Papers

General-purpose robot models increasingly rely on large and diverse datasets. For embodied 3D navigation, however, existing data sources face a fundamental trade-off: simulated data can be generated at scale but often suffer from the visual sim-to-real gap, whereas real-world flight data provide realistic observations but are costly to collect. This paper studies another direction: the use of high-fidelity visual generative models as scalable data engines for embodied 3D navigation. We introduce NavGen, a text-to-video data generation pipeline that produces diverse vision-language navigation (VLN) episodes across indoor and outdoor scenes. We also propose a style-diversification method that scales up long-tail data that are difficult and costly to collect. The resulting dataset contains approximately 400K navigation episodes. We evaluate our dataset against existing UAV navigation datasets across multiple metrics, and find that the model trained on our data generally improves with scale, outperforming those trained on existing datasets. To validate real-world transferability, we deploy the trained model in world-action-model paradigm to real-world flying experiments. The final model achieves a 75% success rate across different navigation tasks and environments.

Cross-domain few-shot learning requires adapting a classifier to a new visual domain from very few labelled examples without target-time parameter updates. We isolate one question: under a fixed global representation, what does joint query-support adaptation contribute to prototype construction? The Within-Instance Prototypical Transformer (WIPT) implements single-query test-time prototype adaptation by jointly transforming one unlabelled query and the labelled support embeddings, then forming query-specific class means. Using a shared frozen ViT-S/16 encoder, miniImageNet source training, and CUB, EuroSAT and ISIC targets, we replicate the key comparisons across five independent training seeds. In 1-shot evaluation, WIPT improves frozen ProtoNet in every run on CUB (+0.21 percentage points) and EuroSAT (+2.07), but decreases ISIC (-0.22). In 5-shot evaluation, ProtoNet remains strongest overall, while WIPT consistently improves a capacity-matched support-only Transformer on ISIC (+0.99). Joint processing of up to five queries yields no reliable accuracy gain; in a head-only 5-shot benchmark, g = 5 reduces analytical attention-token pairs by 73% and peak allocated memory by 29% relative to g = 1, although latency is non-monotonic. Across all target/shot conditions, WIPT changes uncertain ProtoNet decisions far more than confident ones, and rescue/break decomposition accounts for the observed gains and losses. Source-shift and scorer controls further show that the benefit is not universal. Overall, WIPT provides a streaming-compatible form of test-time prototype adaptation that can improve difficult low-shot cross-domain decisions without target-time optimization.

Thinking in reasoning language models (RLMs) has been subject to debate on whether it resolves or amplifies bias. Prior works have shown competing conclusions in both directions. Using a within-model thinking-vs.-non-thinking ablation across QwQ-32B, DeepSeek-R1-Distill-Qwen-32B, and Qwen3-32B on three high-stakes decision tasks (Adult, COMPAS, Credit), we show that thinking has an asymmetric dual effect on counterfactual fairness: it both resolves counterfactual flips produced by the non-thinking baseline and creates new flips at near-saturating model confidence. In all nine (model, dataset) combinations, the created flips outnumber the resolved flips by roughly 5 times. To explain the effect, we treat the thinking trace itself as a measurable site of fairness change and study it through two dynamic instruments: 1) We propose Counterfactual Depth Probability Gap (CDPG) to track bias evolution along thinking depth, and observe that bias propagates and amplifies with thinking. 2) We also formulate the Bias Transition Matrix (BTM) to show how predictions of counterfactual pairs change from non-thinking to thinking, and find that the asymmetric dual effect originates in the pair-state joint transition.

We consider a inverse problem for a hyperbolic equation. The objective is to simultaneous recover both the spatially varying coefficient, whose square root represents the wave speed, and the initial displacement from a single pair of Dirichlet-Neumann Cauchy data. By introducing a suitable transformation and differentiating the resulting equation in time, we derive a coupled system for the differences of the unknown coefficient and initial displacement. Combining weighted energy estimates with Carleman estimates, we establish a Lipschitz stability estimate for both unknown quantities in appropriate Sobolev norms. The proof relies on a priori regularity assumptions, non-degeneracy conditions on the initial data, and structural inequalities controlling the interaction between the coefficient and initial-displacement differences. Our result extends coefficient-only stability results to a simultaneous coefficient–initial-displacement identification problem.

