Papers

The best constructive lower bounds on the capacity of the binary deletion channel come from random codes with independent run lengths, yet the two strongest such bounds, due to Drinea and Mitzenmacher and to Venkataramanan, Tatikonda, and Ramchandran, have been evaluated mainly for geometric or low-parameter run-length laws. We let a learning algorithm choose the run-length law freely, which raises three challenges. First, the Drinea-Mitzenmacher functional is an infinite sum over the ways deletions merge runs; we show that it depends on the law only through its mean, its full-deletion probability, and bilinear forms in the law and its renewal weights, so that gradients of truncations are exact and every truncation can only lower the bound. Second, for non-Markov inputs the output is no longer Markov and the Venkataramanan-Tatikonda-Ramchandran analysis breaks down; we show that the residual length of the current input run turns the output into a hidden Markov chain, which extends the bound to every finite-support law. Third, its correction term counts only output runs formed from three input runs; we prove a larger correction that accounts for every output run formed by several input runs, which improves the published bound even for truncated geometric laws. Certified by interval arithmetic, the new bounds exceed all previously published deterministic lower bounds at every tabulated deletion probability, by up to $6.86\times10^{-3}$ bits per channel use and 6.8%. At large deletion probability the learned laws concentrate on run-length clusters with survivor counts about two standard deviations apart, like a pulse-amplitude constellation.

Dormant tree pruning is labor-intensive yet essential for maintaining modern high-productivity fruit orchards. In this work, we focus on pruning of modern planar tree training systems - V-Trellis apples and UFO cherries - where trunks and primary branches are trained into approximately planar walls. We introduce an end-to-end pipeline to learn a closed-loop visuomotor controller for robotic pruning. This controller is trained entirely using simulation and synthetically generated data and deployed in real orchards in a zero-shot manner. The pipeline comprises synthetic generation of planar orchard tree meshes, construction of a physics-based orchard simulator, automated collection of successful pruning trajectories via motion planning, and policy learning with a novel hybrid reinforcement-learning algorithm that combines offline demonstrations with online simulated rollouts. The controller uses optical-flow inputs from a wrist-mounted camera - avoiding the need for full 3D-reconstruction - and continuously guides the cutter through cluttered branch environments to a specified cutpoint with correct tool orientation. In exhaustive simulated task-space evaluations over 3,000 pruning points, the policy attains 49.9% success on V-Trellis apples and 46.0% on UFO cherries. We validate the learned controller across 38 physical trials - comprising 28 outdoor field trials in commercial and experimental orchards and 10 indoor laboratory tests - demonstrating zero-shot sim-to-real transfer. The learned policy also outperforms a classical RRT-Connect baseline on physical hardware in laboratory trials.

The demands of modern applications require the construction of ever more complex integrated systems, with AI applications in particular serving as a significant driver for increased system size, potentially going beyond the trilliontransistor mark. The path to building these systems requires the use of advanced packaging, with heterogeneous integrated 2D and 3D chiplets placed atop a substrate. Such computationally powerful systems require significant power for computation: reliable and robust power delivery is a major challenge in light of high power densities and pin count bottlenecks. This paper overviews approaches to building design methodologies that overcome this problem, through the design of multistage distributed power delivery systems, optimized for performance and reliability, and built to coexist within stringent performance, thermal, and reliability constraints.

Tone languages constitute over 50-70% of the world's languages, but the vast majority are low-resource, lacking the large transcribed corpora needed for automatic tone classification. Existing datasets are typically collected at the sentence level, whereas field linguists require fine-grained syllable-level annotations. We propose ToneCL, a lightweight contrastive learning framework for few-shot syllable-level tone classification. We simulate low-resource conditions on Mandarin and Vietnamese, limiting labeled data to tens of examples per tone class. ToneCL is pretrained on unlabeled speech with augmentations that preserve tonal identity, then fine-tuned on few-shot examples. Experiments show our method consistently outperforms baselines, achieving 91.6% on six-speaker Mandarin at 10 shots. Cross-lingual transfer is also effective: pretraining on Vietnamese and fine-tuning on Mandarin reaches 91.0% accuracy at 10 shots. Ablation confirms that frequency band rejection is the most critical augmentation.

