Peer Revenue Past citations are no guarantee of future returns

Papers

Fresh from arXiv, typeset properly. Highlighted words trade on the market.

Computer Science

cs Watch Computer Science (sign in to use)

Wednesday 12 August

Artificial Intelligence

General Probabilities of Causation with Causal Knowledge

Probabilities of causation (PoCs) characterize individual causal responses that cannot be directly observed and therefore generally require partial identification. Tian and Pearl first derived theoretically sharp bounds for binary PoCs, including the probability of necessity (PN), the probability of sufficiency (PS), and the probability of necessity and sufficiency (PNS). Mueller et al. subsequently tightened the bounds for binary PNS by incorporating causal information encoded in covariates and mediators. More recently, Li and Pearl, as well as Shu et al., extended PoCs to multivalued settings and derived corresponding theoretical bounds. These developments naturally raise the question of whether additional causal knowledge can further tighten the bounds in multivalued settings. This paper addresses this question by deriving tighter bounds for multivalued PoCs through the incorporation of causal information encoded in covariates and mediators. We illustrate the theoretical results with toy examples, while simulation studies further demonstrate that the proposed bounds are tighter than existing nonbinary bounds.
Read the full abstract

Machine Learning

Training Under Challenge: Executable Certificates and Challenge-Closed Optimality for Neural Networks

A flat training curve does not reveal whether a neural network has reached a global optimum, is locally trapped, is representation-limited, or is mismatched to its trainer. We introduce Training Under Challenge, an executable-certificate framework in which predeclared, architecture-valid procedures construct complete alternatives in the same certified class and reevaluate the same objective. Any lower-valued candidate is a replayable witness that lower-bounds the checkpoint's empirical global-optimality gap. Passing a finite suite is only suite-relative; global-gap conclusions require a separately justified coverage mechanism. We define a resource-indexed challenge-power modulus that characterizes the largest gap compatible with passage. For squared loss, current block-decrease operators make coverage checkable and yield uniform and realized-residual bounds. We prove the converse frontier: without coverage, a first-order ReLU trainer can reach infinitely many exact conditional head optima while converging to a non-global point. On a channel-gated ResNet-18 distillation problem with known optimum, eight internal challenges cover all 240 audited output directions, and realized-residual bounds lie within factors of 1.74–3.02 of the true gap. Paired predictive certificates separate decoder under-use from representation insufficiency, while quantized-denoising studies demonstrate diagnosis, repair, and current-state recertification.
Read the full abstract

Artificial Intelligence

SteerBench-Work: A Benchmark for Agent Steering at Action Boundaries

Long-running LLM agents act through tools, and a single step can send an email, merge a pull request, or wire a payment. The steering decision is the pre-commit choice at that boundary: proceed, or hold for human or policy review. We introduce SteerBench-Work, an incident-anchored, bidirectional benchmark for that decision in workplace agents across developer operations, customer service, finance, legal, medical, HR, and security. Release v2026-05 contains 106 scenarios anchored in public incidents, paired evidence-reversed mirrors, and calibration controls, with labels split nearly evenly between proceed and hold so the two error directions get near-identical numbers of chances. A model sees the proposed action and the available evidence, returns a gate decision, and is scored on whether it crosses or holds the boundary correctly. Across 30 model conditions the failures run almost entirely in one direction: models wrongly hold authorized, evidence-cleared work on 28.1% of opportunities and wrongly allow unsafe work on 1.0%. The hardest cases are risk-resolved commits, where signed or structured evidence has already cleared a real risk trigger, and models score markedly worse on evidence-reversed mirrors of famous incidents (63.8%) than on the incidents themselves (98.5%). General capability is not the same as steering calibration: higher-capability models often over-refuse at the commit boundary, and more reasoning can repair a weak gate while leaving a calibrated one flat. The public leaderboard is at steerbench.com.
Read the full abstract

Computation and Language

Excess Separability: Nuisance-Controlled Residual-Stream Probing for Benchmark Contamination Detection

Benchmark contamination is diagnosed with n-gram overlap, likelihood-based membership inference, or canary strings, and each needs something usually unavailable: the training corpus, a well-chosen test statistic, or foresight at release. A recent alternative reads it off a linear probe on internal activations. We show the natural way to do this does not work, specify one that survives measurement, then find that the correction making it work carries more variance than the null it is tested against. The protocol reports a zero-sum contrast on the depth profile of probe accuracy, recentred on a level-matched placebo baseline, tested against a label-permutation null, with the reference set twice the size of the suspect set. Each choice replaces a simpler alternative we rejected on measurement. Reporting the level of excess separability rather than its shape makes the false positive rate track the size of the analyst's own control set, 0.03 to 0.99 under a true null. Contrasting against a flat depth profile rejects a true null 0.72 of the time when surface decodability rises with depth, and loses all power when it falls. On real transformers the protocol fails a test the simulations did not pose. The recentring subtracts an estimate, and the permutation null holds it fixed. Re-estimated across split seeds on four audits of contaminated checkpoints, its standard deviation is 1.30 to 1.56 times the null's own in every arm: what is subtracted to remove a bias is more variable than what it corrects. The one nominally significant result, p = 0.0075, becomes 0.0745 once that variance is propagated, and no verdict is issued. The simulations missed this because their surface key is the covariate driving item variation; on real text it is a proxy, and degrading key quality in simulation reproduces it. We add a companion measurement and a widened null. No arm shows contamination.
Read the full abstract

