Papers

Optimal transport (OT) is widely used to align distributions and transfer labels between unpaired source and target data, but source-target composition shifts can cause rare classes to be systematically under-predicted even with high transport confidence. We identify a source of this failure in the transport marginal: under the standard uniform weighting of source points, each class has transport capacity proportional to its source frequency, which can be insufficient to meet its target demand even when separated well in the embedding space. We show that displaced mass is preferentially absorbed by high-capacity classes rather than geometrically similar classes, producing confident errors that are difficult to detect from the transport plan. Downstream read-outs, entropic smoothing, and marginal relaxation provide limited recovery, whereas matching the transport marginal to the target composition substantially improves label transfer. On single-cell data, the oracle composition-matched marginal raises macro-F1 from 0.322 to 0.623, and the best deployable estimator closes 69% of the oracle gap. Correcting the marginal also separates a coverage-dependent component of error from residual error associated with class separability, showing that transport capacity and representation geometry are distinct sources of transfer error.

Reinforcement learning (RL) is promising for spatial text-to-image generation, but existing work largely focuses on policy optimization, assuming accurate rewards and effective online rollouts. We observe in-domain gains with out-of-domain degradation, exposing two limitations: unreliable spatial rewards in open-world settings and rollouts lacking basic-to-complex progression. We propose a curriculum-guided RL framework. First, we introduce SpatialCritic, an agentic reward model equipped with a spatial perception harness that combines reusable verification guidance with specialized vision tools. We then construct spatial preference datasets through targeted counterfactual perturbations and perform agent-harness alignment to improve tool selection and evidence integration efficiently. Second, curriculum learning organizes shared foundational capabilities and their compositional dependencies in a capability graph for mastery-guided rollouts, periodic review, and targeted remediation. On SpaRW-Eval, SpatialCritic achieves 95.1% verification accuracy, outperforming 320B GLM-5.3-Flash with a 40x smaller 8B backbone and raising average baseline scores from 78.4 to 83.9 on SD3.5-Medium and 83.2 to 86.5 on BAGEL. Project page: https://xiaofeng-tan.github.io/projects/spatialcritic/

We build a labor market in which AI systems enter as workers: they apply for jobs, pass screenings, get hired, and get dismissed, alongside humans. Firms post vacancies, workers search with friction, and product demand slopes downward. Across 30 seeded runs per configuration, AI entry at 70% of the human wage raises unemployment by 4.1 percentage points (95% CI 3.5 to 4.6) and leaves 12.2 fewer humans employed (CI 10.5 to 13.9). Layoffs dominate when AI is much cheaper than humans: the layoff margin accounts for 7.2 of the lost jobs and reduced hiring for 5.0, though most dismissed workers find work again. A wider price gap reduces displacement, because cheap AI makes firms expand: at price parity, with zero dismissals, the unemployment effect is largest at 9.2 points (CI 8.6 to 9.9), all of it through hiring. That parity result survives cutting AI applications from five per period to one. Demand elasticity decides how many workers AI displaces. Screening changes who gets hired and leaves the displacement total unchanged.

Authenticated state transitions need proof engines that conserve memory, avoid repeated setup, and preserve request semantics across parallel execution. We present StateSync-GKR, a reusable Rust sumcheck/GKR core with a sparse-Merkle frontend, and connect its design mechanisms to controlled measurements. Sparse layer reduction and derived wiring reduce prover ownership and repeated verification work. Cube/affine fusion and parallel path constraints keep the circuit schedule and proof-size growth compact. Reusable preparation and indexed parallel jobs amortize setup while maintaining independent results. Three-state records, strict original-request decoding, and separate core/model interfaces expose the application and assurance boundaries. With circuit, field, transcript and prover driver held fixed, sparse reduction lowers additional requested allocation 3,242-fold and peak process resident memory 89.46-fold relative to StateSync-GKR's test-only dense reference for a two-layer mixed circuit of width 4096. Direct depth-24 fresh/prepared measurements show 3.46-4.45-fold lower per-request proving-path latency. CPU and full-proof delivery studies distinguish useful parallel work from queueing and return-path costs, retaining all outcomes and latency budgets. The evaluation supports larger circuits within finite RAM, lower repeated-request cost, and explicit deployment choices for this artifact. It preserves the cryptographic claim boundary of the existing construction.

