Papers

Audience sizing is a critical component of digital marketing. It enables precise resource allocation, campaign planning, and performance optimization. Traditional approaches using skeleton audiences, sampling, or predictive modeling suffer from significant delays, estimation errors, and poor scalability over high-dimensional profile data. We present REALMS (Real-time Exact Audience sizing via LLM-based Multi-attribute Search), a conversational system for exact audience sizing deployed in production on an enterprise customer data platform. REALMS enables marketers to query massive profile stores with millions of profiles and thousands of attributes using natural language and receive precise counts in seconds. The system introduces three key components: (1) a categorical attribute retrieval mechanism using embedding-based vector search to dynamically identify relevant schema attributes without manual configuration; (2) an LLM-powered NL2SQL pipeline with template-based in-context learning for accurate query generation over complex nested schemas; and (3) schema standardization enabling industry-agnostic deployment across diverse enterprise environments. Evaluation on real enterprise data demonstrates strong recall for attribute retrieval, high SQL execution accuracy, and low latency, which enables real-time interactive audience insights where prior methods required hours.

In this paper, we establish the first asymptotic convergence guarantees for the Muon algorithm through a more accurate proxy for the Newton-Schultz iteration than the typical matrix sign function. We prove that, for appropriate choices of hyperparameters, the iterates satisfy $\lim_{k\to\infty}\|\nabla f(x_k)\|=0$, and, under a global Polyak-Łojasiewicz condition, that the sequence of function values converges linearly. The key insight is that the regularization, implicit in Muon's Newton-Schulz implementation, induces a bounded preconditioner, exposing Muon as a preconditioned Polyak heavy-ball method and enabling a classical Lyapunov analysis. This observation naturally motivates applying the same preconditioning structure to the Nesterov gradient evaluation. We formalize this idea by introducing Muesterov, a Nesterov-based variant of Muon, and prove that it enjoys the same convergence guarantees, extending the theoretical framework beyond the heavy-ball setting. Numerical experiments on a scalar cross-entropy problem corroborate the theory and illuminate the joint role of the learning rate and the Newton-Schulz regularizer in controlling convergence. Preliminary numerical simulations training the nanoGPT dataset provide intuition regarding the relevance of the observations in this paper to practical applications.

As robots transition from structured factory settings into homes, they are required to interact with an ever-increasing variety of objects. Many tasks require grasping, and often it is not sufficient to just pick up the target object. Consider a task like "pouring coffee" — to facilitate the subsequent pouring, the robot should grasp the mug by its handle. Existing learning-based approaches for grasping either find robust and collision-free grasps that are largely agnostic to the task (e.g., picking up the mug by its rim), or leverage foundation models to propose task-appropriate grasp locations that lack fine-grained physical grounding (e.g., reaching for and missing the handle). In this work, we bridge these approaches with a real-to-sim-to-real framework. Based on a single RGB-D observation, we construct a digital twin of the environment, query a large foundation model to propose grasps that align with the object's affordances and task description, and then optimize the proposals to ensure robustness and plausibility before executing the result on the real robot. Our key insight is that the grasp proposals of the foundation model should be regarded as semantic priors that serve as seeds for local, gradient-free optimization. We leverage Bayesian optimization with Thompson sampling to draw batches of nearby poses, which are subsequently evaluated in parallel under domain-randomized physics rollouts. The resulting grasp is both task-oriented and physically feasible for execution by the robot arm. Our full zero-shot real-world transfer only takes a few minutes and improves task-oriented grasping success by up to 33% as compared to other state-of-the-art pipelines. Our code is available here: https://github.com/VT-Collab/GraspTwin/

