Papers

We design auctions for the sale of a single item with unlimited supply given a single prediction of the revenue-maximizing uniform price. This departs from prior work on auctions with predictions which typically assumes predictions of every bidder's value. Our main result is a characterization of the Pareto frontier for consistency and robustness attainable by any universally truthful auction. We show that a mechanism that randomizes between posting the predicted price and conducting an optimal prior-free fallback auction is Pareto-optimal. We then extend our results to achieve graceful degradation of revenue as a function of the prediction accuracy. Finally, we study how such a prediction can be obtained from historical market data through the lens of learning theory. Together, our results give an end-to-end account of how a price prediction can be learned and used robustly to maximize auction revenue.

Public institutions increasingly procure AI systems whose design they cannot inspect or change. In higher education, proprietary Early Warning Systems (EWS) leave colleges with few options beyond adjusting model outputs to address inequity. This raises the question of how fairness work is coordinated among vendors, institutions, advisors, and students with unequal power to change these systems? Using student records from a public college in Ontario, Canada, we evaluate six post-hoc fairness interventions on a research EWS under simulated procurement constraints. We compare fairness, accuracy, and demographic disparities, introducing error-type profiling to trace how interventions redistribute false positives and false negatives. Interventions redistributed disparities without consistently reducing them. Two implementations favored already-advantaged groups because they used group size to define disadvantage; small, marginalized groups remained poorly served. These findings show how procurement constraints and implementation choices shape the possibilities for fairness work. We call the resulting condition fairness theatre; dashboard metrics converge while groups' error burdens persist or worsen.

Defining a weighted mean over probability measures under probability metrics is a central tool in probabilistic machine learning. Under the Wasserstein metric, these are called Wasserstein barycenters. While most approaches compute barycenters for a fixed weight vector, approximating the whole family of barycenters over the simplex, which we call the Wasserstein simplex, remains underexplored. We refer to this problem as Universal Barycenter Approximation, and propose BaryFM, a flow matching model transporting the marginal measures into any barycenter in the Wasserstein simplex. Once trained, the network can draw samples from measures in the Wasserstein simplex through an ordinary differential equation. We validate our method on 4 downstream tasks: domain adaptation, generalization, Bayesian posterior aggregation and algorithmic fairness. BaryFM achieves the best average rank among 15 competing methods across 10 domain adaptation benchmarks, matching or surpassing non-universal solvers.

Machine-learning signals built from financial text treat what institutions say, and what the media repeat, as evidence about value. But whoever shapes a narrative may be trading against it. We study markets with three observable voices: institutional statements (Say), media repetition (Echo) and revealed positioning (Do). We ask when words should be followed and when they should be faded. In a linear-quadratic model of an informed institution that speaks and trades before a partly credulous crowd, talking an asset down while buying it is optimal exactly when $\varphi^2<2\lambda k<\varphi$. A distribution-free identity then shows that when the observable Say-Do covariance is negative, words carry negative predictive content and should be faded. For measurement, we derive (i) an exact factorised posterior over which articles are echoes, combining arrival times with embedding similarity; (ii) a return-aligned contrastive objective that attains its bound exactly when squared embedding distances are an increasing affine function of squared outcome distances, with the tightest loss-based certificate of which neighbour rankings survive imperfect training; and (iii) a path-signature statistic for who moved first. In a controlled market with known ground truth, echo sentiment predicts returns with a significantly negative sign in all 29 simulated markets, the rolling Say-Do correlation flags false-alarm events with an AUC of 0.90, and return-aligned embeddings organise headlines by consequence rather than topic. We also report where the tools fail.

