Papers

We present a regression-based approach to Arabic dialect geolocation that models dialectal variation as a continuous geographic space rather than discrete categories. Speaker origin is predicted as continuous latitude-longitude coordinates using a hierarchical neural architecture that fuses frame-level XLS-R-300M and Whisper-large-v3 encoder representations with phonotactic descriptors through a Transformer encoder and a learnable attention-pooled query. A spherical geodesic loss directly optimizes great-circle distance on Earth's surface, avoiding distortions inherent to planar coordinate regression. Under a leakage-free 5-fold GroupKFold protocol grouped by source recording, our model attains a pooled median localization error of 481.2 km. Auxiliary country and city heads reach 64.5% and 45.2% accuracy, respectively. A permutation Mantel test on the learned latent space provides quantitative support for the Arabic dialect continuum hypothesis. To probe true generalization, we further introduce a city-masking protocol in which two cities per fold are removed from training but retained in validation. Under this zero-shot regime, the mean error rises to 1173.3 km, a 1.32x degradation relative to seen cities. Our findings establish continuous geographic modeling as a principled framework for Arabic dialect geolocation and quantify both its strengths and the substantial headroom that remains.

In HEP data analyses, finding an adequate function to model binned data has largely relied on a manual process: guess a functional form by intuition, fit, examine, then repeat until successful. We show that this iterative process can be automated by a machine using symbolic regression, which performs a data-driven search over function space without requiring prior knowledge of what an adequate function should look like. We present the SymbolFit package, which pairs symbolic regression with uncertainty modeling to target HEP analysis use cases, and demonstrate it on the CMS and ATLAS Run 2 dijet spectra: 560 independent seeded runs across seven simple fit configurations generated over 1000 functions fitting the spectra with $\chi^2/\text{NDF}\approx 1$, and 111 of the runs rediscovered the very dijet and UA2 functions used in published dijet searches.

Model-based reinforcement-learning agents of the DreamerV3 family forget catastrophically when trained on task sequences, even when an unbounded replay buffer preserves every earlier experience. We ask a question the continual-RL literature has assumed an answer to but never measured: which component forgets? Under never-clear replay, pre-registered component-level probes (n=3 seeds throughout) show that the world model retains essentially everything measurable about old tasks – reward discrimination (retention ratio ~1.0), value estimates, and termination structure – while the actor's behavior collapses. Forgetting in this regime is a channel problem, not a memory problem. We demonstrate this by intervention: with the world model frozen and identical imagined rollouts, reinforcement learning in imagination fails to recover a lost skill (0/3 seeds), while supervised self-imitation on the world model's own graded dreams recovers it on 3/3 seeds with zero environment interaction. Interleaved during training, this graded dream rehearsal yields a task-label-free, parameter-constant continual learner: 3/3 four-task chains retained where plain replay passes 0/3, 3/3 eight-task chains, and consistent gains over matched real-episode cloning (paired difference +0.13, bootstrap 95% CI [0.07, 0.24], complete seed separation). The dream-grading step is load-bearing: we characterize two scoring failure modes, provide an offline selection gauge that caught both before they contaminated results, and give a realized-first grading rule that closes them. All experiments were pre-registered with committed protocols; every refuted hypothesis is reported.

The wind energy industry relies on accurate power curve models to make power forecast, evaluate turbine performance, quantify upgrade, or support site-planning decisions. In this paper, we focus on site-planning power curves, i.e., we investigate how power curve models trained using turbine data on an operating wind farm can be transferred to a new, undeveloped farm. The traditional wisdom in the wind energy literature relies on distance, layout, or terrain characteristics for making cross-farm power curve transfer. Through the lens of domain adaptation, we propose a more reliable transfer learning approach for cross-farm power curve modeling. In the cross-farm applications, a domain is specified by the temporal environmental variates and spatial terrain variables. Domain adaptation is to find a capable similarity metric to adapt the domain on the new farm to that on the existing farm. Empirical results show that our domain adapted power curve consistently outperforms competing approaches by an appreciable margin for site-planning power predictions.

