.05046v1 Announce Type: new Abstract: Evaluating generative AI models is a routine, but resource-intensive, process that is conducted over and over again during the course of model development. In this work, we propose Collaborative Evaluation (CollabEval), a simple, effective, and principled method for exploiting dependencies between historical runs of different models on the same tasks to improve statistical efficiency. Specifically, our approach treats model evaluation as a matrix completion problem over an $M \times N$ matrix of evaluation scores, where $M$ is the total number of models and $N$ is the total number of evaluation prompts. We assume that a subset of these $M$ models are targeted for evaluation. For these target models only a small fraction, $p$, of prompts has been annotated with evaluation scores. Leveraging recent results in prediction-powered inference, we build a low-rank approximation of the score matrix, and use the reconstructed values as control variates in a manner that guarantees unbiased estimates of the true evaluation metric mean, in addition to statistically valid confidence intervals. Empirically, across a wide range of datasets, models, and sparsity levels $p$, we find that CollabEval substantially reduces the mean confidence interval size, and the mean squared error of the point estimate, compared to baseline methods at the same annotation budget.
arXiv:2607.05088v1 Announce Type: new Abstract: Text-to-image (T2I) diffusion models have achieved striking progress but still struggle to synthesize rare concepts involving unusual attribute-object pairings, often resulting in concept omission or semantic drift where a dominant entity overwhelms the generation. Tracing these failures to a lack of compositional balance during the denoising trajectory, we propose RADIANCE, a training-free framework that treats inference as a closed-loop feedback process. RADIANCE augments pretrained backbones with three modular components: (1) a Compositional Similarity Monitor (CSM) that tracks the emergence of objects and attributes in intermediate latents via CLIP-based feedback; (2) a Bidirectional Scale Controller (BSC) that applies a reactive "restoring force" using positive and negative IP-Adapter scales to rebalance biased trajectories; and (3) a Feedback Guidance Scheduler (FGS) that coordinates these updates across timesteps without additional training. We further extend the framework to multi-object prompts via Delayed Adapter Activation (DAA) and Layer-wise Alternating Guidance (LAG) to prevent premature concept fusion. By overlapping monitoring and denoising through pipelined execution, RADIANCE maintains competitive latency while significantly enhancing the per-sample success rate and effective throughput. Experiments on RareBench and T2I-CompBench demonstrate that RADIANCE consistently enhances compositional alignment and perceptual quality over state-of-the-art baselines.
arXiv:2607.05098v1 Announce Type: new Abstract: When sensitive attributes are continuous and high-dimensional $-$ demographic score vectors, posteriors over attributes, age or income profiles $-$ enforcing full statistical independence is often too restrictive, and existing relaxations rely on indirect dependence penalties or adversarial schemes that do not directly target the fairness-accuracy trade-off. We instead consider mean demographic parity through DPVar, the variance of the conditional-mean prediction given the sensitive attribute, and show that optimizing it yields a functional bilevel problem. We propose two algorithms for this problem: FBO, which uses a closed-form adjoint we derive for the squared-loss case to obtain an exact hypergradient, and ITD, which differentiates through unrolled inner steps and extends beyond squared loss. On synthetic data and a new semi-synthetic benchmark built from 60 tabular regression datasets, both methods achieve the lowest or near-lowest aggregate fairness-accuracy regret, and consistently match or outperform strong HSIC, adversarial, linear-dependence, and generalized-DP baselines.
arXiv:2607.05243v1 Announce Type: new Abstract: Reconstructing dynamic human-scene environments from monocular videos is a challenging problem that requires jointly modeling scene geometry, camera motion, and non-rigid human dynamics while enabling photorealistic rendering. Recent feed-forward methods can efficiently predict geometry, but they are often limited to non-photorealistic representations such as point clouds and meshes, or they fail to handle non-rigid objects, particularly dynamic humans. To fill this gap, we present GUSH3R (Gaussian-Unified Scene Human 3D Reconstruction), a feed-forward framework for online dynamic human-scene reconstruction. From a monocular human-scene video, our method reconstructs dynamic humans (everyone) and static scenes (everywhere) in a single forward pass (all at once) as 3D Gaussian Splatting (3DGS) primitives (as gaussians), which are geometrically consistent and capable of novel view synthesis. Experiments on monocular human-scene datasets demonstrate that our approach achieves competitive novel view synthesis quality while significantly improving inference efficiency compared to optimization-based methods.
