Papers

Individual-level wildlife identification often suffers from data scarcity, as varying observations of the same animal under diverse poses, viewpoints, and motions are rarely available. Image-to-video (I2V) generation offers a promising way to mitigate this limitation by synthesizing additional observations from a single reference image. However, existing I2V models mainly emphasize global layout, semantics, and motion, and therefore often fail to preserve fine-grained local appearance cues that distinguish one wildlife individual from another, such as fur texture, stripe boundaries, spot configurations, and contour transitions. We observe that these identity-critical cues are closely related to high-frequency information. To address this challenge, we propose WildIcon, a high-frequency-guided I2V framework for wildlife individual consistency. Specifically, WildIcon introduces a frequency-aware identity encoding branch that extracts individual-specific high-frequency cues from the reference image. Combined with isolated foreground information, the resulting identity tokens are then injected into cross-attention blocks as identity conditioning. Building on a frozen backbone with lightweight identity adaptation, WildIcon preserves fine-grained identity cues visible in the reference image while retaining the motion controllability and semantic fidelity of the base I2V model. In addition, to support the training and evaluation of wildlife individual-consistent I2V, we construct WildlifeVid, a wildlife-centric video dataset with high-quality, temporally coherent clips and individual-level identity labels. Experiments on I2V generation and downstream animal re-identification (ReID) show that WildIcon achieves stronger individual consistency than existing baselines, and that its filtered outputs can serve as useful candidate training augmentations for downstream ReID.

As Large Language Models (LLMs) gain tool use capabilities such as web search, they can retrieve and cross-reference public information, creating privacy risks beyond memorization. One manifestation is re-identification: linking an anonymized interview transcript to a named individual. Yet without ground-truth identities, the coverage of such attacks and the protection offered by a defense cannot be reliably measured. We introduce AgentDOXX, an evaluation suite of 822 synthetic interview transcripts grounded in public information about real individuals with known identities. We evaluate fifteen configurations of open-weight and proprietary models, isolating the effect of web search, and analyze their search trajectories to distinguish retrieval-driven from parametric identifications. Ground-truth identities reveal that re-identification risk is distributed across an agent's execution: retrieval and parametric recall both contribute, with open-weight models identifying 15-28% of transcripts without search; identification succeeds in over 88% of cases once the target appears in a retrieved result; entity masking leaves at least one attacker successful on 85.3% of a stratified sample; and privacy instructions suppress naming but not retrieval, with configurations scoring 0% accuracy yet retrieving the subject in up to 62% of transcripts. We further show that observed attack trajectories can provide supervision for localizing identifying spans, offering a path toward attack-informed anonymization.

We establish optimal quantum-classical separations in communication complexity for search problems. We introduce a total search problem called Pelagic Fourier Fishing and show that it admits an $n$-qubit quantum one-way protocol, whereas every randomized two-way protocol requires $\Omega(2^n)$ bits of communication. We then introduce a variant of this problem whose solutions can be verified in polynomial time. This variant also admits an $n$-qubit quantum one-way protocol, while every randomized one-way protocol requires $\Omega(2^n)$ bits of communication. We also construct a family of efficiently verifiable total search problems achieving an $n$ versus $\Omega_d(n^d)$ separation between quantum one-way and randomized one-way communication for every fixed $d \ge 2$. In the quantum protocol, Alice prepares her message using a single unitary from the $d$th level of the Clifford hierarchy, and Bob performs a Clifford measurement. This separation is asymptotically optimal under this restriction on Alice's message. For $d = 2$, Alice's message is a stabilizer state and Bob's measurement is Clifford, so the protocol uses no magic, yet achieves an optimal quadratic quantum advantage. Finally, we discuss how these separations can be adapted to near-term quantum advantage experiments in which the demonstrated advantage is both unconditional and efficiently verifiable.