Classifier-free guidance (CFG) is the default mechanism for conditional generation in diffusion models, but the distribution sampled by its deterministic guided dynamics is not captured by the usual product-distribution heuristic $p_0^\omega q_0^{1-\omega}$. We analyze CFG through the probability flow ODE and derive exact analytic path-integral representations of the induced distributions for both constant and time-dependent guidance. The resulting formulas show that CFG modifies $p_{t_0}$ by an exponential path-integral correction, and that a time-dependent schedule enters this correction through the weight $\omega(t)-1$. This characterization explains how score discrepancies accumulate along sampling trajectories and motivates Distribution-Guided CFG (DG-CFG), a schedule that balances timestep contributions while accounting for signal strength and low-noise score-error amplification. A toy model with analytic scores closely verifies the predicted distributions. Across Stable Diffusion~1.5, Stable Diffusion~2.1, and Stable Diffusion~XL, DG-CFG yields a stronger diversity–fidelity trade-off and robustly mitigates the saturation and quality degradation caused by strong constant or heuristic guidance. Complete NFE experiments on Stable Diffusion~1.5 and Stable Diffusion~2.1 confirm that these gains persist across sampling budgets, while fixed-quality experiments on both backbones show that DG-CFG reaches target metrics with fewer sampling steps.

Latent world models improve sample efficiency in continuous control by optimizing policies over imagined latent trajectories, but common neural transitions offer limited direct control over modal persistence and error accumulation in long rollouts. We propose Koopman Dreamer, a Dreamer-style world model with a spectrally constrained deterministic latent dynamics core. Its Koopman-inspired backbone uses two-dimensional rotation–scaling blocks with bounded radii to represent damping, rotation, and near-periodic modes. Linear and low-rank bilinear action terms capture global and state-dependent control effects, while stochastic-state modulation supplies local correction information. To reduce the mismatch between posterior-conditioned training and prior-only imagination, the model combines posterior-conditioned EMA teacher targets with one-step consistency, multi-step rollout, and open-loop observation-prediction objectives. We further derive a multi-step rollout-error bound that separates amplification by the spectral backbone and bilinear interaction from the additive effects of stochastic-state mismatch and modeling residuals, clarifying the trade-off between error attenuation and long-term information retention. Experimental results on proprioceptive continuous-control tasks from the DeepMind Control Suite and UAV-LiDAR autonomous navigation demonstrate that Koopman Dreamer improves the stability of long-horizon latent rollouts and achieves stronger closed-loop control performance on tasks that rely on high-quality multi-step imagination.

In RLHF pipelines, reward scoring blocks policy updates. Slow scoring bottlenecks the entire loop, since no update runs until every rollout gets a score. And yet most setups just default to PyTorch eager mode or torch.compile, no one checks if that's actually fastest. Scoring itself is small. Rollout generation eats far more of a typical RLHF step. But scoring and generation fight over the same CPU and GPU resources, so a faster scoring engine doesn't shrink step time on its own. It mainly frees up capacity generation can use instead. We built a native C++ inference engine on ONNX Runtime. First step: confirm correctness. Output matched the PyTorch reference to 5.7 x 10^-6 on CPU and 4.2 x 10^-3 on GPU, close enough to trust. Then we tested it against PyTorch eager mode, torch.compile, and FastAPI, on both CPU and GPU. CPU was decisive. Our engine beat every baseline, confidence intervals didn't even overlap. GPU gave a different view: we beat PyTorch and FastAPI, but torch.compile came out ahead. Further testing traced the speedup to ONNX Runtime itself, not C++ as a language. And batching strategy mattered more than either the language or the runtime choice, more than we expected. The results are from repeated, independent runs, since single runs just aren't reliable enough to trust.

LLMs can be prohibitively expensive and slow to run at scale, especially for applications that invoke an LLM per sample over millions of inputs. A natural way to scale is to cluster the inputs, run the LLM only on cluster representatives, and propagate the outputs to other cluster members. However, the outputs a member receives are only as good as its match to the representative. Off-the-shelf clustering methods optimize an aggregate objective, targeting average-case quality without per-sample guardrails. As a result, members can be assigned to poorly-matched representatives, and the inherited outputs – though appropriate for the representative – may be irrelevant or even unsafe for the member. For example, a parent of a toddler grouped with parents of older children could receive age-inappropriate recommendations. Most clustering methods also scale poorly to millions of inputs in runtime and memory, limiting their use at industry scale. We propose a scalable two-stage clustering algorithm with provable per-sample guardrails: every sample is guaranteed to share a user-specified minimal embedding similarity and exact attribute match with its representative. The algorithm first generates initial clusters with Mini-batch K-Means, then greedily selects representatives within each to satisfy the guardrails. We provide theoretical guarantees, complexity analysis, and benchmarks against common methods on internal and public datasets. Our method delivers per-sample guardrails while running substantially faster and scaling to data sizes where most standard methods become intractable. We demonstrate its impact in a real-world deployment clustering 38 million customers, reducing downstream LLM cost and runtime by 50-fold while preserving personalization. This unblocked the launch of a persona-based recommender system that delivers significant gains in revenue and engagement in an A/B test.

