Yu-Cheng Chou, Shihao Wang, Jin Huang, Chi-Pin Huang, Chiao-An Yang, Xianzhe Fan, Jing Wang, Zhiqi Li 等 19 位作者
Models for physical AI tasks, such as robotics and autonomous driving, need not reason solely in language. They can use visual plans--points, bounding boxes, and trajectories--to represent spatial goals and anticipate motion. However, autoregressive vision-language models generate these plans one coordinate token at a time, making richer predictions increasingly costly. We introduce VFlash, a method for fast, accurate visual planning through Flash Primitive Decoding. VFlash exploits the known structure of visual primitives to predict their coordinates jointly, using a lightweight drafter that generates an entire primitive in one forward pass. The layout adapts to the primitive's type, dimensionality, and length, supporting compact boxes and long, variable-length trajectories. Crucially, spatial accuracy need not require reproducing an autoregressive model's exact token sequence. VFlash therefore trains on annotated primitives and directly accepts structurally valid predictions without target-token agreement. Across the evaluated 2D and 3D robot trajectory tasks, VFlash consistently reduces prediction errors relative to autoregressive decoding. Preliminary single-rollout measurements indicate approximately 25x faster generation for 3D point motion forecasting. A world action model conditioned on VFlash plans achieves 70.2% average success across four MolmoSpaces task suites, compared with 62.6% for the baseline.
Xuan Zhao, Haonan He, Qingyu Yang, Minglei Li, Zelin Tan, Bo Wan, Jingqi Ye, Chen Zhang 等 10 位作者
For LLMs, skills are textual recipes encoding mature problem-solving experience. Despite widespread deployment, their utility is limited by the model's ability to comprehend and follow skill instructions. To address this limitation, we propose ParametricSkills, a framework that parameterizes textual skills at test time, enabling context-free management of the full skill lifecycle. Specifically, we first construct a large-scale and high-quality skill collection, and then synthesize single-turn and multi-turn skill-exploitation trajectories. Using this data, we then train a hypernetwork that parameterizes both the content and the exploitation methodologies of skills by converting textual skills into LoRA adapters. To facilitate the real-world application of our framework, we further align the hypernetwork on complex, long-horizon trajectories collected with OpenCode, enabling the models to operate reliably in realistic interactive workflows with ParametricSkills. Across evaluations, ParametricSkills effectively parameterizes skills, yielding substantial gains in task completion. More notably, as parametric skills accumulate as adapters rather than crowding the context, they open a preliminary but promising path toward continual learning at test time.
ChemE-as-Code provides an open-source environment in which AI agents built on large language models (LLMs) can carry out chemical engineering work and engineers can check it. Its calculation tools range from catalysis through process simulation to plant layout, HAZOP and life cycle assessment, and skills tell a general-purpose agent how to use them. Engineering files are linked, machine-readable and versioned in Git; calculations run outside the LLM, each value records its origin, and automated checks report inconsistencies and out-of-date results by file and line. In an illustrative ammonia case, agents developed a written task into a preliminary basic-engineering package (simulation files, P&IDs, layout, HAZOP, datasheets, relief) for USD 224 of API cost in the design sessions. Planted faults and engineering changes show that the checks find what their rules cover and miss the rest, so they guide human review rather than replace it. No independent engineer has reviewed the design.
Large language models (LLMs) are often used in environments where facts evolve, yet factual knowledge updates via fine-tuning on unstructured plain text often suffer from 1) reliance on paraphrasing augmentation, without which training does not generalize to downstream QA tasks, and 2) the reversal curse. Recent evidence of the sample efficiency of masked diffusion large language models (dLLMs) and the bidirectional information flow in their demasking training objective suggests that the demasking objective may facilitate knowledge learning from raw knowledge text. We test this hypothesis in controlled knowledge fine-tuning experiments on dLLMs and autoregressive LLMs (arLLMs) and find that while arLLMs rely on paraphrase augmentation to generalize knowledge text into question-answering (QA) capability, dLLMs do not require paraphrases to achieve high QA accuracy. We find that giving arLLMs a demasking objective, where the LLM must reconstruct the original text from a masked copy given in context, improves the efficacy of knowledge injection, removing the need for paraphrases and mitigating the reversal curse, recovering most of the gap between arLLMs and dLLMs. We also provide preliminary evidence of the broader applicability of using the demasking objective in arLLM fine-tuning on a large-scale knowledge-intensive dataset.