Synthesizing believable 4D hand-object grasping sequences is important for character animation, extended reality, and embodied agents. Grasping requires a hand to approach, contact, and lift or manipulate an object coherently. Existing synthesis methods often model only the final static grasp or rely on additional conditions, such as language, target grasps, or object trajectories, to specify the interaction. We instead study the underconstrained problem of generating a complete grasping motion from a single initial hand-object state. Our framework decouples hand-motion generation from object-motion recovery. Given an object point cloud in the initial wrist frame and the initial parameterized hand configuration, conditional flow matching predicts a sequence-level contact map and a hand pose at each normalized sequence time. This time-indexed formulation avoids the error accumulation of autoregressive rollout while representing the complete motion. We then infer an attachment frame and recover rigid-object motion through training-free, contact-guided weighted registration. We evaluate on held-out DexYCB objects and unseen object geometries reconstructed from in-the-wild videos by Open-CHOIR. Compared with LatentHOI, our method produces smoother hand and object motion in every setting, matches or improves on its contact and penetration metrics in the wild under a shared initialization, and is about 30x faster per generated frame. In a 15-participant study, our motions were preferred in roughly two thirds of (forced-choice pairwise) comparisons. Precise contact closure on novel geometry, however, remains a key open challenge.

Indoor human perception is the foundation for smart homes and healthcare. However, RGB cameras raise privacy concerns in private indoor environments, while low-resolution thermal cameras provide limited spatial and semantic information. Large-scale indoor thermal datasets and real-world deployments remain limited. Here, we introduce Indoor RGB-T, a large-scale paired RGB–thermal dataset for indoor human perception. The dataset covers 20 indoor rooms and contains 90,576 80x62 thermal frames, 87,016 temporally matched RGB–thermal pairs, and 115,557 annotated human bounding boxes. We establish benchmarks for robust thermal occupant-state detection with 0.75 mAP and occupancy estimation with an accuracy of 0.847 in unseen rooms. We further evaluate RGB-to-thermal and thermal-to-RGB translation, achieving a temperature MAE of 0.654 C and an R2 of 0.923. Finally, we deploy the thermal perception model on a commercial sleep-monitoring system in the real world. Field testing with 100 participants and deployment of approximately 1,000 devices further demonstrate its practical feasibility. We identify practical challenges that motivate future research directions, including environmental thermal interference, sensing range and multi-person occlusion. The code, trained models and partial dataset are available at https://github.com/kailaisun/RGBT and https://huggingface.co/skl24/RGBT.

We introduce stochastic physics-informed neural networks (SPINNs) for stochastic boundary-value problems (SBVPs) with random operators. The method enforces physics through a structural probabilistic coupling: a common Gaussian stochastic germ drives both the SBVP random operator and a manifold-based stochastic neural architecture. The stochastic neural network is non-feedforward and intrinsically random. A latent Gaussian field and an inhomogeneous Poisson point process on a compact, boundaryless, multiply connected manifold generate random neuron locations, geodesically local sparse connectivity, and a sparse random weight matrix, all governed by a low-dimensional hyperparameter. For deterministic inputs, the network output is random and can represent non-Gaussian random operators. Training is performed in observation space: SBVP simulations produce random observables, while the SNN defines a predictive conditional probability density function. The supervised objective combines data fidelity, through negative log-likelihood, with a cross-entropy alignment term relative to the SBVP-induced conditional distribution. The resulting target is a convex mixture of observation-induced and SBVP-induced distributions, with a dimensionless parameter controlling robustness to model–data mismatch. The shared stochastic germ yields common-random-numbers Monte Carlo estimators and reduced-variance gradients. The method uses only evaluations of the SBVP solution mapping, without differentiating or modifying it, and avoids PDE-residual or boundary-penalty losses. A stochastic elliptic problem on a periodic cylindrical surface illustrates the approach in SBVP-consistent and SBVP-misspecified regimes. A generalized-posterior formulation is also outlined for hyperparameter inference and posterior averaging without per-query reoptimization.

