Machine Learning
Diagnosing Low-Confidence Patient Profiles via Localized Harmful Covariate Shift Detection
Olivier Lefebvre, Hakima Laribi, Dan Poenaru et al. (+1 more)
Before deploying clinical prediction models, their reliability must be assessed to ensure safe use. Errors may arise from distribution shifts between training and deployment or from heterogeneous performance where the model systematically underperforms for certain patient subgroups. Yet most post-hoc diagnostic methods evaluate reliability only at the population level, checking whether the deployment data resemble the training data and whether the model performs well on average, without accounting for heterogeneity that may cause some patients to be disproportionately affected. We propose a unified diagnostic pipeline that combines both perspectives. MED3pa first discovers interpretable low-confidence patient profiles, and Detectron is then applied within each profile to test whether its degradation is associated with a detectable harmful
covariate shift. Across three clinical prediction tasks and three injected subgroup shifts in MIMIC-IV, we find that shift detectability itself is informative. An injected age shift, undetectable at the population level, was nonetheless localized to specific degraded profiles, whereas sex- and race-related shifts were detected broadly and therefore offered little guidance for identifying the most affected patients.
Read the full abstract ▾
All authors Olivier Lefebvre, Hakima Laribi, Dan Poenaru, Martin Vallières
Artificial Intelligence
Multi-System Cognitive Steering for Generative Communication
Eric Lacosse, Pablo Tano and Daniel C. McNamee
A fundamental bottleneck for translating thoughts to
speech is the high physical cost of motor input forcing a strict tradeoff between communication speed and expressivity. Generative AI offers a promising solution by expanding highly abbreviated text input into fluent sentences, significantly reducing the motor burden on the user. However, sparse inputs are inherently ambiguous; without sufficient context, AI models frequently misinterpret these abbreviations and generate outputs that fail to align with the user's true cognitive intent. We propose Cognitive Steering, a framework that can be leveraged to reconstruct user intent by grounding Large
Language Models (LLMs) in
multimodal context and applying AI control methods. We demonstrate that aligning frontier models with selected environmental referents, emotional states, and communication motives on simulated abbreviation
benchmarks achieves up to $\sim$88% top-5 expansion accuracy, doubling no-context baselines. We also reveal that different types of context require distinct AI control techniques: while physical objects in a scene are best provided through explicit text
prompts, abstract factors like emotion may be more effectively managed by directly altering the AI's internal activations. These findings suggest a hybrid architecture for future interfaces that leverage Cognitive Steering to help users communicate both quickly and accurately, recruiting multiple AI control methods simultaneously to perfectly capture their intended communication goals.
Read the full abstract ▾
Artificial Intelligence
Learning from Self-Generated Responses: Reliability–Uncertainty Self-Distillation for Reasoning
Jinhao Pan, Bowen Wei, Yuqing Zhou et al. (+1 more)
Reference solutions and question-specific rubrics are not always available to guide the teacher in self-
distillation. A large
language model's own solution attempts offer an alternative, but their quality is difficult to assess in open-ended tasks without automatic correctness checks, and even correct attempts can involve uncertain
token predictions. We propose Reliability–Uncertainty Self-
Distillation (\method{}) to learn from these attempts. The same model serves as teacher and student: the teacher receives the question and completed attempt, and the student matches the teacher's
token-level predictions using a question-only
prompt. \method{} weights each attempt's
distillation loss by additively combining judged reliability, estimated from a self-judge's score and confidence, with student predictive uncertainty. Across eleven
reasoning benchmarks, \method{} outperforms all five baselines in average accuracy, reaching 70.47% on Qwen3-4B and 76.69% on Qwen3-8B (8.90 and 2.10 percentage points above the base models). Data and code are available at https://github.com/JP-25/RUSD.
Read the full abstract ▾
All authors Jinhao Pan, Bowen Wei, Yuqing Zhou, Ziwei Zhu
Computational Complexity
Majority and Torus Polynomials: Bounded-Lift Lower Bounds and Explicit Constructions
Saint Wesonga
Bhrushundi et al. (2019) introduced
torus polynomial approximation as an approach to separating Majority from $ACC^0$. In this model, approximation is measured modulo integers. Krishan and Vishwanathan (2026) developed a duality framework for lower bounds and posed five open problems. We resolve two of these, concerning integer lifts and explicit
polynomial approximations. An integer lift records the integer shifts that turn a
torus approximation into an ordinary real approximation. We show that a degree-d
torus polynomial approximating Majority with error at most 1/8 and lift contained in an interval of width $B$ must satisfy $d(B + 1) = \Omega(n)$. This rules out low-degree approximating
polynomials with lifts in {-1, 0, 1}, answering their Open Problem 2. We also answer Open Problem 5 by giving, for every Boolean function on $n \geq 1$ variables, an explicit
torus polynomial approximation of degree at most $n - 1$. Its error is optimal: zero when the accepting set has even cardinality and $2^{-n-1}$ otherwise. The results presented were discovered and formalized in Lean using GPT-6 Astra.