We study the squared Rayleigh-residual functional on complex projective space and its negative gradient flow. For an arbitrary complex matrix, every positive-residual critical point has a strictly descending tangent direction; consequently, the local minima are precisely the eigenlines. For normal matrices, we describe the critical set in terms of circles through spectral points and identify the amplitude dynamics with a replicator equation whose payoff matrix has rank at most four. This gives explicit logarithmic first integrals and a reduced representation of interior trajectories. We compute transverse escape rates near critical components and analyze how polynomial reweighting changes unstable coordinates. Finally, we distinguish local saddle trapping from concentration of Haar-distributed initial states and derive the density of the filtered ensemble. Numerical examples with random spectra and a Jordan block illustrate convergence, nonmonotone Rayleigh motion, and the improvement of finite-time spectral exploration by low-degree random polynomial filters.

Children with autism spectrum disorder (ASD) have social-emotional deficits that lead to difficulties in recognizing emotions as well as understanding and responding to social interactions. This study presents EMooly, a tablet game that actively involves caregivers and leverages augmented reality (AR) and generative AI (GenAI) to enhance social-emotional learning for autistic children. Through a year of collaborative effort with five domain experts, we developed EMooly that engages children through personalized social stories, interactive and fun activities, and enhanced caregiver participation, focusing on emotion understanding and facial expression recognition. Compared with a baseline, a controlled study with 24 autistic children and their caregivers showed EMooly significantly improved children's emotion recognition skills and its novel features were preferred and appreciated. EMooly demonstrates the potential of AI and AR in enhancing social-emotional development for autistic children via prompt personalizing and engagement, and highlights the importance of caregiver involvement for optimal learning outcomes.

Dexterous grasping requires deciding where to grasp, reaching the target, and maintaining stable contact. We connect these stages through a compact three-point interface that separates global geometric reasoning from local contact control. Given object geometry and optional language commands, our framework samples contact triples from a precomputed grasp-affordance heatmap. A model-based reactive controller tracks the object, avoids collisions, and guides the hand toward the selected contacts. In the final centimeters, a Reinforcement Learning (RL) policy uses proprioceptive feedback to refine and stabilize the grasp despite reaching and perception errors. It observes only finger joint states and its recent actions, with no target points, visual observations, or object geometry, so a single policy is shared across objects and grasp configurations. In simulation, we compare grasp-and-lift success against squeeze and end-to-end baselines, characterize reaching convergence, and demonstrate grasp steering; hardware demonstrations on two training objects and one unseen object illustrate the full pipeline. Our modular framework uses geometry to guide the reach and local feedback to secure the grasp.

When an LLM supplies an argument a user could not produce, how can the user decide whether to accept its claim? Inspired by interactive proofs, we pair a computationally unbounded LLM prover with a resource-bounded human verifier. The verifier checks requested details without seeing the LLM's internals; passed checks accumulate evidence toward an acceptance threshold. Given task-supplied bounds on false passes and human checking errors, we prove anytime-valid soundness against adaptive provers: the probability of ever accepting a false claim is at most a chosen error level. For a true claim, acceptance within the budget has probability at least the product of per-round probabilities that the LLM responds adequately and the human checks correctly, provided the threshold is reachable in time. Each additional check guards against false claims but gives a true claim another chance to fail. Which review lengths meet both error targets depends on the verifier's effort, cognitive load, expertise, and fatigue. With equal resources, we identify conditions under which the bounds certify a review by local checks but not a one-shot check. In LLM-only simulations on GPQA Diamond and Humanity's Last Exam, whether answers accepted without revision were more accurate varied by task and model pair.

Whole-slide pathology images (WSIs) contain gigapixel-scale visual content, creating a major scalability challenge for slide-level multimodal large language models (MLLMs). Existing approaches process thousands of patch tokens and typically apply compression only after slide encoding, leaving multimodal attention computationally expensive. We introduce SLICEChat, a slide-level MLLM that integrates progressive token pruning within a hybrid Mamba–Transformer slide encoder. Mamba layers enable efficient long-range propagation, while Transformer layers preserve global interactions as the sequence is progressively shortened. Between stages, language-supervised, region-aware pruning removes spatially coherent low-utility regions under a controlled keep-rate schedule, producing compact slide representations before multimodal fusion. On SlideBench VQA, SLICEChat achieves 79.84% accuracy on TCGA and 59.09% on BCNB cohorts, outperforming prior slide-level pathology MLLMs, and achieves the highest overall WSI-Bench metrics. It also provides competitive memory usage and the inference latency among the evaluated models. These results demonstrate accurate and computationally efficient multimodal reasoning over gigapixel WSIs.