Claims of recursive self-improvement are easy to make and hard to falsify: did improvement come from re-using designer-provided mechanisms, or from mechanisms the system authored itself? We introduce a pre-registered, two-tier accounting: M1 counts machine-generated content instances within a designer-provided vocabulary, while M2 counts machine-authored mechanism types (new operators registered into the runtime's own vocabulary, with a held-out-validation certificate). We report the first audited M2 genesis events. In the primary event, depth-limited compositional search over elementary operators, judged by held-out R^2 on real NIST hydrogen Balmer measurements, produced the operator sq(inv(n)) = 1/n^2 – the Rydberg-level form – which no standard-library transform could express (held-out R^2: -0.546 best standard transform vs. 1.0000000 composed). A protocol flaw (independent variable built by inverting the very law under test) was caught in audit and repaired via an independent-label protocol; extrapolation to unseen levels (n=8,9 trained on n<=7) attains relative error ~10^-6, four to six orders beyond the best standard operator. A second event independently recovered sqrt(inv(a)) – Kepler's velocity law – from JPL ephemeris vectors. Also incorporated: an audited compounding channel (first domain-level measurement: 1.109x accuracy ratio on a real held-out domain) and blind, decurated genesis exams whose honest tally is zero. The Kepler event passes line audit; the hydrogen gap reproduces on He II; the certificate is threshold-stable. Against eleven prior systems, the contribution is the measurement and governance of machine-authored mechanisms, not the search algorithm or rediscovered physics. Limitations: exams were curated by agents who knew the textbook answer, triggers manual, grammar observer-injected; both events demonstrate capability to author, not yet autonomous genesis.

We present a learning-based framework that enables a full-scale bipedal humanoid to sprint at over 7 m/s with motion-prior-guided gait and perform aggressive cornering at high speed with a pronounced trunk lean of up to $25^\circ$. Achieving this combination is challenging: above approximately 4 m/s, periodic foot impacts induce severe, high-frequency yaw-rate oscillations intrinsic to high-speed gaits. This high-frequency temporal structure corrupts the history of proprioceptive feedback that flat-MLP policies rely on, while rendering conventional yaw-rate tracking rewards counterproductive, as they fight against the robot's natural oscillatory dynamics. Moreover, a single style prior shared across skills cannot tell which skill is commanded and inherently compromises the low-speed skill fidelity. To overcome these limitations, we adopt a causal multi-head attention (MHA) module to explicitly model the high-frequency temporal feedback. In place of the oscillatory yaw rate, we design a heading-direction reward that supervises only the low-frequency velocity direction, allowing agile turning at high speed without suppressing natural gait oscillations. We further introduce skill-conditioned multi-adversarial-motion-prior (MAMP) discriminators that condition the style reward on the commanded skill. Ablation experiments confirm that each mechanism is essential: replacing structured temporal encoding with a flat-history MLP caps the top speed; reverting to yaw-rate tracking prevents high-speed turning; and a single shared discriminator makes in-place turning collapse into a quasi-static stance. Our framework bridges the gap between raw sprinting speed and reference-motion fidelity, demonstrating stable high-speed sprinting and aggressive cornering in both simulation and real-robot deployment.

As a key extension mechanism for agent systems, Agent Skills package specialized capabilities for reuse by LLM agents. An agent first retrieves candidate skills based on skill documentation and then relies on their metadata to make the final selection. As third-party skills proliferate on insufficiently vetted open registry platforms, the security risks posed by malicious skills become increasingly prominent, but existing attack research still focuses primarily on the potential harm caused after their execution. The limited related studies typically examine skill retrieval or selection in isolation and have yet to cover a complete end-to-end attack chain. To address this research gap, we find an end-to-end attack surface arising from the process-wide influence of metadata. Based on this finding, we propose MetaCascade, an end-to-end metadata-only poisoning framework. MetaCascade first generates diverse malicious skill candidates through multi-view semantic expansion, then uses tasks and black-box competition feedback to analyze the competitive relationships among malicious candidate skills and iteratively optimize malicious metadata, thereby improving the target skill's end-to-end attack effectiveness. Under a unified evaluation setting spanning four datasets and two agents, Hermes and OpenClaw, MetaCascade achieves state-of-the-art attack performance, with its average attack success rate (ASR) and its average ASR under four defense settings exceeding the strongest baselines under the corresponding settings by 35.53 and 34.65 percentage points, respectively. Our code is provided in the supplementary material.