Robotics

Attune: A Self-Annotation Tool for Understanding Robot Operator Attention Profiles

Deploying robot fleets in complex, real-world environments requires human operators to supervise multiple robots simultaneously. Managing operator attention is a fundamental challenge of designing multi-robot supervision interfaces, encompassing both feed layout and feed content (i.e., robot behavior design). Thus far, designers lack empirical guidance on the latter-how to change a robot's behavior to capture, sustain, or relinquish operator attention during multi-robot supervision. In our vision of the future, designers should be able to use this guidance to calibrate robot behavior to different operator attention profiles. Treating operator eye gaze as a robot behavior design clue, we created a pre-deployment elicitation tool called Attune. Attune automatically identifies when meaningful gaze shifts occur, provides AI assistance for annotating why shifts occurred, and outputs a summary of operator gaze patterns for operator review. We evaluated Attune through a user study in which participants annotated the visual triggers that drew their attention. Our findings unveil variation in observed gaze patterns and reveal how Attune helps characterize operator attention.
Read the full abstract

Computers and Society

Proactive Computing

Computing systems are moving from reactive tools toward systems that sense, interpret, predict, and act before explicit user requests. This transition is enabled by the global scale of mobile connectivity, the rapid expansion of wearable and ambient sensing, advances in machine learning and foundation models, distributed edge infrastructure, and physical actuation. We define proactive computing as a paradigm in which systems infer user context, anticipate future needs or risks, and initiate information delivery or actions at an appropriate time. This survey distinguishes proactive computing from reactive, context-aware, adaptive, and predictive computing, and frames proactivity as a system-level integration problem across sensing, understanding, decision making, action, and governance. We review the technological enablers of proactive computing, organize its design space, analyze technical challenges such as uncertainty-aware triggering and the prediction-to-action gap, and discuss socio-technical issues involving user acceptance, trust, privacy, accountability, fairness, and sustainability. We argue that the key research challenge is not merely improving prediction accuracy, but determining when, how, and whether systems should act on behalf of users.
Read the full abstract

Artificial Intelligence

Jagged Judges: Epistemic Stability Under Perturbation, Pressure, and Persistence

LLM judges have become central infrastructure for model evaluations, online grading, and reward modeling. Judges are typically validated by accuracy on golden data, but accuracy says little about whether they are stable under re-prompting, challenge, or sustained pushback. We introduce the Wiggle Framework, a unified stress test for epistemic stability in LLM judges. The framework decomposes judge robustness along three dimensions: Mechanical Consistency (stability under re-prompting and reframing), Single-turn Conviction (stability under a single challenge), and Multi-turn Persistence (stability under sustained or adaptive pressure). We use the framework to study 9 frontier models across 14 judging tasks spanning safety, toxicity, AI writing detection, and political-response evaluation. Every model exhibits substantial wiggle as a judge — flipping verdicts 25–71% of the time under static pushback, and 62–91% with an adversarial LLM persuader. Critically, we find that pressure that succeeds in changing a judge's verdict is almost always net-corrupting with respect to ground truth. Beyond the framework itself, we identify baseline jury majority strength as the most effective single-shot signal for anticipating which items wiggle. Taken together, this is the first apples-to-apples cross-dataset comparison of mechanical, conformity, and persuadability tests in a judging context.
Read the full abstract

All authors Justin Zhao, Himaghna Bhattacharjee, Hannah Korevaar, Bhaktipriya Radharapu, Khalid El-Arini

Machine Learning

Interpretable Causal Discovery via Causal-Effect Constraints

Causal discovery aims to uncover the underlying causal relationships given data generated from a system. The goal, however, is not merely to predict causal edges given data, but also to be able to interpret and explain either observed or hypothesized phenomena, such as a particularly large causal effect. We consider this task of conditional causal discovery and cast it as a Bayesian inference problem, in which we target the posterior over causal graphs and parameters conditional on an event such as a causal-effect constraint. Unfortunately, this poses a computational challenge: existing approaches to Bayesian causal discovery struggle when the event has small posterior mass. To address this, we adapt rare-event estimation techniques to perform inference the joint graph-parameter space. Our method gradually drives a particle population toward the constrained region while maintaining samples that approximate the conditional posterior. Empirical evaluation on synthetic graphs validates the accuracy of our approach at small and large scales, and we show in a case study on the Sachs protein dataset how our method can be used to aid scientific exploration by providing pathway-level summaries.
Read the full abstract

