Papers

Runtime enforcers observe a system's behavior and exert control over it to ensure that the system always adheres to its requirements. Many natural requirements not only formulate restrictions on the system's present behavior, but also impose obligations on its future behavior; for instance, agentic security may require personal data collected during a run to be erased by some deadline. In an ever-growing compliance landscape, real-world systems may be subject to hundreds of such requirements. However, existing enforcement mechanisms supporting complex policies are often too slow for production software; instead, developers may resort to non-temporal access control mechanisms and ad-hoc instrumentation, but these scale poorly with requirement complexity. To address this problem, we introduce an efficient algorithm and tool for enforcing complex temporal requirements and demonstrate its performance. Specifically, we identify a fragment of Metric First-Order Temporal Logic (MFOTL) that can be enforced with low runtime complexity while supporting a rich family of practically relevant requirements, including obligations. We then design an enforcement algorithm for this fragment and implement it in EnfFlash, a novel tool that enforces requirements with latency up to 44x lower than EnfGuard, the previous state-of-the-art enforcer, on standard benchmarks, and up to three orders of magnitude lower on security policies for LLM agents. This performance is achieved by compiling requirements into imperative programs that we efficiently interpret. We evaluate EnfFlash both standalone, on existing benchmarks, and integrated in web applications as an enforcement backend. We demonstrate that it can enforce a substantial 400-line MFOTL formula specifying the GDPR on a social network while adding under 15 ms to each page view, which is sufficient for most interactive and real-time applications.

Hierarchical control architectures are widely used to decompose complex control problems into interacting control levels and are particularly important in robotics, where planning, whole-body motion, and lower-level control must be coordinated across different levels of abstraction and time scales. Their overall closed-loop performance, however, depends strongly on parameters distributed across the hierarchy, such that tuning controllers on different levels independently may neglect relevant cross-layer interactions. We propose a contextual Bayesian optimization framework for joint parameter learning in hierarchical control systems. Rather than modeling closed-loop performance only as a scalar black-box function, we retain separate observations of task performance, realization quality, and control effort. A correlated multi-output Gaussian process models these performance components, while their known aggregation into the overall closed-loop objective is evaluated analytically. The formulation exploits three complementary consequences of hierarchical control: informative performance quantities exposed by the hierarchy, coupling between parameters of different controller levels, and variations of these relations with operating conditions. We evaluate the approach for humanoid loco-manipulation, jointly tuning a centroidal predictive controller and a whole-body controller for physical box pushing under varying box mass. The proposed method achieves the lowest mean empirical regret during both training and adaptation among the considered baselines.

Robots need to anticipate how their actions will change the world, since manipulation success hinges on the resulting contacts and object motions. However, existing Vision-Language-Action (VLA) policies that predict future observations from shared features leave the forecast decoupled from the actions the policy will actually execute, and impose no physical constraints on how the scene may evolve. We introduce ForeAct3D, a framework for policy-grounded future world modeling within VLA policies. Learnable geometric queries decode depth, semantic segmentation, and camera pose from the policy representation into current and future semantic 3D scene states, and the future queries are conditioned on the policy-generated action chunk to ground the forecast in the planned interaction. A physical-consistency closure relates the two states through background staticity and instance-level rigidity, and anchors the wrist-camera pose to end-effector kinematics. These objectives shape the shared representation used for action generation during training, and no future prediction is required at inference. Without robot pretraining, ForeAct3D achieves 98.3% average success on LIBERO and an average task length of 3.73 on CALVIN, outperforming its base policy on every suite. Ablations show that semantic 3D supervision, physical consistency, and action conditioning each improve manipulation performance, and that action conditioning substantially improves future object localization. Real-world experiments on spatial placement, object insertion, and sequential manipulation further raise average success from 6.7% to 37.8% over the base policy. The project page and code are available at https://github.com/anthonytao80-crypto/ForeAct3D.

We present a 4D Gaussian Splatting framework for the Sparse-View Track of the SIGGRAPH Asia 2026 Volumetric Video Challenge, which requires dynamic scene reconstruction from only six cameras with wide baselines. To achieve robust dynamic reconstruction under such sparse views, our framework integrates three components. (1) Region-adaptive spatial priors: We use foreground masks to guide Gaussian initialization and mask voting to control densification separately for the dynamic foreground and static background. Background geometry is regularized using monocular depth aligned to metric scale. (2) Motion-consistent temporal priors: We provide supervision at intermediate times through frame interpolation and constrain projected Gaussian motion with estimated optical flow. (3) Generative assistance: We place virtual cameras in the widest angular gaps and restore their rendered images using a diffusion-based model conditioned on camera poses. The restored images are iteratively incorporated into training as pseudo-supervision. On the validation set, our framework improves full-frame PSNR from 25.60 dB for the baseline to 29.75 dB. On the official test benchmark, it achieves 30.04 dB full-frame PSNR and 27.88 dB foreground PSNR, ranking first overall in the Sparse-View Track.