Short-horizon model predictive control (MPC) is fast but myopic. ZipMPC compensates by learning a context-dependent correction of the short-horizon cost that imitates a long-horizon expert. We observe that the optimal correction is often multimodal: when a slower opponent can be passed on either side, good corrections of opposite sign coexist, and the expert's choice between them hinges on tiny cost differences. Deterministic regression then averages modes or inherits inconsistent expert tie-breaking. We propose ZipDrift, which trains a one-step drifting generator over MPC cost corrections, tilted toward low closed-loop cost and learned only from cost evaluations of candidate corrections, without differentiating through the optimiser. A few generated candidates are ranked by a learned critic, and the model-based MPC then enforces dynamics and constraints. In a kinematic overtaking benchmark derived from ZipMPC, more than half of the contexts are bimodal and the manual short-horizon MPC crashes in 28% of them. With an eight-dimensional stagewise correction, evaluated on 1000 fresh contexts and five training seeds, ZipDrift with eight candidates crashes in 0.74% of episodes, compared with 3.4% for an idealised ZipMPC-style regressor and 2.1% for critic-ranked random candidates with the same budget. A mixture density network (MDN) with the same selection is equally good (0.76%). The benefit of drifting lies in sample quality: in a pre-specified test on further unseen contexts, a single drifting sample crashes in 8.7% of episodes against 13.2% for the MDN, and ZipDrift needs four candidates instead of eight to fall below 1%. With many candidates, all methods degrade as selection exploits errors of the critic.
Dongdong Wang, Alina Hagen, Isabelle Gatmaitan, Hao Zhou, Yiwen Dong, Shabboo Valipoor, Vivian W. H. Wong, Lingyao Li
Assessing built-environment interaction, such as wheelchair accessibility, is challenging because real-world mobility is shaped by context-dependent and temporary barriers that are difficult to capture at scale. This paper examines whether vision-language models (VLMs) can identify potential accessibility barriers from Google Street View (GSV) imagery. We propose an expert-guided retrieval-augmented framework that combines GSV imagery, ADA-informed guidance, and expert-derived rubrics to evaluate multiple accessibility dimensions. We collect a campus-scale dataset at the University of Florida, linking 407 unique GSV locations with GPS-derived wheelchair dwell behavior as a proxy for potential mobility friction. Results show that VLM ratings are negatively correlated with dwell time and exhibit distributional similarity, with the expert-guided configuration strengthening the correlation from $r=-0.40$ to $r=-0.54$ for the strongest model. Visual cue analysis further shows that features such as curb ramps and crosswalks are associated with higher VLM accessibility scores, while correspondence remains limited for subtle surface conditions, transient obstructions, and viewpoint-dependent barriers. Overall, our findings demonstrate the potential of expert-guided VLMs for scalable preliminary accessibility screening and prioritizing locations for further investigation.
Transformers, with their self-attention mechanisms for modeling long-range dependencies, have become a dominant paradigm in image restoration tasks. However, the high computational cost of self-attention limits scalability to high-resolution images, making efficiency-quality trade-offs a key research focus. To address this, Restormer employs channel-wise self-attention, which computes attention across channels instead of spatial dimensions. While effective, this approach may overlook localized artifacts that are crucial for high-quality image restoration. To bridge this gap, we explore Dilated Neighborhood Attention (DiNA) as a promising alternative, inspired by its success in high-level vision tasks. DiNA balances global context and local precision by integrating sliding-window attention with mixed dilation factors, effectively expanding the receptive field without excessive overhead. However, our preliminary experiments indicate that directly applying this global-local design to the classic deblurring task hinders accurate visual restoration, primarily due to the constrained global context understanding within local attention. To address this, we introduce a channel-aware module that complements local attention, effectively integrating global context without sacrificing pixel-level precision. The proposed DiNAT-IR, a Transformer-based architecture specifically designed for image restoration, achieves competitive results across multiple benchmarks, offering a high-quality solution for diverse low-level computer vision problems.
This is a preliminary version of a book in progress on the theory of quantum communication. We adopt an information-theoretic perspective throughout and give a comprehensive account of fundamental results in quantum communication theory from the past decade (and earlier), with an emphasis on the modern one-shot-to-asymptotic approach that underlies much of today's state-of-the-art research in this field. In Part I, we cover mathematical preliminaries and provide a detailed study of quantum mechanics from an information-theoretic perspective. We also provide an extensive and thorough review of quantum entropies, and we devote an entire chapter to the study of entanglement measures. Equipped with these essential tools, in Part II we study classical communication (with and without entanglement assistance), entanglement distillation, quantum communication, secret key distillation, and private communication. In Part III, we cover the latest developments in feedback-assisted communication tasks, such as quantum and classical feedback-assisted communication, LOCC-assisted quantum communication, and secret key agreement.