Extra inference compute is usually spent on sampling more reasoning chains. We study where inside an existing chain an additional continuation should begin. We define expansion utility, the change in correctness from restarting a chain at a stored step, and measure it at every eligible step for nine models on six benchmarks (41 model and benchmark cells). Restart position matters: steps selected on one set of continuations beat uniform placement when scored on disjoint ones, in held-out audits on 5, 16, and 38 cells (+4.25 points [+2.51, +6.63] in a fresh five-cell audit). A fixed rule that restarts from the last eligible steps, always-last, is a strong baseline: our learned router beats uniform placement but shows no detected gain over it, and on DeepSeek-R1-Distill-Qwen-14B/MATH-500 always-last exceeds the exact self-consistency frontier at matched aggregate generated output by +0.052 [+0.008, +0.098], using 0.774x the aggregate generated output of four-sample self-consistency. Cross-fitted oracle selection still finds held-out headroom beyond declared positional classes, a target for future selectors. Finally, breaking step-label ties by earliest index flips the sign of a pointwise selector's gain over uniform placement in every seed of a five-seed diagnostic with four rollouts per step; randomized ties remove the bias.

Passive leader arms transmit an operator's motion without returning remote contact or load cues. TacGELLO uses the existing servos of a 3D-printed leader for tactile contact feedback at the gripper trigger and current-based load cues at the arm joints. AnySkin contact detection activates a trigger position hold, while changes in follower joint current adjust leader-servo output limits to command resistance during lifting. Across six UR3 sessions with one operator, sent-command tracking error was 0.15–0.36$^\circ$ RMSE, with estimated trajectory lag of 82–98\,ms. Tactile onset was logged in 60 of 62 segmented TacGELLO grasp intervals. Median commanded closure after tactile or width-based contact references was 0.7–2.1\,mm with TacGELLO and 13.0–13.9\,mm with the original interface.

Controlling tail risk in randomized algorithms has received increasing attention. Randomized online algorithms can achieve a lower expected competitive ratio than the competitive ratio of the best deterministic online algorithm. However, individual executions may still incur poor outcomes. Tail constraints address this risk by limiting the probability that the incurred ratio exceeds a prescribed threshold. We investigate how such constraints affect the structure and performance of randomized online bidding algorithms. By revisiting the classical primal-dual lower-bound framework for online bidding, we find that restricting the growth between consecutive bids can yield a stronger lower bound on the expected competitive ratio. We then show that tail constraints with zero exceedance probability impose an asymptotic upper bound on the ratios between consecutive bids. Incorporating this structural property into the primal-dual framework allows us to derive a stronger lower bound. Moreover, the dual analysis suggests a randomized geometric bidding algorithm whose performance matches this bound. The insight from our primal-dual analysis also guides the design of algorithms for general tail constraints allowing positive exceedance probabilities. Motivated by the geometric growth suggested by the dual solution, we study randomized periodic bidding algorithms. We show that, for any fixed geometric base, the uniform offset distribution is optimal in terms of both the expected competitive ratio and tail-constraint feasibility. We then characterize the exceedance probability of these algorithms and use this characterization to choose a geometric growth factor that satisfies the prescribed tail constraints, establishing parameter-dependent upper bounds on the optimal expected competitive ratio.

Academic dishonesty is an urgent problem in computer science (CS) education, compounded by the rise of artificial intelligence (AI) and the prevalence of online learning in a post-COVID world. Self-efficacy and the impostor phenomenon are psychological constructs linked to academic dishonesty, yet little research has examined how they relate to how students perceive it. This study investigates the interplay between the impostor phenomenon, self-efficacy, and CS students' perceptions of academic integrity, in a context where online learning and AI agents have become commonplace. We conducted an online, asynchronous survey of undergraduate students (n = 443) in introductory to mid-level computing courses at a large Southeastern U.S. university. The survey collected measures of self-efficacy, responses to 13 potential cheating scenarios, the impostor phenomenon (Clance Impostor Phenomenon Scale), and demographic information. We observed a significant negative correlation between self-efficacy and the impostor phenomenon, and a positive correlation between the impostor phenomenon and judging an AI-related scenario as serious cheating. The impostor phenomenon was also correlated with perceived course dedication and prior teaching assistant (TA) experience, whereas self-efficacy was correlated with ethnicity. These findings highlight the need to better understand students' perceptions of AI and to keep the impostor phenomenon present in conversations about academic integrity in higher education scenarios.