Constantly evolving real-world knowledge necessitates models to be updated continuously. Especially in medicine, as clinical evidence changes over time, outdated knowledge can pose safety risks. Existing evaluations of knowledge integration focus on factual recall, offering limited insight into whether newly integrated knowledge is actually usable. Our benchmark MedKIT (Medical Knowledge Integration and Transfer) provides a granular evaluation of how models integrate and apply knowledge under realistic sequences of clinical updates. Each instance corresponds to a factual update derived from clinical evidence, paired with targeted probes that assess transfer across lexical variation, relational transformations, compositional reasoning, and open-ended operationalization, as well as locality tests for knowledge preservation. Using MedKIT, we conduct a large-scale empirical study of 12 knowledge integration strategies across 5 diverse models, including both general-purpose and medical LLMs. Our results reveal a consistent gap between recall and usable knowledge: while most methods achieve strong gains on the original update task and under lexical variation, relational generalization is limited, and no method yields meaningful improvements on compositional or operational tasks. These findings highlight a fundamental challenge in knowledge integration and position MedKIT as a testbed for developing methods that make newly integrated knowledge more consistently usable across tasks and contexts.

Instruction-guided video editing has made significant progress, yet existing methods use multimodal large language models (MLLMs) primarily as semantic encoders, so they often fall short in working with implicit edits that require causal or semantic reasoning. To bridge this fundamental gap in video editing, we propose ThinkV2V, a reasoning-driven framework for complex instruction-guided video editing, explicitly activating MLLM thinking before visual generation. At its core, ThinkV2V builds on a practical MLLM-to-DiT architecture to turn explicit thinking over the source video and instruction into refined conditioning signals for video editing. Further, we equip it with a dedicated training and inference recipe, combining Progressive Curriculum Training, which gradually cultivates the model from basic editing to reasoning-intensive cases, with Inference-Time Thinking Scaling, which iteratively refines candidate prompts and selects the most reliable one, to better elicit reasoning in challenging editing scenarios. We also curate the ThinkV2V-150K dataset and introduce ThinkV2V-Bench to support training and evaluation of video editing with implicit intent and causal reasoning. Experimental results demonstrate the state-of-the-art performance of ThinkV2V on both complex and standard editing scenarios, in which our 5B-scale DiT model substantially outperforms larger 10B-scale baselines.

A valid curvature upper bound need not justify either a robustness certificate or an intervention on an intrinsic predictor property. We demonstrate this distinction for a last-layer relative-flatness proxy used in both settings. First, empirical-risk stationarity does not eliminate pointwise first-order loss terms: at a finite global empirical-risk minimum, the retained certificate expression underestimates a loss increase by over $210\times$. We derive a globally valid, gauge-invariant feature-space repair. Second, common-row softmax shifts preserve predictions and the exact contraction while making the proxy unbounded. Even standard reference-class choices double it on average relative to the centered representation. For a single fixed-feature example with at least three classes, scalar retuning generically cannot align the induced probability updates. Row centering gives the orbit-minimized bound and restores value and full-model gradient invariance under this symmetry. Across 45 paired one-step tests on algorithmic and image models, amplified shifts separate raw-regularized predictors while quotient-regularized predictors remain aligned. Long-horizon CIFAR-10 experiments show substantial, reversible suppression of generalization, while evidence for selective delay after memorization is less consistent. Together, these results show that validity as a curvature upper bound does not by itself justify either inversion into a robustness certificate or differentiation into an intrinsic training intervention.

Random splitting can yield non-independent train–test subsets when a dataset contains related samples, as is common in certain applications such as biochemical studies. This leads to overly optimistic generalization estimates. Here, we introduce ReLaG, a modality-agnostic framework that models sample relatedness through a hierarchical latent-variable process and infers groups of related samples using proximity graphs and community detection to produce independent train–test subsets. Across molecular and protein datasets, ReLaG matches existing relation-aware methods while scaling substantially better, enabling splits at previously impractical dataset sizes. We further introduce a label-free procedure that adapts the splitting resolution to production data, aligning evaluation with the intended deployment setting. ReLaG's inferred groups provide a cheap estimate of effective dataset size, enabling diversity-aware dataset scaling. ReLaG is open source and can be installed with pip install relag.