Agentic reinforcement learning (RL) differs from conventional RL in that every task executes inside a complex environment, e.g., a virtual machine or a container. We find that agentic RL pays a heavy environment tax: a large share of the iteration time goes to the environment rather than to learning. The root cause is the lack of a full-lifecycle solution to environment management. We present WeEnv, which manages environments across packaging, initialization, and provisioning. WeEnv packages components as independently published layer groups and composes them at initialization, so that updating a component republishes one small group rather than every artifact containing it. To speed up environment initialization, WeEnv launches environments instantly and fetches contents on demand. During task execution, WeEnv provisions CPU and memory elastically, adjusting each environment's quota from its observed usage to fit the varying demands. WeEnv reduces the initialization by 5.6-14.2x over E2B, Docker, and AgentENV, cutting its share of the iteration time from up to 53.4% to 9.1%. WeEnv is deployed for agentic RL at WeChat.

Insurance reserve estimation is a fundamental actuarial task supporting premium pricing, solvency assessment, financial reporting, capital planning, and risk management. Classical reserve methods based on Thiele's differential equation provide a rigorous and interpretable foundation for life insurance valuation, but repeated reserve calculations become computationally expensive in sensitivity analysis, optimization, and large-scale scenario evaluation. This paper presents an Insurance Reserve Intelligence Platform for term-life reserve modelling that combines a classical Thiele-equation solver with a Physics-Informed Neural Network (PINN) enhanced by Knowledge-Informed Neural Network (KINN) losses. The framework includes synthetic policy generation, risk-adjusted premium calculation, classical reserve trajectory generation, reserve-ratio dataset construction, configurable neural training, validation diagnostics, sensitivity and elasticity analysis, prototype optimization workflows, and interest-rate scenario testing. A key refinement is the use of premium ratio and the explicit separation of pricing-time and scenario-time interest-rate semantics. The final model uses seven features: elapsed time, issue age, pricing interest rate, scenario interest rate, premium ratio, sum assured, and mortality intensity. It predicts a standardized reserve ratio instead of raw reserve values, improving numerical stability across policies with different sums assured. The model achieved an R2 of 0.9887, MAE of 785.48, and RMSE of 1212.76 on the test set. On 200 policies, PINN/KINN inference was approximately 119.53 times faster than the classical solver. Results show strong predictive accuracy, physics consistency, and boundary performance, while highlighting remaining limitations in monotonicity and out-of-distribution generalization.

Identifying dormant compact objects in non-interacting binaries is crucial for constraining the hidden population of stellar remnants. We present a systematic search for long-period compact-object candidates by combining Gaia DR3 astrometry with multi-epoch LAMOST DR13 medium-resolution spectroscopy. Starting from sources with elevated RUWE values, we required at least five LAMOST spectroscopic epochs and peak-to-peak RV variations exceeding 20 km/s. After RV extraction, orbital fitting, and subsequent screening, we obtained Bayesian Keplerian orbital solutions for 19 long-period single-lined binary candidates, with periods spanning approximately 30-1500 days. Multi-wavelength spectral energy distribution fitting was used to constrain the visible stars and evaluate the expected luminosities of unseen companions under a main-sequence assumption. Two systems are identified as the highest-priority compact-object candidates in our sample, each with a minimum companion mass exceeding 1 solar mass. Their spectra and optical-to-infrared photometry show no detectable secondary-light contribution, although such a contribution would be expected if the unseen companions were normal main-sequence stars. These systems therefore represent the strongest compact-object candidates in our sample, although further observations are required to distinguish massive white dwarfs or neutron stars from faint stellar companions or unresolved hierarchical systems. We also identify five intermediate-priority and 12 lower-priority systems for follow-up spectroscopy, ultraviolet imaging, and future astrometric constraints.

