Papers

Longitudinal relational agents rely on memory for continuity, but remembering can lead to intrusion, clinical overconfidence, emotional manipulation, and opacity. We present Relic, a governance architecture for diegetic relational agents, and Gumi, a subject-specific companion agent initialized and governed through Relic. The architecture separates what the system can observe, what researchers can review, what Gumi can remember, and what Gumi can say. We describe three mechanisms. Relic represents sensitive safety signals as researcher-facing governance objects rather than user-facing explanations or agent memories. Shared Continuity Memory organizes relational markers around subject-confirmed wording, corrections, explicit follow-up permissions, and recall limits. We specify a runtime mediation layer for delivery, proactivity, session identity, output transformation, and platform allowlists; adoption across live paths remains partial. These mechanisms aim to preserve relational continuity without turning Gumi into a clinical assistant, mood tracker, general-purpose assistant, or opaque profiling system. We contribute the architecture, object model, researcher workbench design, and a proposed evaluation framework for governed relational memory. An exploratory pilot involved the author as P1 and one external participant as P2. Weekly self-reports from P1 and researcher-led interviews with P2 provide descriptive observations of early use and perceived naturalness. The pilot does not support claims about clinical efficacy, diagnosis, therapeutic outcomes, general usability, or deployment safety. Relic provides research infrastructure intended to make relational memory, safety constraints, and agent behavior inspectable and testable.

Precision pesticide spraying is essential for optimizing application efficiency and ensuring uniform chemical distribution. Spraying performance is influenced by multiple factors, including environmental conditions such as temperature and wind speed, pesticide type, and the robot's capability to accurately perceive crops and target spray locations. Existing approaches predominantly emphasize crop detection and rely on predefined spraying parameters, whereas human operators dynamically adjust their spraying strategies by considering environmental conditions, region-specific crop characteristics, and the type of pesticide being applied. In this study, we propose a context-aware adaptive spraying framework based on Vision-Language Models (VLMs), which enables robots to leverage spatial reasoning and integrate information from multiple sources, including crop type, pesticide type, and weather data, to make adaptive and optimized spraying decisions. Subsequently, a trajectory-tracking controller based on Model Predictive Path Integral (MPPI) control is employed to ensure precise navigation and accurate spraying at crop locations. The comparative results demonstrate that the proposed method improves accuracy by at least 30% in detecting crop rows. In addition, the experimental evaluations conducted in two environments further demonstrate the robot's ability to flexibly adjust spraying volume and travel speed, while reducing pesticide drift.

Reinforcement-learning quadrotor controllers are usually trained under simplified wind models, yet the impact of wind-field fidelity, as opposed to magnitude, on policy robustness remains unquantified. This paper compares five disturbance-fidelity levels, from wind-free flight and discrete 1-cosine gusts through statistical turbulence and synthetic coherent structures to large-eddy-simulation fields of the atmospheric boundary layer, in a full cross-fidelity train test evaluation of proximal policy optimization (PPO) agents, with cascaded PID and geometric SE(3) controllers as training-free references, over a 0-12 m/s wind sweep. Before any controller comparison is made, all disturbance data are validated: every synthetic generator is checked quantitatively against its analytical or certification-standard reference, and the large-eddy-simulation fields against the imposed log law. On a racing-class quadrotor in hover, the train test matrix is remarkably flat, and the cheapest structured training wind, which is discrete-gust domain randomization, ranks first in every test column, a ranking replicated on a wind-sensitive 27 g platform; a once-tuned geometric controller brackets the learned PPO policies at zero crash rate. Mechanism diagnostics show that control authority, not wind realism, bounds robustness, so wind-fidelity investment should scale with platform wind sensitivity.

For infinitely many sizes we exhibit a cycle of binary units, each taking the exclusive-or of itself and its two clockwise neighbours, that is a complex in every state, no proper subsystem being more integrated, and whose integrated information grows as two raised to a power quadratic in the number of units.

Neural subspace solvers offer a promising way to accelerate the large sparse linear systems arising from PDE discretizations, but their value depends on generating effective correction directions at low computational overheads. We study this problem from a residual-image viewpoint: a correction subspace is useful when its image under the system operator captures the current residual. Guided by this view, we propose Gate-RINS, which generates multiple correction directions from shared polynomial residual probes and modulates them with a lightweight residual- and coordinate-dependent pointwise gate. We also introduce a hybrid schedule that uses GRANS-style graph controllers for the first correction block and Gate-RINS thereafter, combining an expressive graph based initial step with a lower-cost corrector as the solve progress. Theoretical analysis establishes a unified residual-image and dynamic approximate-inverse perspective for Gate-RINS and G-RANS, showing that a single neural-generated direction can emulate the residual quality of fixed-step GMRES. Numerical experiments on six PDE benchmarks demonstrate that Gate-RINS reaches a relative residual of $10^{-5}$ with 1.6-2.3$\times$ and 2.2-3.0$\times$ less wall-clock time than G-RANS and GMRES respectively. For Helmholtz systems with meshsize up to $10^5$, Gate-RINS also achieves the lowest residual and outperforms a GPU-accelerated parallel GMRES, while GRANS fails to reach relative residual of $10^{-4}$ in the same time budget.