GPT-6 Astra exhibits a remarkable ability to generate numerical robot actions, extending its role beyond high-level planning. To assess Astra's capabilities as general-purpose embodied policies, we conduct comprehensive evaluations across six domains, examining direct control, cooperation with learned policies, and feedback-driven adaptation. In gripper manipulation, Astra can correct task targets and prepare contact conditions for subsequent policy execution; hybrid control with {\pi}0.5 achieves 48% success on the evaluated RoboDojo subset. In dexterous manipulation, hybrid control achieves 50% success in ten experience-guided DexJoCo trials, while direct in-hand control struggles to coordinate finger contacts. In mobile manipulation, hybrid control reaches 38.7% success on the evaluated RoboCasa365. In navigation, Astra leads our local comparisons, reaching 92% success on RxR instruction following and 82% on HM3D object search, although search incurs substantial detours. In locomotion, dense motion-reference generation remains unreliable: none of five sequential attempts on a single obstacle course reaches the goal, despite improvements in stability and forward progress. In humanoid loco-manipulation, Astra exceeds baseline methods on 13 of 30 HumanoidBench tasks with pretrained whole-body controllers. These findings reveal a gap between useful task decisions and reliable physical control. Inference latency further constrains practical control: across 50 RoboDojo instances per condition, policy-assisted and direct control consume 624.8 million and 1.132 billion tokens. A 30-second locomotion run requires 250 model calls averaging 39.86 seconds each, with physics paused during inference.

Diffusion-based large language models (dLLMs) promise to break the sequential latency bottleneck of autoregressive agents through parallel decoding, but recent evaluations show this efficiency does not transfer to embodied agentic competence: dLLM-backed agents repeatedly fall into retry loops, re-issuing an action long after it has failed. We give a mechanistic account of this failure and a training-free remedy. We trace the retry loop to the adaptivity of masked decoding: the sampler commits the positions it is most confident about and defers the uncertain ones, and at a failure state the context already offers a confident fill for the deferred decision, i.e. the failed action itself, so the retry is committed without the failure feedback ever being confronted. We model the resulting distortion of the action distribution as a task-blind corruption: contextually salient actions (e.g., the action just taken) receive inflated probability by a factor that depends on the state and the action but not on the task. Under this model, we analyse an invariance proposition: the task-blind factor cancels exactly from the reverse conditional, i.e. the likelihood of the task given the state and a candidate action, which coincides with the task posterior of an idealized uncorrupted model. Masked dLLMs evaluate the reverse conditional natively, unlike autoregressive models, by masking the task tokens and denoising, at the cost of a few parallel passes per candidate. We instantiate the rule as Reflect Reverse and evaluate it on four multi-turn embodied benchmarks, where it improves task success and progression rates over forward-scoring baselines.

This paper presents a method for approximating occupancy distributions, a common probabilistic representation used in trajectory planning for autonomous vehicles operating in uncertain environments. The proposed method employs B-spline surfaces in conjunction with regularization techniques to ensure smoothness and differentiability. Interpreting the resulting approximation as an intensity function of a Poisson random field enables seamless integration of multiple occupancy distributions into a coherent risk representation, while retaining compatibility with the semantics of probability distributions. The method is tailored to optimal control problems (OCPs), where solvers benefit from gradient and higher-order derivative information. It also preserves information about the spatial and temporal structure of occupancy distributions, which is critical for handling dynamic obstacles. We demonstrate the feasibility of the approach in a trajectory planning scenario involving autonomous vehicles and moving obstacles with time-varying uncertainty. By enabling controlled risk acceptance, our formulation extends beyond conservative "no-collision" strategies and allows for admissible trajectories that would otherwise be ruled out. In our application scenario, we report a reduction in solver computational load of up to 50% through proper tuning of the regularization.