Multi-camera streaming perception is increasingly deployed on heterogeneous edge platforms shared with co-resident workloads, yet accelerator placement is often evaluated using isolated single-stream experiments and mean streaming average precision (sAP). Using two end-to-end pipelines on a single GPU–NPU platform, we show that isolated evaluation can mis-rank deployment-time placement. Although the GPU pipeline is preferred in isolation, GPU-localized contention introduces deadline misses that make detections stale and can reverse the preferred placement before full GPU saturation. The NPU pipeline is less accurate than the GPU pipeline on small and medium objects in isolation, but nearly matches it on large objects. The largest absolute sAP losses in our latency and contention experiments occur for large objects. In our four-stream experiments, the preferred placement depends on which path becomes stale, and increasing GPU-side contention shifts the best placement from All-GPU to All-NPU. Under a GPU-saturating vision–language co-tenant, All-NPU achieves $5.2\times$ the worst-stream sAP of All-GPU. Because mean sAP can hide severe single-stream degradation, evaluation should report contention sweeps, deadline-miss rates on both paths, and worst-stream sAP alongside mean sAP.

A linear probe can show that a label is recoverable from a model's hidden states, but not whether that goes beyond what the input already reveals, or whether the model uses it. We audit Toto, an observability forecasting foundation model, on the Benchmark of Observability Metrics (BOOM) across five series-disjoint resplits, comparing linear probes on its frozen residual stream with models that read the raw input window and with Toto's architecture stripped of its trained configuration. Short-vs-medium cadence and metric type are more linearly recoverable from Toto's residuals than from the strongest raw-window model in every resplit (macro-F1 0.766 vs. 0.633 and 0.545 vs. 0.498). Domain is nearly tied, and series cardinality is recovered far better from the raw window. MOMENT-base shows related cadence, metric-type, and domain readouts. Recoverability is not use: exchanging Toto's residuals with those of high-burst donors moves a future-burstiness readout as intended but does not make forecasts consistently burstier than a randomized donor. A BOOM-trained coordination probe has negative zero-shot R^2 on the tested external benchmarks. We report each label against its strongest baseline.

Stochastic order-independent transparency enables efficient and elegant rendering of primitive-based radiance fields like 3D Gaussian Splatting models, but remains impractical due to the inherent visible noise in the output. We propose a principled approach to minimize high-frequency noise, addressing its sources at the representation and image synthesis level. During stochastic rendering, our history-based spatial resampling scheme drastically accelerates image convergence, while temporal importance resampling ensures coherence under camera movement. During training, a color regularizer implicitly reduces the variance along view rays in the 3DGS models. With these properties, our optimized, Vulkan-based renderer effectively mitigates output noise at low and high sample counts, achieving a substantial 13~dB PSNR increase in quality over previous stochastic methods at 1 sample per pixel and quickly converging to sorted 3DGS with an average L1 error of less than $10^{-4}$.

Much of expressive text-to-speech research rests on an untested assumption that written text carries enough information to select an appropriate prosodic style for its delivery. Text-predicted style models improve listener preference, and expressive-appropriateness evaluation presupposes that context constrains style, yet neither measures the assumption itself. This paper tests it as a falsifiable hypothesis against style labels derived from acoustics alone. For each of six speakers in a 1,200-hour conversational corpus, utterances are clustered in the spaces of five speech models, including a prosody-only control, and the cluster of held-out utterances is predicted from twelve text embedding models. Three controls are applied: utterance length is erased from the speech embeddings; accuracy is scored against the majority-class floor of unbalanced clusters rather than uniform chance; and a bag-of-words baseline measures word identity alone. Text predicts the cluster above that floor for all six speakers (+0.111 top-3 accuracy), but bag-of-words achieves three quarters of this. Sentence embeddings add only +0.026, largest for encoders not trained for sentence semantics and reversed by tree-based probes for all others. Acoustic clusters are not compact in text embedding space in any of 360 configurations. The prosody-only space weakens the association for five speakers, but not for the speaker showing it most strongly. Text thus informs these delivery clusters mainly through word choice, whether as a cue to prosody or as a marker of topic and recording situation, and reference-free style selection cannot assume more.