Systems and Control

Improving Fast Charging Safety With Core Temperature Estimation Via Kolmogorov-Arnold Network

Fast charging of Lithium-ion batteries can lead to a significant temperature rise, which can cause serious risks to battery safety and lifetime. To ensure safe battery operation, thermal constraints must be enforced during the fast charging process. However, the core temperature of the battery cannot be directly measured in practice, which makes real-time safety enforcement challenging. This paper proposes a framework that incorporates core temperature estimates from Kolmogorov-Arnold Network within robust control barrier function (KAN-rCBF) constraints for battery fast-charging. The algorithm utilizes measurements from battery surface temperature, coolant temperature, coolant power, and charging current to solve a quadratic programming problem under safety constraints. We prescribe analytical safety guarantees for this optimal charging policy under KAN estimation errors and model uncertainty. Simulation results show that the proposed method maintains a safe battery temperature while achieving charging times comparable to the state-of-the-art method, where the latter fails to guarantee the same level of thermal safety.
Read the full abstract

Hardware Architecture

GateTruth: Auditing the Rigor of RTL Design Benchmarks via Mutation Testing

Benchmarks for evaluating large language models on register-transfer-level (RTL) hardware design have proliferated rapidly, yet none reports having applied mutation testing, an established hardware-verification technique for quantifying testbench quality, to ask whether its own testbenches are trustworthy. A testbench that never fails is not evidence of a correct design; it may simply never stimulate the logic that is actually broken. We introduce GateTruth, a mutation-testing engine and methodology for auditing RTL benchmark testbench rigor: inject a deterministic, seeded set of semantic mutants into a reference design and measure what fraction the testbench catches. We validate the methodology against our own 68-task, dual-track reference suite – 60 specification-to-RTL generation tasks and 8 agentic-repair tasks, scored through a pinned, deterministic synthesis-to-timing flow with correctness enforced as a strict gate – certifying that 46 of 60 Track A testbenches kill at least 95% of injected mutants under sequential, reproducible execution; we disclose why the other 14 do not, including a Goodhart effect on testbenches revised to pass this gate. We then point the same engine, unmodified, at RTLLM v2.0, a widely adopted external benchmark: of 46 auditable designs, 72% fall below the 95% floor our own suite is held to, and three score 0% outright. A comparable audit of NVIDIA's CVDP benchmark is structurally impossible: its public release withholds reference solutions, removing the golden RTL mutation testing requires. Auditing our own instrument also surfaced a second finding: an initially uniform 4096-token output cap silently truncated three of seven evaluated models, and re-running at 16,384 tokens moved one model from fifth place to first. We argue mutation-kill certification should become a standard reporting requirement for RTL-generation benchmarks generally.
Read the full abstract

Distributed Computing

Offering Microsecond-Scale Cross-VM Core Elasticity on Colocated Lightweight Virtual Machines

Serverless platforms commonly colocate many diverse workloads, each in a fast-booting, memory-lean virtual machine (VM), to improve deployment density. Overprovisioning each VM for its peak protects tail latency during traffic bursts but hurts density; maintaining high density while effectively protecting tail latency requires the infrastructure to be able to shift physical cores, at a microsecond timescale, to whichever latency-sensitive VM is bursting and reclaim them as the burst subsides. No VM substrate delivers this: conventional VMs resize a guest's cores only through a millisecond-scale vCPU hot-plug path, Firecracker fixes a VM's core count at boot, and the ultralight VMs that boot fastest drop multicore execution entirely. We present HyperFlux, a commodity-KVM ultralight VM substrate that makes a VM's parallelism width (the number of physical cores backing it) elastic at runtime. We show that HyperFlux can move a core across VMs in merely 13$\mu$s, even when forcibly reclaiming it from a busy donor, orders of magnitude faster than vCPU hot-plug. A HyperFlux VM incurs only a 3.2MB memory footprint and can cold-boot in 1.37ms, on par with the fastest-booting ultralight VMs, while uniquely supporting multicore parallelism. Under colocation, it can reduce high-priority VMs' tail latency by up to 10x under high load compared to static core-sharing with Firecracker and Cloud Hypervisor, and deliver a lower and more stable tail latency compared to using cgroup and vCPU hot-plug under changing load bursts.
Read the full abstract