Read the full abstract ▾
Multimedia · Cross-listed from eess.IV
Perceptual Characterization of Scan-induced Artifacts in Dynamic 3D Meshes
Huong Hoang, Truong Nguyen and Pamela Cosman
Dynamic meshes reconstructed from real-world scenes often exhibit scan-induced artifacts such as surface jitter and missing geometry, which strongly impact perceived visual quality. Objective assessment remains challenging due to the absence of artifact-free ground truth and limited perceptual understanding of artifact interactions. This paper presents a systematic and controlled perceptual study of scan-induced artifacts in dynamic meshes, focusing on surface jitter and holes. To enable systematic analysis, we introduce a physically grounded artifact synthesis framework in which holes are synthesized using a reconstruction uncertainty model derived from multi-view geometry. The study reveals asymmetric cross-artifact interactions, non-additive integration, and motion-dependent temporal masking. Based on these findings, we propose a compact, perceptually grounded no-reference quality assessment framework that encodes the observed perceptual mechanisms.
Read the full abstract ▾
Artificial Intelligence
Verification Turns Capability Gaps into Routing Decisions: Small Language Models for Clinical Documentation
Nina Fatehi, Meysam Ghaffari, Animesh Agarwal et al. (+2 more)
Clinical note generation from doctor–patient dialogue is high-volume and
hallucination-intolerant: a fabricated laboratory value can create patient-safety risk, not a quality regression. We ask whether an agentic verification architecture, rather than generator scale, can make a small
language model viable here. Holding a four-evaluator verification stack and refinement policy fixed and swapping only the generator between a 4B-parameter model with a QLoRA adapter and a frontier baseline, the small model reaches $0.984$ claim-level factual entailment against $0.992$ and comes within $3.3$ points on completeness, generating entirely on-device. Its deficit is confined to inter-section structural fidelity—arrangement rather than clinical comprehension, and the axis on which it also falls furthest below the corpus's reference notes. Because that deficit is an explicit verifier decision rather than a silent quality difference, it becomes a routing policy: run the small model by default, escalate what the verifier rejects. Measured end to end, that it achieved a similiar verified-rate acceptance to the frontier-only acceptance in this test set ($99.6\%$ vs.\ $98.4\%$ over $250$ encounters) while routing $62$, documenting three quarters without a frontier generation call. Ablating the loop separates architecture from scale: unrefined, the small model is accepted on $26.8\%$ of encounters and the frontier model on $74.8\%$, so verification does the most work where the generator is weakest. We also contribute section-scoped refinement, which preserves unflagged sections by construction rather than instruction, and find the baseline is not uniformly stronger—its provider refused two trauma-related transcripts the on-device model handled and certified, one facet of a provider dependency a served adapter does not carry.
Read the full abstract ▾
All authors Nina Fatehi, Meysam Ghaffari, Animesh Agarwal, Anushka Swarup, Carlos Morato
Software Engineering
Beyond Functional Correctness: Static Code Quality Profiling of LLM-Generated Code
Jue Huang, Tarek Mahmud, Meiru Che et al. (+1 more)
Large
language models (LLMs) are increasingly used for code generation, yet most evaluations still focus on whether generated code passes
benchmark test suites. Functional correctness alone, however, provides only a limited view of quality:
benchmark tests are often incomplete, and passing them does not guarantee that code is maintainable, reliable, or well-structured. This paper {presents a large-scale static quality profiling of} LLM-generated Python code, with a focus on maintainability and reliability. Using 65{,}663 programs from 73 models in LiveCodeBench, we evaluate generated code with established static analysis tools, including Pylint, Radon, and SonarQube. Our results show systematic differences across models that are not captured by correctness alone, with maintainability emerging as the clearest source of variation. We further find that correctness often comes with structural trade-offs rather than uniformly simpler solutions. Overall, our findings motivate evaluation frameworks that assess LLM-generated code beyond pass rates alone.
Read the full abstract ▾
All authors Jue Huang, Tarek Mahmud, Meiru Che, Guowei Yang
Computation and Language
Fantastic Metrics and How to Find Them: Meta-Evaluating Metrics for Multi-lingual Style-Personalized Generation
Anubhav Jangra and Adrian de Wynter
Meta-evaluation of text generation metrics and LLM-judges is primarily conducted using metric-human correlations. However, prior work has shown that correlation is not an appropriate estimate of a metric's evaluation capability and can be unstable across evaluation settings, such as different
datasets or
languages. Therefore, we propose a regression-based meta-evaluation of metrics that learns on calibrated metric outputs to predict human ratings. We ground this measurement relative to a trivial constant-mean baseline and human agreements to provide a comparable measure of metric capability across evaluation settings. To test our meta-evaluation framework, we developed a large-scale multi-lingual style-personalized text generation (SPTG)
benchmark, collecting multiple annotations across 10 topologically diverse
languages and four evaluation dimensions, each with varying degrees of subjectivity. We meta-evaluated 32 metrics from three style evaluation paradigms (string-based,
embedding-based, and LLM-judges) and their ensembles over these 40 evaluation settings. Our analysis revealed that even simple string- and
embedding-based measurements can match strong LLM-judges when calibrated to human ratings. We also identified characteristics of human annotations that determine metric performance, as well as conditions under which a metric ensemble outperforms its individual constituents.