Observational causal analyses increasingly pool records across sites, vendors, and collection systems, creating vulnerability to append-only attacks in which plausible records are strategically selected to alter a reported treatment effect. We develop a data-poisoning audit for augmented inverse-probability-weighted estimation. The analyst specifies a finite catalog of feasible records, an append budget, and nested source capacities, and the adversary selects a feasible subset to maximize movement in a prespecified direction. With preprocessing and nuisance fits held fixed, we propose a greedy scan that computes the exact finite-sample worst-case movement at every append budget. To account for nuisance refitting, we go on to derive a total-influence score combining each record's direct contribution with its effect through the propensity and outcome models. We further obtain a conservative finite-budget bound for the fully refitted estimate. Extensive simulations validate the exact result and show that total influence improves local refit prediction, while multisite and public-data analyses demonstrate material sensitivity at small append budgets. By translating adversarial data-composition risk into movement curves and critical budgets, the framework supports more reliable causal reporting and the design of source-level safeguards.

Reinforcement learning with verifiable rewards has become the predominant recipe for eliciting test-time scaling in explicit Chain-of-Thought reasoners. Yet this scaling path remains computationally costly, since intermediate reasoning must be externalized as natural-language tokens. Latent reasoning instead carries intermediate computation as continuous vectors and already matches or surpasses explicit CoT at far shorter horizons. Despite this promise, latent reasoners remain largely imitation-bound, while explicit CoT has already moved past imitation via outcome-reward RL. Latent trajectories lack a tractable per-step likelihood and an adaptive stopping interface under fixed thinking budgets, so outcome rewards cannot elicit latent test-time scaling. We introduce Surrogate Latent Policy Optimization (SLPO) to bring outcome-reward RL to autoregressive latent reasoners: a differentiable surrogate policy interface over latent transitions for trajectory-level credit assignment, and a correctness-supervised stopping head that outcome-reward optimization refines into a variable-horizon policy. Across two continuous latent reasoners, two backbones, and three held-out benchmarks, SLPO improves Pass@8 and Pass@16 in all 12 backbone–dataset settings, with gains of up to 12.07 percentage points. SLPO further transfers to soft-token inference and learns difficulty-adaptive computation, allocating longer latent trajectories to harder instances. Project Page: https://modalitydance.github.io/SLPO/

We study the problem of recalibrating an online predictor [KE17, OKS24]: given an arbitrary "hint" sequence of forecasts, the learner must output new predictions that are calibrated while incurring small excess error relative to the original forecasts, under a proper loss. We give an online algorithm that achieves $(\varepsilon, \varepsilon^2)$-recalibration for Lipschitz proper losses in $T \approx \varepsilon^{-3}$ rounds, using an imbalanced extension of the recent simultaneous Blackwell approachability reduction framework of [HTY26]. We show that this tradeoff is optimal by proving a matching lower bound for recalibrating against the squared loss. We also prove a companion $\mathcal{K}_2$-recalibration theorem that obtains the same tradeoffs up to a logarithmic factor. As our main application, we show how our recalibration algorithms can be combined with the online refinement method of [FH23] to obtain simultaneous $\varepsilon$-calibration and $\varepsilon^2$-calibeating for smooth proper losses at the same asymptotic rate, improving upon prior works that achieved these properties separately or with a worse $\varepsilon$ dependence. In particular, the $\mathcal{K}_2$ variant answers a question of [CHJL26] on simultaneously achieving near-optimal calibeating and calibration rates. We also derive extensions to settings with multiple hint sequences. Finally, we empirically evaluate our algorithms on a classification dataset undergoing distribution shift.