Persistent AI agents revise beliefs, consolidate memory, and replace execution substrates. Similar successor states can accompany differently authorized transition claims, while legitimate development can change state substantially. We introduce the Cognitive Continuity Test (CCT), a policy-relative contract for verifying submitted transitions using scoped authority, provenance, deterministic application, semantic predicates, and candidate-persistence receipts. CCT distinguishes verified admissibility, affirmative violation, and unresolved required evidence. Separation results concern transition claims rather than live runtime identity; soundness is conditional on the specified checker and evaluator assumptions. IdentityLineageBench provides 24 generated transition families. The reference post-resolution verifier matches all 576 canonical held-out labels; lexical state similarity and a lineage-only diagnostic baseline admit 60.0% and 80.0% of invalid fixtures. These comparisons establish synthetic conformance, not superiority to a policy-aware deployed system. Signed adversarial regressions cover fabricated interaction counts, unsupported belief changes, and mixed missing/contradictory evidence. SIT behavior and actual model migration remain unmeasured. An 18,000-execution valid-path study measures a 6.21 ms default median on resident inputs. We specify the additional activation and recovery obligations needed for deployment.

Agent developers increasingly compare prompts, tools, policies, and diagnosis algorithms through simulator-grounded verifiers. A verifier can nevertheless make a solver comparison vacuous: if its probes or predicates encode the target identity, an exact optimizer may appear effective without resolving any genuine ambiguity. We report such a failure in an aggregate-trace debugger for a closed-loop decision agent. Exact minimum hitting set (MHS) and a propagation-aware greedy method returned identical supports in 12/12 development cases and the same planted-fault recovery in 9/12. A subsequent audit found that exact-anchor predicates produced the planted pair in 9/9 cases. After removing those anchors, overall planted-pair recovery was 8/9; hard-probe singleton pairs nevertheless matched the planted pair in 9/9, and no case retained a nonempty residual conflict family after propagation (0/9). The optimizer was correct, but the verifier had already disclosed the answer. We replace solver-first evaluation with a support-gated verification contract. A clean reference map must first show repeated component exposure; a matched reference/current gate must then establish comparable runtime evidence; only afterward may an independently calibrated signal rule return a detection. In a preregistered heldout comprising 1,440 cases and 21,600 partition rows, 55/72 regime-component units passed the reference gate, 54/55 passed the runtime gate, and stable false admission was 0/20 represented components with a one-sided exact 95% upper bound of 0.1391. Within admitted units, affected clean traffic predicted detection better than nominal fault-cell fraction. The main lesson is structural: verify evidence eligibility and non-revelation before optimizing the component selector. Otherwise a stronger solver can merely certify a stronger verifier artifact.

One-Pixel Attacks (OPAs) represent one of the most extreme demonstrations of adversarial fragility in deep learning, where modifying a single pixel can reliably induce high-confidence misclassification across domains such as medical diagnosis, autonomous driving, biometrics, and quantum communication. Despite their conceptual simplicity, OPAs remain underexamined in existing adversarial-attack surveys, which provide only fragmented or cursory coverage. This PRISMA-guided review synthesizes high-quality studies from 2017 to 2026 and delivers a unified, multi-axis taxonomy of OPA research spanning algorithmic foundations, black-box evolutionary optimization, emerging hybrid and program-synthesis attacks, defence mechanisms, interpretability tools, and domain-specific vulnerabilities. Our analysis reveals the dominance of Differential Evolution-based strategies, the rise of efficiency-optimized and saliency-guided methods, and persistent gaps in dataset diversity, transferability, and standardized evaluation. We summarized and assess defence paradigms including pixel restoration, anomaly detection, input-space transformations, and robust training highlighting their trade-offs in robustness, imperceptibility, and computational overhead. Building on these insights, we outline future research priorities involving selective pixel recovery, transformer-specific vulnerability analysis, saliency-driven optimization, and real-world domain-adaptive defences. We further propose a regulatory framework emphasizing robustness testing, incident disclosure, and AI security governance. This review establishes a comprehensive foundation for understanding, evaluating, and mitigating ultra-sparse adversarial threats in contemporary AI systems.