Biomedical language models (LMs) encode textual semantics but do not explicitly preserve medical code hierarchies. We present Hyperbolic Clinical Ontology Embeddings (HCOE) for hierarchy-aware clinical concept representation. HCOE maps frozen BioBERT embeddings into a Poincare ball, combining parent-side and child-side ontology-guided contrastive learning with coarse-to-fine ontology-path aggregation. It uses International Classification of Diseases (ICD) codes organized by Clinical Classifications Software (CCS) and Anatomical Therapeutic Chemical (ATC) medication hierarchies. Evaluations show that HCOE performs best on ICD/ATC clinical relation prediction and CCS-to-PheCode hierarchy transfer. On the MIMIC-IV dataset, HCOE also achieves the best performance on mortality prediction, readmission prediction, medication recommendation, and rare drug prediction.

We prove a generalized quantum Stein lemma for parallel discrimination of an arbitrary finite-dimensional channel against families of alternative channels. The alternatives are compact and convex, closed under tensor products, and contain a faithful replacer. At every fixed type-I error tolerance, the optimal type-II error exponent equals the regularized Umegaki channel relative entropy minimized over the alternatives, and both defining limits exist. Inputs may be entangled across channel uses and with a reference system. The main technical result constructs exactly trace-preserving approximations with exponentially small diamond error, dominated in completely positive order by free channels at every rate above the common exponent. The proof combines uniform auxiliary map approximation, iterative reduction of the domination rate, and tensor amplification. It yields asymptotic equipartition with trace-preserving smoothing at every subexponentially vanishing error, an exponential strong converse, and stability under vanishing diamond-norm perturbations. Under additional permutation invariance and closure under insertion of a fixed faithful input state and discarding of its output, we also prove an explicit finite-block completion bound. This quantitative construction uses weighted discarding, local operator corrections, and comparison with auxiliary extensions. Applications include state-preserving, coherence-restricted, covariant, entanglement-breaking, and positive-partial-transpose channels. For isometric targets against entanglement-breaking or positive-partial-transpose alternatives, we obtain exact finite-block testing and smoothing formulas.

Most existing human motion generation (HMG) methods use cross-attention modules to inject text semantics, but ignore the importance of bidirectional modeling between motion and text tokens, which limits text comprehension. A straightforward idea is introducing multimodal diffusion transformers (MMDiT), which have shown effective joint text–visual modeling in vision generation, into HMG. However, we find that articulated motion is temporally coherent but weakly correlated across joints, in which directly applying an MMDiT with flow matching produces poorly coordinated and jerky motion. In this work, we propose Timo, a novel kinematics-aware MMDiT framework tailored for HMG. Timo combines fully shared multimodal attention for bidirectional text–motion modeling with flow matching, geometric and rotational-kinematics supervision that compares actual rotations and their changes over time, and a two-stage curriculum progressing from broad motion learning to detailed caption alignment. Further, we construct a benchmark of $40{,}025$ held-out clips from six public datasets spanning diverse actions, assessing six complementary dimensions under a common evaluator and scoring protocol. Our model substantially outperforms state-of-the-art methods in both quantitative and qualitative evaluations. Remarkably, Timo surpasses Kimodo on five of six dimensions, achieving a $40.8$% relative improvement in the average benchmark score. Project page: https://kyfafyd.wang/projects/timo. Demo page: https://timo.kyfafyd.wang.

In this paper, we investigate transition fronts and spreading solutions of Fisher–KPP equations in one-dimensional almost periodic media, both on the real line and on the lattice. Let $\lambda_1$ be the supremum of the spectrum of the linearized operator acting on $L^2(\R)$ or $\ell^2(\Z)$, respectively, and let \(L(\lambda_1)\) denote the spatial Lyapunov exponent at the spectral parameter \(\lambda_1\). We prove that, if $L(\lambda_1)>0$, the global mean speed of any transition front is at most $\lambda_1/L(\lambda_1)$. Moreover, if a solution of the Cauchy problem spreads faster than this bound, its transition width is unbounded along a sequence of times. This occurs for a class of initial data with slowly decaying exponential tails. This contrasts with periodic media, where pulsating fronts exist at every speed above the minimal speed. As applications, we consider almost Mathieu coefficients and a continuous quasiperiodic coefficient with two frequencies. Together with the results of Nadin–Rossi and Liang–Wang–Zhou–Zhou \citep{LWZZ24}, our results provide an almost complete picture of the admissible speeds of generalized transition fronts, while leaving the critical cases open.