Many visual explanation methods in computer vision highlight pixel importance but struggle to link these low-level cues to semantically meaningful concepts, limiting their interpretability and trustworthiness. We introduce Concept-based Explanations (ConEx), a novel framework that bridges saliency visualization with concept-based reasoning to provide both faithfulness and interpretability. ConEx automatically discovers class-specific concepts and represents them through concept activation vectors (CAVs), learned without manual supervision using an architecture-specific masking mechanism that reduces noise introduced by the segmentation masks to enhance concept purity. ConEx generates faithful saliency maps that reveal where each concept appears in the image and how it contributes to the prediction. To evaluate the reliability of these learned concepts, we propose two complementary metrics, Vector-Concept Match (VCM) and Concept-Class Match (CCM), that quantify concept alignment and enable direct comparison with existing methods. Extensive experiments across diverse settings demonstrate that ConEx achieves state-of-the-art performance on faithfulness, segmentation, and concept-quality benchmarks. Overall, ConEx advances the field toward truly interpretable and concept-grounded explanations in vision models.

Automatic curriculum learning can improve the effectiveness of reinforcement learning by selecting the training experiences presented to the agent over time. Predicting the consequences of such decisions can, however, be difficult. We analyze automatic curriculum learning as a sequential decision-making problem, highlighting a gap between the quantities that determine the value of curriculum decisions and the information captured by local learning signals commonly used to guide them. We then investigate whether Large Language Models (LLMs) can exploit richer information about the learning problem to better anticipate the consequences of curriculum decisions. We introduce a method that combines online learning-progress estimates with LLM-informed estimates of (i) the potential downstream benefits of learning on each task and (ii) whether direct training on a task is currently likely to produce progress. We evaluate the approach on a custom benchmark of 256 textual goals in Craftax under different curriculum objectives. We observe the strongest gains when optimizing for individual target tasks. When optimizing across the full task set, the benefits vary across learners with different mechanisms for cross-task transfer, ranging from modest improvements in learning speed to larger gains that persist through the end of training.

Primitive-based 3D segmentation offers a compact and explicit alternative to dense surface prediction, naturally supporting structural abstraction and boundary localization. However, geometric decomposition alone does not determine how primitives should be organized into semantic parts: a single part may span multiple primitives, while geometrically similar or touching primitives may belong to different parts. We therefore introduce RePart (Reinforcement Part Reasoning), which formulates primitive-to-part organization as a finite-horizon Markov decision process and learns semantic organization through trajectory-level reinforcement reasoning. RePart constructs a Composable Primitive Workspace from fine-grained superquadrics and applies a merge-and-stop policy whose decisions are optimized by their downstream effects on the resulting partition rather than local primitive compatibility. The inferred part identities are then mapped back to the original mesh through Boundary-Aware Surface Labeling, preserving accurate surface boundaries beyond the primitive approximation. On PartNet, RePart achieves the strongest results across all four aggregate partition metrics; on 3DCoMPaT++, it obtains the highest RI and SC without target-dataset fine-tuning. These results demonstrate that reinforcement reasoning provides an effective mechanism for organizing geometric primitives into semantic parts while retaining dense segmentation accuracy. Code is available at https://github.com/EngineeringAI-LAB/RePart.

Magnetic Resonance Imaging (MRI) is widely regarded as the optimal sensor for fetal brain analysis due to its superior soft-tissue contrast and anatomical detail. However, its high cost and operational burden make it invasive and difficult to obtain at scale. Ultrasound (US), in contrast, is cheap, safe, and routinely acquired, and as a result it has produced substantially larger datasets and a growing ecosystem of pretrained models. This asymmetry raises a natural question: Can we teach a US-only model to understand fetal MRI from only a limited set of examples? The standard recipe, training a foundation model on subject-to-subject paired MRI-US scans, is not viable since no such paired fetal dataset is publicly available. In this paper we address this gap with Weakly Aligned Spatiotemporal Pairs (WASP), a framework that formulates cross-modal correspondence as an entropic Optimal Transport problem driven by clinical metadata, in particular Gestational Age (GA) and diagnostic planes, enabling the fitting of a lightweight alignment module that lifts MRI representations into the US latent space, without fine-tuning the backbone. Empirically, WASP yields its largest gains when MRI is unseen by the model during pretraining (on USFM, GA estimation error drops from 21.9 to 17.4 days and standard plane classification accuracy climbs from 61.9% to 69.0%), while providing smaller, backbone-dependent refinements for backbones pretrained on both modalities (e.g., BioMedParse GA estimation error from 6.5 to 6.0 days and SAM-Med2d plane accuracy from 83.3% to 88.1%). Code is available at https://github.com/miccunifi/WASP.