Company name retrieval and final entity clustering can respond differently to encoder adaptation. We study this dependency through a controlled pipeline: train multilingual E5 encoders with matched positive examples and random or hard negatives, select checkpoints on development data, retrieve within equal country-specific edge budgets, and apply unchanged pair classifiers and guarded Union-Find clus- tering. Evaluation uses a subsequently collected GLEIF snapshot; a stratified, assisted human audit and a post-hoc temperature sweep examine label and parameter sensitivity. On 3,633 names with source-silver labels, adapted retrieval raises direct pair recall from 53.74% to 76.98%, whereas cluster recall moves from 32.54% to 33.33%. Most newly retrieved positives fail the existing classifier threshold. The study contributes a controlled comparison and pair-level diagnosis of this loss between retrieval and confirma-tion. It shows why evaluating a replacement retriever requires measuring the resulting entity partition, while leaving joint matcher retraining and independent gold-label evaluation for future work.

Predicting whether an LLM agent will fail has emerged as a promising direction for supporting intervention during execution. Recent approaches report strong predictive performance, often with AUROC values between 0.85 and 0.94. However, predictors are typically trained by pooling runs from many tasks. We hypothesize that part of this performance comes from recognizing that some tasks are harder than others, rather than detecting whether a particular run is heading toward failure. This distinction matters because task-level difficulty supports decisions about where to allocate computation, while run-level prediction is needed to decide whether to intervene in an ongoing trajectory. We study benchmarks with repeated attempts of the same task by the same agent and separate cross-unit comparisons from comparisons between successful and failed runs of the same model-task unit. Across the evaluated corpora, more than 99.93% of the positive-negative pairs underlying pooled AUROC are cross-unit. Accordingly, predictors that never observe the current run can achieve high pooled performance, including a difficulty oracle with AUROC up to 0.945, while remaining at chance within task. Early run-level discrimination is consistently weak across trajectory predictors, released monitors, and hidden-state probes, although it improves later in execution and is stronger for weaker agents. Under fixed token budgets, task-level allocation outperforms abort-only strategies, while early stopping becomes beneficial only when within-task AUROC reaches about 0.84-0.93, far above the 0.50-0.55 range observed for early monitors. These results show that failure prediction should be evaluated not only by outcome accuracy, but by whether the captured signal supports the intended deployment decision.

In safety-critical domains such as autonomous driving, systems must be evaluated across a large number of environment conditions, often represented as composite scenarios built from primitive scenarios. Existing statistical model checking (SMC) approaches analyze each composite scenario independently, requiring many expensive simulations and resulting in substantial redundant computation when scenarios share common structure. This work introduces a scenario-based compositional SMC framework for safety and co-safety specifications, enabling efficient analysis of composite scenarios. Our approach decomposes scenarios into primitives and specifications into sub-specifications, verifies each primitive independently, and composes the resulting statistical estimates using importance sampling and kernel density estimation. Our empirical evaluation shows that the proposed framework can accurately answer verification queries for previously unseen composite scenarios while reducing simulation cost through parallelization and trace reuse.

Existing thermodynamically consistent neural operators enforce GENERIC degeneracy by projecting the reversible operator, introducing state dependence without guaranteeing Jacobi. We instead use a compatible Lie–Poisson pencil $L=\alpha D+\lambda(uD+Du)$ for nonlinear transport and constant Poisson multipliers otherwise. Augmenting the observed field $u$ with latent entropy density $s$ makes $S=\int s$ a Casimir, so $L\,\delta S/\delta z=0$ without projection. Energy combines a fixed mechanical quadratic, learned gauge-free potential, and convex internal energy. The friction operator $M=AA^\top$ enforces $M\,\delta E/\delta z=0$ pointwise and supports diffusion and damping without an independent reversible transport generator. Skewness, positivity, and both degeneracies hold exactly; the continuum pencil satisfies Jacobi, verified numerically on the alias-free band. The parameterization represents the closed-form heat and damped-wave friction operators within its admissible range. Physical energy is bounded under coercivity assumptions, while a discrete-gradient integrator preserves both laws when solved to convergence. Across four PDEs in 1D and 2D and three backbones (FNO, Transolver, CNO), the model wins 61/72 seed-level comparisons against matched unconstrained baselines, recovers exact transport and wave symbols, matches heat and Burgers dissipation within 13%, and exhibits negligible advection dissipation. A constant-$L$ ablation exposes the cost of nonlinear transport, while a learned-energy ablation shows that conserving learned energy need not constrain physical energy.