De novo peptide sequencing from tandem mass spectra is essential for identifying peptides without relying on reference databases. Despite advances in deep learning, accurate sequencing remains challenging because experimental spectra are often sparse, noisy, and incomplete, leaving informative b- and y-ion fragments unobserved. Existing methods attempt to recover this missing evidence via latent-space imputation before autoregressive decoding. However, they typically treat imputation as a fixed reconstruction task, without considering which missing fragments are most relevant to decoder errors. Moreover, existing peak representations do not explicitly model mass differences between peaks, despite their fundamental importance. We introduce GyroNovo, a framework with two main contributions. First, we use decoder errors observed during training to adapt the imputation objective, prioritizing fragments associated with frequent decoding errors. We further use the decoder error distribution to construct easy and hard augmented views of each spectrum, enabling the decoder to learn under varying degrees of spectral corruption and missing-fragment severity. Second, we introduce a mass-aware inductive bias into self-attention by using rotary embeddings to encode pairwise mass differences between spectral peaks. Together, these components align missing-fragment recovery with decoder behavior while explicitly incorporating the mass relationships that underlie peptide fragmentation. At inference time, GyroNovo retains a standard encoder-imputer-decoder architecture and requires neither additional inputs nor auxiliary search procedures. Experiments on NovoBench show gains of about 9 percentage points in peptide-level precision and 7 percentage points in amino-acid-level precision over the state-of-the-art baseline. Code: https://github.com/UBC-NLP/gyronovo.

Optimizing embedding systems for production recommendation pipelines demands systematic exploration that consumes disproportionate engineering effort at scale. We apply Andrej Karpathy's AutoResearch paradigm – a large language model that iteratively edits a training script and retains modifications that improve a held-out scalar metric – to automate this exploration. We report on twelve weeks of running this paradigm at production scale, where iterations consume hours of multi-GPU compute, evaluation involves competing criteria, and campaigns span weeks across many training jobs. Across two independently developed representation-learning systems for a book recommendation pipeline, we ran 220+ experiments and observed five recurring failure modes absent from the original setting: infrastructure fragility, agent memory decay, search-direction stagnation, iteration-cost asymmetry, and metric fixation. We contribute a three-principle scaffolding design – prevent, persist, redirect – that maps each failure mode to a structural remedy and whose instantiation scales with iteration cost. The framework produced a 1.82x Recall@6 lift and a 2.1x coherence lift over hand-tuned baselines, and the agent autonomously designed a text-only fallback that expanded catalog coverage by 5.8x. The two systems span nearly three orders of magnitude in per-iteration cost yet exhibit the same failure modes, suggesting these are structural properties of production-scale autonomous research rather than artifacts of either application.

Text-to-music systems are assessed on audio quality and on how faithfully the music follows its prompt, and the CLAP score, the cosine similarity between a music-text model's audio and text embeddings, is the standard objective metric of faithfulness. We ask how accurately that score reflects the text: when an attribute is linked to an instrument (e.g., distorted guitar), does the text embedding capture that binding? To find out, we introduce an attribute swap perturbation: the caption of a real recording is edited by exchanging exactly one property, timbre, lead versus accompaniment, or order of first appearance, between two instruments. We then test four contrastive music-text models and one large audio-language model on whether the audio scores higher against the original caption than against the perturbed one. No contrastive model distinguishes the two captions reliably. The audio-language model does better, but further experiments show that its advantage rests largely on audio-agnostic language priors. Our results thus provide compelling evidence that the CLAP score and related metrics do not capture fine-grained musical meaning or attribute bindings; their representation is closer to a bag-of-words that leaves them insensitive to meaning-changing perturbations of the caption.

Split Gibbs sampling enables diffusion posterior inference for general nonlinear inverse problems by decoupling prior and likelihood computations, allowing a pretrained diffusion prior to be reused across measurement models. However, its likelihood update often relies on iterative MCMC, which can hinder parallelization, require algorithm-specific tuning, and incur substantial computational cost. In this work, we propose a learning-based framework to replace this MCMC step by reformulating both Gibbs updates as Gaussian denoising problems and implementing them through ODE diffusion. The prior step reuses a pretrained denoiser, while the likelihood denoiser exploits known likelihood structure through a lightweight deep-unfolded network. Experiments on nonlinear phase retrieval demonstrate the effectiveness of the proposed method as an alternative to MCMC-based split Gibbs at lower likelihood-update cost.

SRAM-based FPGA system-on-chip devices are vulnerable to single-event upsets (SEUs) in configuration memory, which may perturb programmable routing resources and degrade communication fabrics. In modern Zynq UltraScale+ MPSoCs, such routing disturbances can introduce small propagation delay shifts that remain logically transparent yet compromise AXI-based data transfers and lead to silent data corruption. Although routing delay degradation and AXI interconnect failures have been studied independently, their experimental correlation under neutron irradiation has not been established. This work presents a cross-layer investigation on a ZCU104 platform integrating routing-dominated delay sensors with an AXI interconnect benchmark comprising replicated accelerators. Neutron irradiation experiments were conducted on the fully operational system, while a frame-level configuration fault injector implemented via the internal configuration access port enables controlled upset emulation. Measured routing delay events are statistically correlated with communication failures, and cross-sections for both timing shifts and AXI malfunctions are derived. The results experimentally demonstrate how neutron-induced routing perturbations propagate into system-level silent data corruption in UltraScale+ MPSoCs, providing insight for resilience-oriented AXI-based design in neutron-rich environments.

