Human-Computer Interaction
Understanding Parents' Complex Views of AI for Children's Pretend Play
Sungho Oh, Mohammad Namvarpour, Maxi Heitmayer et al. (+2 more)
AI could support children's pretend play, but it could also direct the play on behalf of children. Whether AI should have roles in children's lives is controversial because its influence on children remains uncertain. We conducted semi-structured interviews with 10 U.S. parents, each with at least one child aged 4-15. During the interview, we described the concept of AI-supported pretend play and provided participants with two boundary-case storyboards. We analyzed the interview data through codebook thematic analysis, using inductive coding and affinity diagramming organized around the research questions, and then used qualitative systems mapping to examine relationships within and across themes. We found that the same characteristics of AI, e.g., ability to assume characters, responsiveness, and adaptability, were seen by parents as potentially useful but also concerning. Parents imagined that AI could make role-based play accessible to all children or help parents participate in family play. However, they opposed the idea of AI for children's play without a clear understanding of how it works and its long-term influence on their children. Parents worried about children's loss of imagination and creativity, emotional attachment to AI, reduced human interaction, inappropriate behavior by AI and/or children, and their inability to manage children's AI use. Parents viewed AI not only as a play tool but also as a social actor and a possible perturbation in the existing family dynamics. The appropriateness of AI and child–AI interactions therefore emerged as a requirement for AI in children's pretend play, in addition to technical safeguards and parental control. We contribute an integrated account of parents' interdependent judgments and emphasize the need for longitudinal research with children and their diverse families.
Read the full abstract ▾
All authors Sungho Oh, Mohammad Namvarpour, Maxi Heitmayer, Minahil Khalid, Afsaneh Razi
Artificial Intelligence
OSWorld-Science: A Benchmark of Computer Use Agents for Learning and Using Scientific Software
Dingyuan Dai, Heli Qi, Lei Liu et al. (+28 more)
Scientific software presents a demanding test for computer-using
agents based on visual
language models (VLMs): completing a research workflow requires interpreting specialized interfaces, manipulating scientific objects, and producing verifiable results. We thus introduce OSWorld-Science, a
benchmark and evaluation environment that combines scientifically meaningful tasks, artifact-based evaluation, and an efficient
agent harness for studying computer use in the scientific domain. The
benchmark contains 12 VLMs and 146 high-quality tasks across several scientific domains and software configurations, covering workflows such as molecular drawing and retrosynthesis, pathology image analysis, statistical computing, and physical simulation. Tasks are developed through expert proposals and iterative human–AI co-design, with selection guided by scientific value and difficulty. Task-specific execution-based evaluators inspect application states and generated artifacts, including molecular structures,
segmentation masks, plots, and numerical results, and award partial credit for incomplete outcomes. Our special harness integrates model adapters, interaction-loop control, and trajectory logging to support comparisons of models and interaction strategies. Our results show that current state-of-the-art VLMs with a strong harness still face challenges in addressing key questions in the scientific domains. We also analyze the benchmarking results across multi-linguistics,
reasoning efforts, context length and other factors and derive several important conclusions and directions to assist future development. Overall, we provide an integrated framework connecting expert-defined scientific goals to verifiable software outcomes, enabling systematic evaluation of both
agent capabilities and harness design in scientific workflows.
Read the full abstract ▾
All authors Dingyuan Dai, Heli Qi, Lei Liu, Yinxi Li, Baiding Chen, Zijun Dou, Qingcheng Zeng, Qi Kang, Oliver Sun, Eric Wang, Bo Zhou, Haixin Wang, Yufan Du, Shi Bo, Ruihan Lin, Mengqi Yuan, Dunjie Lu, Steven Dillmann, Yiming Shi, Tina Su, Amy Xin, Minghao Liu, Xi Wang, Xu Huang, Ge Zhang, Pengyu Nie, Zhen Yang, Jie Tang, Juanzi Li, Weihao Xuan, Tianyu Liu
Cryptography and Security
CodeMimicry: Exploiting Safety Generalization Lag in Large Language Models via Structured Code Completion
Zhen Liang, Hai Huang and Wentao Chen
Large
language models have achieved remarkable capabilities across diverse domains, yet their safety
alignment remains vulnerable to jailbreak attacks. In this work, we identify a previously underexplored failure mode - safety generalization lag - where
alignment trained predominantly on natural
language fails to transfer to the code domain. We show that this lag induces a code-completion blind spot, allowing malicious intent embedded within syntactically valid code to evade safety mechanisms. To exploit this vulnerability, we propose CodeMimicry, a fully automated black-box jailbreak framework that generates structured, object-oriented code
prompts to induce harmful outputs via code completion. Experiments on 8 state-of-the-art commercial LLMs demonstrate that CodeMimicry achieves a 96.25% attack success rate with 1.51 queries on average, significantly outperforming both template-based and optimization-based baselines. Beyond empirical performance, we provide a mechanistic analysis of code-based jailbreaks through latent space representations, including projection onto refusal-related directions and activation steering. This analysis offers an explanation of how CodeMimicry bypasses safety mechanisms in code-related domains. Our findings reveal a weakness in current safety
alignment and highlight the need for robust
alignments in structured domains such as code.
Read the full abstract ▾
Machine Learning
Do Better Goal Representations Improve Goal-Conditioned Reinforcement Learning?