Read the full abstract ▾
Artificial Intelligence
ListQA: A Benchmark for Evaluating List-Formatted Factual Knowledge Retrieval in Large Language Models
Mayank Kulkarni and Rakesh Vaideeswaran
Many real-world questions demand not a single fact but an organized collection of them, yet existing factual knowledge
benchmarks almost exclusively target single answer
retrieval. We introduce ListQA, a
benchmark of 9,045 human-curated, cross-validated questions (audited error rate of 1.7%) that require LLMs to recall multiple facts and compose them into structured lists of 3-10 elements. Questions range from flat lists ("Which NCAA teams went undefeated between 2000 and 2024?") to hierarchical lists with sub-attributes ("...and what was their record and result?"), spanning eight categories across 60+ countries. An evergreen design (explicit temporal constraints or historically immutable facts) keeps ground truth valid without periodic updates. For evaluation, we frame element matching as a linear sum assignment problem: optimal bipartite matching paired with LLM-based semantic grading jointly captures factual accuracy,
hallucination, and format compliance. We
benchmark 34 models (8 families, 42 configurations across standard and thinking enabled inference) and find: the best standard-inference model scores below 37% LLM-Judge-F1, multi-faceted questions are harder across the board, and providing the source Wikipedia page lifts scores dramatically, confirming that models can organize facts but struggle to retrieve them from parameters alone. Extended analyses cover base vs. instruction-tuned checkpoints and
token efficiency. We release the
dataset and evaluation code.
Read the full abstract ▾
Computation and Language
From Qualitative Text to Integrated Evidence: The Parallel-Then-Integrated (PTI) Procedure
Elyas Irankhah, Ashley Hagaman and Samah Fodeh
Mixed methods research offers established strategies for integrating qualitative and quantitative evidence, but less guidance for integrating two computational representations of the same qualitative corpus. This methodological study introduces Parallel-Then-Integrated (PTI), a four-step procedure for explicit and traceable integration. We present PTI using 1,203 interview paragraphs from 29 mothers in Nepal. The two representations were ontology-guided Patient Voice (PV) coding with PVminer and data-driven themes generated through non-negative
matrix factorization (NMF). A theme-complete crosswalk documented convergence, divergence, and preprocessing-sensitive differences. Depression status, based on Patient Health Questionnaire-9 (PHQ-9) scores, served as a secondary external anchor for exploratory association checks. PTI provides a structured approach for integrating computational representations of qualitative text within mixed methods research.
Read the full abstract ▾
Computational Complexity
The Gap Between Average-Case and Worst-Case Complexity
Halley Goldberg, Jinqiao Hu, Zhenjian Lu et al. (+2 more)
Understanding the average-case complexity of $\mathsf{NP}$ is a central goal in complexity theory and cryptography. A necessary milestone is to understand the corresponding average-case versus worst-case question for the
polynomial hierarchy ($\mathsf{PH}$). In a celebrated result, Hirahara [Hir21] proved that if every distributional problem in $\mathsf{PH}$ is easy on average, then every
language in $\mathsf{PH}$ admits worst-case
algorithms running in time $2^{O(n/\log n)}$. Remarkably, although the statement of Hirahara's
theorem makes no reference to meta-complexity, all known proofs appear to use time-bounded Kolmogorov complexity and its associated meta-computational problems in an essential way. We show that the reliance on techniques and perspectives from meta-complexity is not simply a coincidence. Building on previous work of Hirahara [Hir20] and on a recent result of Hu, Lu, and Oliveira [HLO25], we prove that relating the average-case and worst-case complexities of $\mathsf{PH}$ is in fact equivalent to a purely meta-computational implication: efficient
algorithms for a standard gap version of $\mathsf{MINpKT}$ with $\mathsf{PH}$ oracle access imply efficient
algorithms for a mild gap version. Crucially, in these promise problems the standard gap separates a YES instance with time bound $t$ from a NO instance with time bound $\mathsf{poly}(t)$, whereas the mild gap keeps the YES threshold $t$ and moves the NO threshold to $t+\mathsf{poly}(n)$. Together with prior work, this equivalence points to the study of gap reductions as a potentially promising route toward understanding the relation between average-case and worst-case complexity. We make progress by proving that the gap in running time can be eliminated in the average-case setting. Finally, we prove that in the worst-case setting any efficient reduction between the two problems must use nonrelativizing techniques.
Read the full abstract ▾
All authors Halley Goldberg, Jinqiao Hu, Zhenjian Lu, Jingyi Lyu, Igor C. Oliveira
Human-Computer Interaction
Understanding Goalball Training Across Roles and Team Contexts: Practices, Perceptions, Challenges, and Technological Opportunities
Gyeongdeok Kim, Junhyuk Jang, Donghyeon Kim et al. (+2 more)
Goalball is a team sport for visually impaired athletes, played by throwing and blocking a ball while wearing eyeshades. However, existing studies provide limited guidance on which everyday training difficulties technology should address for players and coaches across team contexts. We conducted semi-structured interviews and focus groups with 18 players and 12 coaches from seven South Korean teams spanning youth, second-division, first-division, and national-team contexts. Using qualitative coding and
matrix-based analysis, we describe current training practices, participants' views of these methods, the challenges they encounter, and their technological support needs. Drawing on the relationships among these four areas, we discuss implications for the design and evaluation of future support technologies that fit everyday goalball training across roles and team contexts.