Evaluation of Computer-Use Agents (CUAs) is often limited to the final deliverables they create (at the end of hundreds of steps) and assessed with functional verifiers, as seen in OSWorld. However, such evaluation of end-state performance lacks transparency into how and why agents fail in various tasks, obfuscating critical insight for subsequent improvement. For instance, agents that err during keyboard inputs would require a different mitigation strategy from those that fail to precisely provide click-based inputs on the graphical UI. We introduce OSWorld-Pro: a set of over 300 tasks containing over 2800 subgoals to enable the procedural evaluation of CUAs grounded in over 67,000 human annotations. We use robust human-aligned LLM-Judges to evaluate the fulfillment of OSWorld-Pro subgoals and thereby reveal the progress that models make throughout a series of sequentially dependent subgoals. Our findings reveal that OSWorld-Pro is challenging even for state-of-the-art LLMs, with top performers like Claude Opus 5 achieving only 75.7% vs. 83.4% on OSWorld. Furthermore, we identify critical process-focused failure modes of various models (e.g. subgoal-irrelevant actions and click-based mistakes) to provide insights to improve performance and efficiency of CUAs.

In DNA data storage, racetrack memories, and packet networks, data are written as many short strands of fixed length. The receiver knows where each strand begins and ends, and deletions occur only inside a strand. The relevant limit for such systems is the block capacity $C_N(d)$, the largest mutual information between a length-$N$ input and the output of a binary deletion channel with deletion probability $d$. Because the boundaries are known, $C_N(d)/N$ is never smaller than the classical capacity $C(d)$. Computing $C_N(d)$ is hard because the input takes $2^N$ values. For $0\le d<1$, we show that the optimal input is unique, gives positive probability to every string, and is unchanged by complementing or reversing the strings. We then introduce the optimized run distribution (ORD), which assigns one probability to each number of runs; it is optimal for $N\le3$ and is solved with a numerical optimality certificate up to $N=16$. For longer strands, an exact recursion for the output distribution gives unbiased rate estimates, and an empirical Bernstein inequality turns them into confidence intervals. Within the statistical precision, a one-parameter Markov input performs as well as the best inputs found. For strands of 100-200 bits, known boundaries increase the rate by up to 0.026 bits per symbol beyond the best certified upper bound on the capacity of the unsegmented channel. Via Fano's inequality, the block capacity also bounds the rate of any code that uses a single strand; in the tabulated case, this bound is tighter than the best known finite-length bound for strands longer than about 90 bits. Conversely, block rates yield lower bounds on $C(d)$; at $d=0.1$, the bound is within $1.1\times10^{-4}$ bits/use of the best certified lower bound. Finally, InfoNCE estimates, even with the optimal critic, empirically lose most of their ability to rank inputs as the strand length grows.

We built a node that grounds a replaceable language model in a maintained ontology corpus, then asked what its successful-looking evaluation could support. Across ten models, grounding raised target-name recall from 0.265 unaided to about 0.92. A copy baseline, the recall a verbatim copy of the shown context already achieves, scores 0.964, and every model sits 0.022 to 0.067 below it. Copying therefore scores higher on this limited recall measure, which does not assess whether answers are better. The comparison tests what a recall score establishes; it does not test whether reasoning occurred, because a reasoned answer and a copy score alike when the answer name is already in context. We report exposure accounting (four counts classifying each gold item by whether the context exposed it and the answer recovered it) and a model-judged audit of 423 sampled item observations. A separate paired production study found a model-judged quality gain of +0.27 [+0.11, +0.45] on a 0-5 scale. Operational studies found failures that recall alone would not show: rephrasing questions out of the graph's vocabulary cut exposure from 0.964 to 0.328, yet the absence-keyed fallback would have fired on only 2 of 506; and inserting extracted facts degraded judged pages in every arm, so that step was disabled. Five-arm controls show that any well-formed on-corpus block beats no context but do not establish that the specific content matters, and no matched comparison against flat-text retrieval was run. The corpus is public and largely LLM-generated, which establishes neither training exposure nor novelty. Each study has its own outcome measure. Where gold derives from the injected corpus, we recommend reporting the accounting beside quality judgements, not in place of them.