The utility of flexible continuum mechanisms for dexterous navigation is often impaired by their low stiffness, making them ineffective at manipulation in high-force scenarios. To address this challenge, we propose a novel continuum mechanism that achieves both flexible and rigid behavior by antagonistic extension and contraction of a rod-driven continuum helical structure. The helical design combines variable-length capacity with force locking for workspace and stiffness enhancement. In this article, we present the detailed design of the proposed mechanism and characterize its performance through experiments that quantify bending and stiffness. The results demonstrate 180 degree bending range of motion with an average distal positioning error of <10%. Further tests demonstrate that force locking directly improves axial stiffness and thus indirectly increases bending stiffness anisotropically, with maximum bending stiffness along load paths with a large axial component. Tensioning the driving rods provides additional stiffness tunability in the force-locked state, where increasing rod tension proportionally increases bending stiffness with a dimensionless gain of 0.56.

Raindrops can cause occlusion and distortion in the background scenes due to their adherence to windows or camera lenses. Existing raindrop removal methods concentrate on designing sophisticated CNN or Transformer architectures to recover distorted and missing texture. In this paper, we try to integrate location information and physical model into off-the-shelf CNN or Transformer architectures to help improve their performance. Specifically, we notice that existing methods deploy a preprocessing sub-network to generate a binary or soft mask to indicate the raindrop location, which will increase the network parameters and computational complexity. In contrast, a location-aware learning branch is embedded to teach the encoder in the training phase with the capability of perceiving the position of the raindrops. Note that this location-aware learning branch can be removed during the inference process (achieving performance improvements at no cost). Furthermore, instead of directly reconstructing the raindrop-free image (i.e., background scene), we devise a physics-based reconstruction scheme to first learn the transparency matrix and the raindrop layer. The latent background layer is then reversely derived based on the physical model. By combining the above-mentioned components, we propose our location-aware learning and physics-based reconstruction (LLPR) framework for this challenging ill-posed problem. We also collect a real-world raindrop-degraded image dataset, which is challenging for single-image raindrop removal (SIRR) methods. Extensive experimental results demonstrate the effectiveness and generality of our LLPR framework, achieving superior performance against state-of-the-art SIRR methods. The code will be made available upon acceptance.

In this article, we prove that the problem of solving $\operatorname{CSP}(\mathbf{A})$, where $\mathbf{A}$ is a finite relational template which admits a Maltsev polymorphism is in a specific complexity class DET, which is related to the complexity of computing the determinant of a matrix with integer entries. Such a class is intimately related to well-studied MOD-logspace classes in the theory of computational complexity. To prove this fact, we develop a new algorithm for solving syntactically simple binary instances of Maltsev constraint satisfaction problems, rather different from the well-known Bulatov-Dalmau algorithm, which does not require the explicit use or knowledge of a Maltsev polymorphism of the template but, rather, utilizes a graph whose vertices are 2-generated subuniverses of $\mathbb{A}$, where $\mathbb{A}$ is the Maltsev algebra parametrizing $\operatorname{CSP}(\mathbf{A})$. The theoretical importance of this algorithm is reflected in two facts: (1) it places the problem $ \operatorname{CSP}(\mathbf{A})$ in a complexity class related to the deterministic logspace with counting, which, in itself, has a strong connection to a variety of standard algorithmic problems in linear algebra, and (2) it only makes use of the relational structure of the template without the need for the explicit use of a compatible Maltsev polymorphism, depending entirely on the strong “symmetry" of constraints compatible with such polymorphisms and the knowledge of 2-generated subuniverses of $\mathbb{A}$.