Syed Nazmus Sakib, Abdul Monaf Chowdhury, Nafiul Haque et al. (+2 more)
Goal-conditioned reinforcement learning (GCRL) relies heavily on how target goals are represented to the policy. While recent methods encode goals via temporal distance, occupancy, or controllability, it remains unclear how much downstream performance actually depends on representation quality. We study this in offline GCRL by constructing an exact temporal-distance goal representation in deterministic mazes. We then systematically corrupt its
geometric quality while keeping the downstream learner fixed. Across OGBench
navigation tasks and two
algorithms, large changes in goal-representation quality produce almost no change in performance. However, applying the same interventions to the
agent's current state more than doubles success, revealing the state pathway as the true bottleneck. Building on this insight, we show that simple random
Fourier positional encodings substantially improve performance on the hardest
navigation tasks without map information or objective modifications. Overall, our findings suggest that in state-based offline
navigation, improving how the
agent's current state is represented matters far more than refining the goal representation. Code will be released soon.
Read the full abstract ▾
All authors Syed Nazmus Sakib, Abdul Monaf Chowdhury, Nafiul Haque, Shifat E Arman, Md Mehedi Hasan
Computer Vision
Learning Where to Look: Anatomical Grounding and Guided Attention for Cardiac MRI Vision-Language Models
Bangwei Guo, Xiao Chen, Boris Mailhe et al. (+8 more)
Cardiac
magnetic resonance imaging (CMR) enables assessment of cardiac anatomy, ventricular function, and myocardial tissue characteristics. Clinicians interpret these images by identifying cardiac structures and focusing on the regions relevant to each clinical question, motivating anatomically guided
vision-
language models (VLMs). Yet CMR-specific supervision for anatomical localisation and clinical question answering remains limited. To address this gap, we investigate fine-grained CMR visual question answering through anatomical grounding and guided
attention. We construct 128,915 anatomical-grounding and 42,799 clinical QA pairs across short-axis cine, late gadolinium enhancement, and long-axis cine. These
datasets support anatomical recognition, localisation, and clinical assessment without requiring paired reports for individual training images. To help the model learn where to look, we introduce Cardiac Anatomy-Routed
Attention (CARA), which selects predicted anatomical priors according to the question and guides decoder
attention with learned task-specific strengths. Combining anatomical grounding pretraining with CARA yields our model, CARA-VL. Experiments demonstrate CARA-VL's strengths in clinical assessment and regional localisation across CMR imaging settings, with promising generalization to an external clinical cohort. Together, our data and method provide a practical framework for studying and advancing cardiac visual understanding in VLMs. We will release the QA data derived from public
datasets upon publication.
Read the full abstract ▾
All authors Bangwei Guo, Xiao Chen, Boris Mailhe, Jia Yao, Yiqing Wang, Ankush Mukherjee, Yikang Liu, Zheyuan Zhang, Hang Yu, Terrence Chen, Shanhui Sun
Robotics
Active Mapping of Underwater Litter Using Camera-Sonar Fusion
David Rete, Patrick Boros and Lucian Busoniu
Marine litter is a growing threat to the
underwater ecosystem, driving demand for autonomous survey methods that can locate debris efficiently over large areas. Existing survey methods typically follow predefined paths or operate with a single sensing modality, typically a camera (with image quality suffering in poor-visibility conditions) or sonar (usually noisy and low-resolution). We present an active mapping framework in which a forward-looking sonar and a camera both feed into a shared
Bayesian occupancy map, and an optimization problem is solved at each step to decide on the next best view. Candidate viewpoints are scored by a two-term utility that balances exploration of uncertain regions via voxel
entropy against exploitation of likely objects. Each sensor is characterized by range- and bearing-dependent detection and false-alarm probability tables determined from data. We evaluate the approach in a realistic
underwater simulator, demonstrating that active mapping finds objects faster than a lawnmower coverage pattern, and that the dual-sensor approach works better than using either of the individual sensors.
Read the full abstract ▾
Systems and Control
Exact Noise Limits for Bounded Scalar Stabilization Experiments
Alexey Peregudin and Ngoc Tuan Dinh
How much unknown process noise can a bounded experiment tolerate while still establishing that the plant can be stabilized? We answer this question for scalar discrete-time systems with bounded inputs, exact state measurements, and a disturbance-energy budget proportional to the experiment length. We distinguish individual stabilizability of every consistent model, stabilization by one common gain, and a common quadratic certificate. We determine their exact noise ceilings for every drift. The last two requirements coincide; individual stabilizability generally tolerates more noise. Bounded periodic inputs approach the ceilings, while
adversarial disturbances prevent their attainment. We also determine the long-horizon limits. For unstable plants, a short experiment can establish individual stabilizability at noise levels where every sufficiently long experiment fails. The same obstruction yields upper bounds for multidimensional systems with real
eigenvalues. Input design may use plant knowledge, but certification uses only the recorded data and noise bound. The results therefore provide fundamental robustness
benchmarks for unknown-plant designs.