Masked diffusion models (MDMs) are a promising family of language generators, but achieving high-quality few-step generation remains challenging. In MDMs, all forward trajectories collapse to a single fully masked state, leaving no terminal entropy for consistency-style few-step generation. While recent few-step alternatives based on uniform-state diffusion avoid this degeneracy, it becomes harder to distinguish clean tokens from noise than MDMs, which usually harms modeling quality and training efficiency. In this work, we propose a multi-mask diffusion model (MultiMDM) that preserves the masking structure towards few-step generation. In the forward process, each clean token is first pushed towards a designated mask and then gradually mixes over the mask set. As a result, the backward process has a drafting capability by predicting a designated mask before refining to a clean token. We derive a closed-form ELBO training objective for MultiMDM that supports continual training from pretrained MDMs. In addition, we formulate a purely discrete-state consistency distillation scheme, with a shared-Gumbel coupling to reduce pathwise entropy. Experiments on pretraining and distillation show that MultiMDM provides an effective foundation for principled few-step generation.

Nuclear quantum effects are rigorously captured by imaginary-time path integrals, which map the quantum Boltzmann distribution onto a ring polymer of classical replicas. Yet the nuclear masses, the coupling to the environment, and the boundary conditions of the path remain hard-wired in the simulation or the trained model, even though this quantum context enters the path measure only through a quadratic action known in closed form. Here we show that a denoiser trained on classical Boltzmann statistics alone, composed at sampling time with an analytic Gaussian component carrying the entire quantum context, yields the quantum Boltzmann distribution of the nuclei. Such a composition exists and is exact whenever the training noise does not exceed the intrinsic quantum uncertainty of the target ensemble, and it is invariant across all quantum contexts admitted by this bound. We show exact transfer across temperature, isotopic mass, dissipation strength, and the boundary conditions of the path in theory and in numerical experiments, without retraining. The last yields the end-to-end displacement and momentum distributions of a tagged nucleus from open imaginary-time paths. The same invariance extends in principle to the permuted boundary conditions of bosonic exchange, with the identical denoiser. In this view, the noise of generative modeling and the quantum fluctuations of the nuclei are two faces of the same quadratic structure.

AI-generated answers in high-stakes domains are often fluent but difficult to verify, especially when they contain multi-step reasoning rather than a single final answer. We propose a reasoning-based, reference-free framework for auditing LLM-generated outputs. The method decomposes a generated reasoning trace into segments, labels local premise-target relations using Natural Language Inference (NLI), and organizes these relations into a hypergraph. A deterministic backward AND-OR search then assigns segment-level audit labels that indicate how each segment is grounded within the generated response. We evaluate the framework in two settings: deductive mathematical reasoning with Hard2Verify, and open-ended medical reasoning with UroReason, a new physician-annotated benchmark of LLM reasoning traces from real clinical cases. Across these settings, our NLI-hypergraph audit provides a more reliable reference-free evaluation signal than direct LLM-as-judge baselines. In the clinical setting, state-of-the-art LLM judges often fail to identify problematic reasoning segments, over-accepting fluent but weakly grounded responses. Our results show that QA evaluation should account for how inferential relations compose across a reasoning trace, rather than relying only on final answers or LLMs as verifiers. UroReason will be made available through an API, and our code will be released as open source.

Federated Graph Neural Networks (FedGNNs) are highly vulnerable to backdoor poisoning, yet existing defenses typically rely on rule-based approaches that lack semantic understanding, making them vulnerable to stealthy triggers and harmful to benign structures. To solve this, we present FedLSG, the first framework that integrates large language models (LLMs) into federated graph backdoor defense. FedLSG introduces a graph and behavior to text grounding scheme that transforms local graph structures and client update behaviors into semantically rich natural language representations. The framework further adopts a lightweight student-teacher architecture. On the server side, a full scale LLM serves as a teacher, providing global contextual guidance and evaluating client updates during aggregation to identify potentially malicious participants. On the client side, a LoRA-based student is maintained to perform semantic reasoning, to suppress the influence of edges associated with backdoor triggers. By enabling semantic interpretation of both graph patterns and client behaviors, the framework adaptively incorporates rule-based signals into message passing and client aggregation for defense. Experiments demonstrate that FedLSG significantly improves resistance to backdoor attacks without compromising graph integrity.