Best arm identification under differential privacy is a pure-exploration problem in which both statistical efficiency and privacy protection must be achieved simultaneously. We study fixed-budget best arm identification for bandits under pure $\epsilon$-differential privacy, where the learner must recommend an arm after a prescribed sampling budget while protecting the full transcript. We prove that the optimal exponential decay rate of the error probability is upper bounded by an instance-dependent privacy-aware transportation exponent that differs from the analogous quantity used to characterize the stopping time in fixed-confidence analysis by Jourdan and Azize [2025]. Guided by this exponent, we propose AO-Pri-BAI, an adaptive algorithm that maintains private running estimates through Laplace-tree mechanisms and learns a sampling design through a min–max interaction between hard alternatives and arm allocations. We prove that AO-Pri-BAI satisfies pure $\epsilon$-differential privacy. We also establish that the exponent of the failure probability of AO-Pri-BAI matches the privacy-aware benchmark. Numerical studies show that even in the non-asymptotic setting, AO-Pri-BAI outperforms benchmark algorithms on various instances, complementing the theoretical analyses.

On-policy distillation (OPD) has emerged as a widely used paradigm for post-training large language models, reducing the train–test mismatch of conventional distillation by supervising the student on its own generated trajectories. However, existing OPD objectives remain largely token-local and outcome-agnostic, optimizing teacher–student agreement at each prefix despite reasoning quality being determined at the trajectory level. Reinforcement learning with verifiable rewards (RLVR), particularly Group Relative Policy Optimization (GRPO), provides complementary outcome-level supervision but suffers from sparse rewards and coarse credit assignment. We show that OPD and RLVR exhibit complementary blind spots: teacher signals provide dense local guidance but are weakly aligned with rollout correctness, whereas group-relative rewards capture task success but provide coarse token-level credit and vanish on all-failure groups. We introduce DiffGate, an outcome-gated objective that combines GRPO with selective, bounded teacher guidance. Teacher supervision is applied only to failed trajectories, scaled by group difficulty, and smoothly bounded to prevent extreme teacher–student discrepancies from dominating optimization. The verifier therefore determines which trajectories receive teacher guidance, while the teacher provides dense token-level update directions within those trajectories. Across Qwen3-0.6B and Qwen3-1.7B students, DiffGate improves code avg@8 over matched GRPO by $+1.7$ and $+1.8$ points and pass@8 by $+1.6$ and $+5.7$ points, respectively. On mathematics, avg@8 remains within $0.5$ points of GRPO while pass@8 improves by $+1.1$ and $+3.9$ points. Overall, DiffGate improves pass@8 across all four model–domain settings, demonstrating improved solution coverage under our evaluation protocol.

Chain-of-Thought (CoT) faithfulness detectors are widely used to audit reasoning models, yet a detector is itself a predictor whose verdicts are treated as stable properties. We ask whether a detector is faithful to itself under distribution shift. We formalize meta-faithfulness as an invariance principle: a valid detector must return identical verdicts on traces that differ only by transformations preserving ground-truth faithfulness. We prove three results: (i) no detector using only intervention-response profiles can separate faithful from epiphenomenal mechanisms with identical signatures; (ii) any detector relying on shift-sensitive features violates invariance at a rate independent of its in-distribution accuracy; (iii) an asymptotic certified selective-risk guarantee enables confident abstention. We operationalize the principle in FaithShift, a stress-test protocol spanning ten shift axes, and propose SIFT, a hidden-state trajectory detector trained with cross-environment invariance objectives and certified abstention. Across 14,996 traces, four domains, and eight models, three findings emerge. First, transfer collapse is real: all existing detectors show gaps $\geq 0.15$ AUROC. Second, the dominant bottleneck is sampling stochasticity, not shift: over 80% of detector instability stems from random seed variation, falsifying our preregistered prediction that shift-attributable violations exceed 0.25. Third, SIFT cuts invariance violations by 64% over the best single-seed baseline, but a four-seed ensemble of any detector narrows the margin to 0.01 (indistinguishable at matched coverage, $p=0.21$), and SIFT needs a 51% abstention rate. Cross-model transfer degrades from within-family to cross-family to open-weight-to-API, partly closed by multi-model training. We offer a framework for auditing auditors: the real barrier is detector variance, not distribution shift.

KRATOS is a group-structured bibliometric diagnostic that compares the distribution of documents (participation) with the distribution of citation weight (recognition) over a fixed, finite universe of analytical groups. This note gives its complete mathematical specification and derives the properties that govern its interpretation. Beyond bounds and equality conditions for each component, we show that the recognition-alignment score depends on citation data only through ratios of group mean citation rates to the corpus mean; that the composition ceiling of the participation–recognition factor is an affine function of the total variation distance to the uniform reference; and that the factor itself satisfies Fréchet-type bounds in terms of this ceiling and a participation-weighted recognition score. We establish an exact logarithmic decomposition of the composite index, an ordering between the primary and a reciprocal-symmetric recognition score, invariance properties, and closed-form first and second moments of the recognition ratios under global and stratified permutation nulls. These results explain why composite orderings can be sensitive to small groups, heavy-tailed citation distributions and metadata reassignment. All results are verified numerically with an accompanying script. The specification concerns measurement structure only; it does not define a measure of epistemic change or justice.