Read the full abstract ▾
All authors Gyeongdeok Kim, Junhyuk Jang, Donghyeon Kim, Billy Park, Gunhyuk Park
Artificial Intelligence
Into the Unknown: Benchmarking AI agents on open scientific research problems
Seungone Kim, Jiayi Geng, Young-Jun Lee et al. (+25 more)
Can AI
agents carry out research on open scientific problems? We introduce Into the Unknown, a
benchmark that provides an
agent with a science paper along with a research direction to pursue and tasks it to write a follow-up paper. We work with scientists at US Department of Energy (DOE) national laboratories, who each contribute an unpublished follow-up direction from their own work together with the necessary conditions a submission must meet. While assessing the quality of a follow-up paper is challenging in general, using these conditions to form a rubric makes evaluation more tractable for research problems that have no reference answer. We have nine frontier
agents write 15 follow-ups each, spanning
quantum computing,
plasma physics, computational chemistry, materials science, and scientific machine learning domains. None of the 135 submissions satisfies all the conditions, and 114 fail our integrity check, most often because the paper claims work that was never done or reports numbers that contradict the recorded evidence. Overall,
agents readily produce papers that look like follow-ups, but none meets the standard of the domain scientist, leaving substantial headroom. Our code and data are publicly available.
Read the full abstract ▾
All authors Seungone Kim, Jiayi Geng, Young-Jun Lee, Bo Liu, Juyoung Suk, Nicholas Lubbers, Mitchell Wood, Marcus Noack, Yong-Xin Yao, Yuan Shi, Roxana Bujack, Cristina Garcia Cardona, Austin Rodriguez, Ilon Joseph, Woojin Cho, Zora Zhiruo Wang, Chuanyang Jin, Ian Wu, Apurva Gandhi, Tianjian Li, Weiwei Sun, Carolin Lawrence, Kiril Gashteovski, Dongyeop Kang, Jay Shin, Akari Asai, Graham Neubig, Sean Welleck
Artificial Intelligence
AgentCIScope: Grounded Contextual Integrity Evaluation for LLM Agents
Chengquan Guo, Zhaorun Chen, Zinan Lin et al. (+2 more)
LLM
agents are becoming increasingly capable of handling daily workspace tasks by interacting with application environments through tool calls. However, as
agents read and write sensitive user data across email, documents, and other applications, a central
privacy question is whether they preserve contextual integrity (CI), that is, whether the information flows they produce comply with context-specific disclosure constraints. Existing work either focuses on model-level
privacy leakage or evaluates
agents in limited application environments with manually constructed disclosure constraints. In this work, we introduce AgentCIScope, a unified platform and
benchmark for evaluating
agent-level contextual integrity through executable, multi-step tasks across diverse, realistic application environments. AgentCIScope transforms public and synthetic
privacy cases into executable
agent tasks, with disclosure constraints grounded in three criteria: governing
privacy policies, persona-based agreement, and a predefined sensitive-attribute taxonomy. Based on AgentCIScope, we evaluate 12
agents on 936 tasks and find that strong task-completion capability does not guarantee contextual-integrity preservation: single-run leakage rates range from 32.5% to 94.4%, while repeating each task five times further increases leakage by 4-19 percentage points. Leakage varies substantially across attributes: personal preferences and booking details have average leakage rates of 84.7% and 76.5%, compared with 17.1% for credit-card information and 29.4% for SSNs; environments: calendar has the highest average leakage rate as an information source, while WhatsApp ranks highest as an information destination; and governing
privacy policies. AgentCIScope provides deep insights into
agent privacy leakage and serves as a unified testbed for developing
privacy-preserving
agents.
Read the full abstract ▾
All authors Chengquan Guo, Zhaorun Chen, Zinan Lin, Xiaodong Liu, Bo Li
Software Engineering
DivAlgo: A systematic evaluation of algorithmic diversity for code generation models
Anubhav Jangra and Smaranda Muresan
Code generation models are actively being used in professional and educational settings. However, the competence of large
language models (LLMs) to generate algorithmically diverse code remains largely unknown. We propose the DivAlgo
benchmark, a large-scale
dataset constituting algorithmically diverse solutions to programming problems. We also introduce a lightweight similarity metric to enable large-scale evaluation. Our experiments across 24 modern code generation models found that uncontrolled model-generated code is significantly less diverse than human solutions (capturing ~31% of human diversity), and even the best diverse code generation strategy could achieve only ~70% of human diversity. Moreover, while it was possible to steer the models to generate solutions based on human strategies, they were unable to reproduce the diversity of the human solutions. These findings indicate the limitations of code generation models in capturing the algorithmic diversity humans exhibit, and that overexposure to model-generated code can narrow programmers' algorithmic vocabulary.