Children in multilingual communities often code-switch, using multiple languages in a single utterance. Can we induce cross-lingual alignment in language models by training on code-switched text? We pretrain small decoder-only transformers on two 100M-word multilingual corpora: a base corpus formed by mixing the English, Dutch, and Chinese BabyBabelLM datasets, and a corpus generated from it by inserting word- and sentence-level code-switching using an LLM. We find that training on code-switched data aligns the representations of parallel text, particularly across different scripts, and that this alignment persists through training on monolingual documents. Under a learning curriculum that progresses from word-level code-switching, to sentence-level code-switching, to monolingual documents, models trained on code-switched data outperform baselines trained without it on the BabyLM evaluation suite. Our work characterizes code-switching curriculum learning as an effective data augmentation method for multilingual pretraining. We release our code, data, and models at https://github.com/drooryck/multilingual-macaroni.

Configuration-induced perturbations in SRAM-based FPGAs may activate dormant programmable routing branches and increase path delay without immediately producing a functional error. Although prior studies have separately investigated the electrical origin of these delay changes, their in-situ detection, and the topology of commercial routing fabrics, a scalable method for predicting their timing impact at the granularity of programmable interconnect points and routed nets remains unavailable. This paper presents GRACIDIT, a graph-circuit digital twin framework for predicting configuration-induced routing delay degradation in Zynq UltraScale+ FPGAs. The proposed framework extracts the routing-resource graph of the XCZU7EV programmable fabric from the vendor design database, identifies inactive programmable interconnect points adjacent to active routes, and represents each candidate perturbation through its branch topology, geometric span, fan-out, physical region, and downstream loading. These graph features are combined with a calibrated reduced-order electrical model to estimate the delay introduced by single and cumulative routing-branch activations. Controlled configuration-equivalent perturbations are generated on a ZCU104 platform and characterized using complementary routing-domain oscillators and phase-sweep probes. The resulting model associates predicted delay shifts with available timing slack to rank vulnerable programmable interconnect points and routed nets and to construct a spatial vulnerability atlas of the programmable fabric. Experimental evaluation demonstrates a mean absolute prediction error of 7.8 ps, achieves 87.4 percent recall for slack-violating perturbations, and attains a Recall at 10 value of 0.90 for the most vulnerable routing resources.

We propose ST-pRRTC, a GPU-parallel space- time RRT-Connect motion planner for problems with known obstacle trajectories and unspecified arrival time. Searching over many arrival times broadens temporal coverage but divides a finite planning budget among more backward trees. To address the challenge, ST-pRRTC builds a shared forward tree and an adaptive forest of backward goal-time trees. Its interval root formulation samples goal arrival times continuously and guarantees probabilistic completeness and asymptotic arrival- time optimality under the stated assumptions in a bounded time domain. The practical root recycling policy has no such guar- antees. It adapts a fixed number of backward trees, replacing later roots while retaining useful search progress. Experiments on three dynamic benchmarks show that both variants achieve lower mean first-solution times and earlier mean final arrivals than ST-RRT* and SI-RRT on problems solved by all compared methods. Further experiments demonstrate the benefit of recy- cling over broad arrival-time ranges. Real-robot demonstrations show root-recycling ST-pRRTC planning motions for a UR5e among moving Crazyflie quadrotors.

