Artificial Intelligence
Does Model Uncertainty Track Human Ambiguity? Evidence from Multi-Annotator Vision Benchmarks
Manya Singh and Arjun Pakrashi
Human-model
alignment is critical for trustworthy AI-assisted decision-making systems. Yet, most work evaluates model predictions against single ground-truth labels, overlooking that humans themselves often disagree on labels, a signal of genuine ambiguity. We investigate whether models struggle on the same instances that humans find difficult. We measure this on two
vision datasets (FER+ and CIFAR-10H) where multiple human annotations per image capture human disagreement patterns. We evaluate eight pretrained models across three architectures (ResNet, EfficientNet, MobileNetV3) in two parts: first, whether model uncertainty (softmax confidence,
entropy) correlates with human disagreement, and second, whether predictive multiplicity measures (inter-model disagreement, Jensen-Shannon divergence) do. We find that it does not:
alignment is weak in both dimensions. At the discrete label level, 50.4% of CIFAR-10H images and 33.5% of FER+ images receive multiple valid classifications from humans, while the models converge on only one. These instances represent a critical failure case where humans perceive ambiguity and would request expert review, yet models decide confidently. At the continuous score level, single-model uncertainty correlates weakly with human disagreement ($\rho = 0.24--0.55$), and predictive multiplicity provides only modest improvement. Widely-used uncertainty quantification methods do not reliably identify instances humans find ambiguous. Model uncertainty should not be treated as a trustworthy signal by default for decision-making in high-stakes scenarios.
Read the full abstract ▾
Logic
Kaplansky decompositions of Polish modules
Ivo Herzog, Gianluca Paolini and Saharon Shelah
Let $R$ be a countable ring. Given an $R$-module $A$, we call a decomposition $A = \bigoplus_{i \in I} N_i$ a Kaplansky decomposition if each $N_i$ is countable. We characterize the uncountable Polish $R$-modules that admit a Kaplansky decomposition: they are exactly the modules of the form $B \oplus M^{\omega}$, where $B$ and $M$ are countable and $M$ is $\Sigma$-algebraically compact. The countable summand $B$ may moreover be taken to be an elementary submodule satisfying a closure condition, which makes $M^{\omega}$ unique up to isomorphism, and hence an invariant of $A$. We use this to characterize the countable rings admitting a free uncountable Polish $R$-module, generalizing results of Shelah and Solecki. This class of rings has a purely ring-theoretic description: it consists exactly of the countable left perfect and right coherent rings, i.e. the rings identified by Chase's
theorem on products of projective modules. We observe that these are also exactly the countable $F$-rings, i.e. those countable rings $R$ for which $R^{\omega}$ is free. Finally, we give a ring-theoretic characterization of the countable rings $R$ for which there exists an uncountable projective Polish $R$-module.
Read the full abstract ▾
Analysis of PDEs
The fractional Fisher-KPP equation with free boundaries
Huyuan Chen, Yihong Du and Wenjie Ni
In this paper, we consider a free boundary problem with fractional
diffusion $(-\Delta)^s$ $(0<s<1)$, as a model for species spreading, which can be viewed as a natural extension of the free boundary model in \cite{CDLL2019}, where the nonlocal
diffusion term is defined via a continuous integrable kernel function $J(x)$. This fractional
diffusion model can also be viewed as a nonlocal version of the free boundary model in \cite{DuLin2010}, whose local
diffusion term is given by the classical
Laplacian. We first establish the global existence and uniqueness of the solution, which is the main contribution of this paper. This well-posedness question has been open for some time now due to the difficulties caused by the singularity and non-integrability of the associated kernel function of $(-\Delta)^s$, and the lack of general enough regularity results for operators extending the standard fractional
Laplacian. A crucial step that enables us to answer this question relies on an approximation approach, which breaks an associated linear fractional
parabolic initial boundary value problem with curved boundaries into a sequence of approximating problems, where the functions representing the curved boundaries are replaced by approximating step functions. We then show that, for Fisher-KPP type nonlinear growth terms, the long-time dynamics of the model exhibits a spreading-vanishing dichotomy, similar to the earlier models of \cite{DuLin2010, CDLL2019}. More precise descriptions of the spreading profile of the solution will be considered in a separate work.