Artificial intelligence (AI) registers and inventories aim to make governmental AI visible, but their institutional scope, schemas, and reporting practices construct different representations of public-sector AI. We compare 8,368 records from country-specific and transnational inventories covering 72 countries. Across 23 harmonized fields, registers shared a descriptive core but rarely requested information about appeals, risks, legal bases, or external evaluation. We found that broad schemas often contained substantial missingness, schema similarity showed no significant patterned convergence, and multiple sources covering the same jurisdictions overlapped only selectively. Based on these findings, we synthesize a layered visibility framework that shows how register records reflect disclosure arrangements and why interoperability requires shared concepts, clear definitions, and preserved provenance.

Hybrid AI-physics climate modeling aims to improve coarse (~100km-resolution) Earth system models by learning to parameterize subgrid processes from high-fidelity data. However, this so far mostly involves local-in-time, diagnostic parameterizations, in which the subgrid state depends only on the current coarse state with no memory of previous states, which is unrealistic for processes such as convection that have intrinsic persistence. To address this, we enhance local-in-time parameterizations by learning prognostic variables that compactly carry important, additional past information where no explicit sub-grid information is available. First we compress past information into a low-dimensional latent space using an autoencoder, which then informs a neural network trained to parameterize targeted subgrid-scale processes. We then replace the autoencoder with symbolic equations that govern the time evolution of the latent variables, yielding additional prognostic memory variables that can be integrated alongside the resolved atmospheric state. We evaluate this approach on two systems: the Lorenz-96 model (online) and surface precipitation from high-resolution atmospheric simulations (offline). A forced multivariate linear ordinary differential equation recovers most of the added value achieved by the autoencoder-based approach in both experiments. Benchmarked against diagnostic parameterizations without memory, our memory-informed approach improves climate statistics and temporal structure, including a realistic diurnal cycle of tropical land precipitation.

In high-stakes decision-making applications of large language models (LLMs), practitioners require not only accurate LLMs but also uncertainty estimates for their predictions. Existing approaches to uncertainty estimation for LLMs require access to log-probabilities output by the model or require fine-tuning access. However, many industrial LLM products use closed-source API models, and many such API models like GPT do not return log-probabilities and may not allow fine-tuning. We introduce Pinocchio, an external calibrator that estimates the correctness of responses from black-box API models. Trained jointly on responses from seven LLMs, it achieves 0.862 AUROC predicting the correctness of held-out responses from those same models, and shows zero-shot transfer to thirteen unseen models across eight organizations. Our model needs only a single forward pass to generate an uncertainty estimate and requires no access to the target model's logits, weights, or internal states. A lightweight text only 0.8B checkpoint matches our largest model's AUROC. We release code for adding uncertainty estimation to existing repos in only two additional lines of code.

Counterfactual image generation answers questions about how a subject would have looked under retrospective, hypothetical scenarios. Recent methods have improved perceptual quality, identity preservation and faithfulness to an underlying causal model, but their adoption in healthcare is limited by scarce annotated data, distribution shift between datasets, and mismatches between pretrained generative models and those required for counterfactual inference. We propose specialisation, a data and parameter-efficient framework for adapting pretrained, non-causal generative models into causal mechanisms under distribution shift. Based on this framework, we train a radiology counterfactual image generation model, called RadCF, using latent flow matching. We validate our approach on three chest X-ray datasets spanning different dataset shifts, data volumes, and counterfactual questions, associated with challenging, highly-localised interventions. Our results show that RadCF and specialisation improve counterfactual soundness over existing methods while being data and parameter efficient, and that the resulting counterfactuals can detect and mitigate shortcut learning in a downstream medical classifier. Code is available at https://github.com/GSK-AI/RadCF/.