Language models increasingly use architectures that vary attention span and positional encoding across layers, such as applying RoPE with sliding-window attention and NoPE with global attention (SWA NoPE). However, how these choices shape in-context retrieval remains unclear. To study this question, we take a mechanistic view, tracing how positional encoding (PE) choice shapes the internal mechanisms models use for in-context retrieval. Across 22 open-weight models spanning eight families, we find that standard RoPE models rely primarily on positional retrieval, while PE hybrids shift toward semantic retrieval. We further show on a controlled pre-training ablation that confining positional encoding to local layers produces this semantic shift, degrading representations of positional information. Finally, we show that the reported long-context gains of PE hybrids mask a retrieval trade-off: SWA NoPE improves over RoPE on multiple-target retrieval and QA, but degrades when distinguishing competing keys. We show that these behavioral differences better track the mechanism shift from positional toward semantic mechanisms than a uniform improvement in long-context retrieval.

The security of industrial control systems (ICS) is important. Yet most ICS security efforts focus on the detection of ICS attacks, with much less attention to the recovery after detection. In this paper, we address this underexplored area by jointly auditing the detection and recovery of ICS. Specifically, we define the too-late-to-recover (TLTR) vulnerability, which allows an attack to drain the available recovery margin before being detected, such that the subsequent recovery procedure will fail to bring the ICS back to a safe state due to the insufficient margin. To audit an ICS for TLTR vulnerabilities, we develop RISK, an automated framework that discovers and validates possible TLTR attack scenarios. RISK holistically models and analyzes, statically and dynamically, the PLC control logic, attack detection policies, recovery procedures, and operational behaviors of an ICS to generate TLTR attack scenarios with concrete attack parameters. We evaluate RISK on three ICS testbeds as well as a real-world fertilizer production plant. Across the three testbeds, a total of 392 TLTR attacks are generated and confirmed, whereas only a small fraction of them can be discovered by existing ICS vetting tools. In the real-world plant, RISK identified a critical TLTR vulnerability which was validated by plant engineers.

This work evaluates the direct transfer of a co-evolved communication protocol from a 2D simulation to a 3D physical environment, without retraining the network weights. Two e-puck-type robots, controlled by a GRU network with residual connection, were evaluated in a food-seeking task with social signaling. The sensory and motor translation layer required three corrections for stable physical operation, including the calibration of a hunger term based on a measurable asymmetry in the trained residual weights. Even with these corrections, the transfer was partial and asymmetric: one agent reached the food source in one of thirty tested seeds, while the other did not reach it in any. Task success was measured by both agents reaching the food area. An additional experiment incorporating explicit directional information in the social channel produced observable changes in the trajectory of the receiving agent and improvements in several specific cases. However, these improvements were not enough to allow the second agent to reach the food source, suggesting that the limitation may not be explained solely by signal translation, but also by the ability to navigate under the new physical constraints. The results suggest that successful transfer of emergent communication may depend not only on preserving the signaling process itself, but also on preserving the ecological and navigational conditions under which the protocol evolved.

Scaling laws for optimization against reward models in AI alignment have pinned down how performance depends on optimization effort—measured by a KL-divergence budget relative to a reference policy. Beyond a certain budget, over-optimization (or reward hacking) can arise: because we optimize against a proxy reward model (distinct from true rewards), performance can plateau or degrade. Naturally, the proxy reward's accuracy depends on how much preference data (often in the form of pairwise comparisons) was used to train it. However, existing research does not cleanly identify how performance jointly scales with the amount of training data and the divergence budget. Our main contribution is to provide an empirically accurate and theoretically grounded scaling law in such context. Performance roughly scales as $\Theta(\sqrt{\min\{\log(M),K\}})$, where $M$ is the number of comparisons in training data and $K$ is the policy's divergence budget. We develop an information-theoretic model to establish this upper bound and prove it is tightly achievable through a constructive procedure. Informed by this, we conduct extensive empirical evaluations using a real-world annotation setup, whereby a large 70B gold reward model generates feedback data and proxy reward models are trained from less capable models (0.6B to 4B). Our scaling law provides an excellent fit (R2 from 97% to 99%), outperforms alternative specifications, and remains robust across model sizes, noise, and optimization procedures (best-of-$N$ or policy tilting). Our evidence suggests that reward optimization is analogous to a surprisingly simple selection task: choosing from a sequence of IID Gaussian random variables using noisy preference feedback.