Read the full abstract ▾
Networking
Bounding Mobile Latency from Network Interconnections
Shefali Tushar Kulkarni and John Heidemann
Mobile latency is determined by how Mobile Network Operators (MNOs) route traffic: from phones, across the MNO's network to exit points where it enters the public Internet. Exit points are few, and MNOs are quiet about details, but their role
prompts us to ask: What is the latency cost of sending traffic through an exit point? We develop a new method to evaluate this question, and demonstrate it on the three largest U.S. MNOs, although in principle it can apply globally. Using new analysis of existing traceroutes, we find that AT&T, T-Mobile, and Verizon funnel nationwide traffic through only 9, 5, and 9 exits, and the geographic detour they incur adds up to 62.1 ms compared to an ideal, direct-path latency. Routing delays also add latency. We show that even assuming speed-of-light paths through the exit points, latency is still up to 46.9 ms more than optimal. To understand if these costs can be overcome, we compare actual to theoretically optimal placements, finding that the latencies of current placements are 18-66% above the population-weighted optimum and 32-72% above the
market-share-weighted optimum with the same number of exits. However, we show this gap is small in absolute terms: perfect placement would recover only a few milliseconds of the tens that remain. We show that geographic optimization saves little latency: the inflation users experience comes from routing and other overhead.
Read the full abstract ▾
Robotics
FACT: A Multimodal Force-Action-Track Foundation Model for Human-to-Robot Dexterity
Zhi Cao, Yining Hong, Jiaolong Yang et al. (+4 more)
Human demonstrations offer a scalable alternative to costly
robot data collection for dexterous manipulation, but most human
datasets lack force measurements. Dexterous manipulation requires not only visual and proprioceptive understanding but also the ability to anticipate and regulate interaction forces. To scale force-aware human-
robot co-training, we introduce EgoForce, a large-scale human tactile
dataset capturing force-rich manipulation experience, and combine it with
robot demonstrations for pretraining. We present FACT, a
robot foundation model that cascades from prospective visual planning to force-aware refinement for dexterous manipulation. FACT comprises two jointly trained components. A Track-Guided Coarse Planner jointly predicts actions, future
video, and visual tracks. Future
video and visual tracks also provide a shared task representation that facilitates cross-embodiment knowledge transfer and coarse action generation. Building on this coarse plan, a Force-Action Joint Refiner jointly predicts future force and refines the coarse action, allowing anticipated force and action to shape each other during refinement. We evaluate the model on ten tasks requiring fine-grained coordination and force feedback, including tool use, musical instruments, and precision laboratory procedures. Using as few as 10
robot trajectories with 90 human trajectories for fine-tuning, FACT outperforms both baselines, with success-rate gains of up to 60 percentage points over T-Rex. Ablations show that force supervision in human pretraining data is crucial for downstream
robot performance after fine-tuning, while visual track prediction and training with future-force prediction improve dexterous execution. Experiments varying the human-
robot data ratio during fine-tuning further suggest that FACT learns from human demonstrations nearly as effectively as from
robot demonstrations.
Read the full abstract ▾
All authors Zhi Cao, Yining Hong, Jiaolong Yang, Yejin Choi, Li Fei-Fei, Jiajun Wu, Huang Huang
Computer Vision
Agronomic Characterization and Time-Series UAV Phenotyping to Support Field Pea Breeding in Iowa
Yanben Shen, Joscif Raigne, Asheesh Singh et al. (+1 more)
Field pea has gained interest in the Midwest U.S. and has the potential to benefit Iowa cropping systems. This study evaluated 17 accessions and 7 Canadian varieties for agronomic and seed yield performance. This study found that PI accession trials exhibit genetic diversity in phenology and canopy traits, whereas the Canadian elite varieties demonstrated great yield potential under Iowa conditions. The accession genotypes matured between 75 DAP (late June) and 95 DAP (late July) across six site-years. The top-yielding Canadian varieties averaged 1961 kg/ha across two site-years. To comprehensively assess field pea performance, this study extracted time-series Unmanned Aerial Vehicle(
UAV)-derived traits, assessed
UAV-derived traits, and evaluated their correlations with multiple agronomic traits and yield. The results found that
UAV-derived time-series canopy area was the most yield-relevant trait (r = 0.63) among all
UAV-derived canopy features, vegetation indices, and manually collected measurements. Compared with yield,
UAV-derived canopy area showed higher selection reliability (H2 = 0.87, CV = 13.46%), making it suitable for phenotypic selection and accelerating Midwest field pea breeding programs. This study identifies useful
UAV-derived features for pea breeding and demonstrates the value of integrating diverse germplasm, elite commercial varieties, and time-series
UAV phenotyping. Combining genetic variation from the accession trial with the yield potential of high-performing commercial varieties provides valuable breeding materials and phenotyping strategies for developing locally adapted, high-yielding field pea varieties for future production in the Midwest.