Generative image communication transmits compact semantic tokens under a limited packet budget, where token selection directly affects the final reconstruction quality after the complete packet is decoded. However, accurately estimating the terminal value of every candidate token requires repeated receiver-side reconstruction, resulting in substantial encoder-side computation. To address this problem, we propose ACV-Gate, an adaptive candidate evaluation framework that learns to approximate full-budget counterfactual evaluation and selectively assigns exact evaluations to the most informative candidates. Specifically, a set-aware student is trained using terminal advantages and regrets to predict candidate rankings directly, while a selective refinement mechanism evaluates only a bounded candidate set containing both Local-MDL and direct actions; cost-based thresholds further enable explicit control of the average evaluation workload. Experiments on CIFAR-10 show that ACV-Gate consistently improves reconstruction quality while substantially reducing candidate evaluations; at 0.20 bpp, the primary adaptive configuration improves PSNR over LocalMDL by 0.636 dB with only 2.13 candidate evaluations per image, corresponding to 27.60% of the calls required by the Exact-Full expert. Matched-candidate comparisons, synchronized GPU measurements, and evaluations on STL-10 and 384 *384 scale transfer further demonstrate consistent quality computation trade-offs, with particularly pronounced gains at low bit rates. These results show that combining terminal-value learning with selective candidate evaluation provides an effective and controllable mechanism for allocating encoder computation in packet-constrained generative image communication.

Multiscale Spectral Rate-Distortion (MS-SRD) estimates the bottleneck channels required at user-supplied spatial cuts from training images and a normalized mean-squared error (NMSE) bound, without fitting a neural network. Its covariance-tail rule is exact for shared linear block-convolutional autoencoders under squared error. A nested-scale dominance result motivates reporting the activation-parameter Pareto frontier alongside the minimum-latent candidate. At NMSE <= 0.01 on thirteen grayscale datasets, its latent-size prediction has 0.84% mean absolute percentage error against nonlinear patch-autoencoder boundaries; ten predictions are exact and the remaining three differ by one channel. In a four-dataset deployable comparison, MS-SRD matches all retrospective external widths and all four selected models pass, without training a selector; a 46-fit validation grid and four Least-Volume fits each pass on two datasets. In a skip-closed U-shaped autoencoder at the same bound, five predictions are exact, nine are within one channel, and every failing prediction is one channel short. Experiments at looser bounds show progressively larger nonlinear savings.

We study the tri-partite genuine Rényi multi-entropy of fully symmetric Gaussian states as a function of the squeezing parameter for different total number of bosonic modes under different subsystem configurations. Exact results for a few modes are obtained, and we conjecture an asymptotic formula at the limit of large squeezing parameter as a function of the replica index $n$, while also finding subleading subsystem-size dependent terms for $n=3$ under a specific tripartition. We analytically show that the genuine $n=2$ Rényi multi-entropy of any pure bosonic Gaussian states is zero for any number of modes and for any tripartition. Furthermore, to investigate the dependence on subsystem size, we plot the curve of genuine Rényi multi-entropy as a function of the number of modes in the subsystems while keeping the total number of modes fixed. We discuss differences and similarities between this result and studies of the multi-entropy curve for Haar random states. In particular, we identify a subsystem size configuration related with the multi-entropy time in an evaporating black hole for which the behavior of the genuine multi-entropy changes.

A punch is a ballistic, full-body action driven by a kinetic chain running from the legs through the trunk to the arm, where a small sequencing error separates a scoring strike from a miss. Wearable sensors can capture this movement in the gym, but most deployable systems only classify which punch was thrown rather than assess how well it was thrown. We present Skill Profiling with Attributable Reasoning (SPAR), an eight-IMU garment and pressure-insole system that classifies each punch as expert or novice and treats an explanation of that prediction as feedback. Feedback is only useful if the person receiving it can act on it, so SPAR explains the prediction at three tiers, a per-joint attribution for the analyst, a counterfactual over kinetic-chain layers for the coach, and a plain-language narrative of the two for the athlete. Across 17 participants and 4,713 punches, SPAR reaches a leave-one-participant-out AUC of 0.842 (95% CI [0.769, 0.907] over participants). A frozen time-series foundation model encodes the joint-angle and plantar-force series, and a small transformer trained on the cohort classifies the encoding. We audit the two quantitative tiers and report six themes from a thematic analysis of interviews with six practicing boxing coaches.