Stereoscopy is fundamental to virtual reality (VR), providing depth perception through binocular viewing. Recent advances in 3D Gaussian Splatting (3DGS) enable high-quality novel view synthesis, making it well suited to immersive VR. We render 3DGS reconstructions stereoscopically and evaluate them in a head-mounted display, replicating how they would actually be viewed in VR. Real-world capture provides only a limited number of views, and under this constraint 3DGS reconstruction often produces localized floaters and misplaced structures. Standard metrics miss these localized artifacts, which become salient under stereoscopic viewing, where geometry is placed at the wrong depth. We investigate whether standard image-quality evaluation reflects the perceptual quality of 3DGS reconstructions under reduced capture. We compare SfM-only baseline with a union initialization that combines SfM with a dense VGGT network. All other training components are held fixed, isolating the effect of initialization coverage. We conduct a user study comparing preferences under monoscopic and stereoscopic HMD viewing, and test whether image-quality metrics predict the observed preferences. Monoscopically, preference for the more consistent reconstruction is weak, reaching 58.4% overall. Stereoscopically, the same preference rises to 78.2% and is consistent across all participants, while image-quality metrics (PSNR, SSIM and LPIPS) and stereo-aware metrics (iSQoe and StereoQA) show only modest differences and fail to penalize them. Our results indicate that monoscopic evaluation and standard image-quality metrics substantially underestimate perceptual artifacts observed in 3DGS reconstructions for VR, making stereoscopic assessment essential for 3DGS quality evaluation in VR.

We consider estimating the one-step-ahead conditional distribution of a multivariate stochastic process. Many existing approaches rely on assumptions such as finite-range memory, sparsity, or additivity, which can be poorly suited to processes with long-range nonlinear interactions. However, without such structural assumptions, nonparametric estimation is challenging due to the curse of dimensionality. To address this challenge, we introduce a new estimation approach based on the predictive states of a process, possibly with infinite-range memory. We show that our estimator achieves fast convergence rates when the past history can be compressed into a low-dimensional statistic that is sufficient for predicting the future. Specifically, we show that the statistical complexity of the estimation problem is determined by the intrinsic dimension of the predictive state space. We establish guarantees for an instantiation of our method based on deep neural network estimators, and we support these theoretical results with experiments.

Financial forecasting from earnings conference calls requires models to reason over complex corporate disclosures, market expectations, and subtle communication signals. However, existing financial benchmarks are often limited to unimodal inputs or single-task settings, making it difficult to evaluate whether multimodal large language models (LLMs) can support real-world financial analysis. In this paper, we introduce MM-FinEval, a novel benchmark designed to evaluate multimodal LLMs across multiple financial tasks. MM-FinEval spans a diverse timeline from 2019 to 2022. The entire proposed dataset contains 2,045 S&P 500 conference earning calls as inputs and 12 financial task labels as outputs. Each input contains three modalities: a word-to-word text transcript of the earning call, the corresponding presentation slides used during the call, and the entire audio recording. To establish a rigorous evaluation framework, we analyze 19 baseline models across three distinct model categories: Image-Text, Audio-Text, and Any-to-Any configurations. We observe that small-size Any-to-Any models processing all three modalities achieve strong performance, even when compared against larger proprietary models restricted to two-modality inputs. This indicates that our tri-modal dataset design introduces useful, non-redundant information. These results validate that text, audio, and visual data serve as important, complementary signals that mimic the decision-making process of expert human analysts.