FlowReconBench: Accuracy, calibration and cost of learned and classical flow reconstruction from sparse sensors
Nicolas Tricard, Linzheng Wang, Jason Chen, Sili Deng
AI 速览：该基准在三种流态下统一比较十种学习型与五种经典稀疏传感器流场重建方法，考察逐通道误差、集合离散度、校准、频谱与计算成本。
Reconstructing full flow fields from sparse sensors requires prior assumptions about unmeasured regions and physical variables. Yet it remains unclear when learned models outperform classical estimators and which aspects of their predictions can be trusted. FlowReconBench evaluates ten learned and five classical methods on three regimes: a laminar cylinder wake across Reynolds numbers, two-dimensional Kolmogorov turbulence and a large-scale three-dimensional (3D) isotropic turbulence. Methods share leakage-controlled splits and sensor draws and are scored on per-channel error, ensemble spread, calibration, spectra and cost. The leading method changes for each regime. Classical methods perform strongly in low-order and dense-sensing regimes. On the cylinder wake, linear stochastic estimation and gappy proper orthogonal decomposition lead, including for unobserved pressure. In 3D, inverse-distance weighting matches the best learned methods on observed channels. Data-driven methods become superior at decreasing sensor density or poor sensor observability. On Kolmogorov flow, continuous ranked probability score and error yield different method rankings: generative models offer broader but underdispersed ensembles, while deterministic models prioritize pointwise error. Generative models balance this tradeoff through their sampler budget, with a larger budget improving ensemble quality at higher computational cost. In 3D, scaling tests demonstrate that queryable methods are flat in memory, while full-grid construction methods run out of memory. Observing only 2 of 4 fields leaves the problem kinematically underconstrained, yet a latent model can reproduce structural similarities to the ground truth.
SAUCE: Summary Analysis Using Conversation Entailment
Man-Ling Sung, Hemanth Kandula, Jeff Ma, William Hartmann, Matthew Snover
AI 速览：提出一种无参考、基于事实的跨语言对话语音摘要评估流程，通过对话与摘要间的蕴含关系衡量摘要准确性与事实覆盖度。
With the growing need for evaluating Large Language Models (LLMs) and their applications to speech, challenges persist in summarizing and evaluating conversations that lack a clear end goal. We introduce SAUCE -- a reference-free, fact-based evaluation pipeline for cross-lingual conversational speech summarization. It measures the accuracy and the fact coverage of a summary through the entailment between conversation and text. We compare SAUCE against several popular summarization metrics and demonstrate the effectiveness of capturing information loss due to transcription and translation error and identifying broken summaries. Crucially, unlike black-box LLM evaluators or dense embedding metrics, SAUCE is inherently explainable: it maps summary scores to discrete, verifiable facts, allowing users to pinpoint exact hallucinations or omissions. We illustrate how this interpretability helps developers systematically profile LLM behaviors and gives end-users an actionable tool to verify summary accuracy in noisy, real-world conditions. Preliminary investigations show SAUCE strongly align with human judgment.
``Emergence'' refers to the fact that different mathematical languages and theories seem to be required to describe scientific theories that operate at different spatial and temporal scales. Highly circumscribed, special cases of emergence have been investigated using many different formal tools, including coarse-graining (over space and / or time), renormalization, dimension reduction, broken symmetry, and various formulations of causality. Here we extend the mathematics of model theory to unify and extend these earlier investigations. As a preliminary application of our framework, we investigate canonical examples of emergence, including the emergence of genetics from chemistry, of psychology from neurobiology, and of different forms of collective behavior from the laws governing their constituent parts. By exploiting the power of model theory we also uncover many aspects of emergence that were previously obscured. In particular, we uncover some of the rich hierarchical structure that relates different scientific fields. For example, we show that scientific fields can be related via a collection of multiple partial orders, all defined over the same set. On the other hand, under an alternative relation among scientific fields, one which allows cycles, we show that it is possible that the set of all of scientific fields must collapse into a single scientific field. Going forward, these investigations point to the formal tools that might need to be developed in order to arrive at a deeper understanding of this emergent hierarchy of scientific reality.