We introduce Factoriax, a GPU-accelerated factory-building simulator written in JAX. In Factoriax, an agent must collect resources, build machines using those resources, and then automate the collection and crafting process by arranging machines on the map to build production pipelines. This paper discusses the structure of the Factoriax simulator and an initial benchmark called Easy Rocket in which an agent is tasked with building a resource-intensive machine called the Rocket in a limited number of game ticks to escape the planet. We also publish results from a number of PPO-based training runs on Easy Rocket. Factoriax is built to be fast. A 1-billion-step PPO training run, equivalent to 500,000 episodes, runs on Easy Rocket in about 8 minutes on a single NVIDIA A100. A standard laptop GPU can complete the same run in about 84 minutes. Our trained PPO agent learns to gather resources, craft machines from those resources, and place them on the map through a curriculum reward directly tied to a manually designed set of achievements. After training, the agent does not place machines in a functional spatial configuration, failing to fully complete the benchmark, and leaving the challenge open for future attempts.

Human health is a continuous, dynamic trajectory shaped by the cumulative interplay of biological processes, clinical events, behaviors and environmental exposures across the life course. Unifying the full breadth of lifelong health information, including longitudinal records, genetic variation, molecular profiles and environmental histories, is essential for whole-person modeling and remains a major challenge. We introduce LifeLong Digital Twin, a unified, event-driven modeling paradigm that organizes Life Events into daily Health States and accumulates them into Lifelong Health Context. An accompanying Agent Harness incorporates multimodal evidence beyond the language model's textual context. We evaluate four language models across 25 disease endpoints on three tasks: Disease Trajectory Forecasting, Disease Risk Ranking and Multi-horizon Disease Prediction. The approach yields marked gains over the reference condition: model-averaged F1 increases by 22.0% for disease identification in trajectory forecasting and 18.3% for five-year disease outcomes; thyroid-disease F1 reaches 0.669. The framework provides a foundation for whole-person digital twins and research on personalized lifelong disease prevention.

Text embedding models trained with contrastive learning learn to follow task instructions from instruction-paired data, while instruction-tuned LLMs already know how to follow them. We show that this instruction-following ability can carry over from an LLM to a Transformer-based embedder without any training. We propose Attention Relay, which passes the attention weights an LLM produces to the embedder's own attention. Across six instruction-tuned LLMs from the Qwen3, Llama 3.1 and OLMo 3 families and ten widely used embedding models that differ in tokenizer, size and pooling type, Attention Relay makes nearly every combination instruction-aware. Experiments that break the method down into its parts show that the LLM's attention weights track the instruction in its later layers and come largely from instruction tuning. They also show that relaying these weights selects which content in the text matters: it makes the aspect of the text that the instruction asks about dominant in the embedding, or restores that aspect where averaging had diluted it.

Small language model (SLM) agents need safety controls that track consequences across tool calls with little monitoring overhead. A private read, for example, becomes a leak when a later action sends that data outside the system. We introduce CARB (Conformal Agent Risk Budget), which calibrates when to stop an agent using a ledger of harm incurred before stopping. Under exchangeable episodes, standard conformal risk control bounds this declared loss in expectation over calibration and a future episode. G-CARB selects scorer evidence along observable dependencies from private sources to outgoing actions. The ledger still covers the entire executed history, and computing the gate score requires no additional language-model inference. On AgentDojo replay with two 14B backbones, G-CARB roughly halves scorer-input records at intermediate risk budgets while improving autonomous task completion relative to full-prefix scoring; random context of the same size achieves similar gains. Controlled examples show how retaining the relevant dependency can further avoid stopping benign work.