Read the full abstract ▾
Computer Vision
Spatial-Temporal Multi-scale Network for Screen Content Video Quality Enhancement
Ziyin Huang, Sik-Ho Tsang, Xinyuan Qin et al. (+3 more)
Different from natural
videos, Screen Content
Videos (SCVs) are characterized by abrupt motion, scene switches, and high-frequency details such as text and graphics. Conventional
video enhancement methods, which rely heavily on temporal continuity, often suffer from performance degradation when processing SCVs due to the disruption of temporal correlations. To address these challenges, we propose the Spatial-Temporal Multi-scale Network (STM-Net), a novel framework specifically tailored for compressed SCV enhancement. Our approach integrates three complementary components: a Prior-Guided Spatio-Temporal Dispatcher (PG-STD) that routes input into three parallel streams to avoid feature contamination, a Bidirectional Temporal Feature Extraction (BTFE) module that adaptively handles abrupt transitions without explicit detection, and a Cascaded Multi-scale Feature
Distillation (CMFD) module that preserves critical high-frequency details. Experimental results demonstrate that STM-Net outperforms state-of-the-art methods in both objective metrics and subjective visual quality, providing a robust solution for screen content artifacts. Code is available at https://github.com/HUANGZiyin1/STM-Net.
Read the full abstract ▾
All authors Ziyin Huang, Sik-Ho Tsang, Xinyuan Qin, Yui-Lam Chan, Xueling Zhou, Feiyu Chen
Machine Learning
Shared Weights, Selected Computations: How Looped Transformers Route What Each Loop Does
Jiaju Wu, Yi Hu and Muhan Zhang
Looped
Transformers repeatedly apply the same set of
Transformer layers, giving them a recurrent architecture for latent computation. Their strong performance on iterative
reasoning and length-generalization tasks suggests an appealing explanation: recurrence may provide an inductive bias that lets the model reuse a learned
algorithm across loops. However, weight sharing alone does not imply that every loop performs the same operation. This raises a basic question: is each loop actually repeating the same computation, and if not, what routes the shared parameters to different operations? We study this question using graph walks as a test case. In the model's native trajectories, decoded predictions can advance by different numbers of graph steps or remain at a reached target, showing that recurrent progress need not follow a fixed one-loop-one-step pattern. We then show that a frozen loop can be steered toward different transitions by modifying its entering hidden state: a learned linear layer $J$ selects the desired transition without changing the shared
Transformer layers. To test how this steering works, we use activation patching and find that
attention patterns can recover its effects and switch the selected transition. Across five matched pairs of graph models, changing intermediate supervision during backbone training changes which transitions $J$ can induce. This suggests that $J$ selects computations learned by the backbone rather than creating new
algorithms. Together, these results show that the hidden state can control shared computation, with
attention routing as a causal pathway.
Read the full abstract ▾
Discrete Mathematics · Cross-listed from quant-ph
Quantum State Routing and Perfect State Transfer on Signed Graphs under Environmental Noise
Nur Mohammad Sanfui and Supriyo Dutta
Routing unknown
quantum information across distributed communication networks requires autonomous, measurement-free mechanisms to prevent wave-function collapse. Szegedy
quantum walks provide a mechanism for spatial state transport. The conventional walks on unweighted graphs suffer from severe back-reflection, spatial dispersion, and channel crosstalk. In this paper, we introduce a deterministic topological
quantum routing architecture based on coined Szegedy
quantum walks on edge-duplicated signed graphs. By treating edge signs as localized phase shifts within a balanced coin reflection, we enforce an exact zero back-scattering condition across routing nodes. We demonstrate deterministic Perfect State Transfer (PST) with unit fidelity at exact arrival times across fundamental archetypes, including the signed dumbbell switch $D_{2m,0,2n}$ and scalable glued binary trees. Furthermore, we analyse routing performance under realistic open-system amplitude and phase damping noise channels.
Read the full abstract ▾
Multiagent Systems
Solving Multi-Agent Sokoban via LaCAM
Keisuke Okumura
Sokoban, a puzzle game in which an
agent pushes boxes onto unlabelled target locations in a grid world, is a long-standing
benchmark planning problem. While it is easy to see the connection to practical applications such as warehouse logistics with autonomous forklifts, its multi-
agent counterpart has remained underdeveloped. This is because Multi-
Agent Sokoban is substantially more difficult due to factors specific to multi-
agent planning, such as the rapidly growing branching factor as the number of
agents grows and the need to handle integrated task assignment and collision-free pathfinding. In this paper, we show that a scalable planner for Multi-
Agent Sokoban can be designed by leveraging recent advances in multi-
agent pathfinding (MAPF). Specifically, our Sokoban-LaCAM efficiently solves instances involving tens of
agents and boxes while preserving both completeness and eventual optimality guarantees. This provides evidence that MAPF can serve as a powerful primitive for solving broader collective automation problems.
Read the full abstract ▾
Machine Learning
Markovian Dynamics Enforcer: Feasibility Preserving Correction on Learned Dynamics Manifolds
Kevin Yu, Tao Guo, Constantinos Antoniou et al. (+1 more)
Neural trajectory predictors can reach low prediction error while violating dynamics, actuator limits, or state constraints, especially when controls are unobserved and dynamics are partially specified. We introduce the Markovian Dynamics Enforcer (MaDE), a time-invariant post-hoc operator mapping state-transition proposals onto a learned feasible dynamics
manifold, trained on feasible states without ground-truth controls. For each transition it infers a control and recomputes the state through a completion model of known physics plus a learned residual. It then corrects that control by gradient-based inequality reduction, so inequality satisfaction is best-effort within an iteration budget. Since every correction iterate re-enters the completion model, the returned state is dynamically consistent by construction relative to that model and the supplied previous-state anchor. MaDE drives dynamics residuals to essentially zero on fully specified simulated systems, and on an underspecified system leaves a smaller true-dynamics residual than the baselines. Designed to attach to arbitrary predictors, the frozen operator is evaluated downstream of recurrent, structured state-space, and
transformer predictors. On recorded vehicle trajectories the one-step residual against a kinematic bicycle model is 0.0071 to 0.0072 for MaDE and 0.1703 to 0.1714 for raw predictors. MaDE raises average displacement error by a factor of 1.57 to 1.83.