Is agentic memory robust against stealthy steganographic attacks? We carry out a large-scale red-teaming exercise to test whether agents can encode attacker-controlled strings in one session and recover them in another without triggering safety oversight. Following SHADE-Arena-style tasks, we embed malicious side tasks to encode secret strings using steganography within otherwise benign tasks and evaluate them using independent task-completion and safety oversight. We test 14,000 attack trials spanning 91 model-attack configurations, 13 models, and 7 steganographic schemes: Acrostic, Mesostic, Telestich, Word-choice, Capitalization, Position-based, and Homoglyph. 41.2% of trials successfully encode the target payload in the generated response, while 29.8% survive the memory-write step with the encoding intact. Overall, 25.4% of trials yield a recoverable payload at retrieval, and 20.1% achieve exact-match recovery, including synthetic API keys and cryptographic material never exposed to the receiver. Among the exact-match transmissions, 71.4% also pass primary task-completion scoring and are independently judged safe by the oversight model, corresponding to 14.4% of all trials in which a successful covert transmission would appear to be an ordinary, benign interaction under task-level evaluation. Our results demonstrate that agentic memory can function as a persistent cross-session covert channel. The results further show that the principal bottleneck occurs at memory persistence rather than retrieval: once a steganographic payload survives the memory-write stage, a substantial fraction remains recoverable. We therefore argue that memory integrity, information-flow control, and covert-channel detection should be explicit security requirements for agentic systems.

Molecular property prediction is central to computational drug discovery, where graph neural networks learn to weight neighboring atomic environments during message passing. Yet it remains unclear how variational quantum circuits alter learned attention behavior in molecular graphs. We introduce an edge-aware variational quantum attention mechanism for molecular graph learning, in which the receiving atom, neighboring atom, and connecting bond jointly determine the quantum attention state. Across five molecular property and bioactivity prediction tasks, QGAT achieves competitive performance relative to GATv2, with a consistent improvement on BBBP across all six evaluated circuit ansatzes. We further compare how the quantum and classical attention scores weight molecular structure beyond accuracy. In the Verubecestat BACE1 inhibitor series, QGAT achieves a higher Spearman correlation than GATv2 and assigns positive attributions to several structural changes consistent with reported structure-activity relationships (SARs). This case study shows that the two attention mechanisms can exhibit different prediction and attribution behavior across structurally related BACE1 analogues, while broader validation is required to determine how consistently these differences generalize across chemical series and targets. Circuit ablations further show that performance depends on the circuit design. Together, these results show that variational quantum attention can serve as a viable alternative molecular attention parameterization while inducing circuit- and chemistry-dependent behavior distinct from a matched classical scorer.

Programmable Data Plane (PDP) switches enable flexible packet processing but remain limited in scheduling capabilities, particularly for priority-based policies that require strict ordering of packets according to user-defined ranks. An earlier work, called Push-in First-out (PIFO), proposed a priority queue that enables ordering enqueued packets based on their priority. It provided an ideal abstraction for programmable packet scheduling; however, its requirement for line-rate packet sorting makes it impractical at high network speeds (100 Gbps and beyond). Approximate schedulers such as SPPIFO, AIFO, and RIFO reduce complexity but introduce priority inversions, thus degrading latency, fairness, and Flow completion times (FCTs) since they rely on First-in First-out (FIFO) queues or use Active Queue Management (AQM) as a substitute for scheduling. To address the scalability limitations of accurate schedulers while avoiding the correctness issues of approximate schedulers, this work proposes two packet queuing architectures, Parallel Processing for Priority Ordering (P3PO) and Parallel PIFO Queuing Architecture (PPQA). Both architectures decompose a large global priority queue into multiple smaller bounded-capacity priority queues that operate in parallel. P3PO uses a cascading set of priority queues with priority-based bounds to ensure that packets are inserted into the earliest queue capable of maintaining ordering. PPQA distributes packets across multiple independent priority queues based on occupancy, using a demultiplexer for balanced queuing and a multiplexer for globally selecting the highest-priority packet at dequeue. The architectures are implemented in the NetBench packet-level simulator and evaluated using empirical datacenter workloads (Web-search and Data-mining).