Today's Quantum Processing Units (QPUs) are too small and too noisy to solve large combinatorial optimization problems directly, so practical hybrid solvers split a problem into pieces and iterate a decompose-solve-aggregate loop over whatever backends are available: classical heuristics, simulators, emulators, or a QPU. In practice, the loop is a driver script. It sits on top of the quantum-HPC middleware, handling task generation, provenance, recovery, and portability. Instead, we treat the loop as a scientific workflow and ask what a workflow layer adds to a generic workflow management system and QPU-sharing middleware. Two decomposition patterns from real applications, iterative consensus (ADMM) and hierarchical partitioning, turn out to stress the orchestration layer very differently: over 120 managed runs, orchestration took 78.4% of end-to-end time for the iterative pattern, almost all of it in a per-round barrier, but only 6.2% for the hierarchical one. Our workflow model adds four things a generic engine does not have: a termination predicate residing in the task graph that reads the previous round's residuals, subproblem-level recovery with warm-start and quorum-deferred aggregation, failover from a QPU to a classical replica within a round, and a provenance schema that describes CPUs, simulators and QPUs with the same fields, including the shot budget included. We report the cost of each layer on our engine, show that speculative re-execution enable runs to complete under injected failures that stall an unmanaged driver. We also use the same provenance to give per-device latency tails across simulators, emulators and IQM QPUs.

We demonstrate a jumping robot that reaches high (7.6 m) and fast (190 ms stance time) jumps from a single long leg driven by a direct-drive transmission, without elastic energy storage. At 281 g, it achieves the highest jump yet reported for an electrically actuated, spring-free system. The leg uses a new fabric-wrap transmission that provides a variable mechanical advantage, keeping a small electric motor near its peak power output through the stroke while bracing the long, lightweight leg against buckling. A balancing module at the top of the leg uses small propellers to control the leg's orientation on the ground and in the air, where the long leg provides a large moment arm for the control torques. The robot is validated outdoors with vertical jumps, attitude control on the ground and in flight, and tilted jumps.

Large language model (LLM)-powered multi-robot systems are vulnerable to semantic manipulation: an accepted false world-state claim can trigger a fleet-wide behavioral cascade, causing unnecessary replanning, increased path costs, congestion, or apparent mission infeasibility. Conditioning on a successful manipulation, we propose an active verification framework that contains its downstream effects before they propagate across the fleet. A dedicated verification module generates a structured Verify-Adapt-Hold plan: selected robots inspect consequential regions, a limited subset provisionally adapts when necessary, and the remaining robots retain their trusted plans. We evaluate the framework in a multi-robot transportation environment using injected false obstacle claims across different impacts and team sizes. Evaluation measures cascade containment, Sum-of-Costs, makespan, and coverage ratio. Results show that treating post-compromise verification as a team-level planning problem, rather than a binary trust decision, effectively limits the cascading physical consequences of semantic manipulation.

Aerial manipulation in outdoor environments remains challenging due to the simultaneous requirements of reliable state estimation, stable aerial motion, and precise manipulation under external disturbances. In this work, we present a real-world outdoor aerial manipulation framework that integrates imitation learning, onboard LiDAR-inertial state estimation, and whole-body model predictive control. A Diffusion Policy is trained from manipulation demonstrations to generate desired end-effector motions from onboard observations. These learned commands are executed by a whole-body MPC that jointly coordinates the aerial platform and manipulator to realize the desired end-effector trajectory. To eliminate reliance on external motion-capture infrastructure, the platform employs onboard LiDAR-inertial odometry for state estimation during outdoor operation. We validate the complete framework on a physical aerial manipulator and demonstrate successful execution of outdoor manipulation tasks. The experimental results show that demonstration-driven manipulation policies can be effectively integrated with onboard state estimation and model-based whole-body control to enable aerial manipulation beyond controlled indoor environments.

Recent progress in speech-driven 3D facial animation has improved vertex-level reconstruction quality, but speech-consistent visible articulation remains difficult. This is because speech production follows structured and constrained articulators' coordination and the mapping from acoustics to motion is inherently one-to-many. Motivated by the structured patterns of visible articulation, we propose a novel articulation-aware framework that models visible speech through directional articulatory motions and composes them into surface-consistent 3D facial motion. To represent visible articulation with three directional articulatory motions, spreading, opening, and protrusion, we propose a Speech–Articulatory Memory (SAM) that captures the correspondence between speech and these motions under phonetic context through retrieval and decoding based on a key-value memory structure. Then, a Topology-aware Articulatory Composition (TAC) integrates the predicted directional articulatory motions under mesh topology to produce surface-consistent 3D facial motion. Experiments on VOCASET and TFHP show that our method achieves state-of-the-art performance on standard reconstruction metrics and improves visible articulatory distance and velocity errors for lip articulation, while a user study confirms clear preference in lip sync and realism.