Computation and Language

Novels generated by language models show compressed formal variation

While large language models can generate entire novels, there is little information about the level of formal variation in their output over many generations. Rather than asking whether individual passages can be identified as AI-generated, this study asks whether repeated AI generation can produce the same range of diversity which is found across human corpora. This paper contrasts six corpora based on generation source and target style: twenty novels generated using GPT-5.5 Thinking in a nineteenth-century British realist style, twenty novels generated using Qwen3-14B in a nineteenth-century British realist style, twenty novels generated using each of these models in a contemporary zero style, 205 nineteenth-century human-written British novels, and sixty-five contemporary human-written Zero-Style novels. At the document level, the research includes MATTR-500, Shannon entropy, average sentence length, readability, and punctuation rate measurements. The most robust and reliable result is compression of sentence structure. Repeated generations produce novels that vary far less from one another in sentence structure than human novels do. Compression is also present in the measures of readability, punctuation, and sentence length variability within novels. Lexical measures tend to be similarly compressed, with the exception of Qwen Zero-Style MATTR. Despite having distinct mean stylistic profiles, GPT and Qwen lack a stable pattern of cross-measure correlation. This article therefore distinguishes between variance overclosure, which represents a limited formal range between novels, and a more specific phenomenon of correlational overclosure. This means that an individual AI-generated novel may resemble human fiction stylistically, while a collection of AI-generated novels occupies a much narrower formal range.
Read the full abstract

Machine Learning

CAKE: Compiler-Agent Co-Design for Frontier Kernel Evolution

GPU kernel agents and GPU programming languages have advanced separately, leaving expert kernels difficult to reproduce. Agents usually treat the compiler as a fixed black box and receive only errors, correctness outcomes, and timing, while existing DSLs either hide critical scheduling decisions or expose them through difficult layout abstractions. We present CAKE, a compiler-agent co-design in which agents author CAKE IR, a typed, hardware-explicit schedule representation. CAKE exposes warp roles, memory movement, synchronization, and pipelines while supporting verification, cost modeling, and localized diagnostics. The harness itself evolves: recurring failures become verifier rules, IR primitives, model calibrations, and reusable optimization tactics. In matched implementation-hidden Flash-KMeans clean starts on B200, the best CAKE IR candidate at an 80-million-token budget runs at 1.144x the tuned FlashML baseline, compared with 0.928x for direct CUDA/PTX. Beyond this benchmark, agent-generated Kimi Delta Attention achieves a 2.05x geometric-mean speedup over official FlashKDA and passes end-to-end serving validation. Dispatcher-backed KNN and KMeans improve performance by 1.42x to 2.12x across more than 400 shapes, and four kernel changes are available as upstream PRs. CAKE targets NVIDIA GPUs from Ampere through Blackwell and separates single-shape evolution from library generalization and dispatch.
Read the full abstract

All authors Zihao Ye, Yingyi Huang, Hongyi Jin, Bohan Hou, Junru Shao, Zhongming Yu, Jinqi Chen, Meghan Cowan, Shiyi Cao, Shanli Xing, Hanfeng Chen, Vinod Grover, Tianqi Chen, Luis Ceze

Data Structures and Algorithms

The Cost of Changing Edges for Diameter Computation and More

The sensitivity setting is a restricted setting for dynamic algorithms, particularly practical for scenarios where extensive preprocessing is feasible but responses to real-time modifications must be near-instantaneous before the data structure is eventually rebuilt. For graph problems, a sensitivity data structure is constructed with a preprocessing time P so that the following queries can be answered quickly, preferably in $O(1)$ time: given an edge $e$, return the answer to the problem on either $G \setminus e$ (decremental) or $G \cup e$ (incremental). We almost entirely settle the decremental setting for the diameter and eccentricities problems in a variety of approximation regimes by matching P to the static runtime while supporting $O(1)$-time queries, thereby improving upon all previous single-failure results [Biló, Cohen, Friedrich, Schirneck, MFCS 2021; Biló, Choudhary, Cohen, Friedrich, Krogmann, Schirneck, ICALP 2023, Algorithmica 2026]. More precisely: (1) We provide a tight reduction demonstrating that any exact distance sensitivity oracle can be used to efficiently solve decremental exact diameter and all-node eccentricities; (2) For the approximate setting, we match the runtime of all known static diameter algorithms across all sparsity settings, up to an additional $1+o(1)$ factor in approximation. Conversely, for the previously unexplored incremental setting of these problems: (3) We develop new lower bounds, demonstrating that no incremental algorithm can efficiently approximate diameter, radius, or eccentricity beyond a $5/3$ factor in undirected graphs or a $2$ factor in directed graphs; (4) We introduce two new instructive techniques and demonstrate how to utilize them to construct several new algorithms. Most notably, we develop incremental single-node eccentricity approximations for both directed and undirected graphs that match our new lower bounds.
Read the full abstract

All authors Sam Hiken, Yael Kirkpatrick, Jakob Nogler, Virginia Vassilevska Williams

Computer Vision

EgoCITE: Context-Augmented Indexing and Time-Aware Retrieval for Long-Horizon Egocentric Memory