Granular slip forecasting can conflate material state, loading progress, and the geometry of event-centered sampling. We separated these contributions in slowly sheared two-dimensional frictional disks using a compact neural score of stress, pressure, coordination, non-affine motion, and force-network observables. The model was developed on 36 trajectories and frozen efore testing on 18 new trajectories under two nested stress-drop definitions. Inspection of held-out results revealed post-event sampling asymmetry; recovery-aware analyses are therefore descriptive. With trajectories weighted equally, the compact score ranked near-slip windows above both prevalence and within-trajectory circular-phase controls under both definitions (representative average precision 0.310 versus prevalence 0.173; phase-null upper bound 0.257). Loading-history coordinates ranked more strongly, reaching 0.534 for causal elapsed strain. The recovery-aware rule retained 78.4% of activity-gated events and preferentially selected longer preceding intervals; ranking by time since the previous catalogued event remained compatible with a count-conditioned geometry null. Compact observables thus contain temporally aligned slip information, but stronger loading-history baselines and window-geometry sensitivity bound that evidence. These startup data do not isolate a state-specific short-horizon precursor beyond loading history or support a renewal interpretation of elapsed-strain ranking.

For the fair allocation of indivisible goods, the milestone work of Caragiannis et al. (2019) revolutionized the understanding of Maximum Nash Welfare (MNW) allocations by revealing their "unreasonable" ability to balance fairness (EF1) and efficiency (PO) for general additive functions. Subsequent work established that MNW allocations simultaneously satisfy EFX and GMMS (and consequently MMS and PMMS) for binary instances (Amanatidis et al. 2021 and Barman et al. 2018), and satisfy EFX for bi-valued instances (Amanatidis et al. 2021). In this paper, we revisit the (personalized) bi-valued instances and provide a tight characterization of the approximation guarantees of MNW allocations with respect to EFX, PMMS, and GMMS, showing that these guarantees are significantly stronger than what is known for general valuations. Furthermore, we demonstrate that even for the slightly more general setting of tri-valued instances, the fairness guarantees of MNW deteriorate significantly, which establishes a sharp boundary on the instances for which MNW allocations are strongly fair.

Lazy clause generation solvers learn from propagation explanations; the form of a Regular explanation therefore determines which clauses reach the learning engine. Standard decompositions introduce variables for automaton states and derive reasons from local table constraints. BDD and MDD propagators instead select individual diagram edges. We study the direct LCG explanation language for Regular: disequality literals of the form $X_i\neq v$. Here, one literal removes every automaton transition with the same position/value label, so an explanation is not an ordinary edge cut. We prove that explanations for value deletions are exactly label $s$–$t$ cuts in the layered DFA unfolding. This characterization establishes NP-completeness for minimum-weight explanations, gives a polynomial algorithm for inclusion-minimal explanations, and leads to an exact $O((U+n)4^{|Q|})$ dynamic program for small automata. A C++ benchmark compares label-cut explanations with Table-LCG and MDD-edge baselines on 250 generated instances. On average, minimal label cuts reduce projected explanation size from 22.2 to 5.5 literals and run in tens of microseconds. Minimal label cuts are therefore the practical default; the exact algorithm provides an oracle for small automata.

In real-world clinical practice, medical images face open-world shifts: (i) long-tailed rare diseases, (ii) subtle lesions dominated by normal anatomy, and (iii) hierarchical taxonomies. Yet most open-world paradigms assume flat, balanced label spaces, leaving these biomedical demands unresolved. We introduce Generalized Biomedicine Discovery (GBD) and a unified benchmark spanning long-tail, anomaly, and taxonomy-aware discovery. Our key insight is that dominant known patterns form a visual manifold that masks subtle novelty. Inspired by expert diagnosis, we propose SCAN (Surprise-evoked Complementary AccommodatioN), which follows a cognition-inspired perceptual progression: it applies predictive suppression to filter expected norms, triggers surprise-evoked salience to highlight unexpected deviations, and performs complementary accommodation to integrate these shifts into global representations. Extensive experiments show that SCAN improves novel concept discovery while generally preserving established clinical knowledge, and it plugs into existing architectures to better navigate the known-unknown trade-off in medical imaging. Code is available at https://github.com/lytang63/generalized-biomedicine-discovery.