Voice agents are increasingly deployed in workflows where failed interactions can affect transactions, access, and other consequential outcomes, creating a need for reproducible and interpretable evaluation. We introduce Inquesto Score (IS), a protocol for measuring voice-agent reliability as the percentage of calls in a fixed, versioned evaluation population that achieve the caller's goal without a functional failure or worse. Rather than combining heterogeneous metrics, IS defines explicit failure events and severity levels and evaluates the deployed voice pipeline. Timing failures, including talk-over and delayed responses, are measured directly from audio, while semantic and state-dependent failures are evaluated using scenario predicates, tool traces, and a pinned open-model judge. Diagnostic views of behavior, acoustic robustness, identity handling, and speaker groups accompany the score without being combined into it. Inquesto Score v0.1 evaluates 30 scenarios, three acoustic conditions, four speaker groups, and 306 calls per agent across 13 configurations of a reference voice-agent system. Our evaluation shows that reliable measurement requires evidence beyond transcripts, explicit treatment of deployment conditions, and validation of the evaluators used to determine outcomes. We release the protocol, reference implementation, and evaluation records.

Wireless local area network (WLAN) performance is jointly shaped by medium contention, propagation, Wi-Fi configuration, and transport-layer behavior. This study evaluates IEEE 802.11g and IEEE 802.11ax in a single-access-point uplink topology, comparing UDP and TCP under Friis, LogDistance, and cascaded Friis-Nakagami propagation models. The factorial design spans 5 to 50 stations, six access-point distances from 5 m to 50 m, and three random seeds. Of 1,080 scheduled executions, 1,073 produced valid CSV outputs; seven runs terminated with internal ns-3 and cppyy segmentation errors and were excluded. Across the global scenario summaries, TCP FlowMonitor packet delivery ratios (PDRs) range from 0.994 to 0.997, whereas UDP PDRs range from 0.298 to 0.731. The highest mean aggregate throughput is 2.619 Mb/s for TCP under the configured IEEE 802.11ax mode with Friis propagation; UDP reaches 25.854 Mb/s in the same topology. These results show that packet delivery ratio, throughput, delay, and fairness must be considered together. FlowMonitor metrics are IP-flow observations, so the study does not establish application-level delivery or isolate optional IEEE 802.11ax multi-user mechanisms.

Slashing is commonly argued to secure proof-of-stake blockchains by confiscating the stake of misbehaving validators. The usual justification is that, without slashing, validators can solicit an equivocation attack by signing conflicting blocks: if enough others join, the attack succeeds; otherwise, the attempt incurs no loss. Slashing is intended to make such attempts costly and thereby guarantee the security of applications whose economic value is comparable to the bonded stake. This rationale, however, rests on heuristic arguments rather than a formal game-theoretic guarantee. We challenge this rationale by constructing a risk-free coordination protocol for rational validators under algorithmic slashing. We show that the prescribed strategy profile, in which rational validators solicit other validators to equivocate, constitutes an ex post Nash equilibrium, even when validators do not know in advance how many others will participate. The equilibrium holds for any gain $\epsilon>0$ from successful equivocation, however small relative to the bonded stake. Thus, slashing alone does not guarantee economic security proportional to the value of bonded stake. Our results expose a fundamental limitation of algorithmic slashing. Whereas conventional collateral arrangements in many real-world scenarios can rely on external enforcement, for example through courts, algorithmic slashing depends on the same consensus process that the attackers control. These findings call for a formal analysis of slashing's security, rather than overly simplistic arguments drawn from financial systems with independent enforcement.

The aim of this work is to examine the connectomes of Caenorhabditis elegans through a computational lens using the reservoir computing framework. Connectomes are mappings of biological neural networks; C. elegans is the first organism for which physical connectomes covering the whole nervous system have been published. The connectomes of C. elegans used in this paper have been derived at different ages of the organism and are based on three different ways of measuring inter-cellular connections. They have, with minimal preprocessing, been implemented as reservoirs in the form of echo state networks, which are recurrent neural networks. In reservoir computing, the reservoir itself is not trained, rather the output of the reservoir is passed to a comparatively small read-out module in which training takes place. Training and testing is conducted in different neuro-inspired tasks, with the aim of using these tasks as a benchmark for the connectomes. This process has been repeated with different configurations of the reservoir and equally sized but randomized null models have been used for comparison. The results show that the biological wiring and a bio-informed configuration of input and output nodes of the reservoirs do not necessarily lead to better performance. Contrarily, the randomized null models are often outperforming the original connectomes on the chosen benchmarks. At the same time it becomes clear that the results depend a lot on the configuration of the reservoir and the way the connectome has been derived from the organism. Connectomes from different ages may produce varying outcome, without a clear trend becoming visible.