Long-horizon egocentric memory transforms continuous first-person video and audio into a searchable record of past experiences. We demonstrate two bottlenecks in existing systems: indices built from context-poor captions are unreliable for agentic search, while retrieval ignores a question's temporal intent. To address both bottlenecks, we introduce EgoCITE (Egocentric Context-augmented Indexing and Time-aware Evidence retrieval), a long-horizon agentic memory framework for egocentric QA. EgoCITE comprises three components. EgoScheme uses local multimodal context to turn fragmentary video captions and speech transcripts into self-contained atomic memory indices. EgoIndex organizes complementary action, activity, utterance, and conversation representations into searchable multi-view memory indices at multiple granularities. EgoRetrv combines semantic search with question-conditioned temporal relevance scoring and curation of retrieved evidence. We evaluate EgoCITE on EgoLifeQA, EgoMem, and EgoR1-Bench in terms of answer accuracy and target-event retrieval alignment. EgoCITE improves accuracy over agentic memory baselines by at least 4.4–14.2% while achieving 36$\times$ lower cost than long-context LLM agents.
Read the full abstract

All authors Le Zhang, Hao Chen, Vlad Roznyatovskiy, Jianzhong Zhang, Ke Sun

Computation and Language

LLMs Are Not Good Strategists, Yet Memory-Enhanced Agency Boosts Reasoning

Strategic reasoning in Large Language Models (LLMs) within long-horizon environments is often limited by inconsistent subgoals. In these settings, finite attention resources prevent the model from maintaining strategic coherence over thousands of steps. This limitation leads to strategic drift, where localized decisions fail to sustain a coherent trajectory across reasoning. To address this, we introduce EpicStar, a framework that enables agents to learn memory as policy to tackle long-horizon reasoning. Specifically, the agent maintains a bank of successful past episodes as a heuristic alongside a working memory to track short-term environmental changes. During inference, a dynamic gating mechanism determines whether to execute a retrieved action directly or to perform new reasoning through a contextual fusion of the retrieved episodes and current working memory. Utilizing StarCraft II as the testbed, we evaluated EpicStar against diverse opponent styles. It significantly outperforms baseline methods, achieving higher win rates while consuming an order of magnitude fewer tokens, and it maintains this advantage consistently across difficulty levels and opponent strategies. Our findings provide compelling evidence that structured cross-episode memory is essential for enabling LLM agents to perform robust, long-term strategic execution in dynamic, autonomous settings.
Read the full abstract

Machine Learning

Structure-preserving uncertainty quantification for GENERIC dynamics

Structure-preserving machine learning embeds physical structure directly into model architectures, yet uncertainty quantification (UQ) for such hard-constrained models remains limited because standard UQ methods may violate the encoded admissibility conditions, require architectural modifications, or impose substantial computational costs. In this work, we propose Structure-Preserving Epistemic Neural Networks (S-PENNs), a general framework for UQ in scientific machine learning models with hard architectural constraints, and instantiate it for GENERIC (General Equation for Non-Equilibrium Reversible-Irreversible Coupling) dynamics. S-PENNs preserve the structural constraints of a pretrained model by attaching lightweight epinets to its constrained components, ensuring that every sampled realization remains physically admissible by construction. When applied to GENERIC dynamics, such a proposed framework yields thermodynamically consistent rollouts that preserve the first and second laws. Furthermore, we combine S-PENNs with split conformal prediction as a post-hoc calibration method to produce prediction intervals with finite-sample marginal coverage guarantees. We validate S-PENNs on three numerical examples: a harmonic oscillator coupled to a heat bath and an idealized chemical motor, both governed by ODEs, and a one-dimensional viscoplastic model governed by PDEs. Across all three examples, S-PENNs produce thermodynamically consistent stochastic realizations and well-calibrated prediction intervals while reducing the computational cost by about one to three orders of magnitude compared to deep ensembles. Although the present study focuses on GENERIC dynamics, S-PENNs can be extended more broadly to scientific machine learning models in computational mechanics with either hard or soft constraints.
Read the full abstract

Computation and Language

When Explanations Betray Backdoors: Black-Box Auditing for Language Model Classifiers

Language model classifiers with explanations are used for moderation, routing, topic triage, and low-resource annotation. We study black-box auditing when the defender has only clean calibration data without trigger information but can ask the classifier for a label plus a short rationale or quoted evidence. We introduce Groundedness Drift, a lightweight score measuring whether the answer summary remains grounded in the input. Across two 7B backbones, five datasets, and four common non-adaptive OpenBackdoor-style attack families, Groundedness Drift achieves higher AUROC and lower residual target ASR than every compared detector in all cases at a nominal 5% clean-FPR budget. We then evaluate Unsupported Groundedness, a multi-probe escalation for explanation-camouflage stress cases. Unsupported Groundedness improves signals but does not close the adaptive gap.
Read the full abstract