Customer churn prediction on the IBM Telco Customer Churn benchmark (n = 7,043) routinely reports test accuracies above 95%, with the most cited published study reporting 99.01%. We audit this benchmark for four trustworthiness failures invisible to the accuracy- and F1-centred reporting that dominates the literature. First, pre-split SMOTE inflates churn-class F1 by 13.1 percentage points across ten classifiers and fifteen seeds (Wilcoxon p < 10^-4 per classifier); the same leaky pipeline ordering paired with class weighting yields no inflation, isolating the effect to SMOTE's geometric construction. We measure the mechanism directly: approximately 36% of synthetic training points are nearest-neighbour interpolations of test-set instances. Second, the TotalCharges field is approximately determined by tenure multiplied by MonthlyCharges (R2 = 0.999); removing it changes accuracy by less than 0.2 percentage points, yet TreeSHAP ranks it ninth in mean absolute attribution - a pattern that materially corrupts SHAP-based interpretation. We propose an R2 > 0.95 pre-modelling diagnostic. Third, in a 15-seed calibration audit, isotonic regression is the strongest default; temperature scaling fails on class-weighted tree ensembles whose predicted-probability distribution is bimodal. Fourth, the cost-optimal decision threshold (under a 50 USD retention offer and 24-month CLV proxy) is approximately 5-10 times lower than the F1-optimal threshold, saving approximately 77,000 USD per 1,000 customers. We replicate F1 and F2 on Iranian Telecom Churn (within domain) and Bank Customer Churn (across domain): F1 generalises; F2 generalises only within telecom. We synthesise these findings into a four-component reporting checklist - pipeline disclosure, redundancy diagnostic, calibration audit, and cost-sensitive thresholds - and release a reproducible implementation.

We study prediction of one unmeasured copy of an unknown finite-dimensional pure quantum state after independently measuring the observed copies with the one-copy Haar POVM. For the resulting fixed separable observation, the Bayes predictive state under quantum relative-entropy loss is the full-rank posterior mean. We evaluate it exactly through permanents of minors of the outcome Gram matrix, prove positivity and normalization of the permanent representation, and establish minimaxity among decision rules based on these fixed outcomes. Using Hilbert–Schmidt projection of the posterior mean and an exactly analyzed linear-inversion competitor, we prove a finite-sample posterior-purity bound and an explicit relative-entropy guarantee with sample count $O((d^2/\epsilon)\log(d/\epsilon))$. Using the exact collective benchmarks proved in a companion paper, we also obtain entropy and posterior-purity comparisons. To connect the fine product data to a regular ray-valued experiment without assuming deterministic finite-sample uniqueness, we draw one random orientation for a finite projective mesh, retain it for the entire sample, and apply a selected finite-alphabet MLE in the resulting reference experiment. A nested recovering mesh uniformly recovers the fine Fisher information. Consequently every sufficiently fine fixed mesh gives a regular finite-alphabet model. Its selected MLE has Haar-averaged inverse-Fisher coefficient $\overline a_k$, and refining the mesh after the fixed-mesh large-sample limit makes $\overline a_k$ approach $d-1$. This yields epsilon-optimal leading relative-entropy and posterior-overlap bounds for the fine posterior and the sharper fixed-dimensional asymptotic scale $(d/\epsilon)\log(d/\epsilon)$. The latter is not asserted as a uniform finite-sample guarantee. No deterministic finite-sample MLE uniqueness or triangular mesh schedule is used.

Model judges now supervise multimodal systems at scale, filtering training data, selecting outputs, and supplying the reward that shapes multimodal reasoning models. Trusting one means first checking that it uses its evidence, and that check is itself worth scrutinizing, so we ask whether a counterfactual probe of visual grounding measures what it claims to. The probe edits the image so the ground truth flips, holds the reasoning trace fixed, and asks whether the verdict follows. We formalize it as the Verdict Grounding Score and show it cannot be read the way such scores are read. A verdict responds only to an edit that reaches the judge's decision-relevant reading, so the score is capped by how perceptible the edit is, and unless editing makes the attribute easier to read, the error is one-sided: the score can only make a judge look less grounded than it is. The practical failure is therefore a false alarm, an auditor discarding a usable overseer. Under assumptions we state, we show this missing quantity is not merely bounded but identified from three quantities the same audit protocol already collects, which makes the false-alarm rate directly measurable rather than merely a concern. Auditing nine judges, we find the predicted ordering holds strictly across our entire primary pool, and the typical judge there acts on only about half of the edits whose attribute it can otherwise resolve. Applying a conservative rejection threshold certifies several cells as false alarms outright, the clearest being a judge that detects the injected error essentially every time while still scoring as if it had not used the image at all. The rule that follows is that an image-side counterfactual score should never be reported alone: a detection probe on the unedited image upper-bounds it, certifies its false alarms, and costs nothing extra to run.