Branch-and-bound (BnB) solves mixed-integer linear programs by constructing and exploring a search tree. Node selection and branching are two recurrent decisions that directly determine the tree. Learning-based approaches typically optimize either decision in isolation and condition on a mostly local view, leaving the coupled evolution of the search tree insufficiently modeled. This paper proposes Seq-BnB, a sequence-structured framework that learns branching and node selection from a shared global representation of the evolving BnB process. Seq-BnB serializes node creations, node updates, node-selection events, and branching events into typed tokens, producing a causal event sequence of the search trajectory. A self-attention encoder summarizes this global search history, a bipartite graph neural network encodes the current LP relaxation, and context-conditioned decision heads score branching variables and open nodes. To reduce distribution shift between expert demonstrations and learned policies, Seq-BnB is trained with DAgger-style data aggregation. On four MILP benchmark families, Seq-BnB consistently processes fewer BnB nodes than heuristic and learning-based baselines, with strong solution times on both standard and larger transfer instances. While this paper evaluates Seq-BnB instantiation for branching and node selection, it accommodates additional solver decisions, such as cut selection, by introducing new action tokens and decision heads.

Speech representation learning requires a discrete modeling interface while preserving high waveform fidelity. Existing approaches rarely achieve both: discrete tokens ease modeling but lose fine-grained acoustic information, while continuous latents preserve fidelity but require specialized generative objectives. We introduce SemiCodec, a novel Semi-discrete neural speech Codec with synchronized discrete tokens and continuous latents. Direct joint optimization may create a reconstruction shortcut through the continuous pathway, leaving the discrete tokens insufficiently grounded. To address this issue, we propose a Preserve-then-Ground training paradigm that first establishes a high-fidelity synthesis space and then grounds SSL-guided discrete tokens within it. Experiments show that SemiCodec outperforms fully discrete codecs in reconstruction quality and intelligibility while remaining competitive with continuous representations in acoustic fidelity and speaker preservation. Audio samples are available at https://pennyw1-se.github.io/SemiCodec-Demo-Page/

Robust manipulation under uncertain object dynamics and geometry remains a core challenge in real-world robotics. Policies trained under fixed assumptions often degrade when object mass, friction, scale, or shape vary. Embedding-based adaptation methods such as Rapid Motor Adaptation (RMA) address this by conditioning actions on latent representations of environment dynamics inferred from interaction history. We investigate whether this paradigm scales from single arm settings to coordinated bimanual manipulation, where higher dimensional control, coupled contacts, and shared object forces introduce additional complexity. We evaluate bimanual RMA on three contact-rich ManiSkill tasks with randomized YCB object properties. Bimanual RMA, using observation-action history and dual wrist depth images, retains privileged policy performance on bimanual picking and lifting, while an otherwise matched stationary PPO policy without latent conditioning achieves low success; all methods remain limited on long-horizon stacking. We further demonstrate direct sim-to-real transfer on a dual Franka lifting task without real-world finetuning. Together, these results suggest that latent conditioning provides useful structure for scaling robust control to coordinated bimanual systems, while longer horizon tasks require additional temporal structure.

This paper presents a reproducibility study of “Boosting the Visual Interpretability of CLIP via Adversarial Fine-Tuning”, published at ICLR 2025, which proposes an unsupervised adversarial fine-tuning (AFT) method with norm regularisation to enhance the visual interpretability of CLIP's image encoder. We attempt to reproduce the key claims regarding improved saliency map quality, increased concept alignment, transferability to out-of-distribution datasets, and the trade-off with zero-shot accuracy. Beyond reproduction, we propose a saliency-guided regularisation extension that introduces an Energy Pointing Game loss, directly supervising the spatial alignment of Simple Gradient saliency maps with target objects. We evaluate our extension across a range of saliency-loss weights and show that explicit saliency supervision \rev{substantially} improves localisation metrics at a modest cost: the reduction in zero-shot accuracy and adversarial robustness is small at the lowest saliency-loss weight ($w_s=0.2$) and moderate at the strongest setting ($w_s=0.6$). We restructure the codebase for configurable, systematic experimentation.