Kejian Zhu, Zhuoran Jin, Shangqing Tu, Tianyi Men, Yupu Hao, Jiachun Li, Kang Liu, Jun Zhao
While multi-turn agentic reinforcement learning (RL) excels on long-horizon tasks, its performance gains remain highly sensitive to interaction constraints. Evaluating across sampling breadth $K$ and interaction depth $T$ via $Pass@(K,T)$, we show that trajectory-level RL advantages depend on sufficient turn budgets, diminishing significantly when budgets tighten. Besides, agentic RL does not uniformly elevate single-step decision quality; rather, its strength concentrates in error recovery and long-horizon resilience. To mitigate the deployment risks caused by this budget dependence, we provide a preliminary discussion on the benefits and limitations of process supervision signals and introduce BudgetMix RL as an alternative that varies interaction budgets during training. Experiments demonstrate that BudgetMix RL achieves robust performance across diverse execution settings. Project Page: https://rethinking-agentic-rl.github.io/
Xi Chen, Julien Cumin, Fano Ramparany, Dominique Vaufreydaz
Ambient sensors offer a privacy-preserving solution for activity recognition in smart homes, yet they face a critical challenge in multi-resident environments known as Data Association, which aims to identify the resident triggering a specific anonymous sensor event. Existing approaches fundamentally fail to maintain global consistency by often yielding conflicting associations for silent residents. Additionally, these methods frequently suffer from severe trajectory fragmentation caused by the ontological mismatch of applying continuous physical motion models to discrete logical behaviors. To address these limitations, we propose a novel framework that reformulates data association as a sequential decision-making task within a Markov Decision Process (MDP). We solve the defined MDP via Behavior Cloning (BC) to avoid complex reward engineering by directly learning from expert demonstrations. We instantiate the policy using two complementary architectures, including a lightweight Transformer that treats association as a multi-label classification task over linearized event histories, and a fine-tuned Large Language Model (LLM) that reformulates the problem as conditional text generation to leverage pre-trained semantic knowledge. Extensive evaluations on three diverse datasets demonstrate that our approach significantly outperforms state-of-the-art baselines, particularly in resolving concurrent multi-resident events. Furthermore, the LLM-based policy shows preliminary cross-environment transfer potential under benchmark settings, while its robustness in real deployments still requires further validation.
Varun A. Paturkar, Shankar Gangisetty, C. V. Jawahar
Motorized Two-Wheelers (MTWs) dominate personal transport across much of the Global South, yet remain largely overlooked in predictive perception research for autonomous driving and ADAS. We introduce MotoVerse, a benchmark for predictive perception from an MTW's ego-centric perspective. MotoVerse comprises 949 maneuver clips collected in dense, unstructured traffic and trajectory annotations for over 31,000 surrounding road agents, including over 16,000 MTWs, enabling two complementary tasks: Ego-Rider Maneuver Anticipation (ERMA) and Traffic Agent Trajectory Prediction (TATP). Each clip is further annotated with an MTW-specific challenge taxonomy comprising dynamic ego-motion, weak traffic structure and contextual occlusion, enabling challenge-aware evaluation. We benchmark established conventional prediction models, general-purpose Vision-Language Models (VLMs), driving-specific VLMs and vision-language-action models. Our experiments reveal three key insights: (i) video backbones reach most of their full-observation accuracy from the first fifth of a maneuver, whereas zero-shot VLMs need most of the maneuver to be observed; (ii) zero-shot VLMs, whether general-purpose or driving-specific, largely remain close to simple baselines on both tasks; a preliminary LoRA study shows that adaptation lifts anticipation sharply but leaves trajectory prediction behind conventional models; and (iii) the rider's own motion drives forecasting difficulty: for every model, including a static baseline, errors are highest during left turns and rise under dynamic ego-motion. We believe MotoVerse will serve as a challenging benchmark for safer and more robust predictive AI for intelligent two-wheelers. The dataset and evaluation code are publicly available at https://github.com/VarunIIITH/MotoVerse.
Siqing Huo, Andrew Parry, Debasis Ganguly, Charles L. A. Clarke
Second-stage neural rankers are commonly applied with a fixed re-ranking depth, assuming that retrieval effectiveness saturates as depth increases. Prior research has questioned the assumption that increasing the re-ranking depth yields linear performance gains, further suggesting that optimal re-ranking depth varies considerably from query to query. In the past, studying such phenomena was methodologically difficult given the scale of manual annotation required. With the advent of LLM-based relevance judgments we can now more easily undertake such studies, in this case to pinpoint the optimal re-ranking depth on a per-query basis. Using dense LLM-based relevance judgments over a typical re-ranking pipeline, we show that many queries exhibit a well-defined optimal re-ranking depth, beyond which effectiveness stagnates or degrades. We formulate re-ranking depth as a query-specific property and study whether it can be predicted a priori from first-stage retrieval characteristics. Through a large-scale analysis, we find that most standard query performance prediction (QPP) methods are ineffective for this task. In contrast, a predictor derived from LLM-assessed first-stage ranking quality, which we term IR-DCG@10, can reduce the average re-ranking depth by up to a factor of 3 while preserving overall effectiveness, depending on the specific first- and second-stage rankers used. Under oracle selection of optimal depths, we further show that retrieval effectiveness can improve by more than 7% while reducing the average re-ranking depth by a factor of 5 on the MSMARCO DEV collection. Given our promising preliminary findings, we would encourage the use of automatic judgments to facilitate research otherwise infeasible under manual annotation. Towards this point, we release relevance judgments, our codebase, and experimental artefacts to support reproducibility and further research.