Read the full abstract ▾
All authors Kevin Yu, Tao Guo, Constantinos Antoniou, Panagiotis Angeloudis
Game Theory
Generalized Prophet Inequalities for Online Auctions
Twan Kroll and Rebecca Reiffenhäuser
Prophet Inequalities for online auctions, as many classical auction settings, traditionally consider
agents who strive to maximize quasi-linear utility, i.e. their obtained value minus the price paid. This simplified view of the
agents' objectives does not capture real-world settings where
agents are almost always constrained by budgets, and can have different objectives altogether (e.g., very prominently, value maximizers in autobidding). We generalize classic prophet inequality auction settings to accommodate unknown, varying types of
agent objectives and budgets, modeling them as
stochastic input similar to the traditional valuation distributions. In this new model, we analyze (anonymous) posted-price mechanisms, one main category of which are the balanced prices central to many auction results in the prophet inequality model. We demonstrate both the resilience and limits of balanced price mechanisms for generalized prophet inequalities with
stochastic agent objectives, budgets and valuations: our generalization of the balanced prices framework incorporates budget constraints and mixed objectives. We show constant competitive ratios for some the most central settings, spanning all the way up to
agents with subadditive valuation functions. On the way, we establish trade-offs between competitive ratio and
agents' price-sensitivity, and give a general reduction from the budgeted setting to budget-free value maximizers.
Read the full abstract ▾
Computation and Language
OPSRD: On-Policy Self-Role Distillation
Weijie Ren, Yanwen Zhang, Hao Li et al. (+3 more)
Role prompting elicits specialized behavior from large
language models through an expert identity, offering a lightweight way to guide
reasoning on demanding tasks. However, evaluating or distilling complete role-prompted answers can miss useful next-
token preferences when the sampled solution remains incorrect. Transferring these preferences also requires an objective that reaches alternatives the student rarely predicts. We introduce OPSRD, which uses a fixed expert role as privileged teaching context for on-policy self-
distillation without reference solutions. A role-free student generates a trajectory, and a frozen instance of the same base model supplies role-conditioned distributions on its exact prefixes, exposing alternatives beyond the sampled continuation. Teacher-weighted forward KL targets alternatives the student underestimates, with clipping to limit individual vocabulary contributions. Supervision is restricted to the highest-
entropy half of student positions, concentrating learning where predictions are uncertain. Experiments on three competition-math
benchmarks with Qwen3-1.7B, 4B, and 8B show improvements over the base models without role
prompts at inference. Forward KL achieves the highest macro-averaged accuracy among the three evaluated divergences at every scale. Code is available at https://github.com/zhansan114514/OPSRD.
Read the full abstract ▾
All authors Weijie Ren, Yanwen Zhang, Hao Li, Zhuolin Qi, Hengyi Zhang, Naibo Wang
Computer Vision
Grounding with Confidence: Controllable Generative Video Temporal Grounding
Jinhao Chen, Benlei Cui, Ruijian Jia et al. (+7 more)
Video temporal grounding supports applications such as
video search, content review, and automated editing by localizing events described in natural
language. Yet existing generative models typically output timestamps without explicit interval-level confidence scores to guide candidate selection. We separate candidate generation from acceptance by scoring individual intervals within the original decoding pass. A lightweight confidence head reads pooled decoder states, providing an explicit score trained for interval selection. Offline verifier scores supervise the head on fixed candidate sequences, and temporal-overlap labels adapt it to current rollouts during reinforcement learning. GT-anchored candidate-pool supervision and set-level optimization train the generator. The resulting scores support ranking, threshold-based selection, and rejection without invoking an external verifier at inference. On a fixed OMTG-Bench candidate pool, confidence raises query-macro Recall@0.5 from 9.95% to 14.42% over generation order at a 10% global return budget, and from 26.48% to 31.12% at a 25% budget. The continuous scores let downstream applications adjust return budgets or acceptance thresholds to match their precision-recall preferences, without regenerating candidate intervals. Code is available at https://github.com/Alibaba-VELLDEPTH/Grounding-with-Confidence.
Read the full abstract ▾
All authors Jinhao Chen, Benlei Cui, Ruijian Jia, Ziheng Wang, Tianyu Wo, Pengfei Sun, Longtao Huang, Hui Xue, Yitong Yang, Haiwen Hong
Computation and Language
LLM Persona Unlearning
Kemou Li, Zhuan Shi, Qizhou Wang et al. (+4 more)
Pre-training equips large
language models (LLMs) with a broad repertoire of behavioral patterns associated with roles, styles, values, and goals. Post-training teaches conditional enactment and makes a helpful Assistant the default, but it does not erase alternative modes from the weights; explicit
prompts can therefore elicit personas that repeatedly shape judgment,
language, and action. In open-weight settings, runtime controls can be removed, motivating persona unlearning: a weight-level edit that makes a designated persona difficult to elicit and enact on unseen contexts. We introduce PersonaUnlearnBench, a model-specific paired
benchmark spanning six LLMs from three families and five personas, with aligned forget/retain sets, held-out instruction paraphrases, and four-axis evaluation. The
benchmark shows that standard unlearning methods cannot reliably erase the target persona without sacrificing meaningful generation or general utility. We therefore propose PaCE, which compares target and desirable responses to the same questions to locate an internal behavior direction, then trains target-
prompt states away from the target mode and toward the matched desirable response. Experiments show that PaCE consistently suppresses target personas with high response quality and useful counterpart behavior, at moderate utility cost. These results establish persona unlearning as a distinct behavior-level editing problem and a practical route toward persistent control of latent LLM response policies.