The rapid expansion of generative AI is driving computing infrastructures toward interconnected AI data centers. Multi-band optical networks have become the backbone of such connectivity. To accommodate increasingly dynamic traffic demands, these networks require continual resource re-optimization to improve resource utilization and reduce service blocking. However, multi-band transmission amplifies inter-channel stimulated Raman scattering(ISRS), inducing nonlinear coupling among services. This coupling complicates re-optimization, as local adjustments perturb the global power profile, creating interdependent optimization decisions across services. Moreover, the nonlinear interactions vary with the subset of services selected for re-optimization, and inappropriate selection may reduce re-optimization effectiveness or diminish achievable benefits. To address these challenges, we propose a Stackelberg Game with Multi-Agent Transformer (SG-MAT) approach for ISRS-aware resource re-optimization. SG-MAT employs a leader-follower structure, in which the MAT-based follower models nonlinear coupling and generates coordinated channel reallocations, feeding the utilization improvements to the leader. Using this feedback, the leader identifies critical service subsets, approximating a Stackelberg equilibrium to guide global decisions and enabling consistent and efficient re-optimization. Simulation results show that SG-MAT achieves the highest utilization improvement and reduces the blocking ratio by approximately 30% under moderate traffic loads, with computational complexity comparable to benchmarks.

Office workflows are a demanding testbed for self-improving agents because their deliverables must be correct, natively editable, and mutually consistent. A central question is whether gains on feedback tasks reflect reusable procedures rather than task-specific fixes. We introduce EvoCowork, a 240-task benchmark for evaluating harness-level recursive self-improvement across four office modalities, with model weights held fixed. The benchmark covers presentations, documents, spreadsheets, and cross-office workflows, and scores submitted artifacts for content, native structure, formulas, cross-file consistency, and visual quality where needed. Its protocol separates feedback, revision selection, and final testing: methods learn from single-modality tasks, then are evaluated on unseen single-modality tasks and cross-office workflows under a shared initial harness and explicit budgets. In static evaluations of two models and four harnesses, the best configuration scores 42.25 overall and 30.62 on cross-office tasks. Starting from the same MSA harness with GLM 5.3, ACE and AHE improve in-domain scores by 4.90 and 2.64 points, respectively, but change cross-office scores by only +0.03 and -1.72. Thus, gains on the file types that provide feedback do not necessarily transfer to coordinated workflows. EvoCowork makes this distinction explicit while recording the capability, transfer, and cost of harness evolution. Code and task packages: https://github.com/DeepThinkingZhouLiu/cowork-evolution-benchmark.

Recent alignment-free Text-to-Speech (TTS) models achieve high synthesis quality by removing explicit alignment modules and simplifying training. However, they often struggle in cross-lingual scenarios due to differences in character durations across languages, leading to duration mismatch and degraded speech quality. Existing approaches typically address this issue using explicit duration predictors, increasing model complexity. Systematic evaluation of TTS performance for Indian languages in cross-lingual settings remains under-explored due to the lack of standardized evaluation benchmarks. In this work, we construct a cross-lingual evaluation benchmark covering English and nine Indian languages and propose a language-aware inference-time duration estimation strategy for alignment-free TTS that incorporates language-specific duration-per character statistics without retraining or architectural modifications. We further develop heuristic formulations that refine duration estimation based on language-dependent duration variations. Experiments on bilingual and multilingual A-DMA models demonstrate improved speech naturalness, intelligibility, and speaker similarity while reducing duration mismatch.

Artificial intelligence is increasingly used to support product management tasks. At the same time, AI-native research and development (R&D) may increase software realization capacity. Organizations may realize software faster than they can identify, qualify, and reconsider what should be realized. This paper asks how product management should be re-envisioned under these conditions. We synthesize research on software product management, product learning, human-AI collaboration, and the Product Management and R&D boundary. We propose a vision in which AI becomes a persistent participant in product work. The vision covers sensing, exploration, decision-making, realization, and learning. We propose six principles and make the vision tangible through an operating model grounded in human professionals, AI personas, agents, skills, and a shared product context. We further argue that AI-native Product Management and AI-native R&D can form a continuous product-learning process. Finally, we identify four AI-specific research directions that require empirical investigation.