Multi-attribute user records are inherently heterogeneous, often combining continuous, categorical, and binary attributes, and they frequently exhibit strong cross-attribute dependencies. Designing high-utility metric differential privacy (mDP) mechanisms for such records is challenging. Simple predefined mechanisms, such as distance-based noise, may be poorly aligned with task-specific utility loss, whereas fully optimization-based mechanisms can be computationally prohibitive for multi-attribute records. We propose Dependency-aware Heterogeneous Data Perturbation (DepHDP)}, a framework for multi-attribute mDP that combines dependency-aware attribute grouping with heterogeneous perturbation design. Rather than applying a one-size-fits-all mechanism, DepHDP selects an appropriate perturbation strategy for each attribute or attribute group, choosing between efficient predefined mechanisms, such as Laplace or Exponential mechanisms, and optimization-based designs. This selection is guided by both domain size and a predefined-noise adequacy criterion, which quantifies whether task-induced utility loss can be well explained by perturbation magnitude. To support scalable end-to-end optimization, DepHDP estimates group-level utility loss through sampling and lightweight surrogate modeling, and jointly optimizes privacy-budget allocation and group-wise mechanism design under a global $\ell_p$-metric mDP constraint. Across three case studies, DepHDP improves privacy–utility trade-offs over uniform baselines at lower computational cost than full-record OPT on evaluated domains.

Industrial sequential recommender systems operate over massive item catalogs (e.g., 10^5–10^7 items). Multi-label recommendation models are trained with Binary Cross-Entropy (BCE) loss over the full vocabulary, but standard BCE materializes a dense [B, N, V] logits tensor in High Bandwidth Memory (HBM), incurring prohibitive $O(BNV)$ memory and fatal Out-Of-Memory (OOM) errors. While chunked loss optimizations exist for Softmax Cross-Entropy in LLMs, large-scale multi-label BCE optimization remains unexplored across deep learning ecosystems. We propose CutBCE, an exact, hardware-accelerated BCE loss and gradient operator implemented in JAX and Pallas for large-vocabulary workloads. CutBCE introduces (1) an exact fused reformulation evaluating dense background loss and sparse target corrections; (2) a custom Vector-Jacobian Product (VJP) with a dedicated Pallas TPU backward kernel computing logit tiles on-chip in both passes so logits and their gradients never reside in HBM; (3) dynamic VMEM budgeting and sharding-aware collective hoisting for distributed meshes; and (4) count-based zero-overhead training metrics. On single-chip TPU v5e/v6e mini-benchmarks, CutBCE eliminates OOM errors with up to 91.9% speedup. On 8-chip TPU slice training for multi-label SASRec with 876k items (Yambda-50M), CutBCE reduces peak HBM by 65.7% (>14 GiB saved per chip) and increases training speed by 225.9% with comparable accuracy. CutBCE is open-sourced at https://github.com/AI-Hypercomputer/RecML/blob/main/recml/core/ops/binary_cross_entropy_ops.py.

The Dobrushin coefficient of each attention-rollout factor satisfies $\kappa(\frac12(I+A))\le\frac12(1+\kappa(A))$, and multiplying these inequalities over layers bounds the coefficient of the whole rollout. We characterise exactly when the layerwise bound is tight: equality holds if and only if some token pair attaining $\kappa(A)$ is mutually self-dominant - each of the two attends to itself at least as strongly as the other attends to it. The condition is far from automatic: uniformly random stochastic matrices satisfy it only 24-30% of the time. When tested on the head-averaged attention of each individual input and restricted to content tokens - image patches, words or tabular features, excluding cls, register and separator tokens - the condition holds for essentially every input at every layer of DINOv2 (three model sizes), RoBERTa and DistilBERT. In the supervised models DeiT-B and ViT-B/16 it holds for 91% and 64% of input-layer pairs respectively, with all failures occurring late in depth. In FT-Transformer trained on two standard tabular benchmarks it holds for only 11-44% of input-layer pairs. The special tokens account for almost all failures in DINOv2 and the language models: when they are included, the condition holds for only 82-97% of input-layer pairs.