In distributed control schemes, the communication topology that defines information sharing between agents must be designed prior to online control execution. Previous data-driven works typically decouple the topology and controller design problems. This paper investigates data-driven approaches to topology design that guarantee the existence of a stabilizing controller, whilst trading off the level of required communication against control performance. We formulate a data-driven co-design scheme that directly co-optimizes the topology and controller over the link costs and closed-loop control cost. When the topology designer does not have access to the agents' control objectives, we propose a control-aware approach that couples the two design problems within a sequential scheme. In both cases, the topology is optimized within a mixed-integer semidefinite program (MISDP). Simulations including the IEEE 14-bus power system test case demonstrate the effectiveness of both co-design and control-aware schemes. Numerical examples show lower computation time for the control-aware case than for co-design.

We introduce ShamAN-Q, a sub-1-bit post-training quantization method that extends NanoQuant by replacing each its diagonal reconstruction geometry with a tractable dense curvature metric, using a general paradigm popularized by the Shampoo optimizer. For each linear weight, ShamAN-Q fits a Kronecker product to the empirical Fisher information matrix of a small calibration set by Kullback–Leibler minimization, forming a Mahalanobis reconstruction loss from the result. The continuous ADMM updates from NanoQuant become solutions to Sylvester equations, while its discrete projection and deployment format remain unchanged. Because the curvature is local to a given set of weights, ShamAN-Q re-measures the input curvature statistic for each layer immediately before layer factorization, periodically refreshing all statistics on the partially quantized model. ShamAN-Q also redistributes the uniform rank from NanoQuant across layers at the same total number of bits. On Qwen3-Base, ShamAN-Q lowers WikiText-2 perplexity at $\approx$1 bpw from 27.56 to 22.96 (0.6B), 19.21 to 16.72 (1.7B), and 14.29 to 13.80 (4B) while matching or improving zero-shot accuracy on the Eleuther LM Evaluation Harness. On 0.6B, ShamAN-Q at $\approx$0.8 bpw matches the published perplexity of NanoQuant at $\approx$1.0 bpw.

Egocentric gaze prediction enables many downstream applications but remains challenging, as human gaze is inherently stochastic. This stochasticity is constrained by structured temporal dynamics alternating between fixations and saccades, top-down influences from tasks, and bottom-up visual saliency. Based on this observation, we introduce GazeFlow, a framework that directly models gaze as a joint distribution of temporal gaze positions conditioned upon both top-down and bottom-up information. In particular, GazeFlow uses conditional flow matching (CFM): a learned velocity field iteratively transports a Gaussian noise sample into a plausible gaze trajectory drawn from this joint distribution. The velocity field is conditioned on bottom-up visual features extracted by a video encoder and on top-down task information obtained by globally querying these features. On standard datasets, GazeFlow achieves state-of-the-art performance on per-frame metrics, and the generated trajectories align better with human gaze temporal dynamics.

Lower error from a text-conditioned neural surrogate does not, by itself, show that the model uses the meaning of the text. We examine this attribution problem with OperatorCLIP, comparing an unconditioned FNO, a constant-sentence FiLM control, and a fixed task description trained with contrastive alignment. Three-seed experiments cover Darcy2D, ShallowWater2D, and three-dimensional compressible Navier-Stokes (CNS3D). Constant conditioning has lower mean test error on both 2D tasks. Relative to this control, task text plus alignment has a similar mean on ShallowWater2D and CNS3D and a higher mean on Darcy2D; these descriptive comparisons have substantial seed uncertainty. The latter comparison changes both prompt content and loss, so it isolates neither effect. The text encoder is trained from scratch, and each conditioned model sees only one description during training. In this regime, pairwise InfoNCE cannot identify matched pairs and has minimum $\log B$. Prompt interventions show no reliable semantic ordering. This methodological caution demonstrates why pathway controls are needed; it neither establishes semantic competence of the encoder nor tests the effectiveness of text under varying physical context.