Agentic AI moves generative AI applications toward systems that coordinate reasoning, enterprise context, model inference, and external actions. Integrating these capabilities into enterprise software introduces diverse architectural concerns, from orchestration, knowledge and memory, and model access to tools and actions, security, runtime infrastructure, and evaluation. Existing research and industry architectures address many of these concerns but differ in scope, abstraction, responsibility organization, interaction representation, and assumptions about which capabilities are required. This paper presents a technology-neutral reference architecture for enterprise agentic AI integration. We synthesize architectural capabilities from research publications, industry architecture guidance, and interoperability specifications by architectural purpose, organize them into ten responsibilities, and define boundary invariants, typed cross-responsibility interactions, and variation points that distinguish responsibilities from condition-dependent capabilities and replaceable realization mechanisms. We instantiate the architecture as an ESG portfolio-analysis and pre-trade compliance agent over an existing service-oriented ESG metric computation and reporting system, and complement the case with a mapping of an independently published agentic architecture. The case realizes seven of the ten responsibilities; different questions take different interaction paths, controls activate only under their conditions, and the probed boundary invariants hold. The independent architecture maps onto the proposed responsibilities without requiring an additional one. These results provide initial evidence for the architecture's organization and applicability rather than its completeness. The deployment and recorded results are available as a replication package.

State-of-the-art beat tracking is based on neural networks that model beats and downbeats as individual events, often followed by a separate Dynamic Bayesian Network (DBN) enforcing musical consistency. We propose a novel architecture that combines deep learning with differentiable theory-based modules: Specifically, we design a system that first predicts a tatum grid, then groups tatum events to beats and downbeats, explicitly modelling multiple options for the current tempo and time signature in a bar-pointer-like fashion. Our approach improves continuity metrics compared to existing DBN-free systems and is more versatile than the de-facto standard DBN, but still falls behind the best DBN-based methods on average. Given the many design choices and hyperparameters involved, we assume we have not yet explored the full potential of this idea and publish our code and invite others to explore this further.

This report studies passage retrieval and re-ranking on the MS MARCO benchmark using lightweight Qwen3-0.6B models. Across three experimental settings — BM25-then-reranking task, corpus-wide dense retrieval task, and dense retrieval then re-ranking task — the results demonstrate that competitive ranking performance can be achieved without complex architectural modifications, custom loss functions, or cross-encoder distillation. Instead, substantial gains stem from data-centric strategies: corpus-targeted continued pre-training, rigorous data curation, hard-negative mining, training–inference distribution alignment, and weight merging via Model Soup. In particular, Model Soup delivers marked performance gains while preserving the inference efficiency of a single model. These findings highlight how data curation and weight merging can push sub-billion-parameter models to state-of-the-art performance. My models can be downloaded from Hugging Face: https://huggingface.co/shuguangh/models

Industrial IoT sensors produce continuous, high-volume data streams that predictive maintenance needs to analyse in real time. Cloud-centric architectures send all raw telemetry to central servers, which costs latency, bandwidth and resilience. This paper presents a hybrid cloud-edge architecture for manufacturing predictive maintenance built on AWS IoT Core and AWS IoT Greengrass v2, with local machine learning inference at the edge and selective cloud synchronization. We deploy two configurations on real AWS infrastructure and compare them: a cloud-only baseline (Configuration A) and the proposed hybrid edge architecture (Configuration B). We measure end-to-end inference latency, bandwidth consumption and inference accuracy. Configuration B cuts cloud-bound bandwidth by 86.8% (63.6 KB to 7.2 KB per 200-reading window) and decision latency by 256x (23.1 ms cloud round trip to 0.09 ms local inference). At the edge, with no cloud involvement, it keeps an anomaly-class F1 score of 0.84 and 91% recall. The evaluation also instruments system uptime and Stream Manager queuing under cloud disconnection; the quantitative disconnection experiment is left as planned work. Our review of the literature points to four gaps that this work addresses: the lack of empirically validated Greengrass v2 deployments for predictive maintenance, unquantified bandwidth savings from selective edge synchronization, unmeasured resilience under cloud disconnection, and the open MLOps feedback loop at the edge.