Read the full abstract ▾
All authors Yanben Shen, Joscif Raigne, Asheesh Singh, Arti Singh
Human-Computer Interaction
Iterative Design and Evaluation of a VR Nursing Training System: Insights from Clinicians and Student Learners
Danhua Zhang, Cynthia Bradley, Christopher Kissell et al. (+5 more)
This paper presents the iterative design and evaluation of a virtual reality (VR) nursing training system developed in collaboration with nursing education specialists to enhance procedural skill acquisition, clinical decision-making, and critical thinking among pre-licensure nursing students. Two clinical scenarios, chest pain and oxygen therapy, were created to simulate acute care settings, with design refinements informed by an expert evaluation study (n=8) and further assessed through an effectiveness study involving nursing students (n=17). Results demonstrate high user acceptance, perceived usefulness, and significant post-simulation increases in learner confidence. The VR system was found to be an accessible supplemental training tool that can foster self-directed learning. Finally, we present design recommendations for developing VR simulations for nursing education, emphasizing collaboration with domain experts, accommodating diverse learning goals, and simulating complex clinical workflows.
Read the full abstract ▾
All authors Danhua Zhang, Cynthia Bradley, Christopher Kissell, Courtney Hutton Pospick, Seraphina Yong, Qiao Jin, Tongyu Nie, Evan Suma Rosenberg
Software Engineering
A Systematic Study of Deprecated Android API Usage Updates
Tarek Mahmud, Meiru Che and Guowei Yang
Android Application Programming Interfaces (APIs) continuously evolve, causing existing APIs to become deprecated and requiring developers to migrate their usages to recommended replacements. Although prior studies have proposed automated migration techniques, their effectiveness is often limited by the diversity and contextual complexity of API changes. This paper presents a systematic study of deprecated Android APIs, their recommended replacements, and real-world usage updates performed by developers. Based on an analysis of 1,000 deprecated APIs and 4,336 migration examples collected from GitHub, we identify six migration categories and derive recurring usage-update patterns involving Android-version checks, parameter adaptation, object initialization, data-type conversion, and changes in API interaction mechanisms. To assess their applicability, we augment the zero-shot GUPPY
benchmark prompts with the migration category and corresponding usage-update pattern. On 156
benchmark tasks, the pattern-guided
prompt improves correct updates from 139 to 147 and performs better in five of the six categories.
Read the full abstract ▾
Artificial Intelligence
Compiling Expert Procedures into Verified Programs: When a Small Model Is Enough
Vishvesh Bhat, Asad Aali and Muhammad Ahmed Mohsin
In procedural tool-use domains, how much of the gap between base models is procedure rather than capability? We build an explicit program from a teacher's traces and run it in front of unchanged small models, including an 8B model. The construction, PLVR , takes the
reasoning traces of a teacher, Kimi-K3, clusters their segments to locate recurring operations, has a frontier model author one typed primitive per operation, each run by a small frozen model and assembles the program by A* search over a mined rule library, under a reference-action objective. At inference the program takes one of two forms: for troubleshooting and tool search it produces the chain of thought the student would otherwise generate for itself, and the student acts on it; for multi-turn tool matching the student proposes each action and the program checks, repairs, or retries it before it goes out. On the official tau2-Bench Retail and Telecom test sets and on LiveMCPBench, with three Nemotron base models and the same program for each, the answer depends on the domain. On Telecom, Granite-4.2-8B as the student goes from 43.0% to 91.2% under the program, and every Nemotron student reaches 93.3-94.4%, against at most 58.2% for fine-tuning on the same traces,
prompt optimisation of the student, or two
token-matched baselines. With Granite-4.2-8B as the student, the program is within 2 to 3 points of the Nemotron students on Telecom and within 3 on Retail, and 3 to 13 points below them on LiveMCPBench: where the domain is procedural an 8B student is enough, and on tool search the student still matters. On Retail and LiveMCPBench the program is competitive with the best baseline. The spread between base models shrinks from about 7 points to about 2, averaged over the suites, with no weights changed.
Read the full abstract ▾
Machine Learning
Demystifying On-Policy Distillation: Where Does the Teacher's Advantage Live?
Yiping Li, Fan Zhao, Zhibo Hou et al. (+2 more)
On-policy
distillation (OPD) is increasingly studied as a cheaper alternative to reinforcement learning, yet it remains a form of knowledge
distillation (KD) that relies on teacher supervision. We revisit OPD from the KD perspective by asking where the teacher's advantage lies along student-generated trajectories. Controlled
token flips at teacher-student disagreements directly measure the accuracy gained from teacher corrections. Single-
token flips yield a modest average gain on selected failed trajectories, whereas repeated flips raise accuracy from 28.4% to 74.5%, close to the teacher's 76.9%. Gains continue to accumulate with more flips, but mass- and KL-based selection outperform random flips by 15-18 percentage points at counts of similar magnitude. Selective intervention remains useful after OPD, but greater argmax agreement does not consistently improve accuracy across model pairs. We advocate training schedules that learn more valuable teacher corrections while maintaining distributional stability. Controlled flips and fork-resolution analysis evaluate OPD beyond accuracy by measuring which teacher preferences the student acquires and what further correction can recover.