Machine Learning

The Boolean Power of ReLU

We prove that, on finite simple undirected graphs equipped with a single Boolean node feature, the Boolean queries expressible in $\Sigma$-MPLang, for any collection $\Sigma$ of eventually constant activation functions and with arbitrary real coefficients, form a strict subclass of the Boolean queries expressible in ReLU-MPLang. We thereby settle a recently posed open problem: whether ReLU-MPLang is more powerful than trReLU-MPLang when it comes to Boolean queries. In particular, this implies that ReLU-GNNs are strictly more expressive than {TrReLU,id}-GNNs with respect to Boolean queries on Boolean-featured graphs.
Read the full abstract

All authors Pablo Barceló, Floris Geerts, Matthias Lanzinger, Klara Pakhomenko, Jan Van den Bussche

Sound

Drive-to-Music: Context-Aware Generative Audio for In-Vehicle Experiences

In-vehicle music can serve as an adaptive interface to enhance driver experience, attention, and well-being. We present Drive-to-Music, a context-aware system that generates music in real time from multimodal driving signals. Using dashcam imagery and vehicle telemetry, the system extracts scene semantics and driving context, maps them to high-level musical descriptors, and conditions generative audio models to produce contextually aligned soundtracks. The architecture combines perception and generative components to translate visual and kinematic inputs into structured musical attributes and synthesize audio with low latency. It supports smooth transitions as driving conditions evolve, and to ensure robustness and deployment readiness, we incorporate constraint-based controls and safety checks across the generation pipeline. Our results demonstrate the feasibility of real-time, context-aware music generation in automotive settings, providing a foundation for personalized and adaptive in-vehicle audio experiences.
Read the full abstract

Computer Vision

From Visual Widgets to UI Code: Efficient Tool-Grounded Generation

Existing screenshot-to-code systems face a trade-off between flexibility and controllability. Direct multimodal generation can hallucinate visible details, whereas structured pipelines reduce such errors through component-wise decomposition, predefined templates, and customized intermediate representations. These structures, however, introduce additional generative orchestration and restrict outputs to designs covered by the representation. We investigate whether selective tool grounding can improve the fidelity–efficiency trade-off of direct widget-to-code generation. We introduce WidgetGen, a lightweight tool-grounded framework that extracts observable text and color evidence, performs high-level layout and optional chart reasoning, and directly generates executable JavaScript XML (JSX). This design reduces reliance on component-wise generation while avoiding a fixed UI schema. Across six multimodal models and \(1{,}000\) held-out widgets, WidgetGen outperforms direct prompting and the structured Widget2Code pipeline on most visual reconstruction metrics, with consistent gains in area, legibility, and style. Finally, reconstruction-derived image-code pairs improve six Qwen-family open-weight models across every reported metric through supervised fine-tuning. These results establish WidgetGen as a strong lightweight baseline and show that selective evidence grounding offers an effective alternative to extensive representation constraints.
Read the full abstract

All authors Houston H. Zhang, Tao Zhang, Li Gu, Linfeng Ye, Yuanhao Yu, Xinxin Zuo, Yang Wang, Zhixiang Chi

Artificial Intelligence

@skills: Attention is all you have

There are 56,804 public agent skills today, and teams write many more privately. The dominant delivery model is installation: once installed, a skill's description remains in the system prompt, competing for fewer than 100 reliable trigger slots. This leaves the long tail with no practical path to use and forces teams' own playbooks to compete for the same scarce space. We observe that installation bundles three separable functions: content, persistence, and automatic triggering. Only the last requires prompt residency. We therefore propose @skills, an open protocol that separates them. A path addresses any skill, subtree, or collection, and reading a skill is sufficient to use it, so nothing is installed or made resident. The operation vendors a copy at the same path into a project's Git-tracked tree for adaptation and ownership. The operation adds one .gitignore-style line, the only element that costs prompt residency. A directory is a menu, making bundles ordinary directories rather than all-or-nothing units. The protocol requires no manifest, lockfile, or registration, and SKILL.md remains unchanged. @skills is additive, ships as an installable package, and turns any agent that can read files and run commands into a client through a single instruction file. Its open specification is at https://github.com/SylphAI-Inc/atskills and it is implemented in the AdaL CLI at https://adalagent.ai . Because paths address skills well but cannot find them, the protocol is paired with a free hub at https://atskills.one for corpus-wide search and ranking, repository-free hosting, private and team collections, and one-screen authoring. The hub is optional: gh: and local paths resolve without it, and indexed GitHub skills retain their gh: identities. Install less, use more.
Read the full abstract

All authors Li Yin, Zhi Li, Zhan Shi, Haoran Zhang, Haebin Seong, Zhangyang Wang

Systems and Control

Security-Constrained Operation of IBR-Dominated Power Systems: Static and Dynamic Security Across Preventive and Corrective Decisions