DomiRank is a node-importance algorithm for unweighted networks, defined by a dynamical model governed by a competition-strength parameter, a dominance threshold, and a decay rate. We establish three structural results. First, on symmetry. Automorphism-related vertices share the same DomiRank value, and a graph whose values are pairwise distinct must be asymmetric. The orbit count bounds the number of distinct values, and regular and vertex-transitive graphs admit closed forms. Second, on entropy. The maximum of the DomiRank entropy over connected graphs, log_2 N, is attained if and only if the graph is regular. The initial entropy derivative is the degree-log-degree edge covariance, making the decrease rigorous near vanishing competition for structurally disassortative graphs, and an assortative counterexample shows it does not extend to all graphs; a sufficient-condition theorem and a refined conjecture cover the rest. Third, on spectrum. The normalized distribution is sigma-invariant if and only if the degree vector is an adjacency-matrix eigenvector. The parameter sigma interpolates continuously between degree and smallest-eigenvector centrality within the resolvent (Bonacich-type) family, its sensitivity being a second-order suppression operator on the degree vector. Graph transformations are also characterized, including the m-product. Experiments on four real networks and synthetic families up to 10^4 vertices confirm the interpolation and exhibit monotone entropy decrease, continuous ranking interpolation, decaying positive fraction and ranking reversals; where the positive fraction has decayed far from one, the limit describes the solution vector rather than the induced ranking. DomiRank is thus a tunable complement to principal-eigenvector centrality. A companion study quantifies how much of its task-level edge over a degree baseline survives degree correction.

Deep learning and large language models (LLMs) are rapidly gaining adoption in semiconductor design, driving demand for training datasets. Most efforts focus on hardware description languages (HDLs) while designs for high-level synthesis (HLS), a popular approach to domain-specific accelerators, remain scarce. HLS dataset efforts emphasize manual curation or design parameterization, seldom addressing high-quality LLM-based generation or diversity in code length, hierarchy, design-space size, latency, resource utilization, and application domain, potentially limiting model generalization. We propose SyntheticHLS, a framework for generating large-scale, complex, diverse synthetic HLS datasets using LLMs. Its two key ideas are: 1) an iterative feedback-guided mutation loop that uses paired HLS source code and design-space specifications to incrementally transform seed designs into more complex, scalable designs; and 2) quantitative metrics of HLS design complexity and design-space scalability that serve as measurable objectives for LLM-guided mutation. We systematically cross-validate an HLS Quality-of-Results (QoR) deep learning model trained and tested across common HLS benchmarks, zero-shot synthetic designs, and iteratively mutated synthetic designs. Synthetic designs transfer well to common benchmark test sets while the reverse does not hold. SyntheticHLS's iteratively mutated designs provide the most generalizable training corpus among the datasets studied. Analysis of the mutation process and dataset shows that metric-guided trajectories consistently improve targeted complexity and scalability objectives without regressing non-target metrics. Mutated designs span a substantially broader, more diverse design space than zero-shot generated designs. Our framework, dataset, and evaluation are open-source: https://github.com/sharc-lab/synthetic-hls.

Mixture-of-Experts (MoE) models enable efficient scaling of large language models but face critical deployment challenges due to massive memory requirements. Existing pruning methods either incur prohibitive search costs or neglect the dynamic interdependencies between experts. To address these challenges, we present OMP-MoE, a novel training-free compression framework for reducing expert redundancy in MoE-based LLMs. Based on observations of expert contribution patterns, we reformulate the pruning problem as a sparse signal reconstruction task solved through Orthogonal Matching Pursuit. Specifically, our method first treats individual expert contributions as dictionary atoms and selects experts that greedily minimize reconstruction error with linear computational complexity. Then, we optimize cross-layer expert allocation through a water-filling strategy that accounts for both reconstruction quality and routing stability. Finally, we introduce OMP-MoE{\dag}, an adaptive inference mechanism that dynamically adjusts expert activation based on energy prediction. Comprehensive experiments on Qwen, DeepSeek-V2, GPT-OSS, and Mixtral MoE demonstrate consistent improvements over existing methods at 25-50% pruning ratios. For Qwen3-30B-A3B at 50% compression, we retain 93.3% of original performance, achieving 33$\times$ faster search and 1.55$\times$ inference speedup. Codes will be available after acceptance.