Dengue is a viral infection caused by the dengue virus (DENV) and a major public health concern in Bangladesh, where symptom overlap with other febrile illnesses complicates early diagnosis. This study compares Logistic Regression, Random Forest and XGBoost to predict dengue from clinical and hematological data using two Bangladeshi hospital datasets (2024, n=1,511; 2025, n=1,283) with SMOTE. Extended models outperformed benchmarks within 2024 (Random Forest ROC-AUC 0.640 to 0.661), with RDW-CV the most consistently influential added predictor. 2025 benchmark performance was higher (ROC-AUC 0.904), unexplained by class imbalance and possibly reflecting data quality. External validation is needed.

Three-dimensional (3D) velocity model building (VMB) remains computationally challenging with conventional approaches and native 3D neural networks, largely due to the prohibitive memory and training cost of full 3D formulations. Therefore, we introduce a depth-progressive framework that achieves 3D VMB using 2D generative diffusion models through a depth-as-channel formulation, in which the depth dimension of each 3D velocity patch is mapped to the channel dimension of a 2D U-Net. This allows the model to synthesize overlapping depth patches sequentially from shallow to deep while conditioning the prediction of the deeper patch on the shallower one, as well as on any available geophysical constraints, including well logs and structural attributes. During training, paired shallow-deep patch pairs with randomized overlaps are used to teach the network how deeper velocity structures relate to shallower information, and a classifier-free guidance strategy enables the model to handle missing constraints gracefully. At inference, starting from a shallow velocity prior, the model recursively generates deeper patches in a top-down manner, and a depth-attenuated Gaussian blending scheme merges overlapping predictions into spatially coherent 3D volumes while accounting for the progressive accumulation of uncertainty at greater depths. Numerical experiments on both in-distribution benchmark models, including Overthrust, SEAM Arid, and SEG/EAGE, and the out-of-distribution Marmousi model demonstrate that the method effectively propagates shallow velocity priors downward and produces high-quality 3D velocity volumes across a range of geological settings and conditioning scenarios. Compared to a 3D benchmark of equivalent architecture, the proposed method significantly reduces parameter count, training cost, and inference cost, while maintaining superior VMB accuracy.

Enterprise AI agents can execute altered versions of approved actions, concurrently reuse the same permission, or retry operations whose responses were lost. These failures arise when approval and resource execution lack a shared contract. KedgeFlow specifies language-independent contracts for trusted controllers to authorize state-changing operations and privileged gateways to enforce that authority independently of agent reasoning. Inspired by OpenFlow, it connects policy checks supported by evidence, signed permission for an exact action, a shared allowance that can be consumed only once, target-side conditions for applying the change, and retained outcome records. Under trusted issuance of exact-action authority, two conditional properties establish at most one successful claim per allowance and link every governed dispatch to a matching grant, claim, and subsequent dispatch authorization, even when the agent is compromised. A reference implementation exposes this execution path to agent systems through the Model Context Protocol (MCP). In the single-resource evaluation, 6,560 concurrent ledger claim attempts yielded exactly one successful claim for each of 82 allowances. Boundary tests rejected unauthorized and altered requests before consumption. A 32-call gateway race produced one committed mock effect, and a retry after a lost response produced no additional dispatch. Deliberately permissive policy nevertheless authorized an undesirable effect, exposing the limits of execution authorization. Evaluation uses three members of the etcd coordinated key-value store on one host, synthetic authentication and authorization inputs, and a mock target that rejects stale requests. Distributed reservations, enforcement of every production access route, native crash recovery, exactly-once effects at real targets, and interoperability between independent implementations remain untested.

Influence functions provide an efficient alternative to retraining for assessing the effects of removing or reweighting training data. For groups, however, the standard first-order estimate reduces individual contributions to a sum that can conceal substantial differences among members, including opposing effects that cancel. We establish a Bregman centroid formulation of the linearized group influence objective, interpreting this aggregate as a single representative and using Bregman information (BI) to quantify the variation it omits. Extending this formulation to multiple clusters reveals distinct contributions whose sum recovers the original estimate. We further propose an estimator that jointly optimizes the weights of these cluster contributions, rather than simply summing them. Experiments uncover cluster-specific influence patterns and a positive association between target-specific BI and approximation error. The proposed estimator achieves higher $R^2$ than standard group influence in predicting target changes under the nonlinear proximal Bregman response function. Simplified clustering and correction variants reduce computational cost. The centroid view thus explains what additive group influence leaves out and provides a basis for using that information to improve estimation.