Large language models (LLMs) can now improve themselves by revising the instructions they follow, and LLM agents are increasingly orchestrated to work together on complex problems. However, self-improvement methods typically optimize one system at a time, and multi-agent frameworks often have every model work toward a shared goal. We ask a different question. When each agent pursues its own reward, can self-improving LLMs learn from one another well enough to improve the whole population? We call this capability recursive social improvement. We study populations that revise skill files and choose whether, when, and whom to copy from. Independent search, learning from peers, and acting all share one token budget. In controlled environments, established social-learning algorithms benefit from peers, but three LLMs do not. They earn less reward per token than solo learners, and explore too narrowly or run out of tokens before acting. We then let the models write and revise their own skills. Observing peers changes how they improve, helping one model find useful skills sooner and another spend less on private search. Neither, however, outperforms independent learners at the same cost. Skills are copied, revised, and passed on, so one discovery can seed further search. Yet these exchanges concentrate the population around fewer independent discoveries. Together, these results show that LLMs can make learning more efficient by copying from peers, but not yet more effective.

The discrete algebraic Riccati equation (DARE) is used to solve for the optimal feedback gain in linear-quadratic regulator (LQR) control of discrete-time systems. In this letter, we consider the effect of perturbations to the LQR data on the DARE solutions. We present a new frequency domain approach to derive an explicit bound on the difference in DARE solutions under such perturbations. Our bounds are similar to other results that have recently appeared in the literature with two distinctions. First, we use a frequency domain constant that measures the degree of closed-loop stability, in contrast to other results that use a time domain measure. Second, we start from weaker detectability assumptions on the LQR state cost matrix.

Therapeutic exercises can help slow cognitive decline in dementia, but conventional programs are often tedious and difficult to sustain. Virtual reality (VR) offers an alternative through game-based approaches designed to improve engagement and training-based approaches focused on structured functional recovery. Prior reviews report inconsistent findings about these paradigms, while it remains unclear whether the labels represent systems that are technologically distinct. Following PRISMA 2020 guidelines, we systematize 34 studies published between 2015 and 2026, including 16 controlled efficacy trials and 18 design and feasibility studies involving mild cognitive impairment, dementia and Alzheimer's disease. We develop a taxonomy covering design paradigm, immersion, feedback modality, difficulty adaptation and hardware. Our analysis shows substantial overlap between game-based and training-based systems, suggesting that these labels do not clearly distinguish their technological characteristics. We also introduce VR-RES, a seven-dimensional framework for evaluating study quality. Its application highlights recurring limitations in the evidence base, particularly limited follow-up, poor reproducibility and insufficient analysis of demographic factors such as age, sex and education. Based on these findings, we provide recommendations for future VR cognitive rehabilitation research, emphasizing specific design features, rigorous evaluation and improved reporting practices.

Voice agents in production must handle several requests, background speech, and customers who lose patience. We introduce VAmoS Energy, a benchmark that combines these challenges in 100 calls about utility billing and payment assistance. Each caller makes two to four requests. The agent has sixteen tools backed by a stateful Stripe billing twin and the Apache Fineract loan engine, with account access blocked until caller verification succeeds. The tasks use public household electricity data and a policy based on Pennsylvania's residential billing rules. An LLM-as-a-verifier checks the agent's actions and spoken figures against explicit requirements. On a calibration run, it agrees with a code verifier on 99.1% of checks. Across fourteen voice stacks and three repeats per task, completion ranges from 17.3% to 44.7%. Grok Voice leads, and Gemini 3.8 Live and GPT-Live follow at about the same cost per call. Background television reduces pooled completion from 38.7% to 8.6%. The simulated caller often accepts an incorrect result because it hears the agent's words but cannot inspect its actions. These findings show why voice agents need evaluation across the whole call, including what they say, what they change, and how they handle competing speech.