Read the full abstract ▾
Machine Learning
Distribution-Conditioned Task Routing for Class-Incremental Learning
Longhuan Xu, Zhipeng Zhou, Wei Ji et al. (+3 more)
Parameter-efficient adaptation enables continual learners to acquire task-specific knowledge through compact model updates while maintaining strong within-task performance. However, class-incremental inference requires each input to be classified among all classes seen so far without access to its task identity. For learners equipped with task-specific parameter-efficient modules, this introduces a critical task-routing challenge beyond catastrophic forgetting. We study post-hoc task routing without retraining the learner or introducing a separately trained router. Such training-free inference-time calibration remains comparatively underexplored in parameter-efficient class-incremental learning. We identify three sources of routing error (feature-level, task-level, and class-level misalignment) and propose Feature Distribution Calibration (FDC). Its three components address these misalignments: Task Subspace Filtering (TSF) suppresses feature components outside each task's principal subspace, Residual Likelihood Calibration (RLC) evaluates the typicality of its subspace residual, and Prototype Affinity Calibration (PAC) measures compatibility with the task's class prototypes. Experiments demonstrate plug-and-play applicability to eight parameter-efficient class-incremental methods using a shared encoder. With one component configuration selected per method across all five
benchmarks, FDC improves final accuracy in all 40 method-
dataset pairs by 4.39 percentage points on average. Enabling all components improves 35 of the 40 pairs, with an average gain of 4.45 points. When applied to a simple baseline, FDC achieves strong overall performance.
Read the full abstract ▾
All authors Longhuan Xu, Zhipeng Zhou, Wei Ji, Chunyan Miao, Peilin Zhao, Lijun Zhang
Computer Vision
SubjectAnchor: Subject-Aware Memory-to-Video for Multi-Shot Storytelling
Xinyu Wang, Huafeng Shi, Zian Li et al. (+4 more)
We present SubjectAnchor, a Subject-Aware
Memory-to-
Video paradigm for multi-shot storytelling in which the current shot is generated by conditioning on explicit visual
memories extracted from previous shots. The objective is to preserve subject identity and scene consistency across cuts while retaining the controllability of shot-wise prompting. Built on Wan2.2-I2V-A14B, SubjectAnchor contains three key components: subject-related
memory construction, subject-aware temporal rotary position encoding, and
memory-aware
attention partition. For each target shot, the method constructs a compact
memory bank by tracing each required subject to its historical appearance and retrieving the most relevant precomputed keyframes. These
memory frames are encoded into the model input as explicit visual conditions, while different subjects are assigned to separated negative temporal slots to reduce identity interference. In addition,
memory-aware
attention partition regulates the interaction between
memory tokens and generated content within a shared backbone. This formulation preserves the appearance anchoring of explicit visual
memory while remaining compatible with script-driven shot-by-shot generation. Experiments show that SubjectAnchor improves cross-shot identity consistency over representative
memory-based and holistic baselines while maintaining competitive visual quality.
Read the full abstract ▾
All authors Xinyu Wang, Huafeng Shi, Zian Li, Yan Zhou, Xiaoqiang Liu, Yue Ma, Pengfei Wan
Computer Vision
Can Attack Difficulty Be Characterized Before Optimization? A Study of Pre-optimization Difficulty in Person-Vanishing Attacks
Jingyao Xu, Dongdong Wang and Siyang Lu
Adversarial attacks against object detectors are traditionally studied from an optimization perspective, where attack difficulty is regarded as an outcome observed only after
adversarial optimization. This raises a fundamental question: can the relative attack difficulty of different inputs be characterized before optimization begins? In this paper, we investigate this question for person-vanishing attacks by introducing the concept of pre-optimization attack difficulty, which captures intrinsic differences in optimization effort across input images. To estimate this latent difficulty before optimization, we propose Quad-CLEVER, an efficient geometry-based
estimator derived from a quadratic approximation of the local person-vanishing margin along the most attack-relevant direction. Extensive experiments across multiple attack
algorithms demonstrate that Quad-CLEVER consistently correlates with the observed optimization cost, providing empirical evidence that attack difficulty exhibits a predictable pre-optimization structure. Building upon this finding, we further propose a difficulty-aware attack framework that leverages the estimated difficulty to adaptively allocate optimization budgets for a base attack under a fixed computational budget. On BDD100K, the proposed framework improves the image-level attack success rate by up to 5.78$\%$ while reducing the average optimization cost by up to 11.42 iterations. On the more challenging EventPed
dataset, it saves 2.25 optimization iterations while maintaining comparable attack performance. These results demonstrate that attack difficulty can be meaningfully estimated before optimization and that exploiting such estimates enables more computationally efficient
adversarial attacks.