Many deep learning approaches to RNA secondary structure prediction have recently been proposed. They typically output a weight matrix $W$ where $W_{ij}$ is an arbitrary weight for base $i$ pairing with base $j$. Converting this matrix to a predicted secondary structure or base-pairing probability matrix typically involves ad hoc and problematic downstream algorithms. Despite the importance of this conversion step, which we refer to as structure extraction, it has received relatively little attention in the literature. In this work, we analyze how the congruence between training and extraction methods affects prediction performance. To do this, we compare four extraction algorithms: a Nussinov-like dynamic programming method, maximum-weight graph matching and the greedy extraction algorithms used by SPOT-RNA and RiNALMo. These are evaluated on outputs from the pretrained RiNALMo model and three toy models trained in this paper: a differentiable Nussinov-like model, a binary cross-entropy (BCE) baseline, and a model that incorporates a novel symmetric doubly stochastic matrix (SDSM) normalization algorithm during training which allows it to output base-pairing probability matrices directly, without a separate extraction step. This SDSM normalization algorithm is differentiable and can be added inline to any deep learning model during training and evaluation. We find that the performance of each extraction method depends strongly on how the corresponding model was trained. Considering the toy models themselves, the SDSM model showed the strongest overall performance: it outperformed the BCE baseline under all four extraction algorithms and produced pre-extraction outputs closest to the ground truth. These results suggest that SDSM normalization is a tractable alternative to traditional structure extraction.

Pairwise language-model judges can gather evidence through direct comparison, reasoning, or reference-based verification, but no single protocol is best across benchmarks and judge backbones. We introduce Backbone-Adaptive Evidence Routing (BAER), which adapts the evidence mechanism while preserving candidate symmetry: swapping the two responses may reverse the preference but cannot change its strength. BAER separates each expert's signed preference from candidate-invariant reliability and builds three symmetric heads: evidence stacking, reliability-based expert routing, and candidate-blind reference verification. Development data select one head for each benchmark–backbone condition, and that choice is frozen before testing. Across four benchmarks and two 8B judge backbones, BAER achieves the highest test accuracy among the compared methods in all eight conditions, with full prediction coverage and gains of 0.87–7.32 points over the strongest external baseline. The results show that adapting how evidence is gathered is more reliable than fixing one judging protocol everywhere.

We propose a Sparsely Connected Rank-Inspired Neural Network (SCRINN) for function approximation and the numerical solution of partial differential equations (PDEs). By introducing a structured sparse connectivity architecture and an orthogonality- and normalization-guided loss function, SCRINN constructs an approximately orthonormal neural basis while promoting progressive rank growth of its evaluation matrix and reducing the number of trainable parameters. A two-stage framework is developed, in which an approximately orthonormal neural basis is first constructed, and the output weights are subsequently determined using least-squares methods. Numerical experiments on function approximation and a variety of steady-state, time-dependent, and nonlinear PDEs demonstrate that SCRINN consistently achieves high approximation accuracy with substantially lower training costs. The code is publicly available on GitHub.

Data Science Code Translation (DSCT) is the process of converting code between data science libraries while preserving functional equivalence and enabling interoperability across data science ecosystems. While Large Language Models (LLMs) have demonstrated considerable progress in Data Science Code Generation (DSCG), their performance in DSCT remains insufficiently studied. To address this gap, we introduce ORCA, a comprehensive benchmark with two complementary settings: ORCA-MAIN, which comprises 1,600 carefully curated grounding-level tasks across 3 representative domains: Data Querying, Data Manipulation, and Deep Learning; and ORCA-PROJECT, which contains 200 translation tasks over complete data science projects across 7 data science task types. Each task is accompanied by annotated reference translations and test cases for validating functional equivalence. We further incorporate a multi-stage quality verification process that thoroughly verifies task correctness and test case robustness. Experimental results demonstrate challenges in DSCT, with even frontier LLMs showing limited performance. Specifically, Claude-Opus-4.6 achieves a success rate of 56.92% on ORCA-MAIN and 33.67% on ORCA-PROJECT, indicating considerable room for improvement in DSCT. We also observe a clear directional preference in DSCT, where translation is consistently easier when the source code expresses the task through more explicit, fine-grained operations. Motivated by this, we propose an intent-augmented method, in which the model first infers source-code intent and then uses it as additional context for translation, achieving average absolute success-rate gains of 4.80% and 5.33% on ORCA-MAIN and ORCA-PROJECT, respectively.

We study third-order linear differential equations through their associated Pfaffian and projective foliations. In the regular-singular setting, we introduce a Fuchs-adapted Pfaffian model in which the indicial polynomial appears directly in the special-fiber singular scheme, and Frobenius resonance acquires a projective geometric interpretation.