Several edge computing platforms, such as autonomous vehicles and smart sensing devices, need to adapt to dynamic environments in real time by learning from new data in the field. Continual learning has emerged as a promising solution for edge training, by incorporating techniques that successfully combine a highly summarized version of previously trained data (to avoid catastrophic forgetting) with recently sensed data. However, as is the case with other ML algorithms, continual learning generates significant data movement between general-purpose CPUs/GPUs and memory, impacting the suitability of continual learning for edge platforms. In-memory computing (IMC; also known as processing-using-memory) can curtail this waste and make continual learning feasible at the edge, but it faces two unique challenges: (1) IMC architectures make use of noisy computation operations that significantly harm training accuracy; and (2) IMC architectures have poor and often incomplete support for resource-efficient training. To address these challenges, we propose CLASP (the Continual Learning Acceleration System Platform), which to our knowledge is the first end-to-end system with IMC acceleration for continual learning. The hardware and software of CLASP are co-designed to support a wide range of continual learning algorithms, through software-visible assembly-level instructions that can be incorporated without constraints into ML-based algorithms. CLASP is designed around a back-end-of-line (BEOL) compatible ECRAM device that we fabricate, which can overcome the challenges of IMC-based training using other emerging memory devices. We show that CLASP with ECRAM approaches the accuracy of in-GPU training, while delivering a speedup of 67x and energy savings of 132x for learning without forgetting and experience replay using MNIST.

Time-series foundation models can forecast across heterogeneous domains without task-specific training, but their forecasts are fixed once produced and cannot directly incorporate task-specific expert feedback. We study expert-guided forecast editing: a frozen foundation model generates candidate future trajectories, and an expensive expert evaluator scores them to guide forecast revision. Under a tight query budget, two natural strategies sit at opposite ends: best-of-$N$ purely exploits the foundation model's predictive distribution, while optimization approaches mostly explore the forecast horizon as an unstructured high-dimensional vector. Each extreme is individually sub-optimal. We introduce DEFT, an expert-guided forecast editing framework that balances the two by first exploiting the foundation model's predictive samples in a decomposed trend–seasonal space, then exploring around them via component-wise refinement. DEFT queries the expert only on complete trajectories, then reuses scores for the trend and seasonal components that appeared in the queried recombinations. This lets each expert query provide structured component-level feedback while keeping the foundation model frozen. We compare DEFT against direct search approaches, including best-of-$N$, cross-entropy methods, and Bayesian optimization, under matched expert-query budgets. Across two forecasting benchmarks consisting of 78 datasets, three time-series foundation models, four feedback types, and seven query budgets, DEFT consistently improves the effectiveness of expert guidance. A molecular-dynamics case study further suggests that the same principle extends to more physically grounded feedback, supporting the hypothesis that sparse test-time guidance should be spent balancing prior exploitation with structured exploration.

Neural solvers are built to deduce, branch, and revise intermediate states. The Lattice Deduction Transformer (LDT) appears to do exactly that. In clue-rich Sudoku, it does not: one forward pass commits essentially the entire grid (every blank cell on standard 6x6, 94-96% on augmented 9x9), turning the iterative solver into a one-shot predictor wrapped in an exact verifier. All hard-slice failures are decided before search begins, when the first pass confidently deletes a value required by the true solution. We call this first-pass poisoning. Adding learned branching, MRV, backtracking, value exclusion, and shared nogoods (CoLT) does not change which Sudoku instances are solved; it cuts repeated invalid derivations 1,497-fold. At the frozen training budget, constraint-graph attention alone matches full-CoLT accuracy, while positional tables recover only under substantially longer training, indicating an optimization and sample-efficiency advantage rather than an absolute capacity difference. The diagnosis predicts two effective interventions. Digit-permutation augmentation raises 9x9 accuracy from below 1% to 96.5 +/- 0.3 across three training seeds on a symmetry-disjoint split. Test-time union over symmetry-transformed passes raises all three hard-slice checkpoints from 72.8-78.9% to 100% without retraining. On from-scratch graph coloring, one-shot behavior disappears and search changes accuracy. In clue-rich completion, LDT-like systems are one-shot amortized predictors rather than learned search procedures: accuracy is determined by calibration and symmetry, while search primarily removes computational waste.

Adaptive optimization workflows in machine learning, federated learning, quantum machine learning, and hybrid classical quantum systems often embed controller logic directly inside task specific training scripts. This coupling limits reuse, reproducibility, safety validation, and fair comparison across execution environments. This paper presents DeepUnfolding Agent, a schema-driven FastAPI platform that exposes deep unfolded adaptive control as an external software service. External executors register a strategy schema, submit round-level diagnostic variables, receive schema-bounded control actions, execute one optimization round, and return feedback for controller update. The framework separates controller intelligence from domain specific execution through a strategy registry, diagnostic to state adapter, controller factory, safety guard, executor abstraction, feedback update path, SQLite persistence layer, Docker deployment, and reproducible benchmark scripts. The implementation supports classical, quantum-aware, hybrid, Qiskit Aer, and optional IBM quantum processing execution pathways. We validate the software through unit, schema, API, safety, orchestration, Quantum execution, checkpointing, and Docker tests, and demonstrate external user fixed versus adaptive workflows across finance, healthcare, genomics, transport, noisy quantum simulation, and hardware backed IBM Quantum execution. The results show that DeepUnfolding-Agent provides a reusable and traceable adaptive control layer for heterogeneous optimization workflows. Our quantum experiments are interpreted as API level quantum control and hardware portability evidence.