Bimatrix games may have an exponential number of mixed Nash equilibria if both dimensions of the game are allowed to grow. Bounds on their maximal number give structural insights that have been used to construct hard-to-solve games. We show new sharp or asymptotically sharp bounds on the (polynomial) number of equilibria for generic games where one dimension of the game is fixed and the number of strategies of the other player grows. These results go beyond the hitherto studied square games. Our methods employ combinatorial properties of polytopes, and recent obstructions that relate to the graph of those polytopes. For $n\ge5$, we construct $3\times n$ games that have all $2n+1$ vertices of the best-response polytope as equilibrium strategies, proved using a simple case of the 4-color theorem for planar graphs. Generic $4\times 5$ games are shown to have at most 17 equilibria, using computer calculations with existing datasets for all combinatorial types of the relevant polytopes. For $d\times n$ games, we construct games where all but a fraction of $O(1/n)$ of the maximum number of vertices are equilibrium strategies.

In automated clinical coding, where the label space spans tens of thousands of diagnosis and procedure codes, models are currently evaluated against a single gold annotation, treating any deviation as error. But we find when two teams code the same 110 ACI-Bench encounters, they agree on only 73% of codes (Jaccard similarity) for the same note; even after an independent clinical audit removes erroneous codes, agreement rises only to 77%. Is that gap error or something systematic? We model the systematic component as coding style $\psi$, a coder- or site-specific policy over what to code and how much to document, and recast coding as $p(\mathrm{code}\mid\mathrm{note},\psi)$, estimating $\psi$ with a 10-dimension rubric. If style were noise, conditioning on it would do nothing. Instead, across five datasets a model conditioned with a data-matching style raises ICD F1 by up to 26 points and an extreme mismatched one lowers it by up to 21. Four prompt based coding methods spanning 39-49 F1 converge to 52-56 once style is supplied (All p<0.05). Much of what single-gold evaluation charges to model error is recoverable, unmodeled style.

In multi-agent social settings, model reliability varies across relationships. Beyond inferring what others will do, an agent must calibrate how confidently those inferences should guide policy selection for each relationship. An agent may maintain a well-validated model of one partner, a fragile model of another, and a model under revision for a third; collapsing these into a single confidence estimate loses information relevant to policy selection. We therefore formalize affective precision as a relationship-specific metacognitive estimate of confidence in the current partner model. Each partner's behavioral evidence updates a local confidence estimate that modulates policy precision during selection, regulating how strongly current beliefs are expressed in policy rather than changing the content of those beliefs. Simulations in a multi-partner graded trust game show that partner-local affective precision influences behavior primarily through policy commitment rather than direct improvement of partner-state inference. Because the mechanism tracks partner-response predictability rather than realized payoff, greater confidence produces sharper policy commitment without necessarily producing higher rewards. Under abrupt shifts in social behavior, confidence accumulated from previously reliable predictions can remain behaviorally active after the relationship changes, showing that confidence revision can lag behind social change. Finally, varying precision gain and priors produce distinct trust-calibration dynamics, showing how confidence accumulation and revision depend on model parameters. Together, these results show how relationship-specific affective precision can distinguish social prediction from social policy commitment.

Recent foundation models are moving toward native multimodal Vision-Language Models (VLMs), making VLMs a central form of next-generation foundation models. However, their large language backbones make edge deployment difficult due to high memory footprint and memory-bound autoregressive decoding. Weight-only post-training quantization is a practical solution, but pushing VLMs to extreme low bit-widths remains challenging: existing rotation-free methods suffer from outliers at 2-3 bits, while rotation-based methods improve accuracy at the cost of additional runtime overhead. We propose SPHQuant, a rotation-free spherical weight-only quantization framework for VLMs. Instead of quantizing weights directly in Cartesian coordinates, SPHQuant decomposes each 8D weight vector into coordinate signs, radius, and a positive unit direction. This representation isolates outlier magnitude into the radius while keeping directions bounded and statistically regular. Based on this insight, SPHQuant allocates extra precision to the radius to mitigate accuracy degradation induced by outliers. It further uses a compact positive-direction codebook and fine-tunes codebook entries through angular parameterization to preserve the unit-sphere constraint. We also design a hardware-friendly GEMV kernel that keeps the direction codebook small enough for shared-memory lookup and packs radial bits efficiently. Experiments show that SPHQuant matches the performance of state-of-the-art extreme low-bit quantization methods while improving decode throughput over QTIP by 30.3% on RTX A6000. Code will be released in https://github.com/Pushazf/SPHQuant.