As artificial intelligence (AI) becomes embedded in everyday life, its environmental footprint, particularly water consumption remains largely invisible. While energy and carbon impacts are widely recognized, the substantial freshwater demands of data center cooling and electricity generation receive little attention. To address this gap, we introduce SustainAI, a water-aware, closed-loop framework incorporating environmental accountability into AI deployment. SustainAI integrates real-time water metering, a hallucination-aware penalty model, and a water-aware routing algorithm that accounts for regional water stress. Evaluated via Small Language Models (SLMs) extracting health misinformation, results reveal an 11-fold variation in water footprint across geographically distributed data centers (0.0477 mL to 0.5360 mL per inference). Across 1,335 inference runs, the system consumed approximately 399 mL of water but produced only 240 correct outputs, demonstrating that substantial resources are spent on inaccurate responses. Crucially, SustainAI extends beyond technical optimization through a Care by Design lens, framing AI sustainability around relational ethics, regional equity, and ecological stewardship. By combining water monitoring, adaptive accountability, and Care by Design principles, SustainAI provides a practical foundation for integrating ethical care and environmental responsibility into AI infrastructure design and lifecycle management.

Extreme events in chaotic systems are difficult to learn from short trajectories because they are controlled by finite-time instabilities rather than by frequently observed bulk dynamics. We propose a mechanism-aware conditioning plug-in framework that turns a nudged ensemble of an imperfect model into a non-intrusive sensor of the local instability geometry. In the small-noise regime, the ensemble covariance has the same finite-time deformation kernels that govern local instability, providing a Jacobian-free proxy for local amplifications around a trajectory. A small Feature-Wise Linear Modulation (FiLM) network injects the ensemble geometry into an otherwise unchanged backbone without modifying the low-fidelity model simulator. We demonstrate this interface in two settings: a Transformer-style residual-attention corrector for a controlled low-dimensional chaotic system and a probabilistic recurrent STORN corrector for topographic two-layer quasi-geostrophic (QG) flow. In the low-dimensional benchmark, leading ensemble-covariance directions identify transient instabilities that are also detected by Optimally Time-Dependent (OTD) modes. FiLM conditioning improves 99th-percentile exceedance-frequency errors over an otherwise identical unconditioned Transformer. In QG, an ensemble-conditioned FiLM-STORN model substantially improves long-horizon rare-event statistics in the data-limited regime, including density-tail errors, exceedance frequencies, and spatial exceedance-area distributions relative to an unconditioned STORN trained on the same data. On averaged high-threshold exceedance diagnostics, it also outperforms the unconditioned baseline STORN trained with 20 times more expensive trajectory data. These results show that local instability geometry is not merely interpretable post hoc, but an actionable conditioning signal for data-efficient rare-event emulation.

Performing complex medical procedures with continuum robots requires careful selection of their geometric design parameters. The robot should have high dexterity in the specific anatomical environment of its procedure. This work presents a design optimization method that considers both dexterity and anatomy. We introduce the Reachable Volumetric Dexterous Solid Angle (RVDSA) metric as our objective, which measures the ability of a robot's end effector to reach the points in a goal volume from different directions via collision-free paths from a start configuration. We present a computationally efficient motion planner to compute this objective function for a given robotic design, and we use an asymptotically optimal simulated annealing optimizer to compute an optimized design. We applied our new method to optimize the design of a bimanual dexterous sheaths robot for performing procedures on cancerous polyps in colon anatomies, achieving a 78% higher RVDSA on average than optimizing for 3D voxel coverage alone.

Combining $p$-values is a fundamental procedure in global hypothesis testing. In modern high-dimensional settings, however, component $p$-values often exhibit complex dependence and rely on asymptotic approximations rather than exact finite-sample uniform distributions. This paper establishes a unified asymptotic theory for weighted transformation statistics that decouples marginal finite-sample approximation error from the joint dependence structure. We also provide sufficient conditions based on conditional probability bounds to verify the joint-tail conditions. Utilizing this framework, we derive explicit dimension-growth and correlation rates for test statistics operating under asymptotic Gaussian and chi-square calibrations. For non-exact finite-sample statistics, we analyze standardized weighted sums, demonstrating how Cramér moderate deviations control relative tail error. Analytical examples demonstrate why both marginal and joint conditions are mathematically indispensable for valid global inference under dependence, and numerical experiments confirm that our asymptotic framework maintains accurate finite-sample size control at extreme significance levels.