Read the full abstract ▾
High Energy Physics (Experiment)
Using Graph Neural Networks for the segmentation of overlapping objects in high granularity calorimeters
Matthieu Melennec and Frédéric Magniette
High-granularity calorimeters at the High-Luminosity LHC require novel
algorithms to resolve overlapping particle showers. We present an optimised Graph Neural Network (GNN)
segmentation block that predicts node-level energy fractions to disentangle overlapping two-
photon showers. By accelerating graph construction and convolution operations, our pipeline achieves competitive separation efficiency with significantly reduced algorithmic complexity.
Read the full abstract ▾
Machine Learning
Scalable GNN-based Knowledge Graph Representation Learning with Efficient Message Passing
Huu Tan Mai, Cuong Xuan Chu, Heiko Paulheim et al. (+1 more)
Graph neural networks (GNNs) excel at representation learning on Knowledge Graphs (KGs), achieving stateof-the-art performance on tasks like link prediction or entity classification. However, their high computational complexity, inherent to their user-defined message passing (MP)
algorithm, still prohibits their widespread adoption, especially for large KGs. Current efforts to mitigate the scalability bottlenecks of GNNs on KGs, such as subgraph sampling, are often task- and model-specific, and do not reliably guarantee lossless (if applicable) runtime/space reductions. To address this, we extend Relational Sparse
Matrix Multiplication (RSPMM), originally designed to losslessly lower the space complexity of composition-based MP with pointwise composition functions, to support more expressive functions (e.g., 2x2 block-diagonal
matrix multiplication, Givens rotation, circular correlation). Our method delivers significant task-independent reductions in runtime and space for current GNNs on KGs and facilitates efficient re-implementations of GNNs that maintain near state-of-the-art performance on challenging KG tasks, for a fraction of computational costs.
Read the full abstract ▾
All authors Huu Tan Mai, Cuong Xuan Chu, Heiko Paulheim, Daria Stepanova
Robotics
Robot-Assisted Deployment and Maintenance of Inflatable Modules for Lunar Habitation: A Field Demonstration
Kentaro Uno, Shamistan Karimov, Ashutosh Mishra et al. (+5 more)
Long-term human habitation and in-situ development on the Moon open a new era of space utilization. In this context,
robots are a key technology for facilitating the construction of future human outposts. Toward the deployment and establishment of human habitation modules on the lunar surface, we propose a combined system consisting of inflatable modules and a modular, reconfigurable robotic system. This paper presents a report demonstrating various
robot-assisted task executions using real hardware, namely the modular and reconfigurable
robot MoonBot and the inflatable module HIDAS, to enhance the reliability of their deployment and maintenance. The demonstrated tasks include robotic inspection during inflation, module position
alignment, final safety locking, and three-dimensional mapping for post-deployment maintenance. All demonstrations were conducted either in a laboratory environment or at a lunar analogue test site. Finally, lessons learned are discussed to provide essential insights for this robotic application to future lunar habitation.
Read the full abstract ▾
All authors Kentaro Uno, Shamistan Karimov, Ashutosh Mishra, Elian Neppel, Hazal Gozbasi, Shreya Santra, Shinichi Kimura, Kazuya Yoshida
Machine Learning
QAMM: Adjoint MeanFlow Matching for Few-Step Offline Reinforcement Learning
Yuehu Gong, Shutong Ding, Mokai Pan et al. (+4 more)
Flow policies can model rich action distributions, but their iterative sampling limits decision speed. Adjoint matching uses the critic's action gradient to improve a flow policy without backpropagating through its sampling trajectory, yet its supervision is defined for instantaneous velocities. We propose QAMM, a method that turns the critic-derived adjoint signal into supervision for MeanFlow's average velocity. The resulting policy learns finite-interval transport directly and generates actions with few network evaluations. We derive the adjoint MeanFlow target, specify its gradient boundaries, and train it with an offline actor-critic. On ten HumanoidMaze tasks, QAMM produces effective two-call policies and achieves competitive performance against strong flow-policy baselines. These results show that adjoint-based Q optimization can be combined with average-velocity learning to obtain expressive offline policies with few-step action generation.