Replay-based continual learning rehearses past data either in an offline phase, during which the agent stops acting, or interleaved with the live stream, where it perturbs the computation serving the current input. An agent that learns in deployment can afford neither. Motivated by local sleep, the use-dependent off periods of individual cortical circuits in awake animals, we show that replay can instead be written into the degrees of freedom the current input leaves unused. In a network with k-winner-take-all hidden layers, confining replay updates to synapses whose presynaptic unit is silent or whose postsynaptic unit is inactive leaves the hidden computation on the current batch invariant: exactly so for silent and suppressed units, and for all but 0.3% of samples in practice. A refractory rule under which units that have just fired sit out the next competition doubles the width of this channel and carries most of the accuracy. On class-incremental split-MNIST the resulting learner, with no offline phase, matches or exceeds the best offline rehearsal schedule and outperforms experience replay, ER-ACE and unmasked interleaved replay, each re-tuned under the same micro-batch schedule. Against DER++ the comparison splits by protocol: with five epochs per task DER++ leads by 1.5 points once it runs under that schedule, and in a single pass over the stream, the regime closest to the agent deployment setting, the system leads it by 1.6 while offline rehearsal falls 15 points behind. On split CIFAR-10 it again leads offline rehearsal and experience replay, but trails ER-ACE and DER++ by two to three points. The construction is not tied to the local learner: on a backprop network with k-winner-take-all hidden layers under the same schedule, refractory rotation adds half a point in five epochs and three in a single pass, and isolation again costs nothing on top of it.

Structured phenotype extraction from radiology reports supports cohort construction, quality auditing, and clinical analytics, but practical deployment requires local inference and auditable predictions, while expert annotations remain scarce. Conventional labelers provide structured findings and assertion states but no supporting evidence, while API-hosted large language models may be unsuitable when clinical text cannot leave institutional infrastructure. We present CHESTPHENOT, a compact 0.5-3B language model that jointly extracts finding labels, three-class status (present/absent/uncertain), and verbatim supporting evidence spans. CHESTPHENOT is trained using hybrid CheXbert+72B silver supervision followed by supervised fine-tuning and lightweight GRPO refinement. Across three human-annotated gold sets spanning in-distribution, cross-taxonomy, and cross-institution evaluation, the 3B model remains below its CheXbert silver teacher in distribution but is competitive under distribution shift, significantly surpassing CheXbert on cross-institution detection (+2.0 F1). Task-specific training also enables the 3B model to match or exceed substantially larger prompted models on most detection and status comparisons. For evidence-grounded extraction, over 99% of final evidence spans are locatable in the source report, and the 3B model achieves 47.5 auditable-F1, outperforming Qwen2.5-7B one-shot prompting by 7.6 points and approaching Qwen2.5-72B. These results demonstrate that locally deployable models can provide competitive and directly auditable radiology-report extraction without relying on external inference APIs. Code and the full extraction/judge prompts will be made available at https://github.com/yukkai/ChestPheNoT.

Production text-to-SQL pipelines often end with an LLM-as-judge whose agreement with human annotators has never actually been measured. When we checked ours, the deployed gpt-4o-mini judge agreed with two-author gold at only Cohen's kappa = 0.04 on a disagreement-enriched set and 0.42 on a uniform-random spot-check, over-flagging 77.1% of the human-FAITHFUL cases in the enriched set. Most of its over-flags trace back to a single mechanism we call GRADE-HALLUCINATION. A self-hosted Qwen3.6-27B replacement (kappa = 0.72) lands in the same range as Claude Opus 4.7 (kappa = 0.71); the head-to-head is underpowered at n = 96, but for the deployment decision that hardly matters, since Qwen costs roughly 1/300 as much per call. Ensembling does not help for free. Pairing the weak judge with a stronger one degrades agreement, whereas three strong judges under unanimity routing reach kappa = 0.79 at 89.7% auto-coverage. Applied out-of-domain, the same audit recipe flags 25.5% of BIRD-financial's expert-authored gold SQLs as candidate gold-SQL issues under our annotation protocol. Code and pre-registration are at https://github.com/JamesL404/synca-audit.

In team collaboration scenarios, memory is heterogeneous and continually evolving. Team memories capture collective decisions, protocols, and current consensus, while individual memories preserve member-specific observations, execution traces, and intermediate progress. Existing memory-augmented systems typically retrieve from all stored memories as a flat pool, ranking them by semantic relevance, importance, or recency without modeling hierarchical structure or evolving validity. As a result, they often surface semantically relevant but outdated or conflicting memories, especially individual memories that no longer align with current team consensus, instead of prioritizing currently valid memories. This is particularly problematic when collaborative LLM agents answer user questions, since their responses should be grounded in valid memories. We propose HiCoMER, a framework for hierarchical collaborative memory management and validity-aware retrieval in LLM agents. HiCoMER first maintains the validity of team and individual memories and then retrieves memories that remain valid, rather than retrieving directly from all stored memories. It consists of three components: a Hierarchical Memory Conflict Updater, a Validity-Aware Memory Retriever, and a Memory-Grounded Answer Generator. To evaluate HiCoMER, we construct two new datasets for memory-grounded question answering in collaborative settings. Experiments on both datasets show that HiCoMER consistently outperforms strong baselines by reducing outdated retrieval, preserving current team consensus, and improving downstream QA quality.