A key challenge in machine consciousness research is translating theoretical models into computational-level implementations. In this paper, we address this challenge by proposing a five-layer implementation architecture for the S3Q (Simulated, Situated, Structurally Coherent) theory of consciousness. Rather than introducing novel formalisms, the architecture composes published computational primitives into a single pipeline. S3Q identifies three jointly necessary conditions for qualia: (1) grounded sensorimotor situatedness, (2) internal simulation via a world model, and (3) structural coherence between predictions and observations. No existing computational system implements all three simultaneously. We map each S3Q tenet to specific, compatible computational machinery and specify how these components interface within a single representation pipeline that operates on continuous, differentiable, per-object slot vectors, along with a developmental bootstrap sequence and falsifiable predictions for the composed system that no subset of the architecture produces in isolation. The model suggests that a basic sense of "self" develops by linking actions to their outcomes, and that behavior falls into three patterns (hesitation, curiosity, or avoidance) depending on how unexpected an outcome is and whether it is experienced as positive or negative. Each prediction is individually falsifiable, providing the field with a testable framework to advance our understanding of machine consciousness.

We initiate the study of prophet trading, an online trading model in which a trader interacts with sellers and buyers who arrive in a uniformly random order and whose prices are drawn independently from a common known distribution. The trader aims to maximize the expected gain from trade (GFT), with performance measured against an omniscient prophet that knows the realized arrival order and all prices in advance. Unlike the classical prophet inequality problem, the trader must make both purchasing and selling decisions while managing the inventory, which makes both the prophet benchmark and the analysis of online algorithms substantially more intricate. For arbitrary numbers of buyers and sellers, we propose a simple threshold-based algorithm and prove a distribution-free competitive ratio of~2, which is the best possible. Our main technical contribution is an exact characterization of the inventory process induced by threshold trading. By expressing the algorithm's expected GFT in terms of the cumulative holding probability at buyer arrivals, we derive an exact formula for this inventory term, which serves as the foundation of our analysis and yields sharper guarantees in several important special cases. For balanced trading (with $n$ sellers and $n$ buyers), we improve the competitive ratio to $(2n^2-n)/((n+4^{-n}-1)(n+1))$, which is strictly less than 2 for every $n>1$. For the single-seller case, we sharpen the analysis of the fixed-threshold algorithm to obtain an asymptotic competitive ratio of $2e^2/(e^2+1)\approx1.76$. Furthermore, by exploiting the additional structure of this setting, we design an adaptive-threshold algorithm whose competitive ratio approaches $e/(e-1)\approx 1.58$. Due to a symmetry property of our general algorithmic idea, the same $1.76$-competitive guarantee also holds for the single-buyer case.

Binocular rendering requires two nearby views of the same scene and therefore repeats substantial visibility and shading work. We present a 2D Gaussian Splatting (2DGS) pipeline that fully renders a dominant-eye RGB image and an alpha-weighted depth proxy, reprojects that image to the affiliated eye, and repairs uncovered pixels. Small interior gaps are interpolated, whereas larger disoccluded regions are identified as regions of interest (ROIs) and selectively re-rendered. The depth proxy reuses the alpha-blending weights computed during dominant-eye rasterization, avoiding a separate depth-rendering pass. An adaptive ROI generator localizes the required updates using reprojected image boundaries and optional connected center-hole detection. On DTU, Tanks and Temples, and MipNeRF-360, the method reduces the measured time of a sequential two-pass binocular reference by 15.5% to 28.8% and peak GPU memory by 6% to 11%. The corresponding affiliated-eye quality degradation is at most 1.3 dB PSNR, 0.02 SSIM, and 0.02 LPIPS, representing a measurable trade-off that requires application-specific perceptual validation. These results establish a practical efficiency-quality trade-off for controlled static-scene stereo rendering and motivate future evaluation under continuous motion and on physical VR hardware.