Linear probing is the standard instrument for detecting social biases in the hidden representations of large language models. Yet reported probe accuracies come almost exclusively from counterfactual evaluations in which every input carries an explicit demographic marker. Once only a fraction $\alpha$ of inputs carries demographic information, performance degrades sharply, and a weak probe may reflect either an unbiased model or an underpowered detector. We develop a theory that resolves this ambiguity. Modeling representations as two class-conditional clusters with Mahalanobis separation $s$ on a manifold of curvature $\kap$, we prove: (i) a finite-sample generalization bound governed by the manifold's extrinsic radius with a matching $\smash{\sqrt{\dB/n}}$ minimax lower bound; (ii) an exact purity law for the maximum linear-probe AUC, strictly increasing in $\alpha$; (iii) a curvature ceiling: ambient chordal separation on a space form cannot exceed $2/\sqrt{\kap}$; and (iv) a detectability threshold below which no audit can distinguish probe output from chance. Every theorem is validated on synthetic manifolds with known ground truth and on six open-weight models $\times$ four bias dimensions, where the purity law predicts entire AUC–$\alpha$ curves from a single cross-fitted $\hat s$ measured at $\alpha=1$, with no parameters fitted to those curves. The framework turns bias auditing into a power analysis: given a target purity and effect size, it prescribes the sample budget $n(\alpha)$ for a conclusive audit.

Empirical legal scholarship increasingly treats judicial text as data, and much of it still runs on sparse, interpretable pipelines (TF-IDF features and linear classifiers) because the textual feature is often the object of study rather than a means to a prediction. Yet these pipelines inherit preprocessing defaults from mid-century information retrieval that were never validated against classification accuracy. The most entrenched of these is stopword removal. This study introduces an exhaustive single-word ablation that measures a preprocessing step's effect directly against the downstream objective, and applies it to stopword removal. Matching Supreme Court Database labels to Caselaw Access Project opinion texts, the study examines two binary tasks, ideological direction (no-removal baseline F1 about 0.68) and constitutional versus non-constitutional law type (about 0.92), across 7,668 and 7,001 opinions. For each task, the ablation removes each of roughly 18,500 candidate words in turn, and a task-specific stoplist is built from the resulting measurements. Generic stoplists in common use fall below the no-removal baseline on held-out opinions in all twelve tests. The task-specific stoplists move held-out F1 by +0.0023 (95% CI [-0.0124, +0.0170]) on ideology and by +0.0001 ([-0.0082, +0.0085]) on law type. Neither task shows a detectable benefit from removal, and a supplemental analysis finds that word-level statistics predict a word's removal effect poorly, because the words' true removal effects differ by less than the measurement can register. The method generalizes to any inherited preprocessing default, and the result is a caution specific to interpretable legal text-as-data, where a step that reshapes which features a model sees can distort the doctrinal and ideological signal the research is meant to recover. The burden of proof sits with removal.

In the context of differentiated on-demand goods delivery services, this study proposes an integrated optimization method for automated guided vehicles (AGVs) based smart warehouse operations and the last-mile multi-modal transport. A deep reinforcement learning algorithm for multi-objective joint scheduling is designed to establish a dynamic connection between two systems, solving key challenges such as achieving high-throughput continuous order scheduling, meeting competing requirements, and improving the overall system sensitivity and adaptability. For warehouse optimization within this framework, we propose an improved algorithm based on multi-objective, Multi-Reward Machines-A* Guided Deep Q-Network (MORM-AGDQN), which combines service level, system cost, and external transportation demand. For external optimization, we propose an improved algorithm based on a Multi-Reward, Multi Head attention-Heterogeneous Capacity Vehicle Routing Problem (MRMH-HCVRP) framework, which incorporates the optimized scheduling order sequence and grouping, combined with customer location, demand, and priority, vehicle capacity, speed, and service range. The results show that the proposed framework significantly outperforms traditional methods, achieving 100% on-time delivery rate for warehousing operations. After joint optimization, the average delivery time for the last mile was reduced by 29.3% to 53.2%, the total transportation distance was reduced by 46.4%, the high-priority service rate was increased to over 92%, and a balance was maintained between operating costs and customer satisfaction.