Sherry Choi, Sitao Sunny Li, Joseph Romero, Lillian Chin, Ashwin G. Ramayya, Allison M. Okamura, Ava Chen
Motor responses evoked by noxious stimulation are used to assess neurological function in hospitalized patients with disorders of consciousness. In standard bedside assessments, these stimuli are applied manually, resulting in substantial variation in force, duration, frequency, and location. Here, we present OUCH (Objective, Uniform, Controlled Haptic stimulation), a wrist-worn device that uses pneumatic actuation to deliver noxious mechanical stimuli. OUCH combines stacked pneumatic pouch actuators, a rigid indenter, and a compliant spacer designed to buckle at a set load, so that the indenter contacts the skin only during actuation. We characterize the device using blocked force tests, clinician evaluation, finite element analysis, and a deformable pressure testbed, and benchmark it against a commercially available handheld pressure algometer. At 200 kPa pouch inflation pressure, our indenter concentrated its load into an estimated contact pressure of 18,500 kPa, over 25 times that of the algometer tip, while requiring less total force. On the deformable testbed, it localized deformation near the surface, while deformation at depth remained comparable to the algometer. As a result, in preliminary perceptual testing, our indenter elicited discomfort at approximately 89% lower applied force than the algometer, demonstrating the feasibility of evoking discomfort with a compact, wearable soft actuator. These results show that combining pneumatic actuation with designed contact geometry enables controlled, repeatable noxious stimulation at the wrist, providing a foundation for objective neurological assessment.
Multi-teacher on-policy distillation (MOPD) extends on-policy distillation (OPD) to consolidate capabilities from multiple teachers. Although prior work reports near-perfect in-distribution (IND) distillation performance, we find that this can mask incomplete capability consolidation beyond the supervised distribution. A preliminary study on synthetic reasoning shows that OPD does not fully transfer teachers' generalization capabilities. We then extend this investigation to real-world tasks, evaluating extrapolative and compositional generalization across mathematical reasoning, coding, agent, and long-context capabilities using Qwen3 models. Across extrapolative settings, OPD and MOPD reach 96.04-102.73% of their teachers' IND scores. Yet their out-of-distribution (OOD) scores remain 2.45-16.25% below the base model's. Across three compositional settings, MOPD improves IND performance over the base model, but its performance on composed tasks as OOD remains 18.19-24.34% below that of the best teachers. To understand these gaps, we examine teacher capability and data coverage as two potential bottlenecks. Jointly alleviating these bottlenecks eliminates OOD forgetting in our experiments and suggests the potential for generalization beyond the teacher. (M)OPD also reduces OOD forgetting on average relative to its reinforcement learning (RL) baselines. Analysis of the associated update geometry reveals smaller and more spectrally concentrated updates on average than those of the RL baselines, along with greater shared update structure under MOPD. Motivated by these findings, we propose geometry-based patching and base-preserving replay to improve OOD performance while largely preserving IND performance. Our findings identify a blind spot in capability consolidation via (M)OPD, highlighting the need for algorithms that explicitly support OOD retention and generalization.
Roberto Mauceri, Stefano Dafarra, Giulio Romualdi, Marco Gabiccini, Daniele Pucci
This letter presents a trajectory planner for humanoid robots to perform dynamic motions on complex, parameterizable terrains using a contact-implicit whole-body optimization framework. The planner generates feasible movements without predefined contact sequences, considering the robot's full dynamics and kinematics. To plan bipedal locomotion on steps, ramps, and other terrains, we propose a mathematical model to approximate ground geometry with a smooth surface. The rigid interaction between the robot and the ground is modeled via novel contact constraints, extending the domain of applicability from flat and horizontal surfaces to any arbitrary smooth surface. Effectiveness is demonstrated using nonlinear programming to plan motions on various terrain topologies. We also explore dynamic trajectory generation by embedding high-level requirements in the cost function and the initial guess. Preliminary feasibility tests were conducted over non-coplanar terrains, both in simulation and on the real robot ErgoCub.