arXiv:2605.09030v2 Announce Type: replace Abstract: Raw cosine in the 768-dimensional output space of the Contrastive Style Descriptor (CSD) is now widely read as an absolute, calibrated style-fidelity score for text-to-image and style-imitation evaluation. We introduce the discrimination gap, a corpus-internal, prototype-free and threshold-free diagnostic that tests whether contrastive style cosines admit an absolute same-versus-different interpretation on a candidate artist corpus. On a 1799-artwork, 91-artist public-domain corpus, raw CSD cosine yields negative point-estimate gaps for $23/91$ artists at the pairwise level ($2/91$ robust under bootstrap) and for $15/91$ in the aggregated-pool scoring regime style-fidelity evaluations typically use. CSLS readout on the frozen backbone reduces the aggregated negative-gap count to $4/91$; combined with positional-embedding interpolation to $336$ pixels it raises unsupervised pair-verification AUC from $0.883$ to $0.905$ across $25$ artist-disjoint splits. We refer to this diagnostic-driven readout protocol on the frozen backbone (CSLS as default, pos-interp $336$ as the stronger optional setting) as CSD+, not a new encoder.A cross-backbone check on CLIP-ViT-L/14, SigLIP-large and DINOv2-Large reproduces the same shared-tradition failure pattern, providing evidence that the residual reflects a shared limitation of the four backbones we tested rather than a CSD-specific artefact. Practical implication: before reporting CSD cosine as an absolute style-fidelity score, run the diagnostic on the candidate corpus; CSLS is the minimal correction when it fails.
arXiv:2605.10840v4 Announce Type: replace Abstract: We present Clin-JEPA, a multi-phase co-training framework for joint-embedding predictive (JEPA) pretraining on EHR patient trajectories. JEPA architectures have enabled latent-space planning in robotics and high-quality representation learning in vision, but extending the paradigm to EHR data -- to obtain a single backbone that simultaneously forecasts patient trajectories and serves diverse downstream risk-prediction tasks without per-task fine-tuning -- remains an open challenge. Existing JEPA frameworks either discard the predictor after pretraining (I-JEPA, V-JEPA) or train it on a frozen pretrained encoder (V-JEPA 2-AC), leaving the encoder unaware of the rollout signal that the retained predictor must use at inference; co-training the encoder and predictor under a shared JEPA prediction objective would supply this grounding, but na\"ive co-training is unstable, with representation collapse and online/target drift causing autoregressive rollout to diverge. Clin-JEPA's five-phase pretraining curriculum -- predictor warmup, joint refinement, EMA target alignment, hard sync, and predictor finalization -- addresses each failure mode by phase, stably co-training a Qwen3-8B-based encoder and a 92M-parameter latent trajectory predictor. On MIMIC-IV ICU data, three independent evaluations support the framework: (1) latent $\ell_1$ rollout drift uniquely converges ($-$15.7%) over 48-hour horizons while baselines and ablations diverge (+3% to +4951%); (2) the encoder learns a clinically discriminative latent geometry (deteriorating-patient cohorts displace 4.83$\times$ further than stable patients in latent space, vs $\leq$2.62$\times$ for baseline encoders); (3) a single backbone outperforms strong tabular and sequence baselines on multi-task downstream evaluation. Clin-JEPA achieves mean AUROC 0.851 on ICareFM EEP and 0.883 on 8 binary risk tasks (+0.038 and +0.041 vs baseline average).
arXiv:2605.11021v3 Announce Type: replace Abstract: Q-learning is a fundamental algorithmic primitive in reinforcement learning. This paper develops a new framework for analyzing linear Q-learning from a switching linear system (SLS) viewpoint, where linear Q-learning denotes Q-learning with linear function approximation. We derive a stochastic SLS representation of the linear Q-learning error and obtain a finite-time error analysis for linear Q-learning through the joint spectral radius (JSR) of the associated SLS family; the JSR is the exact worst-case exponential rate of the corresponding SLSs. The JSR-based rate is tied to the intrinsic worst-case exponential rate of the SLS representation. Moreover, we provide a JSR-based certificate for convergence of linear Q-learning, which can be less conservative than one-step norm bounds.
arXiv:2605.12191v3 Announce Type: replace Abstract: Given rationals $\alpha$ and $\beta$, the sure-almost-sure problem for a threshold Boolean objective $\varphi$ in a Markov decision process (MDP) asks if one can simultaneously ensure that all outcomes of the MDP have $\varphi$-value at least $\alpha$ (i.e. sure $\alpha$ satisfaction) and with probability $1$ the outcome has $\varphi$-value at least $\beta$ (i.e. almost-sure $\beta$ satisfaction). The sure-limit-sure problem asks if for all $\varepsilon > 0$ one can simultaneously ensure that all outcomes have $\varphi$-value at least $\alpha$ and with probability at least $1 - \varepsilon$ the outcome has $\varphi$-value at least $\beta$. Moreover, if simultaneous satisfaction of objectives is possible, then one would also like to construct a strategy (for sure-almost-sure) or a family of strategies (for sure-limit-sure) that achieves this. In this paper, we solve the sure-almost-sure and sure-limit-sure problems for window mean-payoff objectives. The window mean-payoff objective strengthens the standard mean-payoff objective by requiring that eventually, from every point in the infinite run, the average payoff becomes greater than a given threshold within a finite window length. We study two variants of window mean payoff: in the fixed variant, the window length $\ell$ is given, while in the bounded variant, the length is not given but is required to be bounded throughout the run. We show that the sure-almost-sure problem and the sure-limit-sure problem are both in P for the fixed variant (if $\ell$ is given in unary) and are both in NP $\cap$ coNP for the bounded variant, matching the computational complexity of sure satisfaction and almost-sure satisfaction when considered separately for these objectives. We also give bounds for the memory requirement of winning strategies for all considered problems.