We address an incipient type of data-based faults, driven by increasing amounts of data reuse in AI-enhanced computational science workflows. A dataset is created under specific conditions; its categories, measures, and labels depend on that context, but that context is usually unavailable to downstream users and is completely abandoned when datasets are used to train models. We propose the encoding and association of this context, called domain bounds, with the data to which it applies. By specifying the conditions for valid reuse, a domain bound flags apparently valid data from being reused in an incompatible context, even when every value falls within its expected range. We present cases from computational science and biomedicine where missing domain bounds allow silent reuse errors, and show why description and provenance approaches do not detect them. Our detector uses standard data container technologies, catches faults drawn from a taxonomy of published cases, irrespective of dataset size. Against injected faults it caught 17 of 18 domain-bound reuses that lineage and descriptive records accepted.

Humanoid hands require tactile feedback across the whole finger, not just the fingertip, to grasp and manipulate objects properly. Vision and proprioception alone cannot reliably provide this information, particularly when the hand's own fingers occlude the camera's view of the grasp. We present a low-cost tactile array for a humanoid finger, made from Velostat and conductive tape. The fingertip carries seven contact points including a 2x3 matrix wrapped across its front, left, and right faces, and a separate contact point at the tip. The proximal and middle phalanges each carry a single front-facing contact line. We measure the sensor's hysteresis and recovery time after release, through repeated loading and press-release tests. We also test a compliant, 3D-printed contact structure with a gap and a bump, inspired by similar designs in prior work, and show it cuts recovery time by 74% compared to a flush-contact baseline. We then show the sensor can produce distinct activation patterns for different contact geometries (flat, edge, corner) at the fingertip, and that it registers contact across all three phalanges during a grip. Finally, we discuss the limits of our fabrication changes and point to software-based compensation as a promising way to more directly fix the remaining hysteresis in the future.

The evidence behind a scientific or operational decision is often held by hospitals, banks, or registries that cannot pool individual observations. Cross-silo federated learning moves computation to the data and exchanges agreed summaries. Targeted maximum likelihood estimation (TMLE) refines a flexible initial fit, yielding plug-in estimators that respect the model and support efficient inference. TMLE itself, however, has remained a fully centralized procedure. To fill this gap, our paper introduces the first federated TMLE algorithm. We federate targeting itself, for an arbitrary target, loss, and fluctuation family, through two complementary frameworks. FedTMLE-G aggregates local gradients and reproduces centralized targeting step for step. FedTMLE-L lets each institution complete its own fluctuation fit before a single exchange of fitted updates, trading synchronized fidelity for local autonomy. For gradient aggregation, we develop a finite-precision protocol that transmits changes rather than values and certifies targeting accuracy within explicit bounds on exchanges and bits. A description-length analysis of the accepted updates then shows that this finite communication leaves numerical targeting error negligible against sampling uncertainty. The cost of computing an estimator is thus distinct from the complexity of selecting it. Our analysis also indicates that keeping data local is not itself a privacy guarantee of TMLE, since instability of full-record reconstruction need not prevent recovery of a specified sensitive attribute. For a personalized version of local averaging, institutions retain their own estimates and leave once local targeting is complete. A nonconvex convergence bound charges the improvement forfeited through averaging to disagreement among local fits and exposes a tradeoff between equal institutional influence and the sampling variability of small silos.