Quantification of Tail-trimming Effects for Interval CVaR Based Nonlinear Regression
Yulei You, Junyi Liu
AI 速览：该文从理论上量化了In-CVaR风险度量对损失右尾的截断在非线性回归抗异常值中的必要性与有效性。
The tail trimming strategy is widely adopted for robustness against outlier contamination in statistical learning and operations research. However, it generally lacks the thorough understanding that to what extent the tail-trimming technique is effective for nonlinear regression. In this paper, we address the robust nonlinear regression based on the so-called interval conditional value-at-risk (In-CVaR), which is introduced to guard against outliers by trimming extreme losses. We first analyze the trimming effect of the In-CVaR based estimator under distributional perturbation. Our first finding is that the In-CVaR based estimator is qualitatively robust under distributional perturbation in terms of the Prokhorov metric if and only if the largest portion of losses is trimmed. Furthermore, under sample contamination, we derive a probably approximately correct (PAC) bound for the In-CVaR based estimator, showing that the preliminary covariate filtering that is customary in the literature is not needed for In-CVaR based regression. The nonconvexity of the In-CVaR objective, together with unboundedness of covariates, responses and parameter space create the technical challenges for our developed theory, and thus necessitate the new treatment of the qualitative robustness and PAC analysis. Overall, this study rigorously analyzes robustness properties of In-CVaR based nonlinear regression models, which illustrates to what extent the right tail-trimming of the loss by In-CVaR risk measure is essential and effective for robust nonlinear regression. These theoretical findings are further supported by numerical experiments.
Ravishka Rathnasuriya, Nidhi Majoju, Zihe Song, Wei Yang
General-purpose graphics processing unit (GPU) computing has emerged as a leading parallel computing paradigm, offering significant performance gains in various domains such as scientific computing and deep learning. However, GPU programs are susceptible to numerical bugs, which can lead to incorrect results or crashes. These bugs are difficult to detect, debug, and fix due to their dependence on specific input values or types and the absence of reliable error-checking mechanisms and oracles. Additionally, the unique programming conventions of GPUs complicate identifying the root causes of bugs, while fixing them requires domain-specific knowledge of GPU computing and numerical libraries. Therefore, understanding the characteristics of GPU numerical bugs (GPU-NBs) is crucial for developing effective solutions. In this paper, we conduct a comprehensive study of GPU-NBs by analyzing 397 real-world bug samples from GitHub. We identify common root causes, symptoms, input patterns, test oracles that trigger these bugs and the strategies used to fix them. We also present GPU-NBDetect, a preliminary tool designed to detect numerical bugs across six distinct bug categories. GPU-NBDetect detected a total of 226 bugs across 186 mathematical functions in four libraries, with 60 of the bugs confirmed by developers. Our findings lay the groundwork for developing detection and prevention techniques for GPU-NBs and offer insights for building more effective debugging and auto-repair tool.
Coding agents work in an environment built for them: a compiler or a test checks each change and points to the fault, and version control keeps every change in a project people can continue. Video editing agents lack one: an edit's correctness shows only in the costly rendered video, which does not point to the decision at fault, and existing systems offer either editing operations that cover only anticipated edits or a script whose output is a video the user cannot keep editing. We present Cassette-Editor, a complete agent harness for video editing that lets the agent edit the way a person does: knowing what the project allows, seeing what each change affects, and revising from there. The agent writes patches of typed changes to the editor's timeline document. A schema check and a rulebook shared with manual editing check each patch before it commits; a rejected patch leaves the project unchanged and returns each problem located with repair options, and an accepted one becomes a step of the history the user also edits. Reads map source analysis to the frames of the current edit. Because manual gestures are writes in the same language, folded by the same executor and rulebook, the agent can express every change a manual edit makes to the project. On 31 editing requests with the model held fixed, the complete harness passed 89% of trials against 47% for the same model with ten basic editing operations and without the rulebook, at less than half the agent time and cost per successful request; the loss fell on requests at rule boundaries, composite edits, and undo, not on finding content.
When students use generative AI to produce their work, the learning process becomes invisible. Established frameworks such as Bloom's taxonomy then classify the cognitive level of what the AI produced, not what the student contributed. We propose the Human Agency Depth Taxonomy (HADT), a preliminary six-tier taxonomy that classifies the engineering contribution a student makes in a prompt, independent of the AI's output. HADT combines three dimensions: contextual bandwidth, engineering abstraction and student agency. We applied HADT to 962 prompts from 105 students' structured AI Journals in an AI-permissive, first-year software engineering course of 145 students, and examined how agency changed over ten journalled weeks. Most prompts (84.2%) carried some student contribution beyond delegation. Agency tracked the development lifecycle. Architecture-discovery prompts dominated the requirements phase (48% of turns) and fell to 5-12% from week 9, while prompts analysing existing systems rose during build and verification (odds ratio 2.88, with turns clustered by student). Two-thirds of the variance in tier lay within students, so agency depended more on the phase of work than on the student. A turn-level rise in delegation in deadline weeks did not hold once turns were clustered by student. Explicitly specifying constraints on the AI's output was rare throughout, which we interpret as a knowledge bottleneck for novices rather than a gap in instruction. We discuss implications for course and assessment design, and for using HADT as a formative lens on how students engage with AI.