Read the full abstract ▾
All authors Yiping Li, Fan Zhao, Zhibo Hou, Zhiyu An, Wan Du
Robotics
Post-Training, Finetuning, and Steering:A Field Guide for Curating Training Data
Maria Attarian, Yifan Ruan, Claas Voelcker et al. (+5 more)
While
Vision-
Language-Action models have enabled impressive cross-task transfer in zero-shot settings, adaptation methods are often necessary to achieve consistent performance on novel tasks. However, even though a wealth of methods for adaptation have been proposed, it is unclear how to choose the best method based on available trajectories. We close this gap by studying the impact of the adaptation method under a variety of common data scenarios: on- and off-policy data, offline vs online adaptation, and whether the data contains optimal or suboptimal trajectories. Our evaluation spans simulated tasks in the LIBERO suite and real tasks on a Franka platform. In the offline data regime, critic-based steering approaches outperform supervised finetuning when failure data is available. However, offline RL techniques for training critic functions fail to outperform simpler Monte-Carlo-based approaches. Finally, in the online setting, critic-based steering is significantly more sample efficient compared to policy-gradient-based finetuning methods, but has a lower performance ceiling than full finetuning.
Read the full abstract ▾
All authors Maria Attarian, Yifan Ruan, Claas Voelcker, Chenyang Cao, Amy Zhang, Peter Stone, Nicholas Rhinehart, Igor Gilitschenski
Machine Learning
Towards Training and Inference of Graph Neural Networks in Graph Databases
Victor Pekkari, Harry Wik, Alfred Clemedtson et al. (+2 more)
Graph Neural Networks on large graphs commonly rely on in-
memory graph storage with ad hoc data processing pipelines for both training and inference. Graph databases provide scalable storage and efficient traversal for graphs that can evolve over time, but their applicability in GNN training and inference are rarely studied. We show that graph DBs can be used in GNN training and inference directly, executing sampling, feature
retrieval, and even the full forward pass. We show different GNN training pipelines can perform on-the-fly sampling and
retrieval in graph DBs using Cypher. We further provide optimisations that speed up the training process by \~2.5x while maintaining the same accuracy. We illustrate that fully in-DB inference is possible, independent of how the GNNs are trained. Our inference setup can be >10x faster than cold loading the graph into RAM with no extra
memory overhead on real-world graphs. Our work lays the foundation for in-graph-DB GNN training and inference.
Read the full abstract ▾
All authors Victor Pekkari, Harry Wik, Alfred Clemedtson, Borun Shi, Xuan-Son Vu
Robotics
Collective Learning for Unified Robotic Manipulation via Predictive Dynamics Adaptation
Shaocheng Liu, Yuan Meng, Zhenshan Bing et al. (+1 more)
Learning a collective policy for state-based Cartesian manipulation across diverse robotic embodiments presents a fundamental challenge due to embodiment-dependent transition dynamics. Collective learning aggregates multi-
robot experience to discover shared task structure, yet naive aggregation can average incompatible action modes when different embodiments realize the same Cartesian command through different transition behavior. This leads to strategy ambiguity and performance collapse on dynamically outlying embodiments. To address this, we propose PACE, a two-stage collective learning framework that separates shared task-space intent from embodiment-dependent transition dynamics. The first stage employs a representation layer pre-trained on offline trajectories to extract task-level context from collective data. The second stage introduces a decision layer equipped with a predictive dynamics adapter. By forcing the latent state to predict future transitions, this adapter acts as a latent regularizer that grounds the policy in the transition behavior of the executing
robot while preserving real-time inference without online planning. Evaluations across simulated embodiments demonstrate that our method prevents performance collapse on distinct
robots. It achieves over 93% overall success and 89% on dynamically out-of-distribution zero-shot simulated
robots, outperforming the
Transformer behavior cloning (82%) and
diffusion policy baselines (66%). Physical KUKA deployment further validates the feasibility of the full state-based pipeline under zero-shot sim-to-real transfer.
Read the full abstract ▾
All authors Shaocheng Liu, Yuan Meng, Zhenshan Bing, Alois Knoll
Data Structures and Algorithms
Online Tokenization with Optimal Delay in Linear Time
Mina Dalirrooyfard and Christopher Ye
Tokenization is an essential preprocessing step in almost all large
language models (LLMs). One of the most popular frameworks is BPE tokenization, which consists of special
token segmentation, pretokenization, and byte-pair encoding (BPE). However, existing
algorithms are sequential, with each stage only processing complete output from the previous stage. In order to reduce latency and
memory footprints, recent works (Jiang and Gong, ICML 2026) (Li, Yang and Mamouras, ASPLOS 2026) (Mamouras, Li and Yang, PLDI 2026) have initiated the study of online
algorithms for subroutines such as pretokenization and BPE with a goal of streaming input to output as the input arrives online. However, the search for efficient online tokenization remains open. In this work, we formalize and resolve online tokenization. We introduce the notion of delay for online tokenization which characterizes the extent to which the
algorithm output lags behind the (possibly computationally intractable) optimum. We give a near-linear time
algorithm with optimal delay (up to constant factors). We complement this
algorithm with a conditional lower bound: unless $\mathbf{P} = \mathbf{NP}$, there is no
polynomial time
algorithm that beats the delay of our
algorithm by more than a constant factor. We implement a practical variant for tokenizers from OpenAI's tiktoken and HuggingFace's tokenizers. We obtain a $7.9\times$-$34.8\times$ latency advantage (measured as time to first
token) over tiktoken (as well as the recent gigatoken tokenizer) and our implementation maintains approximately constant
memory usage independent of input size. Our implementation also achieves a $2.4\times$-$7.0\times$ improvement in throughput over tiktoken and $15.8\times$-$38.1\times$ over tokenizers.