Although bilevel optimization (BLO) has emerged as a powerful framework for addressing many complex and nested machine learning problems in recent years, most existing studies are confined to the lower-level strongly convex (LLSC) or lower-level generally convex (LLGC) settings (i.e., the lower-level objective function is assumed to be, at least, convex). While the LLSC/LLGC assumptions render more tractable algorithmic design and theoretical analysis, they are too rigid to encompass many machine learning problems in practice. The limitations of LLSC/LLGC assumptions in BLO motivate us to investigate solving the BLO problem in the general lower-level nonconvex (LLNC) settings, which remains in its infancy. In the literature on LLNC-BLO, most of the existing works either require additional structures in the lower-level objective function for tractable theoretical analysis, or adopt the first-order stationarity reformulation as a lower-level surrogate problem, which is inherited from the LLSC/LLGC settings but could lose their effectiveness in the LLNC setting. To bridge this gap, we propose to reformulate the nonconvex lower-level problem using a second-order stationarity-based surrogate, the solution of which guarantees a local optimal solution at the lower level. Based on this reformulation, we propose the PROBE (Perturbed gradient algorithm for bilevel problem) and show that it overcomes the limitations of prior works by probing and escaping lower-level saddle points. We prove that PROBE achieves a finite-time convergence rate of $O(T^{-2/5})$, where T denotes iterations. To our knowledge, this work is the first to establish the finite-time convergence for achieving lower-level second-order stationary solutions in general LLNC-BLO. Our experiments on both a large language model-based data curation task and a meta-learning task also show that PROBE outperforms SOTA methods.

Can causal softmax attention implement policy mirror descent as a repeated controller rather than a one-step algebraic identity? Negative-entropy policy mirror descent (PMD) has the statewise update $\operatorname{PMD}_\eta(\pi,Q)=\operatorname{softmax}(\log\pi+\eta Q)$. Building on the known Q-TD-PMD recursion, we construct one fixed causal-softmax actor–environment–one-step-critic protocol with explicit actor, routing, sampling, and normalization residuals, and propagate them to the policy actually returned. The construction states the finite-logit/full-support domain, the external tokenization and sampling boundary, and the mean-zero LayerNorm carrier conditions required by the normalized compilation. Separately trained pre-LN Transformers recover the target computation empirically. A frozen one-step audit model is closest to PMD among the tested fixed rules; in a preregistered five-run $S=4$ repeated-control test, the learned actor with an exact one-step critic reaches median returned-policy loss $1.052\times$ the Exact PMD oracle and retains the criterion across four no-retraining shifts. The same checkpoints with their learned critic give descriptive median $1.050\times$ the oracle (no registered margin). At $S=8$, replacing the exact critic by the learned critic raises median $T=20$ loss to $0.0225$ yet leaves the Liang–Lai and Algorithm Distillation adaptations $20.2$–$24.2\times$ higher-loss; this is a one-sided sampled-critic bound because PolicyAttention consumes 144 generative transitions per round versus 20 on-policy transitions for the adaptations. The strict 20-transition comparison remains open. At $S=8,16$, the exact-critic common-harness comparison remains $17.7$–$28.2\times$ lower-loss than those adaptations, with the information asymmetry stated locally.

Uniform noise-moment bounds exclude stochastic gradients whose variability increases with the iterate. We study ordinary, single-sample stochastic gradient descent for smooth, lower-bounded, possibly nonconvex objectives under distance-dependent conditional moments. Under second moments alone, a direct descent–displacement argument yields $T^{-1/3}$ expected average squared-gradient stationarity with a horizon-dependent stepsize. An explicit oracle-complexity corollary matches the known smooth Blum–Gladyshev (BG-0) lower bound, including the $Lb_2\Delta^3\varepsilon^{-6}$ and $L\Delta\sigma^2\varepsilon^{-4}$ stochastic terms, where $\Delta$ is the initial objective gap and $\sigma^2+b_2\|x-x_1\|^2$ bounds the variance. Thus unchanged SGD attains the minimax stochastic complexity in this second-moment class. For $p>2$, predictable localization and a Hilbert-space Fuk–Nagaev inequality yield a high-probability bound separating logarithmic variance and polynomial rare-shock contributions. The localization radius is derived from the recursion: no bounded-iterate assumption, clipping, normalization, momentum, or increasing batch size is needed. We also give increasing-confidence rates, an objective-gap-growth refinement recovering root-$T$ stationarity, and stochastic $L^p$-Lipschitz examples. The broad BG-0 optimality statement is distinguished from the smaller mean-square-smooth class, in which additional oracle structure permits faster algorithms.