Joint-embedding predictive architectures (JEPAs) for world modeling train an encoder so a predictor maps a current embedding and action to the next frame's embedding, always from a single rendered frame. This has a structural blind spot: a renderer without motion blur draws a scene from configuration alone, so a single-frame embedding carries no velocity information, for any encoder, including the official released LeWM weights. We confirm this on official checkpoints across four real benchmarks (PushT, Reacher, Cube, TwoRoom): every linear velocity probe sits at or below chance while position probes reach R^2 about 0.95. We introduce RateIdent, a three-stage diagnostic protocol, and TI-JEPA, a lightweight fix splitting the latent into a pose code and an explicit finite-difference motion code, predicted jointly. Across three physically grounded environments, TI-JEPA gives a significant, seed-robust gain on a stop-at-goal planning task over a matched-memory baseline, e.g. 55% lower final distance on Pendulum (p=3.2x10^-10) and 64% on CartPole (p=5.1x10^-15). We reproduce this at official ViT-Tiny plus AdaLN-transformer scale, then push the same recipe onto real dm_control Reacher photographs trained from scratch, where TI-JEPA's branch separation exceeds the memory-having baseline's by roughly 38x, the paper's largest margin. Against a same-footprint recurrent RSSM-style predictor, TI-JEPA matches or beats its rollout accuracy on two of three environments, stays separately probeable for pose and motion, and wins outright on the most coupled one. A checkable formal argument and six evaluated environments show single-frame targets are the wrong object to predict when velocity matters, and a small, interpretable structural change fixes it with no privileged supervision. Code, checkpoints, and the project page are linked below the title.

Storage functions are widely used to relate a control system to a simpler model for analysis and controller design, and to quantify model mismatch when a controller is designed on one model but implemented on another. In applications, several models of the same physical process are available at different levels of refinement, while refinement relations, consisting of a storage function and an associated interface, are constructed only between neighboring levels. Thus, a direct refinement relation may be unavailable between the model used for controller design and the model used for implementation. To address this gap, we consider open control systems with internal ports for interconnection and external ports for input-output analysis. We define a category, $\mathsf{OCS}_{\mathrm{chain}}$, whose objects are open control systems and whose morphisms are finite chains of refinement relations. Using this category, we derive an output mismatch bound and a closed-loop performance result for controllers refined through a sequence of interfaces. We then define a functor that transfers refinement relations from open control systems to systems without internal ports. We also develop a network lifting result showing that, under standard interconnection compatibility conditions, subsystem storage functions can be combined to obtain refinement relations and performance bounds for composite networks. Two thermal network examples illustrate recursive controller refinement and the propagation of model mismatch along refinement chains. Simulations show that an HVAC system tracks a time-varying reference temperature with error below $0.2^\circ\mathrm{C}$ even when the controller is designed on the coarsest model and deployed on the finest model.

Multi-modal large language models (MLLMs) achieve strong modality understanding by pairing a large language model (LLM) with an encoder for a target modality such as vision, video, or audio. However, improving an MLLM's capability for a given modality typically requires additional training on large modality-specific datasets, incurring substantial data collection and compute costs. Model merging offers an alternative, but it is often infeasible for data-scarce, large per-sample size, or domain-specific modalities (e.g., audio and video), where same-modality model variants are rarely available. In this work, we characterize an intriguing asymmetric phenomenon: merging a well-aligned, data-rich source-modality MLLM into a data-scarce target-modality MLLM substantially improves the target on its own benchmarks. Our theoretical and empirical analyses show that this gain stems from enhanced alignment between modality-specific and textual tokens, induced by the stronger donor modality. Specifically, we derive a mutual-information lower bound that is monotonic in alignment-related quantities and strongly correlated with downstream MLLM performance. Building on this principle, we propose Directional Cross-modal Alignment Transfer (DCAT), a novel framework that transfers textual alignment from a strong, well-aligned source (donor) modality to a weak target (recipient) modality, boosting target-modality performance without further fine-tuning. We further show that the alignment-enhancing objective admits a closed-form weight-space solution computed from only a small calibration set. DCAT outperforms existing model-merging methods, offering an efficient path toward cross-modal alignment transfer. Project page with code is available at \url{https://seohoiki3215.github.io/DCAT_project_page}

Recent advances in artificial intelligence-radio access network (AI-RAN) are placing large language model (LLM)-driven agents within the open RAN (O-RAN) control hierarchy. A promising deployment for this agentic AI-RAN co-locates LLM inference with physical-layer (PHY) communication processing over the same accelerated compute pool for infrastructure sharing, data locality, and low control latency. However, this co-location induces bidirectional control-compute coupling, as the agent competes with PHY processing for compute, while its reasoned gNB control actions may alter future PHY workload and hence the compute available to its next inference. To this end, this article proposes the control-compute contract, a coordination protocol linking AI-RAN workload governance with O-RAN control execution. Specifically, we first expose direct compute contention on an over-the-air (OTA) O-RAN testbed, where continuous LLM inference increases the PHY decoding time approximately eightfold. We then formulate the contract as three protocol rules with operator-requirement protection, and map it onto O-RAN and AI-RAN functions as a five-stage workflow. Afterward, an OTA-calibrated case study of simulated uplink gNB control indicates that the contract keeps the proportion of slots violating the PHY time budget below $0.9\%$, against $20.7\%$ under ungoverned co-location, while achieving faster gNB control than a fixed compute reservation benchmark. Finally, we identify several open issues and outlooks for its practical deployment.