Inverter-based resources (IBRs) couple power system operation to fast dynamics and controller-dependent responses. Their configurable capabilities are reshaping the formulation and coordination of security-constrained operation. This paper presents a two-axis view: static versus dynamic security and preventive versus corrective decision timing. Preventive scheduling is extending from static post-contingency feasibility toward dynamic security, while corrective operation spans equilibrium-based corrective actions and trajectory-based control. A generic formulation represents this change and makes the preventive–corrective tradeoff explicit. Existing formulations, methods, and capability representations are reviewed and synthesized within this framework. The surveyed work yields two findings. First, IBR capability can expand the feasible set or relieve security constraints, reducing operating cost or improving security performance. Second, shared capability and constraints across formulations determine whether that capability remains operationally deliverable. These findings motivate future research in IBR capability characterization and quantification, joint scheduling, and scalable solution frameworks.
Read the full abstract

Human-Computer Interaction

Surprise2Refine: Axis-Centered Exploration-To-Refinement for Agent-Assisted Creative Scaffolding

Designers require different design spaces across creative stages: broad during exploration, and targeted during refinement. Yet existing agent-driven tools assume a fixed or continuously expanding space, leaving designers to manage and navigate it themselves. Informed by a formative study with five designers, we propose an axis-centered workflow that adaptively broadens and narrows the design space to support structured exploration and refinement. We implemented this workflow in Surprise2Refine, a prototype that allows users to build and reshape an nxn design space through a set of axis-centered interactions as their creative intent evolves. A within-subjects study with 14 designers shows that Surprise2Refine enhances users' sense of control, supports tracking of scaffolding paths, and improves the perceived creativity of design outcomes. We further distill design insights to guide future agent-assisted tools for creative scaffolding.
Read the full abstract

All authors Yuzhe You, Gromit Yeuk-Yin Chan, Shunan Guo, Anlan Zhang, Eunyee Koh, Jian Zhao, Tongyu Zhou

Computer Vision

PseudoMapLabeler: Confidence-Aware Pseudo-Label Generation for Semi-Supervised Online Mapping

A critical challenge in deploying online HD map construction systems to real-world scenarios is the scarcity of labeled training data, which limits model generalization in diverse environments. To address this limitation, we propose a teacher-student semi-supervised learning (SSL) framework that generates high-quality pseudo-labels from unlabeled data through confidence-aware map refinement. Our approach first trains a teacher model on limited labeled data, then leverages Beta-distribution-based confidence maps to assess the reliability of predicted map elements across temporal observations. Unlike conventional filtering methods that discard entire elements, we introduce a spatial clipping technique that selectively preserves high-confidence regions while removing unreliable segments. The refined map elements serve as map priors that improve the teacher model's prediction accuracy on unlabeled data in a second pass. These enhanced predictions become pseudo-labels for training a student model from scratch, followed by fine-tuning on the original labeled data. Experimental results on the nuScenes dataset demonstrate that our teacher-student framework with refined pseudo-labels improves performance by +6.1 mAP under a low-label regime compared to training on labeled data alone, offering a practical solution to the labeled data scarcity problem in online HD map construction.
Read the full abstract

All authors Chikao Tsuchiya, Dhaval Bhanderi, David Ilstrup, Hsinmin Cheng, Christopher Ostafew

Artificial Intelligence

Dead text or binding clause? Measuring and restoring constraint influence in black-box LLM dialogues

Multi-turn dialogues let users revoke constraints as easily as impose them, but revocation does not reliably take effect: models keep enacting withdrawn requirements (occasionally beneath comments asserting their removal), a failure we call behavioral relapse, or revocation inertia. No existing instrument measures this influence per clause, predicts it before delivery, or repairs it under matched budgets. \sysname{} closes the three gaps through the model API alone: a contract ledger pairs every constraint with an executable checker, records revocations as tombstones, and compiles the net constraint state ahead of time into a single specification; a sequential ablation probe measures per-clause adherence and incremental behavioral effect; a repair ladder operates under token- and attempt-matched budgets. On \dataname{} (\NTasks{} HumanEval tasks, \NClauses{} verified checkers), relapse at an 8B operating point climbs from \ScaleDelayedMTwo{} to \ScaleDelayedMEight{} as constraint load grows, while stronger models sit at floor. Under matched checkers, model, and budget, ahead-of-time compilation significantly reduces relapse against a no-ledger verifier-retry baseline (\RestoreDiff{}, 95% CI \RestoreDiffCI{}, $p$ \RestoreDiffP{}); adaptive ladder interventions stacked on top add no detectable gain (95% confidence excludes gains $\geq$ \LadderExcludedGain{}). The probe predicts relapse before delivery (AUROC \AurocPrimary{}); a one-sentence tombstone note recovers about a third of the compilation effect and survives a placebo control. At \CostDeliveryFactor{} delivery overhead and \CostTotalHedged{} of API compute for every result, revocation failure becomes a measurable, predictable, and repairable property of dialogue state rather than an invisible one.
Read the full abstract