Read the full abstract ▾
All authors Yuehu Gong, Shutong Ding, Mokai Pan, Yimiao Zhou, Jiashu Hou, Ye Shi, Yanwei Fu
Multiagent Systems
MASTraceBench: Diagnosing Collaboration Gains through Proposal Trajectories in LLM-Based Multi-Agent Systems
Yapeng Li, Songze Li, Shuang Yu et al. (+4 more)
LLM-based multi-
agent systems (MAS) have shown promise in complex problem solving. As MAS methods diversify, systematic evaluation becomes increasingly challenging. However, existing
benchmarks largely focus on final outcomes, leaving unclear how collaboration gains arise, are preserved, or are lost. To address this limitation, we introduce MASTraceBench, a
benchmark for diagnosing collaboration gains through proposal trajectories in MAS. Across six cooperative and competitive tasks, MASTraceBench tracks and grades proposal trajectories and provides a multi-layer metric suite covering Task Score, Collaboration Gain, proposal-trajectory indicators, and
Token Cost. Using MASTraceBench, we systematically compare representative MAS methods not only by final performance, but also by how
agent proposals evolve and are aggregated into the final answer. This analysis reveals a recurring pattern: final MAS answers rarely surpass the strongest initial proposal; interaction often lifts initially weaker proposals toward it, while strong initial proposals are seldom further improved and may regress. To reduce this risk, we propose CLEARS, which replaces whole-proposal exchange with claim-level evaluation across
agents to guide reliable synthesis. CLEARS more often preserves or improves upon the strongest initial proposal and achieves the highest Collaboration Gain on five of the six tasks.
Read the full abstract ▾
All authors Yapeng Li, Songze Li, Shuang Yu, Jing Yu, Zhixin Liu, Liqiang Wen, Tonghua Su
Dynamical Systems
Cooperation dynamics between persuasion-prone and persuasion-averse populations under random sequential guidance
Lichen Wang, Shijia Hua, Yuyuan Liu et al. (+2 more)
Social guidance, as a universal mechanism to promote collective cooperation, effectively maintains and enhances the level of population cooperation by correcting the behavior of defectors. However, existing guidance models have two key limitations: first, they assume that guidance actions are inevitably successful; second, they neglect information sharing among guides, leading to repeated guidance of the same successfully guided defector. Additionally, the psychological characteristics of individuals are often not fully considered in existing models. Here, we construct a
stochastic sequence guidance model by introducing random ordering of guides and termination conditions for guidance actions to optimize the efficiency of guidance. Besides, we incorporate individual psychological traits such as persuasion-prone (where the success rate of persuasion increases with attempts) and persuasion-averse (where the success rate of persuasion decreases with attempts) into the modeling framework. We find that the introduction of random sequence guidance can not only effectively promote cooperation but also mitigate the second-order free-rider problem. Importantly, cooperation thrives with stronger persuasion, lower costs, and larger groups.
Read the full abstract ▾
All authors Lichen Wang, Shijia Hua, Yuyuan Liu, Siyu Liu, Linjie Liu
Computer Vision
ConCAD: Constraint-Aware Image-to-CAD Generation with Dual-Granularity Rewards
Chenxi Zhai, Xi Cheng, Hang Cheng et al. (+5 more)
Image-to-CAD generation seeks executable parametric programs that recover both the geometry and design intent of a reference object. Existing systems are commonly evaluated by validity and shape overlap, although two solids with similar volume can encode different CAD relations. We introduce ConCAD, a constraint-aware image-to-CAD framework optimized via Group Relative Policy Optimization (GRPO) with rewards at two complementary granularities: a code-level constraint reward and an execution-level
geometric reward. This complementary design disambiguates structurally distinct yet volumetrically similar shapes while ensuring valid 3D geometry. To verify that these rewards recover geometry and design intent, we introduce a B-rep
geometric constraint satisfaction rate (G-CSR), which analytically extracts and evaluates
geometric constraints from boundary representations. Experiments on the DeepCAD and Zero2CAD demonstrate that ConCAD achieves the best IoU and Chamfer Distance over competitive baselines, while also outperforming them on G-CSR, validating its superior recovery of both
geometric fidelity and parametric design intent.