Feedback can improve the reliability of communication over additive white Gaussian noise (AWGN) channels. Classical feedback codes are interpretable, or easy to understand, but often rely on linear estimation, while deep-learned feedback codes can achieve strong performance but require many learned parameters and are often black boxes that are difficult to interpret. In this work, we propose a new posterior-mean feedback coding framework for AWGN channels with feedback. The proposed scheme uses posterior-mean refinement to construct nonlinear feedback codes under both noiseless passive feedback and noisy active feedback, with maximum a posteriori (MAP) decoding at the receiver. This scheme is analytically described, but a few learned parameters related to power allocation, and hence we consider this an “interpretable,” or human-understandable code. We further develop a projection-based design to improve robustness under noisy feedback and support larger message sizes. Numerical results show that the proposed schemes achieve strong finite-blocklength performance and outperform several analytical and learned feedback coding baselines, while using only a small number of learned design parameters.

Solid State Drives (SSDs) are becoming the dominant medium for performance-critical storage. Zoned Namespace (ZNS) SSDs are getting more and more attractive because sequential writes and explicit zone resets reduce address-mapping, over-provisioning, and internal garbage-collection costs. However, reclaiming space requires resetting an entire zone, so deleting one file does not free its space while other files there must be kept. This erase-before-write constraint becomes a bottleneck for write-intensive workloads, particularly AI checkpointing during model training, where frequent saves of model and optimizer state compete for space with long-retained checkpoints. We observe that retention policies inherently encode when data can be retired, avoiding the need for a learned lifetime predictor. We present RetainZ, a storage backend that translates these policies into explicit reclaim epochs. Its allocator isolates long-retained data and groups objects with nearby reclaim epochs, balancing delayed space reclamation against unused space at zone ends. Evaluated on FEMU with multi-tenant streams and checkpoint manifests up to Pythia-1B, RetainZ reduces space occupied by deleted data and unused zone tails by 41.7% and mean per-input checkpoint p99 latency by 47.5% at 84% target load compared with the allocator of ZenFS, an established lifetime-aware ZNS backend, and lowers host write amplification from 1.165 to 1.003.

Three-dimensional gait analysis guides rehabilitation after spinal cord injury but depends on marker-based motion capture and force plates, which few clinics have. Monocular markerless pipelines have been established in fewer healthy adult cohorts but not in neurological cohorts. We present the SCAI SCI Gait dataset, comprising 239 adult individuals with spinal cord injury with synchronized video, motion capture, and force-plate measurements, we fitted a parametric body mesh to a single sagittal-view video, driving an anthropometrically scaled OpenSim model via virtual markers. Markerless lower-body kinematics showed state-of-the-art agreement with motion-capture measurements (r = 0.68-0.90, p < 0.001, and RMSE = 4.18-6.49 degrees), and accurate kinematics-based predicted ground-reaction forces closely matched those measured by force plates (r = 0.85-0.87, p < 0.001, and RMSE = 2.13-2.19 Newton per kg). Furthermore, conditional-dependence graph analysis with Markov blankets revealed that waveform components were conditionally associated with functional independence, and speed-stratified clustering revealed distinct mechanical strategies among individuals walking at similar speeds. These findings establish the use of monocular video as a scalable approach for clinically meaningful biomechanical assessment and data-driven phenotyping in patients with spinal cord injury. Github: https://github.com/SCAI-Lab/SCAI-SCI-Gait-Dataset

The component that dominates a latent world model's prediction error need not be the one whose repair most improves action selection. We show this by comparing action sequences from identical physical starts and separating endpoint error into a candidate-pool center and action-relative responses. Across four model families and four tasks, a confirmation pool of 256 new starts per task and 300 shared candidates per start shows that center error dominates MSE in 14/16 model-task cells. Yet in six of these cells, an oracle that corrects only the action-relative responses yields better physical rank correlation and top-30 elite quality than one that corrects only the center, while leaving more latent MSE (family-wise corrected intervals). The preference differs across the evaluated settings: a separate LeWorldModel (LeWM) study that executes oracle-selected actions favors center repair on PushT and on Reacher with a render-matched goal. Matched-candidate tests localize ordering loss: for LeWM, encoding realized endpoints raises physical Spearman from 0.464 to 0.975 on that Reacher setting and from 0.193 to 0.631 on PushT (64 starts per task), while Cube's encoded-goal cost remains uninformative. A 72-run objective study improves selected response diagnostics, while incremental closed-loop planning gains remain unconfirmed. These results separate error magnitude from the decision effects of oracle correction and motivate evaluating representation, prediction, and planning as separate stages.