Two-stage oriented detectors achieve high localization accuracy in synthetic aperture radar (SAR) ship detection, but their large backbones, feature pyramids, proposal modules, and heavy region of interest (RoI) heads hinder deployment. Existing lightweight SAR ship detectors typically use one-stage frameworks that lack proposal-level refinement for precise rotated localization. This paper presents a dual-teacher knowledge distillation and pruning (DTKDP) framework for lightweight oriented SAR ship detection. DTKDP introduces learnable gates into convolutional, normalization, and linear layers to prune convolutional channels and RoI-head neurons. Rotated proposal alignment (RPA) distills teacher and student predictions in a shared teacher-generated rotated proposal space, while a dual-teacher scheme combines classification and regression guidance from a homogeneous main teacher with complementary classification cues from a heterogeneous auxiliary teacher. Experiments on the SAR Ship Detection Dataset (SSDD) and Rotated Ship Detection Dataset in SAR Images (RSDD-SAR) show that DTKDP reduces the parameters of Oriented Region-based Convolutional Neural Network (Oriented R-CNN) and RoI Transformer equipped with ResNet-50 backbones by 87.5-91.8% and their floating-point operations (FLOPs) by 75.6-79.9%. In terms of average precision (AP) and mean average precision (mAP), the resulting Oriented R-CNN-slim and RoI Transformer-slim retain accuracy close to their full-scale counterparts. Relative changes across $\mathrm{AP}_{50}$, $\mathrm{AP}_{75}$, $\mathrm{mAP}_{50:75}$, and $\mathrm{mAP}_{50:95}$ range from a 2.38% decrease to a 0.65% improvement. Compared with RTMDet-tiny, they improve all four metrics on both datasets by 0.52-27.55% and consistently surpass representative distillation methods, demonstrating a favorable accuracy-efficiency trade-off.

High-order differential operators and nonlinear coupling make it challenging to construct conservative and energy-stable schemes for coupled gradient-flow systems. We present GradAgent, a knowledge-guided multi-agent system that coordinates three agents across model analysis, algorithm design and proofs, and numerical implementation and validation. Independent audits strengthen reliability by uncovering mathematical errors and proof gaps, guiding revisions, and maintaining consistency across stages. In Reconstruction Mode, GradAgent reconstructs 20 published studies and organizes audited knowledge in an extensible knowledge graph (KG), GradAgent-KG, linking model structures, discretization strategies and proofs, implementations, and numerical evidence. In Design Mode, the agents assess the applicability of retrieved knowledge and develop new schemes informed by relevant discretization strategies. Applied to the fully coupled multicomponent vesicle phase-field-fluid model, GradAgent yields three first-order and three second-order schemes across three algorithmic families, including four linear, decoupled schemes. Under stated assumptions, all six schemes conserve membrane component mass and vesicle volume and dissipate their respective temporally discrete energies unconditionally. Comparisons with and without GradAgent-KG show that it promotes diversity in structure-preserving scheme design for this target model. Numerical tests confirm second-order spatial accuracy, the expected temporal orders, conservation, and temporally discrete energy dissipation, while three-dimensional shear-flow simulations agree qualitatively with experiments. These results demonstrate GradAgent's ability to combine reusable knowledge, coordinated reasoning, and independent auditing to develop and validate structure-preserving algorithms for complex coupled systems.