Ivan Diliso, Roberto Barile, Nicola Fanizzi, Claudia d'Amato
Benchmark datasets for Knowledge Graph Refinement typically contain only ground facts, discarding the schema available in the source knowledge graph. This limits the evaluation of Neural-Symbolic methods that leverage expressive schemas. We present JEDIKG the first resource that systematically addresses these gaps through two components: JDEX a general configurable tool for extracting complete, portable, modular dataset from any RDF/OWL knowledge graph; and JDSET, a curated suite of eleven datasets with varying expressivity, volume, and domain. JDEX preserves full schema expressivity, employs standard OWL reasoning to detect and correct inconsistencies and materialize implicit knowledge, applies schema modularization, and provides utilities for integration with mainstream machine learning libraries such as PyTorch and PyKEEN. We validated the completeness and portability of the datasets across several dimensions and preliminarily proved the utility of JEDIKG in experimental workflows combining data-driven methods with schema-driven reasoning.
Given a relational database (RDB) storing heterogeneous tabular information, how can we predict missing (or future) values in some target column of interest? As candidate targets are numerous in enterprise settings, it is preferable to avoid learning a new model from scratch each time there is a new prediction task. Frozen foundation models (FMs) based on in-context learning (ICL) and RDB-specific pre-training provide a viable solution, but the ideal design still remains largely unresolved. Perhaps unexpectedly, preliminary evidence has recently shown that existing single-table FMs (aka TFMs), when combined with suitable parameter-free relational encoders, can be quite competitive in practice despite zero exposure to RDB pre-training or relational data of any kind. In this work we first empirically confirm this phenomenon with a more diverse array of experiments. We then turn to our main contribution, namely, surfacing multiple complementary explanations for why TFMs behave so effectively. These explanations ultimately hinge on innate synergies whereby parameter-free encoders map relational effects to fixed-length embeddings that loosely mimic distributions for which TFMs were originally designed; in so doing, desirable single-table properties transfer to relational settings (e.g., convergent posterior predictive distributions). Collectively, our analysis forges new pathways for improving RDB FMs, particularly when we prioritize interpretability and inevitable integration within agentic systems.
Antoine Amarilli, Nofar Carmeli, Clémence Dumoulin
This note studies the fine-grained complexity of ranked enumeration and ranked direct access of conjunctive query answers over a dynamic database. We focus on lexicographically sorted answers, defined by an ordering on the query's free variables. From the literature, when no particular order is required, we know that when the query is self-join-free and q-hierarchical, we can build a data structure for enumeration (resp. direct access) with linear (resp. linearithmic) preprocessing and constant (resp. logarithmic) update time in the size of the database. For enumeration (resp. direct access), this data structure yields an algorithm that enumerates all query answers (resp. that returns the $k$-th query answer) with constant delay (resp. logarithmic access time). Our goal is to extend these results to ranked enumeration and ranked direct access, with the ranking function defined by a lexicographic order. We define a property on the order over the variables of $Q$, which we call being hierarchy-consistent. Given a user-specified query and hierarchy-consistent order, we first propose, for ranked enumeration under updates, an algorithm with linear preprocessing and logarithmic update time that enumerates all the query answers according to the user-specified order with constant delay. Moreover, for ranked direct access under updates, we propose an algorithm with linear preprocessing and logarithmic update time that returns the $k$-th tuple according to the user-specified order with logarithmic access time. In contrast, given a user-specified query and non-hierarchy-consistent order, we show a lower bound for ranked direct access under updates.
Personalized neural audio watermarking systems embed user-specific payloads into audio to trace the user associated with a leaked or misused copy. Existing evaluations mainly assume access to a single personalized copy, but real-world distribution may expose multiple copies of the same recording. We find that simple sample-wise averaging breaks traceability: averaging only two copies produces tracing-failure rates of 87.7-99.7% across the five systems while largely preserving audio quality. Decoder outputs show distinct responses to coalition payload composition across systems, with high majority agreement in TimbreWM but substantially lower agreement in WMCodec. In a more sophisticated payload-aware setting, mixture weighting can further steer the decoder toward a selected nonmember, achieving a target success rate of 92.3% in TimbreWM. Preliminary confidence screening rejects many collusion-induced assignments while retaining most valid single-copy outputs. Code and results are available at https://github.com/Silwan5z/neural-audio-watermark-collusion-attack. This work highlights multi-copy traceability as an additional evaluation dimension for personalized neural audio watermarking alongside conventional single-copy robustness.