Activation probes can predict safety-relevant properties of language models with high area under the receiver-operating-characteristic curve (AUROC), but deployed agent monitors make thresholded alarm decisions under tight false-alarm budgets. These are different estimands. We introduce an Operational Validity Contract that fixes a monitor's target, observability, identity, timing, intervention unit, comparator, calibration, and cost. We formalize risk at the semantic request or trajectory level: when one task contains repeated alarm opportunities, row-level AUROC and false positive rate do not identify semantic-unit any-alarm risk. A confidence-certified threshold also requires enough independent negative units, a tie-safe rule, and transport to deployment. Across Models Under Pressure, LASR refusal prediction, immutable AgentDojo, and a prospectively protocol-frozen ST-WebAgentBench replication, joint activation-observable monitors reach AUROC 0.957 and 0.935 on the first two benchmarks, yet their locked 5%/10% detection rates are only .642/.742 and .719/.782, respectively. On AgentDojo, the secondary mean-activation rollout monitor reaches AUROC 0.922 but detects none of 38 positive semantic cases at the locked 5% operating point; thresholds intended for 10% false alarms realize 18.7-20.0% on test. Because the test misses its prospectively frozen 40-positive support gate, we label it support-insufficient. On ST-WebAgentBench, activation reaches AUROC .874, but 23 independent calibration negatives cannot identify even a 10% controller; the locked policy abstains rather than reporting its mechanical zero FPR as a success. An exploratory counterexample also lowers full AUROC while improving realized 10% utility. The fail-closed compiler caps MUP and LASR at restricted predictive value and AgentDojo and ST-Web at representation accessibility; no setting reaches alarm-policy validity.

An $\mathcal H^2$ matrix represents well-separated interactions using nested low-rank bases while retaining nearby interactions explicitly. We consider the problem of constructing an explicit, strongly admissible $\mathcal H^2$ approximation using only products with the matrix and its adjoint, and develop two randomized recovery algorithms on an adaptive geometric hierarchy. Carried recovery begins with a single pair of dense Gaussian test matrices, without hierarchy-specific probing, and updates the resulting forward–adjoint sketches across levels. All operator samples can therefore be acquired in one batch. Resketched recovery applies the same recovery procedure using fresh Gaussian test matrices at each level. For this variant, we prove a global quasi-optimal bound on the expected Frobenius error relative to the best approximation with the prescribed hierarchy, rank bounds, and retained near-neighbor pattern. Carried recovery requires only $O(k+p)$ applications of the matrix and its adjoint, independent of tree depth, whereas resketched recovery requires $O((k+p)\log(N/k))$ on trees of logarithmic depth. Here $N$ is the matrix dimension, $k$ the maximum prescribed box rank, and $p$ the oversampling parameter. These bounds assume bounded near-neighbor counts and $O(k)$ local dimensions. Experiments on Laplace, Dirichlet-to-Neumann, and Helmholtz operators in two and three dimensions with up to $1.28$ million unknowns show that, with sufficient oversampling, carried recovery achieves nearly refinement-independent error and accuracy comparable to resketched recovery while using many fewer operator applications. Its compressed application cost scales linearly for a fixed rank.

We study the fine-grained complexity of evaluating Boolean bounded-variable first-order queries over sparse relational structures. For every fixed $k \ge 2$, every relational signature, and every fragment between $k$-variable primitive positive ($\mathrm{PP}^{k}$) and first-order ($\mathrm{FO}^{k}$) logic, we prove, assuming the Sparse MAX-$3$-SAT hypothesis, a dichotomy theorem for evaluation in $O(m^{k-\varepsilon})$ time, where $m$ is the number of tuples in the input structure. The only tractable cases fall into three families: (1) three-variable fragments, (2) two-variable fragments, and (3) fragments over unary signatures. On the hard side, for every fixed $k \ge 4$ and every $\varepsilon > 0$, there is a fixed sentence $\varphi_\varepsilon$ in $\mathrm{PP}^{k}$ over a single binary relation symbol, depending on $\varepsilon$ but not on the input structure, whose evaluation cannot be performed in $O(m^{k-\varepsilon})$ time. For the tractable cases, we show that the evaluation problem can be solved in $2^{O(|\varphi|)} \cdot m^{k-\varepsilon}$ time for some $\varepsilon > 0$. Moreover, every tractable fragment reduces, with a $2^{O(|\varphi|)}$ blowup in formula size under DAG representations, to one of the following query languages: (1) Tarski's calculus of relations, (2) a new Boolean modal logic for sparse model checking, and (3) one-variable counting logic.