World Action Models (WAMs) jointly generate robot actions and predict future world states, transferring priors from video pretraining to robot control. However, future visual prediction is computationally expensive, so existing WAMs often rely on long action chunks to amortize inference cost across control steps, at the cost of closed-loop responsiveness. We present \method, a dual-system WAM that preserves broader-horizon world-action generation while enabling high-frequency closed-loop action updates by decoupling global planning and local refinement. \systwo periodically performs high-noise bidirectional denoising over a broader world-action chunk to establish a global plan, while wrist-only \sysone extracts a temporally aligned short window from the intermediate denoising state and completes low-noise refinement using the latest wrist observations, which provide action-aligned cues about local geometry, motion, and contact during interaction. The two systems operate asynchronously along a shared denoising trajectory: each global plan is reused across multiple local updates, while \sysone repeatedly incorporates fresh interaction feedback. Across zero-shot manipulation tasks on Franka and Galbot, \method improves success over the strongest evaluated baseline by 4.5 percentage points on average, while achieving a 16.6$\times$ critical-path speedup. Further studies show that role-matched egocentric and UMI data improve success by 14 percentage points, and that the decoupled design naturally supports edge–cloud deployment with substantially lower communication overhead than the baseline.

This paper investigates the path-planning problem for systems required to satisfy a linear temporal logic (LTL) specification while achieving a desired long-run visit proportion. For a path represented in prefix-suffix structure, the long-run visit proportion quantifies the asymptotic occurrence proportion of an atomic proposition (AP) sequence of interest in the suffix trace. Such a quantitative requirement generally cannot be expressed by standard LTL specifications. Furthermore, we develop a planning approach that synthesizes an LTL-satisfying path whose long-run visit proportion remains within a prescribed tolerance of a desired value while satisfying an overall cost constraint. By adjusting the desired proportion, the synthesized path can allocate more or less long-run attention to the atomic proposition sequence of interest, thereby improving the flexibility and efficiency of the task execution. Finally, experiments on a quadruped robot demonstrate the practical significance of the proposed long-run visit proportion and the effectiveness of the proposed planning approach.

Reaching a 6-DoF grasp pose in clutter requires a collision-free trajectory, conventionally obtained by reconstructing the scene in 3D and planning inside that reconstruction, at the cost of its accuracy and compute. Potential fields learned directly from images remove that dependency but inherit the classical weakness of artificial potential fields: where attractive and repulsive gradients cancel, the descent grazes the obstacle instead of going around it, and can stall short of the goal. We present an SE(3) neural potential field learned from posed RGB images and supervised with a navigation function, the geodesic distance to the grasp through free space recovered from those same images during training, which removes both failures. On two tabletop scenes, from obstacle-blocked starts executed on a UR10, the field converges within 3 cm of the grasp from every start and every path it executes is collision-free against the ground-truth geometry, against 25% and 0% under image supervision alone; mean clearance rises from under a centimeter to 8.6-8.8 cm and arm-link contacts fall from 20.6-50.4% to 2.7-5.5% of executed configurations. Executed grasp success is 90.0% and 40.0% on the two scenes, the residual failures being refusals of the Cartesian executor rather than of the field. Planning takes about 2 s against 67-133 s for RRT* on a reconstruction of the same images, though under a common offline harness the two are comparable: the deployed margin is the cost of collision-checking a dense reconstruction, not planner complexity.

Effective communication between pilots and air traffic control (ATC) is essential for aviation safety, but verbal exchanges over radios are prone to miscommunication, especially under high workload conditions. While cockpit-embedded visual aids offer the potential to enhance ATC communication, little is known about how to design and integrate such aids. We present an exploratory, user-centered investigation into the design and integration of icon-based visual aids, named ATCion, to support in-cockpit ATC communication, through four phases involving 22 pilots and 1 ATC controller. This study contributes a validated set of design principles and visual icon components for ATC messages. In a comparative study of ATCion, text-based visual aids, and no visual aids, we found that our design improved readback accuracy and reduced memory workload, without negatively impacting flight operations; most participants preferred ATCion over text-based aids, citing their clarity, low cognitive cost, and fast interpretability. Further, we point to implications and opportunities for integrating icon-based aids into future multimodal ATC communication systems to improve both safety and efficiency.