Read the full abstract ▾
Machine Learning
MA-Bench: Measuring Operational Planning in Language Models
Rodney Lafuente-Mercado, Robert Sincero, Phil Sage et al. (+1 more)
How well can a
language model turn a large, incomplete and partly contradictory body of documents into a plan when no single correct answer exists? We introduce Mission Analysis (MA)-Bench, built on mission analysis, the first step of military operational planning, in which a staff reads the full situation and states the problem before anyone proposes a solution. Its 10 expert-built scenarios pair synthetic packets of ten to twelve documents with 1,257 expert-written pass/fail requirements, each containing information on their source, question type, and importance level. A
reasoning-model judge grades each brief against the requirements without seeing the documents; it grades like a fifth credentialed planner, leaving a four-planner panel's agreement unchanged (Fleiss $\kappa$ 0.42 to 0.41), and a judge from a second provider reproduces the model ranking (Spearman 0.94). Across twenty frontier and open-weights models the best gets 62% of the rubric items right. Models are strongest on facts stated in the documents (58%) and weakest on judgments that must be inferred (33%), and six failures in ten are omissions rather than errors. MA-Bench grades the determinations, not the prose. We release the packets, rubrics,
prompts, scorer and every graded brief with item-level verdicts.
Read the full abstract ▾
All authors Rodney Lafuente-Mercado, Robert Sincero, Phil Sage, Yuan Xue
Artificial Intelligence
Graph-Based Orchestration of Heterogeneous AI Models: A Control Node Approach to Composite Intelligence
G. Michael Youngblood, Filip Dvořák, Slavo Švancár et al. (+3 more)
We present a graph-based framework for Composite AI systems that integrate multiple AI techniques to address complex problems. We describe an architecture using specialized control nodes to orchestrate diverse models including planning, machine learning, constraint programming, and large
language models. The system employs directed acyclic graphs and behavior trees to manage model relationships and execution sequencing. Our methodology encompasses data connectors, computational services, and a containerized deployment framework supporting hierarchical, sequential, and concurrent model composition patterns. Through case studies, we demonstrate how this architecture enables the creation of composite systems that leverage the strengths of multiple AI techniques within a unified operational schema, overcoming the limitations of single-model approaches.
Read the full abstract ▾
All authors G. Michael Youngblood, Filip Dvořák, Slavo Švancár, Tomáš Balyo, Michal Ficek, Martin Dousek
Machine Learning · Cross-listed from stat.ML
Student Copula Markov Networks
Salha Mamane and Cheikh Tidiane Seck
This paper extends the applicability of probabilistic graphical models to non Gaussian data. It establishes a characterization of the pairwise Markov property in undirected probabilistic graphical models in terms of copula densities. Building on this characterization, we derive a necessary condition for the pairwise Markov property in Student copula Markov networks. An Expectation-Conditional Maximization
algorithm (ECM) is provided to facilitate the penalized maximum likelihood estimation and graph selection. The performance of the proposed
algorithm is evaluated through simulation studies, which demonstrate its effectiveness in estimating model parameters and recovering the underlying graph structure.
Read the full abstract ▾
Computation and Language
CAFE: Confining Feature Distillation to Language-Routed Adapters for Compact Multilingual Automatic Speech Recognition
Tianchi Liu, Nicholas Moratelli, Khurram Azeem Hashmi et al. (+5 more)
Feature
distillation is usually expected to add to logit
distillation. We find that this expectation does not hold for two common feature losses in compact multilingual automatic
speech recognition (ASR), and analyze why through their gradients. The gradient of a projection-based loss is orthogonal to the task gradient, while that of Centered Kernel
Alignment (CKA), a similarity-based loss, is weakly aligned with it. CKA lowers the word error rate (WER) on non-English
languages, but at the expense of data-rich English. Three loss-level remedies (one trained, two probed) all fall short, and the CKA gradient overlaps with the subspace English uses in the shared encoder by 97.5% to 99.5% (about 81% by chance). Guided by this diagnosis, we propose CAFE (Confined-Adapter Feature
distillation), which confines the CKA gradient to adapters that English bypasses, addressing the trade-off in the parameters rather than in the loss. On the Open ASR Leaderboard, CAFE lowers the average WER from 8.55% to 8.02%, beats an adapter-only capacity control at 8.51%, and makes English more stable across checkpoints. At 254M parameters, it trails the 0.6B teacher by 2 WER points and is competitive with much larger models across 48 test sets in 24
languages. We use 564k hours of training data and state-of-the-art models to keep the findings relevant to practice.
Read the full abstract ▾
All authors Tianchi Liu, Nicholas Moratelli, Khurram Azeem Hashmi, Mohammadreza Zolfaghari, Rishabh Jain, Louis Lu, Changdae Park, Amril Nazir