Read the full abstract ▾
All authors Kemou Li, Zhuan Shi, Qizhou Wang, Fengpeng Li, Negar Rostamzadeh, Golnoosh Farnadi, Jiantao Zhou
Cryptography and Security
PassGPT+: Leveraging Linguistic Priors for Password Modeling
Rajneesh Anand, Neeraj Lakshmanan and Masoud Yari
Passwords remain the dominant online authentication mechanism, and understanding how humans choose them is essential for defensive strength estimation and attack simulation alike. Recent learning-based approaches such as PassGAN and PassGPT have shown that deep generative models can learn password structure directly from leaked corpora. However, both train from random initialization on password data alone. The role of linguistic prior knowledge in password modeling, and what it reveals about how humans create secrets, remains largely underexplored. Here, we address this gap with PassGPT+, which adapts the linguistic prior of GPT-2 to password observations through character-aware tokenization. We also introduce PassDiffusion, the first absorbing-state discrete
diffusion model for password generation, as a probe of whether non-autoregressive approaches are competitive. On the RockYou
benchmark, PassGPT+ recovers 22.53% of held-out passwords at 108 guesses, a 16% relative gain over PassGPT, and retains 79% of this match rate when transferred without retraining to a disjoint 2020 leak
dataset, demonstrating that linguistic priors capture persistent regularities of human password generation. PassDiffusion underperforms by two to three orders of magnitude, indicating that autoregressive modeling is substantially better matched than iterative denoising to the discrete, exact-match nature of password generation.
Read the full abstract ▾
Machine Learning
Algorithmic Recourse Under Competition
Shahin Jabbari
Algorithmic recourse provides individuals who have received undesirable outcomes from machine learning models with suggestions for minimum-cost improvements to achieve the desired outcome. A central assumption when computing recourse is that the decision rule remains fixed throughout the recourse implementation phase. We challenge this assumption in settings where individuals compete for limited resources. In such settings, widespread recourse implementation can change the acceptance threshold even when the scoring model that is used to evaluate individuals remains the same. This change in acceptance threshold can, in turn, invalidate the original recourse recommendations (i.e., following the recourse may not lead to the desired outcome). To address this problem, we introduce a framework called recourse under competition that jointly optimizes for recommendation recipients and the recommended score target they need to satisfy to balance the recourse cost and post-shift validity among initially rejected individuals. We develop an
algorithm based on the Implicit Function
Theorem and empirically analyze its performance. Experiments on synthetic and real
datasets show that personalized score targets can achieve higher validity, albeit at a higher cost. In contrast, common score targets generally offer favorable cost-validity trade-offs for lower to medium validity values.
Read the full abstract ▾
Robotics
SplineWAM: Adaptive Action Horizons for World Action Models via B-Spline Representations
Jun Guo, Xiaoshen Han, Qiwei Li et al. (+7 more)
World action models (WAMs) are large
embodied policies that jointly predict future
video and the actions to execute, emitting a fixed-length action chunk per inference call. Such a policy allocates its computational budget uniformly in time, unable to execute for longer over free-space motion or to spend more inference on contact-rich manipulation, which limits the throughput a WAM can reach when served in the cloud. We present SplineWAM, which adaptively compresses the action trajectory into a fixed-size window of cubic B-spline parameters, fitting the
knot times to the characteristics of the motion. One parameter budget then decodes into chunks of varying temporal resolution and duration, and both the executed span and the interval until the next policy call follow from the prediction itself. Aligning the
video supervision to the fitted
knot times of the demonstration rather than to a uniform grid concentrates the supervised frames where the action trajectory is complex. For asynchronous deployment we introduce Jacobian-Pullback Real-Time Chunking (JP-RTC), which imposes chunk continuity on the decoded raw actions the
robot executes rather than on the spline parameters, and corrects the parameters through the decoder so that the executed prefix agrees with the actions already committed. On LIBERO-Plus and RoboCasa, SplineWAM improves success rate over an action chunking WAM by $8.2$ and $4.4$ points while cutting policy calls per episode by 22% and 26%. On three bimanual real-
robot tasks under asynchronous execution, it leads or matches the baseline while decoding 1.2 to 1.6 times as much executed motion per call.