Autonomous underwater robots require robust perception, estimation and control to operate in confined environments. This paper presents an open-source BlueROV2 platform combining onboard vision with nonlinear Model Predictive Control (NMPC) for autonomous navigation and docking. The platform integrates an NVIDIA Jetson Orin NX and an Intel RealSense D435i stereo camera in a modular pressure housing. Underwater-calibrated stereo depth and realtime object detection provide relative position measurements of nearby BlueROV2 vehicles in the camera and body frames. A quaternion-based estimator fuses external pose and inertial measurements, while an NMPC controller based on a nonlinear six-degree-of-freedom model tracks planned navigation and docking trajectories. To support reproducible development, we also provide open-source physics-based PX4 SITL and Gazebo environments, multi-robot simulation tools and a lowcost physical docking station. Experiments evaluate underwater perception, onboard computational performance, state estimation, trajectory tracking and autonomous docking.

Speculative decoding accelerates autoregressive LLMs by having a lightweight drafter propose tokens that the target model verifies in parallel. Diffusion-based drafters further reduce drafting latency by proposing multiple tokens at once. However, these tokens are predicted independently, so a single early error causes prefix verification to discard the rest of the draft, even when it contains useful downstream predictions. We introduce DEdit, a diffusion-based drafter that can not only draft by conventional parallel unmasking but also iteratively edit its draft through token-to-token predictions. Through editing, later predictions can serve as bidirectional context for repairing earlier errors and extending the accepted prefix. To teach the model to repair errors while preserving correct predictions, we propose ProposalMix, a training scheme that mixes draft predictions with ground-truth tokens based on first-pass confidence during training. Across seven benchmarks on Qwen3-4B and Qwen3-8B, DEdit achieves the highest macro-average token acceptance and speedup among the evaluated drafters, reaching macro-average speedups of $5.72\times$ and $5.97\times$ over autoregressive generation under greedy decoding, respectively. Further analysis shows that acceptance improves with more editing passes and wider drafting windows, and that ProposalMix halves harmful edits that shorten the accepted prefix. Moreover, restricting the editor to causal attention lowers acceptance, especially on highly predictable outputs, indicating that future context is a key source of these gains.

Tree-like branching structures are common in nature, from botanical trees to neurons, blood vessels and respiratory trees. Their branching shape often reflects function, making structural modelling central to understanding how these systems work. Because acquiring real-world 3D data is often expensive or infeasible, realistic generative models are valuable for simulation and data augmentation. Existing morphology-specific models either constrain how topology is generated or rely on hand-tuned, mechanistic procedures. Generic 3D graph generators, by contrast, do not exploit or enforce the structure of trees. We propose Autoregressive Frontier Expansion, a generative framework that constructs trees through an iterative expansion process, simulating the biological growth of real trees. At each step, a flow-matching model parameterised by an SO(2)-equivariant GNN expands the frontier by predicting whether each active branch bifurcates or terminates. We evaluate our method on cortical neurons and botanical trees in unconditional, class-conditioned, and morphology-guided generation. Across both domains, the generated morphologies agree closely with the reference distributions and, in conditional experiments, with the specified targets.

Effective AI adoption in cyber-physical systems (CPS) depends on embedding design knowledge into engineering practice. Yet as AI-enabled components increasingly replace analytically derived control laws, this occurs without a systematic understanding of how controller architectures differ or remain similar across paradigms. We address this gap with an empirical study of traditional and AI-enabled Simulink controllers, guided by a literature-derived taxonomy of ten structural categories and nine functional roles. The study analyzes 62 real-world models spanning 8 controller types and 10 application domains, and surveys 13 practitioners, identifying three architectural tensions. First, subsystem organization dominates all controller structures regardless of paradigm, occupying 68-72% of controller footprint, while core control logic occupies minimal space. Second, AI-enabled controllers rely heavily on discrete dynamics and user-defined abstraction, categories largely absent from AI literature, exposing a gap between described and implemented architectures. Third, constraint enforcement blocks largely disappear from AI-enabled models despite practitioner expectations. This reveals a misalignment where safety mechanisms shift from explicit structure to implicit training-time artifacts, breaking traceability.