Guard models are increasingly used to safeguard LLM-based agents, primarily by identifying actions that agents are forbidden to perform. However, identifying forbidden actions alone is insufficient to ensure agent safety. In this paper, we argue that agent safety also depends on identifying required yet unperformed safety-critical actions, which we call obligations. Our preliminary study on a popular benchmark for evaluating safety shows that 56.92% of GLM-5.3 trajectories contain unfulfilled obligations, compared with only 30.00% containing forbidden actions. This finding reveals unfulfilled obligations as a major and previously overlooked source of safety risk. However, to our knowledge, no existing benchmark evaluates whether guard models can identify these obligations. To close this gap, we introduce ObligationBench, the first benchmark for evaluating the capability of obligation identification, comprising 240 expert-validated trajectories covering issue resolution, feature development, and terminal operations. Our evaluation of 14 representative models reveals substantial limitations: the highest recall and exact-match rate are only 48.97% and 10.00%, respectively. To address these limitations, we develop ObligationGuard using 40,000 synthetic training examples. ObligationGuard achieves 57.52% recall and an exact-match rate of 21.67%, surpassing all evaluated models on both metrics. We call on the community to incorporate obligation identification into the design and evaluation of future guard models to improve agent safety.
Power-grid customer service increasingly relies on community social media, where customers describe outages, billing, and equipment faults in informal regional dialect. Such messages exhibit non-standard morphology, semantic drift, and out-of-vocabulary expressions that make manual lexicon construction costly and degrade conventional NLP tools. We propose a weak-supervision framework constructing a regional slang lexicon from curated dialect anchors and power-domain seed terms. Candidates are generated via Pointwise Mutual Information with soft-label bidirectional anchoring, retaining dialect-anchored terms while recording power-domain relevance as separate metadata, and are scored by combining Sentence-BERT semantic similarity with a jieba-based wordhood measure. Uncertainty-aware active learning with rule-based and retrieval-augmented LLM oracles is applied under three query strategies, and the resulting lexicon is evaluated by a higher-capability LLM calibrated against human expert annotations via Cohen's $κ$. On 11,177 real WeChat messages from Yuxi (Yunnan, China), the framework achieves an evaluator-estimated dialect precision of DP~$=$~1.0 with zero false positives. An ablation shows that soft-label layering retains 751\% more candidates than strict power-gating at identical precision, expanding the candidate pool from 41 to 349 terms. Human calibration ($n=46$) yields $κ_{\text{dialect}}=1.0$ and $κ_{\text{power}}=0.85$. The resulting 25--33-term lexicon, 4--5 of which are power-relevant, provides a preliminary resource for dialect-aware power-grid service NLP.
Tool-using artificial intelligence (AI) agents are increasingly adopted as systems that plan, observe their environment, and take actions over extended time periods. This shift challenges the current evaluation practice, in which models are tested in restricted, fully observable settings. We argue that such evaluations are vulnerable to a failure mode long known in computer security: a system that behaves benignly when it detects that it is being analyzed. Malware has exploited this for decades, by probing sandboxes, virtual machines, and instrumentation, before revealing its payload. The shared challenge is that the subject under observation can detect the conditions of its evaluation, so the setup used to observe behavior ends up shaping the behavior observed, yielding overly optimistic safety and robustness assessments. Recent AI-safety studies demonstrate pieces of this risk, though only preliminarily and under controlled conditions. Drawing on decades of malware-analysis experience, we outline concrete principles for evaluating AI agents as potentially adversarial: explicitly threat-modeling evaluator-discrimination; testing across harness variants and reporting the worst case; using shadow executions to provide a realistic runtime without irreversible side effects; treating environment probing as a risk signal; and performing unpredictable reassessments after deployment.
Neural controlled differential equations (Neural CDEs) evolve hidden states along continuous paths constructed by interpolating discrete observations. Sparse measurements leave the input between observation times undetermined, and admissible continuous paths consistent with the same data can produce different terminal states. We characterize this ambiguity for planar drivers with bounded speed. The set of compatible terminal states admits a leading-order zonotopic approximation determined by feasible signed areas and transported Lie brackets. Its projection onto a scalar prediction yields a computable, target-specific ambiguity certificate. We also study the number of measurements needed to reduce the remaining uncertainty. For nondegenerate planar CDEs, the optimal worst-case radius over deterministic adaptive sampling policies scales as $N^{-1}$ when speed is bounded and $N^{-2}$ when both speed and acceleration are bounded, where $N$ is the number of observation intervals. Synthetic experiments assess the certificate using admissible continuous completions and examine the role of path regularity.