Sequential inference estimates latent states from noisy and incomplete observations. Particle Filters (PFs), a class of Monte Carlo methods based on importance sampling, provide a flexible framework for this task, but often suffer from poor sample efficiency and unfavorable scaling with dimension, partly due to suboptimal proposal distributions. We address these challenges by integrating learned proposals into the PF framework. We introduce Neural Optimal Particle Filters (NOPFs), which learn an amortized approximation to the optimal proposal from offline simulated one-step conditioning tuples. The learned proposal is used as a drop-in replacement in standard PF updates, with samples corrected by standard importance weights so that the method asymptotically targets the same filtering distribution under standard support and density-evaluation assumptions. Across stochastic nonlinear benchmarks of varying inference complexity, NOPFs improve sample efficiency and distributional accuracy over standard PF baselines with modest computational overhead. The approach integrates data-driven proposal learning into classical inference without altering the underlying filtering objective.

As modern data analytics workloads become increasingly heterogeneous and hardware-intensive, achieving efficient multi-core performance across diverse applications remains an open challenge. We present Reffine, a compiler-based in-memory analytics engine that delivers high performance across a broad range of data analytics workloads. Reffine introduces a novel intermediate representation (IR), grounded in relational algebra and sparse iteration theory, that provides a unified abstraction for data and computation. This representation enables workload-agnostic, end-to-end optimizations such as operator fusion and automatic parallelization across diverse analytics applications. We further develop a sparse compiler backend that translates Reffine IR into hardware-efficient imperative code, achieving high multi-core performance without domain-specific implementations. On the TPC-H benchmark, Reffine outperforms the in-memory analytical database DuckDB by up to $24.9\times$ and the state-of-the-art compilation-based database Umbra by up to $3.2\times$. Reffine also achieves average speedups of $18.3\times$ and $47.9\times$ over Polars and NetworkX on streaming and graph analytics workloads, respectively. Source code: https://github.com/ampersand-projects/reffine

Autonomous navigation in previously unseen environments requires effective perception, persistent environmental representation, and collision avoidance while maintaining progress toward a goal. Existing perception-based methods often rely on prior maps or short-horizon observations, limiting their ability to exploit previously observed structure. We propose a memory-aware multi-sensor navigation framework that integrates LiDAR and RGB perception, online distance-field representation learning, and a stage-adaptive Modulated Control Barrier Function Quadratic Program (MCBF-QP). The framework persistently represents static infrastructure while tracking dynamic obstacles, enabling the MCBF-QP controller to exploit previously observed geometry for obstacle circumvention and adapt its safety constraints and guidance to local conditions. Experiments in complex indoor and outdoor environments demonstrate improved navigation efficiency and goal-reaching performance while maintaining collision avoidance in narrow passages and around dynamic obstacles.

Navigable graphs for nearest-neighbor search are built either incrementally, each inserted point searching a graph that mutates as construction proceeds, or in batch over a fixed substrate, which buys determinism and parallelism at a price in build time. We measure that price and find where it comes from. Instrumenting a tuned Vamana and PiPNN and building every system repeatedly in a paired design on one 64-thread machine, we separate build time into work (distance evaluations) and cost per evaluation. Letting the batch builder's substrate mutate in $B$ synchronous blocks recovers the feedback loop of incremental construction while the graph stays a function of (data, seed, parameters, $B$): eight trees with batched feedback match thirty-two frozen trees, and the build does $0.88\times$ Vamana's distance work. Yet it takes $1.55\times$ Vamana's wall-clock, because the mutating substrate costs more per evaluation. Pushing further, we find a wall that no search-based builder crosses. Every one of them, incremental or batched, evaluates distances adaptively, one dependent random access at a time, and runs $20$-$27\times$ below a dense kernel on the same machine at $d \approx 100$, five to six times of it with the data resident in cache. The gap is not a low-dimension artifact: an adaptive evaluation costs $d^{1.04}$ and a blocked one $d^{0.63}$, so the wall grows as $d^{0.4}$ and is twice as high at $d = 960$ as at $d = 128$. PiPNN's order-of-magnitude build advantage is that kernel: it evaluates as many distances per point, but as fixed-in-advance dense blocks. We show the beam cannot be batched after the fact (the useful density of a lockstep block is 2-3%), state the wall as a two-ceiling roofline, and delimit it: it binds whenever the distance is a black box or the evaluation order is data-dependent.