Agentic approaches for automated test generation can reach high-quality results, but they improve a given test suite incrementally, so a weak starting point may lead to many iterations or insufficient tests. To address this, we present Testuary, which provides the agentic phases with an improved starting point. Testuary first generates multiple test suites through independent, parallel zero-shot requests, checks and repairs them deterministically, and combines them into a single suite with a novel structural merging approach. A runtime-weighted set-cover reduction removes redundant tests without losing covered lines, branches, or killed mutants. After that, two agentic phases target the remaining gaps in coverage and mutation score. We compare Testuary with established search and LLM-based test generation approaches. The non-agentic first phase alone already significantly outperforms the current state-of-the-art. After the agentic phases, Testuary achieves on average more than 99.9% line and branch coverage as well as a mutation score of 98.6%, significantly outperforming all compared baseline approaches. Testuary needs fewer model requests and its test suites are on average smaller and faster than those of the compared agentic approach.

Evaluating autonomous agents requires examining whether they can translate goals into coherent action across extended interactions. In persistent environments, this requires coordinating interdependent actions under incomplete observations, accounting for delayed effects, and adapting as earlier decisions shape subsequent opportunities. We introduce ASIWorld, a survival sandbox that combines persistent world and character state with character-scoped observations and a programmable asynchronous interface to study sustained goal execution. Agents pursue interdependent production and exploration tasks through direct actions or agent-authored programs that continue running between model calls. The evaluation assesses task success, the attainment of development achievements, and survival costs, complemented by an analysis of execution behavior. In an exploratory study of nine agent configurations using a common harness, eight complete the production task and six complete both tasks. Analyses of execution trajectories and performance across difficulty levels reveal different preparation, combat, and recovery behaviors among configurations with similar task outcomes. Incomplete preparation is associated with stalled progression, while configurations that complete the tasks differ in survival costs and the fulfillment of additional achievement criteria. These findings illustrate the value of assessing sustained goal execution through both task outcomes and the behaviors and costs associated with achieving them.

Agent applications are evolving into workflows composed of large language model (LLM) calls and tool invocations, termed modules. Existing distributed agent systems typically adopt a disaggregated architecture, deploying different modules on separate devices. While this enables pipeline parallelism, imbalanced module latencies introduce severe pipeline bubbles that limit throughput. A natural alternative is an aggregated architecture that co-deploys all modules across all devices, eliminating bubbles by keeping every device continuously active. However, this introduces request blocking: short requests are forced to progress in lockstep with longer ones in the same batch, and newly arriving requests must wait until the entire ongoing batch completes the full workflow. To address this, we propose AgentWeave, an efficient distributed serving system for agent applications built on the aggregated architecture. Its core mechanism, flow decomposition, decomposes long agent requests into fine-grained execution units while preserving agent semantics, allowing short and newly arriving requests to proceed without being stalled by long-running ones. Complementing this, a flow-adaptive scheduler dynamically balances the throughput gains of decomposition against its scheduling overhead. Experiments across four representative agent applications demonstrate that AgentWeave improves throughput by 1.81x, reduces average latency by 2.45x, and reduces P90 latency by 2.04x over state-of-the-art baselines.

End-to-end driving policies can achieve strong task performance while offering limited control over their driving style. Driving style describes how a vehicle accelerates, brakes, and maintains distance. Policies trained without explicit preference conditioning lack a direct mechanism for adjusting these behaviors at inference. We propose YOUDrive, a vision–language–action planner for continuous and composable driving-style control. Each teacher's behavior is distilled into a task vector, a learned parameter update that induces a style direction in the planner's representation. These directions can be scaled and combined at inference without retraining the backbone. Conditioned on these directions, a flow-matching decoder models a multimodal trajectory distribution and generates kinematically feasible motion alternatives. We introduce the Style Alignment Score (SAS) to describe human-referenced kinematic behavior after safety and task gating. On NAVSIM navtest, a single coefficient monotonically controls assertiveness across six teacher-derived personas, while PDMS remains above 0.90 across the tested individual and blended configurations, reaching 0.954. Further analyses reveal systematic policy-specific kinematics after controlling for scene context, whereas the evaluated discrete style labels provide limited additional explanatory power. Code, checkpoints, and the metric will be released.