Read the full abstract ▾
All authors Jun Guo, Xiaoshen Han, Qiwei Li, Nan Sun, Peiyan Li, Heyun Wang, Hang Lai, Weinan Zhang, Xinghang Li, Huaping Liu
Computer Vision
A PyTorch Library for Hyperspectral Image Models: Technical Report
Tanishq Rachamalla, Aryan Das, Srishti Kaushik et al. (+1 more)
Hyperspectral remote sensing has advanced across diverse deep learning paradigms, including spectral spatial CNNs,
Vision Transformers, Mamba, graph neural networks, Kolmogorov Arnold networks, and self supervised masked autoencoding. Yet progress remains hindered by fragmented repositories, incompatible tensor conventions, and non standardized evaluation. Hyperspectral Image Models addresses these challenges through a modular framework unifying 55 representative models across six paradigms with a common registry, automatic 4D/5D tensor adaptation, and standardized constructors. It integrates 24
benchmark scenes from Airborne, Spaceborne,
UAV, and Mars CRISM sensors, with caching, label remapping, PCA, explicit band selection or raw spectra, optional spatial max pooling, and arbitrary PxP patch extraction. To prevent inflated accuracy from overlapping windows, it supports class balanced random partitioning and spatially disjoint regional blocking with Chebyshev guard bands that eliminate train test pixel overlap. Experiments use a single config with deterministic seeds and complete provenance, generating LaTeX
benchmark tables and classification maps. Across 1,320 model scene evaluations and 6,600 seeded runs, scene difficulty dominates architecture, with mean accuracy ranging from 96.40% on Botswana to 56.70% on Houston 2018, versus a 15 point spread across paradigm means. No paradigm universally dominates, while sub 1 M parameter models can match architectures two orders of magnitude larger. Code is publicly available at https://github.com/Tanishq251/Hyperspectral-Image-Models.
Read the full abstract ▾
All authors Tanishq Rachamalla, Aryan Das, Srishti Kaushik, Swalpa Kumar Roy
Robotics
Magic-W0: A Structured World-Action Foundation Model for Physical Intelligence
Xuhua Chen, Zhenhan Yin, Yuan Zhang et al. (+15 more)
World-action models (WAMs) augment
robot policies with action-conditioned environment dynamics, yet existing approaches largely rely on future observation reconstruction or generic latent prediction and lack structured, control-oriented world representations tightly coupled with action generation. We introduce Magic-W0, a world-action foundation model that jointly models structured physical state
evolution and continuous actions. Magic-W0 represents interaction as a Structured World Transition consisting of Current State, Transition, and Future State. Current State combines
vision-
language context with Current 3D Geometry; Transition is represented by 3D Motion capturing action-induced three-dimensional changes; and Future State is represented by Future Semantics describing task-relevant outcomes. To couple prediction and control, we propose a layer-aligned world-action interaction architecture in which evolving action hypotheses condition world-transition prediction, while predicted world representations continuously inform action generation. Magic-W0 is pre-trained on large-scale
egocentric human manipulation, UMI, real-
robot, and simulation data, with latent supervision for geometry, 3D motion, and future semantics from pre-trained visual models. Inference-time interventions show that structured world representations respond systematically to changes in candidate actions and that action-related information propagates through shared 3D representations into future semantic predictions. On RoboDojo-Sim, Magic-W0 achieves an average Score of 27.10, the highest among the compared WAMs. Across multiple real-
robot tasks, it also demonstrates strong downstream performance after fine-tuning with limited downstream data, supporting generalization and rapid adaptation.
Read the full abstract ▾
All authors Xuhua Chen, Zhenhan Yin, Yuan Zhang, Lingfeng Zhang, He Zheng, Tong Mu, Shun Zuo, Dian Zhou, Di Wu, Xuan Zhou, Shaojie Wan, Rongtian Shen, Qiulong Xu, Yiduo Li, Yinglong Wang, Yanqian Wang, Kun Wang, Tao Zhang
Artificial Intelligence
GrammarRL: Effective Grammar-Constrained Decoding via Reinforcement Learning
Gabriele Tuccio, Antonino Furnari, Aldo Gangemi et al. (+1 more)
Grammar-constrained generation guarantees syntactic validity, but can substantially degrade semantic quality when the model's preferred outputs are poorly aligned with the imposed grammar. This trade-off is particularly severe when the
prompt is underspecified or the model has limited instruction-following ability. Beam search can partially mitigate these failures by exploring multiple valid sequences, but its computational cost grows with beam width, while sequence-level probability is only an imperfect proxy for semantic quality. We introduce GrammarRL, a label-free reinforcement learning method that adapts
language models to grammar constraints without requiring annotated data. GrammarRL optimizes the model using two complementary self-supervised rewards derived from its own likelihoods: a direct reward, measuring how likely the constrained output is given the input, and a reverse reward, measuring how well the input can be reconstructed from the generated output. We optimize these rewards with a Reinforce Leave-One-Out (RLOO) objective over groups of grammar-constrained rollouts, augmented with the top-1 beam-search hypothesis and regularized towards a frozen base model. We evaluate GrammarRL on sign
language gloss translation, hierarchical text classification, and named entity recognition using Llama models ranging from 1B to 8B parameters. GrammarRL consistently outperforms constrained greedy decoding, with an average improvement of 9.8 points and gains of up to 22.8 BLEU. It matches or outperforms beam search on two of the three tasks while preserving greedy-decoding inference cost. Ablations further show that the two rewards are complementary: either reward alone can underperform the untrained baseline, whereas their combination consistently improves upon it.
Read the full abstract ▾
All authors Gabriele Tuccio, Antonino Furnari, Aldo Gangemi, Misael Mongiovì
Artificial Intelligence
Completion-Aware Cross-Fidelity Offline-to-Online Reinforcement Learning for Multi-Line Bus Holding
Yifan Zhang, Qifan Zhang and Liang Zheng
Exploratory reinforcement learning (RL) on an operating bus fleet is impractical,while policies trained only from historical data cannot acquire new experience. Hybrid Offline-and-Online (H2O) RL combines fixed target replay with simulator interaction, but the inexpensive online simulator can differ from the target in transition and event-duration dynamics. We study this cross-fidelity problem for multi-line bus holding and address a failure mode in which lower generalized passenger time coexists with incomplete passenger journeys.