Read the full abstract ▾
All authors Chenxi Zhai, Xi Cheng, Hang Cheng, Zhicheng Guan, Mingyu Fan, Yanzhe Tang, Pingfa Feng, Long Zeng
Machine Learning
LLN: Learnable Lens Networks for Parameter-Efficient Long-Horizon Dynamical Prediction
Binbin Yong, Zhao Su, Lan Guo et al. (+3 more)
Explicit residual connections of the form (x+f(x)), often combined with normalization layers, have become a standard strategy for training very deep neural networks. However, residual addition primarily provides an algebraic shortcut for gradient propagation, while leaving the
evolution of feature geometry across layers largely unconstrained. We introduce Learnable Lens Networks (LLN), a physics-inspired architecture that replaces direct feature-space residual accumulation with learnable optical transport in an augmented position-angle phase space. Each layer alternates between free propagation, which provides an implicit transport path, and a learnable lens field that performs nonlinear trajectory transformation and focusing. Theoretically, we establish that LLN transport is globally invertible and volume-preserving for any differentiable lens field, with the implemented coordinate-wise Gaussian transport further satisfying symplecticity. Importantly, these structural constraints do not limit expressivity: with unrestricted
embeddings and readouts, LLN retain universal approximation of continuous end-to-end maps. Experiments across diverse dynamical systems demonstrate that LLN improves long-horizon prediction while using substantially fewer parameters than same-depth comparators. Further analysis reveals stable depth-wise gradient transport and interpretable learned dynamics under the coupled propagation and refraction design.
Read the full abstract ▾
All authors Binbin Yong, Zhao Su, Lan Guo, Haoran Li, Jun Shen, Qingguo Zhou
Artificial Intelligence
Xijing Wang, Yinsheng Yao, Jinru Ding et al. (+5 more)
Large
language model (LLM)
agents offer new opportunities for automated analysis in industry. However, rigorous evaluation of such
agents-for example, within power system scenarios-remains hindered: real operational data are confidential, and existing public resources fail to fully capture the chained dependencies and heterogeneous evidence. To address this gap, we propose PowerBench, comprising (1) a generation framework that derives interconnected heterogeneous operational data through a common dependency chain, and (2) a synthetic
dataset generated by this framework. The
dataset covers 761 devices across 100 device types, with 13.35 million hourly telemetry records spanning two years and 24,939 operational documents. Building on this
dataset, we construct 300 questions across three task families that evaluate frontier LLMs' ability to complete analysis tasks that require autonomous evidence
retrieval and
reasoning across interconnected and heterogeneous data under restricted tool calls and time budgets. Results demonstrate that the evaluated frontier LLMs remain challenged on these tasks: the best model reaches only 74.2% joint accuracy. Our trace analysis further reveals that model performance varies across evidence discovery, content
retrieval, tool use,
reasoning over evidence, and answer submission. These findings provide detailed insights for evaluating LLM
agents and guiding their reliable deployment in industry. The framework,
dataset, and
benchmark tasks are available at https://github.com/open-compass/PowerBench.
Read the full abstract ▾
All authors Xijing Wang, Yinsheng Yao, Jinru Ding, Yidong Jiang, Ziwen Xu, Yiwen Jiang, Jie Xu, Dawei Cheng
Machine Learning
M3OS: A Monte Carlo Graph Search-Orchestrated Multi-Agent LLM System for Evidence-Traced Molecular Optimization
Junjie Wang, Yaowei Jin, Ruohui Tang et al. (+7 more)
Small-molecule optimization integrates medicinal-chemistry
reasoning and computational evidence through iterative, multi-objective decisions. When large
language models (LLMs) reason over optimization histories stored primarily in conversational context, they must recover candidate identities, prior evaluations, and task constraints to guide subsequent decisions. We present M3OS, a multi-
agent LLM system that decouples molecular-design
reasoning from optimization-state management through Monte Carlo graph search. A persistent graph links evaluated candidates, parent-child transformations and evaluation evidence, while rewards and visit statistics guide LLM-assisted parent selection. Two branches combine tool-driven candidate generation with knowledge- and case-guided medicinal-chemistry editing. An execution harness controls graph updates through structured output extraction, molecular validation and task-bound evaluation.