Code optimization plays a crucial role in the development of virtual machine compilers, with optimization frameworks significantly enhancing the performance of generated assembly code. However, existing virtual machine compiler outputs frequently exhibit redundant computations, inefficient loop structures, and suboptimal function implementations, which collectively impair execution efficiency. To address these shortcomings, we propose CompileRover, an advanced optimization framework specifically designed for virtual machine compilers. CompileRover employs a sophisticated three-role collaboration mechanism, comprising a referee, an advisor, and an operator, effectively overcoming performance bottlenecks by leveraging comprehensive optimization algorithms and novel methodologies, including control flow analysis, code structure transformations, and dynamic execution pattern recognition. Extensive evaluations demonstrate that CompileRover consistently surpasses state-of-the-art virtual machine compilers, achieving significant improvements in execution performance across various benchmarks. Furthermore, performance analyses validate that the introduced optimizations notably reduce execution overhead, improve dataflow consistency, and robustly enhance compiler performance, showcasing CompileRover as an effective and reliable approach to optimizing virtual machine compilers.

This paper studies instrument classification of solo sheet music. Whereas previous work has focused on instrument recognition in audio data, we instead approach the instrument classification problem using raw sheet music images. Our approach first converts the sheet music image into a sequence of musical "words" based on the bootleg score representation, and then treats the problem as a text classification task. We show that it is possible to significantly improve classifier performance by training a language model on unlabeled data, initializing a classifier with the pretrained language model weights, and then finetuning the classifier on labeled data. In this work, we train AWD-LSTM, GPT-2, and RoBERTa models on solo sheet music images from IMSLP for eight different instruments. We find that GPT-2 and RoBERTa slightly outperform AWD-LSTM, and that pretraining increases classification accuracy for RoBERTa from 34.5% to 42.9%. Furthermore, we propose two data augmentation methods that increase classification accuracy for RoBERTa by an additional 15%.

Recent advances in generative AI have substantially accelerated the creation of high-quality ad creatives, dramatically expanding the number of candidate variants per campaign. This shift increases the need for scalable dynamic creative optimization (DCO) systems that can match creatives to the most relevant audiences under stringent latency and cost constraints. We present PinDCO, a production DCO system for ad creative retrieval and selection on Pinterest, a billion-scale visual discovery platform. PinDCO is built around a Creative Component Fusion Network (CCFN) that performs dynamic creative scoring by modeling each creative component (e.g., image, title, layout) with a dedicated tower, using component-specific hyperparameters to account for differing modeling complexity. The component representations are fused to predict a creative-level score conditioned on the ad-level prediction, and we improve training data quality via an exploration-exploitation strategy. To account for Pinterest's waterfall grid layout, where a creative's rendered size affects nearby content and session-level engagement, we introduce a Pixel-aware Adjustment Module(PAM) that adjusts scores based on creative size to encourage efficient screen real-estate utilization and better whole-page outcomes. To support the large volume of creative candidates, we further employ a lightweight pre-selection model for early pruning, and optimize serving efficiency through caching and dynamic batching. Extensive offline analyses and online A/B experiments demonstrate the effectiveness of PinDCO, yielding a +3.09% lift in ad Click-Through Rate(CTR) with positive whole-page metrics. With the strong performance, we launched PinDCO in the Pinterest Ads platform.

In health and nutrition consulting, widely used prompting methods pass the user profile as an unstructured block without a dedicated analysis step, leaving personalization as a critical structural gap. We introduce PA-CoT (Profile-Adaptive Chain-of-Thought), a multi-stage prompting method that treats profile interpretation as an explicit, standalone reasoning step prior to response generation. To enable systematic evaluation, we introduce the QPA (Question–Profile–Answer) benchmark – 200 nutritional consulting samples with structured user profiles scored on four criteria. In a comparative study against 11 comparison methods (CoT, Few-Shot, Role Prompting, DSPy, TextGrad, Self-Refine, and others, plus a Zero-Shot Baseline; 12 total including PA-CoT), PA-CoT achieves the best average score (4.21 on the G-Eval 1–5 scale) and leads on both Personalization (4.71 vs. 4.39) and Safety (4.68 vs. 4.52) with non-overlapping 95% confidence intervals over the nearest competitor – the only method to simultaneously top both criteria. The results confirm that an explicit profile-analysis step is the key driver of personalization gains over widely used prompting approaches.