In Transformer-based masked language models, attention is the primary mechanism for context mixing, but there are other ways to mix data across tokens. Recent attention-free mixers replace attention with fixed or hypernetwork-generated MLPs, alternating their dynamic, content-dependent weighting for computational simplicity. We build an alternative that gets the same property from a low-rank bottleneck autoencoder. We replace attention with a stack of autoencoder-based mixing modules, one operating over local neighborhoods, one over the full sequence, and one across attention heads, each compressing and reconstructing its input through a bottleneck, and its width is a hyperparameter rather than a training effect. In masked positions, we introduce an iterative refinement procedure that has two distinct steps. A pulling step that pulls an embedding representation toward a weighted average of its neighbors, and a correcting step that projects the result back to the learned manifold via an autoencoder. Our architecture achieves a significant portion of attention's performance at about $1.9 \times$ fewer FLOPs when pretrained on C4 and evaluated with parameter-matched BERT baselines. Our model equals parameter-matched BERT and TinyBERT baselines on the rarest-token frequency bucket using a frequency-aware training schedule that samples rare tokens more than uniformly for the masking tasks.

Test-time reinforcement learning can adapt vision-language models (VLMs) to unlabeled target data, but its effectiveness is fundamentally limited by the reliability of self-generated learning signals. To assess the reliability of consensus-based learning signals, we analyze VLM test-time reinforcement learning across diverse VQA datasets and model sizes, revealing two limitations. First, gains from consensus-based test-time training largely come from answer normalization rather than content correction. Second, many initial VLM responses are incorrect due to the model's limited ability to jointly use the image and the question; consensus rewards derived from these outputs may preserve the resulting grounding errors rather than correct them. Motivated by these, we propose TTIQ, a test-time reinforcement learning framework that harnesses image-question dependence for better vlm adaptation. TTIQ teacher-forces each sampled response under the original image-question pair and its image- and question-ablated variants, using the resulting token-level likelihood changes to estimate dependence on each input. It combines image and question dependence with calibrated confidence to construct a response-level reward that favors jointly grounded responses, and uses the token-level signals to assign greater positive policy credit to tokens supported by both inputs. This design favors responses that are jointly grounded in the image and the question and sufficiently confident, rather than merely popular. Experiments across eight VQA datasets and multiple VLM sizes show that TTIQ achieves the best average performance at every model scale. It further generalizes across VLM families, while models trained on one dataset improve performance on unseen datasets without further training.

Diffusion learning leverages the statistical mechanism of diffusion processes for learning, reasoning, and inferring complex distributions from data. Recent advances in diffusion learning have been transformative, with robot learning emerging as a key opportunity area, with applications spanning perception, control, and decision-making. At the same time, the statistical mechanism of diffusion processes can be controlled to shape the temporal evolution of the state distribution underlying robot trajectories, inducing ergodic behavior in robotic systems. The frameworks of controlled diffusion and ergodic control were developed around the same time as diffusion learning, and their theories and algorithms have increasingly converged. Ergodicity induced by controlled diffusion has several significant implications for robot learning, distinct from applying diffusion learning to robotics problems: it formally enforces statistical properties required to ensure optimality of robot learning, enables non-myopic search over uncertain information landscapes for data collection, and enables behavior specification based on spatial rather than temporal characteristics of trajectories. This survey introduces the intuition behind controlled diffusion for robot learning, explores its connection to diffusion learning, presents theoretical foundations and numerical tutorials for solving controlled diffusion and ergodic control problems, and reviews applications across robotics. Finally, we discuss key challenges and future opportunities in leveraging controlled diffusion for robot learning.