Precise constraint satisfaction is a prerequisite to deploying learned models in many areas, motivating methods that repair raw neural predictions with a repair procedure. Current methods unroll multiple repair steps in training and softly penalize constraint violations that remain after the unroll. This is compute- and memory-intensive, lacks robustness when the repair fails to converge, and surrenders most of the constraint satisfaction work to the repair. Our central finding is that, contrary to common practice, a single detached projection step suffices in training. We accomplish this with a Projection-Adaptive Loss (PAL), which uses the constraint residual after this single step to adaptively weigh constraint penalties on the raw prediction. In experiments, PAL is the only method that retains virtually perfect feasibility on extremely nonlinear constraints, and matches or outperforms current methods on synthetic and engineering benchmarks. Because it only requires a single detached projection step, PAL trains 2.5x faster than the canonical repair-based method (DC3) on its own ACOPF benchmark. PAL can also be trained when constraints are expensive to evaluate (e.g., via neural surrogates), a setting where current unrolled methods are memory-intractable.

In this article, we present a method of spectral serialization envisioned by G. Mahler and A. Schoenberg between the late 19th and early 20th centuries that enables the selection of timbres rooted in musical structure. Based on information geometry, we evaluate the Wasserstein distance between polyphonic timbre spectra, as demonstrated in our previous paper, in terms of the second moment of spectral chords comprising three or more notes, expressed in squared hertz. By embedding these quantities in a Banach space, we analyze specific passages from works by R. Strauss, Mahler, A. Berg, and A. Webern from the perspective of timbre, showing how the same chord exhibits different affinities and divergences depending on orchestration. Taking the wah wah mute as an example, we propose a model that treats instrumental timbre and speech within the same Banach space, and we attempt to quantify the "vowel triangle" in Hz. These efforts constitute a partial but integrated solution to the historical three problems of Schoenberg. Serialism, Klangfarbenmelodie, and Sprechgesang which neither Mahler nor Schoenberg in their lifetimes, nor the postwar generation of composers including Nono, Boulez, and Stockhausen, was able to resolve fully. We aim to reconsider musical thought as a whole from the perspective of timbre and to open new possibilities for interpretation, performance, and composition. All tools are publicly available on GitHub, so that anyone can reproduce and extend these analyses.

Large language models (LLMs) are increasingly deployed in safety-critical settings, yet their black-box nature makes it difficult to provide formal guaranties about their behavior. Existing verification approaches rely primarily on empirical probing and testing, leaving open the question of how to reason rigorously about general-purpose trans- former architectures. In this work, we establish a principled bridge between transformers and weighted automata, a classical model from formal language theory. This connection enables us to transfer verification tools from automata the- ory to the analysis of LLMs. Our contributions are twofold: First, we develop a formal correspondence between transformer architectures and weighted automata over reals, showing how distributional properties of LLMs can be captured within this framework. Second, we introduce an identity testing algorithm for weighted automata that provides a statis- tical method for distinguishing whether two stochastic models define the same distribution up to a tolerance threshold. This work provides the first formal bridge between modern neural se- quence models and classical automata theory, clarifying both the poten- tial and the computational challenges for rigorous LLM verification.

We introduce a sampling approach for energy- and score-based generative models that requires no gradient evaluations of the model. Replacing the drift term that would normally contain the score $\nabla_\mathbf{x} \log p_\theta(\bf{x})$ with a high-frequency dithered cosine of the model's value, $\sqrt{\alpha\omega}\,\cos(\omega t + k \log p_\theta(\bf{x}))$, produces, in the high-frequency averaging limit, Langevin Markov chain Monte Carlo for energy-based models and the reverse-time SDE of score-based diffusion. We prove that trajectories of the dithered Itô SDE converge to those of the target SDE, driven by the same Brownian motion, uniformly on compact time intervals in probability, by an averaging argument that extends bounded extremum seeking (ES) to Itô processes, with an explicit $O(\omega^{-1/2})$ mean-square rate under global bounds. The approach is not confined to smooth targets: it extends to $C^{1,1}$ energies with discontinuous curvature (without ellipticity requirement) and to Sobolev energies whose Hessians exist only off measure zero sets; for Lipschitz energies with gradient kinks the averaged limit remains well posed; the Krylov-Röckner integrability class is the boundary of provability. The approach provides a hard a priori bound on the per-step update rate and applies to explicitly time-varying targets on finite horizons. Gradient-free pixel-space sampling is not competitive with well-tuned backpropagation-based samplers at practical evaluation budgets; the regime where the approach offers an advantage is latent-space sampling when the model is a black box and the target drifts in time. We demonstrate latent-space tracking for time-varying images on CelebA-HQ ($256{\times}256$) from limited 1D projection measurements and latent-space EBM sampling on CIFAR-10.