Agentic time series forecasting concerns systems whose underlying mechanisms evolve, making the relative effectiveness of numerical models, reasoning strategies, and intervention rules inherently time-varying. Consequently, a time series agent must adapt the forecasts it produces and the orchestration policy that determines which components to trust and how to coordinate them. The deployment process naturally provides supervision for this adaptation as forecast horizons elapse and realized targets reveal the effectiveness of earlier decisions. Committing all numerical expert forecasts and candidate agent paths before target observation allows each realized outcome to evaluate the entire alternative set, providing delayed feedback without additional annotation. However, existing time series agents primarily incorporate prior experience through forecast refinement, reflection, or retrieval, without systematically converting realized outcomes into persistent updates to the joint orchestration policy governing later origins. To exploit this delayed feedback systematically, we introduce TimEvolve, a frozen-backbone time series agent that converts each realized outcome into persistent joint updates of expert trust, agent path selection, and intervention strength. A temporally ordered predict, reveal, and update protocol applies this feedback to subsequent forecasts. Experiments across eight Time-MMD domains show that TimEvolve achieves the best average MSE and MAE ranks among fifteen methods and the lowest errors on both metrics in seven domains. These results demonstrate the value of learning forecasting policies from the futures encountered during deployment.

The ideation phase of participatory AI risk assessment often starts with a blank slate or a limited list of predefined risks, making it difficult to surface indirect or systemic harms. To address this limitation, we propose a three-stage ideation support tool. The tool complements participatory AI, rather than replacing it, and helps focus later engagement with affected communities. First, it dynamically discovers stakeholders depending on the given AI use and recursively expanding outward, allowing overlooked or indirect stakeholders to emerge. Second, it simulates these stakeholders with LLMs, connecting them into a network of a given topology, and having them ideate about risks. Third, it prioritizes risks using network centrality measures. In an initial evaluation, we found that betweenness centrality run through agents connected in a small-world network works best as it elevates risks raised by stakeholders who bridge disconnected groups, surfacing novel, systemic harms that traditional methods often miss. On an AI chatbot companion use case, this approach increased the novelty of the identified risks by approximately 1.1 points over single LLM brainstorming, and by 0.5 points over agentic LLM brainstorming, measured on a normalized five-point Likert scale, without reducing the plausibility or severity of the identified risks. To test whether our framework helps a human-led ideation session using the Futures Wheel approach, we divided 11 teams of non-western young chatbot users into two types: control (team) and treatment (team) in a participatory AI risk assessment. The control teams started from a list of risks generated by the 45 AI practitioners in the initial evaluation; the treatment teams started from a list generated by our framework. The treatment teams identified more risks overall, and more systemic, human-computer interaction, and environmental risks.

Argumentative component detection (ACD) is a core subtask of Argument(ation) Mining (AM) and one of its most challenging aspects, as it requires jointly delimiting argumentative spans and classifying them into components such as claims and premises. While research on this subtask remains relatively limited compared to other AM tasks, most existing approaches formulate it as a simplified sequence labeling problem, component classification, or a pipeline of component segmentation followed by classification. In this paper, we propose ITFACD, a novel approach based on instruction-tuned Large Language Models (LLMs) using compact instruction-based prompts, and reframe ACD as a language generation task, enabling arguments to be identified directly from plain text without relying on pre-segmented components. Experiments on standard benchmarks show that our approach achieves higher performance compared to state-of-the-art systems. To the best of our knowledge, this is one of the first attempts to fully model ACD as a generative task, highlighting the potential of instruction tuning for complex AM problems. Our code and the datasets used are openly available in the following GitHub repository.

Computing accurate geometry from multi-view images is a fundamental problem in computer vision. Recent feed-forward (FF) models jointly estimate 3D geometry and camera parameters, but they typically suffer from geometry distortion caused by reconstruction ambiguity, even when ground-truth camera parameters are supplied. In this paper, we study the multi-view stereo (MVS) problem with known camera parameters and propose a novel approach that bridges conventional MVS and FF methods. Rather than casting MVS as a sequence-to-one mapping that predicts depth only for a single reference view, we reformulate it as a sequence-to-sequence task, akin to FF models, that jointly predicts geometry for all input views. We introduce a global transformer-based architecture with two components that explicitly exploit camera-induced priors: ray-map embeddings that inject camera parameters into image patch tokens, making the transformer camera-aware, and a unified global cost volume that replaces conventional per-view cost volumes to jointly capture 3D structure across all views. Extensive experiments on multiple public benchmarks show our approach achieves state-of-the-art performance, surpassing both MVS and FF reconstruction baselines.