Converting scientific graphics into editable representations remains a challenging problem for image-to-code generation because of their heterogeneous elements and complex layouts. Recent multi-agent reconstruction systems have advanced this line of work, but often follow a copy-paste paradigm: the reconstructed image closely resembles the original, while complex regions remain effectively uneditable. We instead formulate a different objective, raster-to-authoring reconstruction, which aims to recover an authoring representation that supports native, customized editing rather than mere visual replication. To this end, we present VectorHarness, a multi-agent framework for raster-to-authoring reconstruction that recovers heterogeneous components using type-appropriate native representations. Text, formulas, shapes, connectors, icons, charts, and tables are reconstructed as natively editable objects, while intrinsically image-based regions remain raster content. To systematically evaluate reconstruction quality, we introduce VectorHarness-Bench, which jointly assesses rendering fidelity, raster fallback coverage, executable object edits, and relation-preserving edits. Experiments show that VectorHarness improves executable edit success and relation preservation, reduces avoidable raster fallback, and maintains high visual fidelity across heterogeneous graphics.

Wearable action anticipation systems must remain reliable despite missing frames, masking, and sensor noise, yet existing egocentric anticipation methods largely assume clean observations. We identify two complementary failure modes under temporal corruption: unreliable temporal evidence during encoding and implausible, low-support verb-noun compositions during decoding. We address them with a lightweight framework combining Temporal Reliability Suppression (TRS) and Robust Verb-Noun Graph (RVG) decoding. TRS predicts a per-frame suppression score from the projected input embedding and uses it as a learned key-side attention penalty at every encoder block and to derive reliability-weighted temporal pooling. RVG re-ranks verb-noun pairs using a PMI-based compatibility graph constructed from training labels. Under corruption-augmented training, TRS+CA+RVG reaches 29.1% average corrupted accuracy and 88.2% relative robustness across six corruptions, including three mechanisms absent during training, while reducing rare verb-noun predictions from 15.4% to 1.1%. Multi-seed and diagnostic experiments show that TRS responds to synthetic masking; shuffled-graph and frequency-only controls further indicate that RVG gains depend on genuine pairwise compatibility rather than marginal-frequency effects alone.

Medium-range weather forecasting underpins operational and planning decisions across the energy industry. Developing competitive weather models was once the domain of national meteorological centers, but recent advances in machine-learned weather prediction (MLWP) have opened the field to industry. We present Aries, a SwinTransformer-based MLWP model developed at InCommodities. Aries is trained on ERA5 reanalysis data at 0.25\textdegree{} resolution, predicting 74 prognostic and 11 diagnostic atmospheric variables. We evaluate the model on 2025 ECMWF Analysis initializations, ensuring a recent and strictly out-of-sample test period for all models compared. On 10-metre wind speed, Aries outperforms both ECMWF HRES and AIFS in terms of RMSE for lead times up to four days, while on 2-metre temperature it achieves RMSE on par with AIFS operational. These results demonstrate that proprietary development of competitive weather models is technically viable, supporting a broader set of forecasts available for operational and planning applications in the energy industry.

We present ScorePrompts, an interactive system in which users upload a score, receive natural-language descriptions of its musical structure, ask questions about specific passages, and inspect the corresponding analysis results in staff notation. Specialist MIR components first estimate harmony, tonality, cadences, formal boundaries, texture, and note-level roles, organizing their outputs at note, beat, measure, and piece levels. A schema-constrained language model converts these results into descriptions rather than inferring musical structure directly from raw MusicXML. For questions such as "What changes in measures 14-18?", a deterministic router selects the relevant measures and analytical levels and returns a concise response together with the underlying results and caveats. Verovio renders the score and links the returned information to cited measures and note-level attributes. The interface also exposes intermediate tables and disagreements between analytical levels. ScorePrompts is intended for exploratory score analysis and explanation, not score editing. The demo shows how existing analysis models, constrained language generation, Q&A retrieval, and notation-based visualization can provide natural-language access to symbolic music analysis while keeping intermediate results inspectable.

Achieving biological-level running speeds has largely been pursued through advances in control algorithms, which improve the utilization of existing hardware. However, the ultimate speed limits remain governed by the underlying force and torque requirements of rapid locomotion, which are typically addressed through increased actuator capacity. Inspired by Huygens' coupled pendulums, we demonstrate that superior locomotion can emerge from principled exploitation of intrinsic dynamics rather than brute-force hardware scaling. Inter-limb inertial coupling redistributes energy across the gait cycle and reduces peak joint torque required for rapid periodic motion, thereby expanding the achievable speed without proportional increases in actuator capability. Incorporating hardware parameters as additional design variables further extends this analysis into a co-optimization framework, enabling the systematic utilization of inertial coupling in robot design. Guided by this framework, a quadruped robot achieves a running speed of 10.74 m/s (Froude number 21.4) and completes a 100-meter sprint in 12.2 seconds, representing the first legged robot to surpass 10 m/s. These results establish inertial coupling as an underlying mechanism governing high-speed legged locomotion and highlight its role in reducing force requirements, offering new insights into the design of agile robotic systems.