Computation and Language

Intensional Anaphora

Intensional operators are often treated as quantifiers over possible worlds, parallel to the treatment of determiners as quantifiers over individuals. Yet individuals introduced in intensional contexts cannot serve as antecedents to later pronouns as easily as those introduced in merely quantificational contexts. For instance, "Everyone is eating a cheeseburger" may be followed by "They are large", where "they" refers to the cheeseburgers being eaten. However, as Stone (1999) points out, the similar "Andrea might be eating a cheeseburger" does not support later anaphoric references such as "It is large" or "They are large". Stone (1999), Stone and Hardt (1999), and Brasoveanu (2010) address this by requiring a pronoun's value (its referents) to exist in the world of evaluation, ruling out anaphora from non-veridical intensional contexts. We show, however, both cases where such anaphora is disallowed even when the pronoun's referents clearly exist and cases where it is allowed even though they might not exist. We argue that intensional anaphora is best captured using a description-based rather than value-based account. A pronoun presupposes that its corresponding antecedent description is instantiated in each world of the context set. Thus, there must be a cheeseburger being eaten by Andrea in every candidate world for "It is large" to be felicitous after "Andrea might be eating a cheeseburger". We implement our proposal via a new logic, building on Keshet (2018) and Abney and Keshet (2022), called Plural Intensional Presuppositional predicate calculus (PIP). Each PIP formula translates directly into standard first-order predicate calculus with set abstraction, providing a classical foundation for this work.
Read the full abstract

Machine Learning

Predicting When Random Low-Dimensional Reparameterizations Train Neural Networks

Neural networks can often be trained or fine-tuned through random low-dimensional reparameterization, where a small latent vector is mapped into a full parameter update by a frozen random map. This raises a practical question: how large must the latent search space be to reach a low-loss region? We first express the known accessibility transition in an equivalent conic form, centered for compact convex targets at the statistical dimension of the polar cone. Our main theoretical contribution is an orientation-resolved quadratic master formula that predicts the random-slice residual from both the curvature spectrum and the reference-to-solution displacement profile. It yields a self-consistent isotropic-orientation predictor and, in a conservative radius-only specialization, recovers the earlier Gaussian-width quadratic bound. Building on this analysis, we introduce Random Mapping Networks (RaMaN), which instantiate the predicted latent dimension using structured Hadamard or seed-regenerated Gaussian maps. These constructions avoid the O(dP) storage of dense random maps and reduce optimizer-state memory from O(P) to O(d). We also develop matrix-free curvature approximations and sweep-free dimension selection. Across controlled quadratic and neural-curvature experiments, the orientation-resolved predictor closely tracks measured transition locations and outperforms orientation-agnostic approximations when displacement direction matters. End-to-end experiments further show sharp, protocol-dependent training transitions across image and language models.
Read the full abstract

All authors Andrew Cheng, Ali Eslamian, Jie Cheng, Mehdi Zargham, Qiang Cheng

Information Theory

On Nearly-Perfect Covering Codes Beyond Radius One

We study (binary) nearly-perfect covering codes, which are codes that attain the Van Wee bound with equality. They act as the covering counterparts to nearly-perfect error-correcting codes, which attain the Johnson bound with equality. These codes have been completely classified for covering radius $R=1$. We prove that no code with $R\geq 2$ can attain the original Van Wee bound with equality, since it omits the dependence on the minimum distance of the code. We refine the bound to account for the minimum distance and show some nearly-perfect covering codes. By proving some structural properties of such codes, we prove all nearly-perfect covering codes with $R=2,3$ must be equivalent to the codes we showed. We also prove that for any $R\geq 3$, there are at most a finite number of nearly-perfect covering codes.
Read the full abstract

Artificial Intelligence · Cross-listed from q-fin.ST

What Makes a Peer? Valuation-Anchored Similarity in Private Markets

As more investors contemplate private markets and contend with limited transparency, sparse disclosures, and infrequent transactions, identifying economically meaningful peer companies for comparison is a fundamental challenge for valuation, due diligence, portfolio construction, and risk management. We propose an ensemble tree-based supervised similarity learning framework that defines company similarity through the lens of market valuation rather than static feature matching or semantic descriptions. Specifically, we train a CatBoost gradient-boosted decision tree model on observed private company valuations and derive a valuation-aware similarity metric from importance-weighted leaf-node co-occurrences across the ensemble. The similarity metric captures shared valuation drivers while accommodating nonlinear relationships, mixed data types, and pervasive missing data common in private markets. Using a global private-market universe of approximately 270,000 companies, including more than 53,000 firms with observed or derivable post-money valuations spanning multiple industries, geographies, and deal stages, we demonstrate that the proposed similarity framework improves upon traditional distance-based and text-embedding-based approaches in downstream k-nearest-neighbor valuation tasks in the evaluated industry groups, while retaining case-based explainability.
Read the full abstract

All authors Sebastian Frank, Jingrao Lyu, Max Jarmey, Preetha Saha, Mingshu Li, Sweet Kaur, Sola Akinola, Dhagash Mehta