We formulate joint estimation of common-slope decay rates and amplitudes from room impulse responses (RIRs) as parameterized nonnegative matrix factorization with the Itakura–Saito divergence as the loss function (IS-NMF). Estimation at each short-time Fourier transform frequency bin produces detailed reverberation time (RT) curves directly from RIR powers with no backward integration needed. Standard space-alternating generalized expectation-maximization (SAGE) algorithm yields closed-form amplitude updates and a convex subproblem for each decay rate update. To accelerate estimation, we introduce contribution-weighted SAGE, which emphasizes observations where each component contributes strongly to the modeled power. Experiments with synthetic data show accurate recovery of well-separated decays and faster loss reduction than standard SAGE. Application to measured coupled-room RIRs yields frequency-dependent RT curves and reveals complementary space-time contributions of the shared decay components.

This paper derives analytical expressions for the asymptotic variance of the Hermite-Domain Predictor-Based Subspace Identification (HD-PBSID) method. Unlike continuous-time subspace approaches that rely on intermediate-domain transformations, HD-PBSID identifies continuous-time state-space matrices directly. The derivation first establishes the uncertainty of the estimated state-space matrices and then exploits these results to obtain asymptotic variance expressions. These expressions provide analytical uncertainty bounds for system eigenvalues, which are invariant under similarity transformations and therefore uniquely characterize the identified dynamics. The proposed formulas are first validated in an ideal Hermite-domain setting, where the conditions underlying the derivation are satisfied, and then assessed on noisy time-domain data through Monte Carlo simulations. The predicted bounds show very good agreement with the eigenvalue distributions in the ideal setting and acceptable agreement in the time-domain case when the innovation sequence is enforced to be white.

Digital libraries, repositories, and AI-mediated knowledge services increasingly rely on generative systems to produce summaries, descriptions, and other multi-claim knowledge objects. Yet generation can scale far more easily than verification capacity: a reviewer may need to decide whether an object is suitable for publication or downstream use after checking only a small fraction of its claims. This creates a fundamental gap between claim-level verification and confidence in the object as a whole. The central question is therefore what a successful partial check implies about the reliability of the complete artifact when its size grows but the verification budget does not. This paper contributes a Bayesian model of bounded verification centered on the Predictive Value of Pass (PVP). The model predicts that evidentiary value decreases as artifacts grow under fixed verification capacity, improves with larger verification budgets, and is especially fragile when errors are sparse. Controlled experiments on FEVEROUS and FEVER support these predictions and show that adding supported claims around a fixed number of false or unsupported claims can make passing more likely while making a pass less informative. The model further yields the minimum verification budget required to maintain a target PVP, providing a practical component for AI-assisted quality-assurance workflows in which generated knowledge objects must be checked before publication or downstream use.

LiDAR-inertial odometry (LIO) is widely used for state estimation in ground-based autonomous mobile robots. However, the geometric constraints provided by the local ground surface remain largely underexploited in existing LIO systems. This paper proposes a filter-based local ground-aware LIO framework that explicitly incorporates local ground plane geometry into the state estimation process to improve both localization accuracy and computational efficiency. Specifically, a local ground plane is parameterized by the robot orientation and the body-to-ground (B-G) height and continuously propagated within the state estimation process. Based on the proposed B-G geometry model, a propagated local ground plane enables efficient and reliable ground segmentation. The segmented ground points are then incorporated into the filter update through point-to-plane geometric constraints, improving both state estimation accuracy and efficiency. Furthermore, a planar motion update is introduced to exploit the propagated local ground plane as an additional geometric constraint, effectively suppressing vertical drift and improving estimation robustness. To address the initially unknown B-G height, an efficient initialization strategy is developed, followed by an online calibration procedure for continuous refinement. The proposed system is evaluated on several public benchmark datasets and self-collected real-world datasets covering diverse operating scenarios. Experimental results demonstrate that the proposed method consistently outperforms representative LIO methods in terms of both localization accuracy and computational efficiency.