Read the full abstract ▾
Machine Learning
Preemptive LLM Unlearning against Forbidden Capability Acquisition via Gradient Sealing
Kemou Li, Qizhou Wang, Yue Wang et al. (+6 more)
Open-weight LLMs are released not only as fixed products but also as substrates for downstream fine-tuning. This openness, however, creates legal and ethical risks because users may misuse fine-tuning to instill illicit knowledge or enable hostile operations. Model providers therefore need apre-release defense against such acquisition, motivating the problem of preemptive unlearning. Unlike retrospective unlearning, which removes capabilities already present in a fixed model, preemptive unlearning seeks to prevent their acquisition under unseen attack data and future fine-tuning procedures. Despite its practical importance, this setting remains largely unexplored, presents distinct challenges, and is therefore the central focus of our work. We first verify that existing retrospective methods provide insufficient pre-release protection. Even when forbidden capabilities are suppressed in current outputs, forbidden-domain data can still induce gradients through internal pathways, enabling later acquisition. Motivated by this finding, we propose a gradient-sealing principle that blocks these pathways by pushing relevant pre-activations into the negative region, where ReLU-family activations exhibit zero or near-zero derivatives. Experiments across multiple LLM families demonstrate our stronger resistance to downstream acquisition than retrospective baselines, validating gradient sealing as an effective mechanism for pre-release protection.
Read the full abstract ▾
All authors Kemou Li, Qizhou Wang, Yue Wang, Fengpeng Li, Zhuan Shi, Negar Rostamzadeh, Golnoosh Farnadi, Masashi Sugiyama, Jiantao Zhou
Artificial Intelligence
FIGS: Evaluating Multi-Turn Sycophancy Without Penalizing Empathy
Sidharth Pulipaka, Ruta Binkyte, Ivaxi Sheth et al. (+1 more)
Large
language models frequently fail to balance staying truthful with being supportive. They often exhibit sycophancy in responses to users, agreeing with false claims, offering unwarranted flattery, and giving advice skewed toward users' expressed views. In reality, sycophancy rarely happens in a single exchange; it may emerge organically as users repeatedly insist or subtly steer the dialogue over time. Current evaluations, however, rely on rigid, single-turn tests or fixed scripts that fail to capture these natural dynamics. Furthermore, these
benchmarks often mistake showing basic empathy for yielding, penalizing models for acknowledging a user's feeling. This view may drive future models to over-correct into cold, dismissive
rigidity. To address this gap, we introduce FIGS (Factual Integrity and Grounded Support), a dual-axis evaluation framework built around extended, realistic dialogue. We use an adaptive 10-turn conversational simulator that dynamically challenges the target model, reflecting how users repeat requests, push back, or steer a conversation toward a preferred answer. To accurately evaluate these trajectories, we apply a taxonomy that strictly separates Sycophancy (whether the model holds firm to the truth and keeps its praise proportional) from Calibrated Validation (showing empathetic understanding of the user's feelings without overdoing it). We release our complete testing environment, including 500 diverse multi-turn scenarios and an automated judge. Our evaluation of leading models reveals a consistent trade-off: over the course of a sustained interaction, current systems either slowly drift to sycophancy or over-correct into robotic detachment. This demonstrates that balancing honesty with appropriate support throughout a natural conversation remains a critical, unsolved challenge.
Read the full abstract ▾
All authors Sidharth Pulipaka, Ruta Binkyte, Ivaxi Sheth, Sahar Abdelnabi
Machine Learning
Fork-dLLM: Avoiding the Flexibility Trap in Diffusion Language Models
Stipe Frković, Metod Jazbec and Christian A. Naesseth
Masked
diffusion language models (dLLMs) have shown strong potential for faster inference through parallel
token generation when combined with confidence-based samplers. However, recent work has shown that such methods can defer unmasking high-
entropy fork positions at which multiple plausible continuations exist. This results in reduced generation diversity, as shown by worse pass@k scaling, and limits gains obtainable from RL post-training. To avoid this flexibility trap, prior work advocated for autoregressive (AR) sampling. Here, we show that discarding confidence-based sampling is unnecessary and, once inference cost is taken into account, wasteful. We first propose Fork-dLLM, a simple hybrid sampler that uses AR-style ordering only at uncertain fallback steps while retaining parallel generation otherwise. We then extend the same principle to post-training with ForkGRPO, which uses Fork-dLLM rollouts and applies the GRPO objective only at fallback steps, preserving exact policy-likelihood ratios while substantially reducing rollout and optimization cost. In our experiments, Fork-dLLM matches the strong pass@k scaling of AR sampling while being 2-3x more efficient, and ForkGRPO achieves downstream performance comparable to or better than AR-based GRPO baselines at a substantially lower training cost.
Read the full abstract ▾
Numerical Analysis
Exact Representation of Piecewise Polynomial Finite Element Functions by Two-Hidden-Layer Multilayer Perceptrons
Jun Hu, Pengzhan Jin and Shengyang Xu
We construct exact representations of finite element functions of arbitrary
polynomial degree on simplicial meshes in any spatial dimension by two-hidden-layer multilayer perceptrons (MLPs). The first hidden layer uses $\mathrm{ReLU}^0+\mathrm{ReLU}$, and the second uses the degree-dependent activation $\mathrm{ReLU}^k$. The neural networks can realize both zero-skeleton and prescribed-skeleton representatives of discontinuous finite element functions, where the former vanish on the mesh skeleton and the latter admit independently prescribed
polynomial data on each relatively open lower-dimensional mesh subsimplex; in particular, continuous finite element functions can be represented pointwise on the closed domain. In the continuous case, a half-open decomposition reduces the second-hidden-layer width by assigning each subsimplex to a single incident element. The number of nonzero parameters grows linearly with the number of elements for fixed spatial dimension,
polynomial degree, and output dimension, and it is of the same order as the number of global degrees of freedom of the finite element space in the continuous case, provided that the mesh is shape-regular. All parameters in the neural network can be explicitly computed via the information of the mesh and finite element function without training.