Agile flight in unknown, cluttered, and dynamic environments requires a planner that knows where and when danger will appear, not only that a trajectory is dangerous. One-stage learning-based planners trained with differentiable privileged costs are fast and expert-free, but the only signal reaching their encoder is a scalar trajectory cost with no spatial or temporal structure, so avoidance degrades into late reactive maneuvers. We present RiskFly, a one-stage planner that predicts risk in the same space in which it acts. A dual-stream observation pairs a short depth sequence with a frustum-aligned inverted spherical range-map sequence, whose angular cells match the end-state proposals one to one. An auxiliary head regresses a frustum-aligned spatio-temporal risk field, supervised by a privileged closest-point-of-approach (CPA) target. This self-predicted field is queried differentiably along the instantiated quintic trajectory at its own arrival times, and also enters the training objective, so representation supervision and planning gradients meet in a single space. Privileged signals are discarded at deployment, and the planner runs map-free from onboard depth and proprioception. Extensive simulation and zero-shot real-world flights on resource-constrained platforms show higher success rates at comparable end-to-end latency.

Engaging K-12 students in authentic scientific research remains a significant challenge, particularly at the intersection of environmental science and robotics. We introduce the Jar Jar ROV, a low-cost, open-source Remotely Operated Vehicle (ROV) platform designed for citizen science-based water quality monitoring by middle school students. This paper presents the design of the platform and the results of a large-scale deployment with over 100 students across a US state who built, programmed, and deployed the ROVs in local lakes. The educational framework yielded high student engagement in hands-on activities, with ROV construction earning a perfect average score from mentors. Scientifically, the program established a grassroots monitoring network, generating nearly eleven thousand validated measurements of temperature, pH, dissolved oxygen, and turbidity. However, our evaluation identified a critical "engagement gap," with student interest declining sharply during more complex tasks such as electronics assembly and data uploading. This paper contributes both a validated, scalable model for integrating robotics into environmental education and a data-driven roadmap for future improvements. These enhancements focus on lowering technical barriers and creating a more intuitive link between data collection and scientific discovery, addressing a key challenge in empowering the next generation of citizen scientists.

Differentiable programming connects scientific computation with gradient-based inference, learning and design. Extending these capabilities across a heterogeneous software ecosystem requires specialized effort to implement derivatives, integrate interfaces and evaluate quality. AI coding agents can accelerate this transformation, but translating their capabilities into useful scientific software requires identifying research needs and evaluating how well implementations meet them. We present an environment for agent-driven evolution of differentiable scientific software that connects demand identification, development and quality evaluation. A unified differentiation interface exposes reusable derivative rules alongside existing numerical routines, allowing research tasks to share these capabilities. Research requirements guide development, with implementations assessed through independent derivative checks, workflow tests and performance evaluation. Validated software, research programs and tests become shared resources for subsequent studies. We construct and validate automatic differentiation extensions across 20 packages spanning physical, chemical and biological modeling, with research workflows demonstrating reuse across tasks. Benchmarks demonstrate computational savings over finite differences in gradient evaluation and complete parameter estimation. Research-driven revisions make previously unsupported workflows differentiable, correct derivatives of scientific observables and eliminate redundant computation. Quantum-control and thermal-design studies revise objectives in response to physical evaluation, improving designs while reusing existing derivatives. This work provides a practical approach to expanding differentiable programming across established scientific software and organizing AI agents around the recursive improvement of a shared computational ecosystem.

We study the quantum query complexity of maximizing a non-negative submodular function, considering both the unconstrained setting and, for monotone functions, a cardinality constraint $k$ on an $n$-element ground set. In the exact reversible digital value-oracle model, our unconstrained algorithm achieves an expected $(1/2-\varepsilon)$-approximation using only $O_\varepsilon(\log n)$ queries. In contrast, any classical randomized algorithm that attains a fixed expected ratio above $1/4$ requires $\Omega(n/\log n)$ queries (Li, Feldman, Kazemi, and Karbasi, 2022), establishing an exponential separation in query complexity. For cardinality-constrained maximization, we give a bounded-error quantum algorithm that achieves a $(1-1/e-\varepsilon)$-approximation using $\widetilde O_\varepsilon(\min\{\sqrt n,n/k\})$ queries. When $k=o(n)$, our algorithm achieves at least a quadratic speedup up to logarithmic factors over classical randomized algorithms (Mirzasoleiman, Badanidiyuru, Karbasi, Vondrák, and Krause, 2015; Peng and Rubinstein, 2025). Moreover, when $k=cn$ for any fixed rational $c<1-1/e-\varepsilon$, the query complexity reduces to $O_{\varepsilon,c}(\log n)$, yielding an exponential separation from the classical $\Omega(n/\log n)$ lower bound (Li, Feldman, Kazemi, and Karbasi, 2022). We further prove quantum lower bounds of $\exp(\Omega(\varepsilon^2n))$ queries for achieving a ratio beyond $1/2+\varepsilon$ without constraints, and $\exp(\Omega(\varepsilon^2k))$ queries for exceeding $1-1/e+\varepsilon$ when $k/n\le\varepsilon$. These barriers demonstrate that quantum computation offers no exponential speedup at these approximation thresholds.