Automatic Prompt Optimization (APO) often rewrites prompts monolithically, which can improve one behavior while degrading others. We present SAPO, a segment-level APO method that decomposes prompts into role, context, tasks, and output format, then applies targeted improvements based on top-5 and bottom-5 examples. The optimization loop uses one LLM with static meta-prompts and structured outputs for segmentation, weakness analysis, and candidate generation. We describe a train/validation protocol and a two-stage generation process: (1) segment-level diagnosis and recommendation extraction, (2) candidate synthesis constrained by weak/strong segment signals. Using the evaluation setup across SQuADv2, TweetEval, XSUM, CommonGen, and GSM8K on GPT-3.5-Turbo and GPT-4o-mini, SAPO achieves the best average score against Zero-shot and strong APO baselines including APE, OPRO, EvoPrompt, GEPA, and StraGO.

Independent agents that reason in latent space can share computed state as key-value cache fragments rather than text. Merged by a conflict-free replicated data type, these fragments form a store that converges under any delivery order or duplication. Yet a later query, unknown at encode time, cannot reliably read the merged cache: colocated fragments interfere, so colocation is not addressability. MaSRead addresses the read to content. It routes through opaque keyed tag sets derived from fragment words and decodes each selected fragment under a hard attention mask that hides the rest. Under lexical connectivity, a graph walk reaches the fragments required by a multi-hop query. Across chain, pipeline, symmetric, hub, and natural-language stores, MaSRead recovers visited fragments in isolation, remains effective as unrelated fragments accumulate, and transfers to another model family. After routing, materialized decoding depends on fragment length rather than total store size; end-to-end work still includes store-dependent routing and one read per visited fragment. The limits are explicit: lexical routing can miss disconnected evidence, and answer composition remains bounded by the frozen reader. Thus a replicated latent store becomes selectively readable for later queries when the needed fragments connect to the query through content.

Linear probes detect corrupted context in language models with near-perfect accuracy, yet this does not translate into reliable failure prediction. The result is a dissociation with direct implications for deployment monitoring. Across multi-hop arithmetic chains, probes that detect corruption turn out to be uninformative about final answer correctness; models forced into structured confidence formats collapse to two values with indistinguishable error rates; and probe persistence across hops fails to separate correct from incorrect outcomes, refuting our pre-registered "persistence beats peak" hypothesis. This pattern of knowing but not saying generalises across model families including reasoning models. As a real-time monitor, probe-based interventions are sharply model and error-type dependent: branch-and-pick is net-positive across models and uniquely non-breaking on Llama-3.1-8B (4 rescued, 0 broken), while reprompt and replace-prior break correct traces at roughly the rate they rescue wrong ones. Probe-based monitoring is a necessary complement to verbalised confidence, but no single intervention dominates, and the deployable answer is model-aware, error-type-aware routing.

Refinement operators generate many functions used in wavelet constructions, subdivision schemes, and geometric modeling. Their finite iterates can develop rapidly increasing numbers of linear pieces, making them a natural test case for the expressive power of deep neural networks. Earlier work showed that, for scalar binary refinement with a finitely supported mask, every compactly supported continuous piecewise linear seed has finite refinement iterates that admit exact ReLU realizations of fixed width and depth growing linearly with the number of refinement steps. The present paper gives a new construction of this known theorem. The difficulty is that the refinement cascade is driven by discontinuous binary digit choices, whereas ReLU networks produce continuous piecewise linear maps. We represent the residual dynamics on a polygonal model of the circle and describe each residual position in two overlapping coordinate systems, one ordinary and one shifted by one half. Their discontinuities occur at different points. The network switches between the two descriptions only where both are valid and the corresponding fixed linear cascade updates agree, so the switch is exact and requires no multiplication by a variable selector. The construction also gives exact readout of every continuous piecewise linear circle function satisfying the natural endpoint compatibility condition. Localized seeds are handled by a two-pass network, and translation covariance, finite decomposition, and gluing extend the result to arbitrary compactly supported continuous piecewise linear seeds in a preserved support window.