Read the full abstract ▾
Machine Learning
Dimension-Free Rank Lifting from Random Hyperplane Arrangements
Luca Becchetti, Matteo Russo and Ruben Skorupinski
We study the width required for a randomly initialized hidden layer of a neural network to achieve rank lifting. Namely, given a
dataset $X \in \mathbb{R}^{m \times d}$ of $m$, $d$-dimensional input vectors separated by an angle of at least $\theta$, we consider the random feature
matrix $\sigma(XR)$, where $R$ is standard Gaussian. For positively homogeneous nonpolynomial activations, which include sign, Heaviside, ReLU, and ReLU powers among others, we prove that $$n \gtrsim \frac{1}{\theta}\max\left\{m,\log\left(\frac{1}{\delta}\right)\right\}$$
neurons suffice for $\sigma(XR)$ to have full row rank $m$ with probability at least $1-\delta$. This dimension-free bound exponentially improves the previous general-dimensional guarantee for sign features (Drago et al., 2026) and is essentially tight. The proof shows that one random feature column escapes every proper subspace of $\mathbb{R}^m$ with probability $\Omega(\theta)$, using a coupling of nearby Gaussian directions and a local crossing of the induced hyperplane arrangement. We also study stable rank lifting, where the goal is to establish a quantitative analogue of exact rank lifting, i.e., a lower bound on the smallest
eigenvalue of the empirical feature Gram
matrix in high-probability. Our analysis unifies and generalizes stable rank guarantees for all $q$-homogeneous non-
polynomial activations following prior work in Panigrahi et al. (2020) and Song (2026). In particular, we combine a diagonally dominant Taylor tail of the population kernel with truncation and
matrix concentration, to show that for positively homogeneous nonpolynomial activations, stable rank lifting is achieved at width $$n \gtrsim C^q \frac{m}{\theta^{2q+1}} \log^{2q+\frac{1}{2}}\left(\frac{m}{\theta}\right) \log\left(\frac{m}{\delta}\right),$$ where $q$ is the degree of the activation and $C > 0$ is some universal constant.
Read the full abstract ▾
Robotics
RL-Guided PAC-NMPC for Probabilistically-Safe Perception-Based Navigation in Unknown Environments
Adam Polevoy, Dillon Capalongo, Katherine Tang et al. (+3 more)
In this paper, we present an approach for combining
stochastic nonlinear model predictive control (SNMPC) and reinforcement learning (RL) to enable probabilistically-safe perception-based
navigation in unknown environments. Our method first uses RL to train probabilistic actor-critic and sensor prediction models. We then leverage these probabilistic models in a sampling-based SNMPC framework known as Probably Approximately Correct (PAC)-NMPC, which uses hard constraints to enforce finite-time statistical guarantees on the probability of collision and value function improvement. By ensuring that our finite-horizon SNMPC policies decrease the value function in expectation, we can approach the long-horizon performance of the RL approach while satisfying probabilistic safety constraints. Through simulation experiments, we show that our approach can improve the safety of perception-based RL
navigation policies and scale to high dimensional systems with large sensor input spaces and complex nonlinear dynamics. We also demonstrate our approach through hardware experiments, showing improved performance for
vision-based
navigation with an agile fixed-wing aerial vehicle in unknown environments.
Read the full abstract ▾
All authors Adam Polevoy, Dillon Capalongo, Katherine Tang, Mark Gonzales, Marin Kobilarov, Joseph Moore
Computation and Language
Cognitive Enhancement: Rethinking the Necessity of Role-Playing for Large Language Models
Xingjie Zhuang, Jialong Tang, Chulun Zhou et al. (+5 more)
Role-playing prompting has become a popular yet simple technique for improving LLM
reasoning and output quality. However, whether it consistently boosts performance across diverse domains remains unclear, as systematic validation is lacking. To fill this gap, we run multi-model, cross-domain, and
multilingual experiments on MMLU and MMLU-Redux. We find that gains from role-play prompting depend heavily on model capacity, knowledge domain, and
prompt language. Drawing on metacognition theory, we propose the persona-related cognitive
alignment hypothesis: role-play works only when the LLM correctly grasps the designated persona and its associated knowledge domain. We test this hypothesis through persona information richness ablation, layer-wise
entropy divergence analysis, and latent thought-space deflection observation. To reduce persona cognitive bias and stabilize role-play performance, we propose Mixed-
Language Concatenate Prediction (MLCP), a simple, training-free, and efficient
multilingual prompt concatenation strategy. It aggregates semantically equivalent role
prompts to enrich complementary representational cues. Extensive experiments show that MLCP consistently outperforms vanilla role-play prompting across all tested LLMs.
Read the full abstract ▾
All authors Xingjie Zhuang, Jialong Tang, Chulun Zhou, Buchao Zhan, Zhirui Li, Junhui Li, Yazheng Yang, Jinsong Su