Agents receive role-specific contexts, while the graph preserves optimization trajectories beyond their active contexts. Across three molecular optimization
benchmarks, M3OS achieves higher success rates than baselines, supporting the integration of persistent search state, specialized
agents and controlled execution for multi-constraint optimization.
Read the full abstract ▾
All authors Junjie Wang, Yaowei Jin, Ruohui Tang, Guonan Cui, Haojie Wang, Penglei Wang, Dingyan Wang, Duo An, Shuangjia Zheng, Qian Shi
Computer Vision
HPMD: A Historical Persian Manuscript Dataset for Word Spotting with Line-Level Annotation
Saeid Firouzi Daghigh and Majid Iranpour Mobarakeh
Large collections of historical Persian manuscripts have been digitized, but searching them is still slow and mostly manual. Historians usually want to find where a specific name, date, event, or topic appears, which is a word spotting problem. Progress on this task is limited by two things. First, there is almost no public
dataset of historical Persian handwriting; the only notable resource, OpenITI MAKHZAN, contains a relatively small Persian portion. Second, word spotting models usually need word-level bounding boxes, which are very expensive to annotate. In this paper we introduce a new
dataset of 223 pages, 3,678 lines, 37,631 words, and 130,630 characters, collected from diverse historical Persian books of poetry and prose and annotated at the region, line, and text level. We also propose a baseline that is trained only with line-level annotations but returns word-level locations. A fine-tuned line detector finds text lines, and a fine-tuned CRNN recognizer trained with CTC produces a frame-by-character posterior
matrix for each line. Instead of decoding the most probable character at each frame, the query is scored directly against this
matrix, so visually similar characters in Persian such as be and pe no longer cause hard failures. The frame
alignment also gives the horizontal position of the word inside the line. On the test set, the fine-tuned line detector reaches an F1 of 0.892, and posterior-based search raises the word spotting F1 from 0.487 to 0.558 compared with exact matching on the decoded text, with the decision threshold selected on a held-out validation set. A PHOC attribute-
embedding baseline that additionally receives oracle word boundaries at test time reaches an F1 of 0.449, below the proposed method. We also report a distributional analysis of the
dataset, a taxonomy of
retrieval errors, and a per-conditionbreakdown of performance.
Read the full abstract ▾
Machine Learning
When Less Data Favors Smaller Teachers: Rethinking Teacher Capacity and Data Selection for Knowledge Distillation
Minjae Park, Taesun Yeom and Jaeho Lee
Data
pruning reduces the training cost of knowledge
distillation (KD). However, the preferred teacher capacity changes with the data budget: smaller teachers can outperform larger ones when limited training data are available. Understanding what drives this shift is important not only for teacher choice but also for identifying which samples are useful for
distillation. We analyze teacher supervision by decomposing it into relational ordering—the ranking of classes—and score geometry—the magnitudes and margins of class probabilities—and show that the small-teacher advantage in the low-data regime arises not only from score geometry but also from relational ordering. Beyond understanding teacher capacity, our analysis reveals two properties of effective subsets: samples should match the difficulty appropriate for the available budget, and their relational signals should be diverse rather than redundant. Based on these findings, we propose DVA (Difficulty- and Volume-Aware data selection for KD), a training-dynamics-free method, which uses a small teacher as a proxy for budget-aware difficulty filtering and class-conditional relational volume maximization. Despite requiring no training dynamics statistics, our method remains competitive with training-dynamics-based methods while consistently outperforming training-dynamics-free baselines.
Read the full abstract ▾
Machine Learning
FlexLoop: Depth-Elastic Looped Policies for Adaptive Test-Time Computation in Deep RL
Xun Wang, Ruishuo Chen, Yu Chen et al. (+2 more)
Looped architectures scale computation by reusing the same parameters across recurrent steps, and recent work shows that they substantially improve deep reinforcement learning policies on long-horizon tasks. Since recurrent depth directly controls computation, one may expect looped policies to naturally support elastic inference across recurrent depths. Surprisingly, we find that pretrained looped policies exhibit severe recurrent-depth specialization: reliable decisions are concentrated near the full trained depth, tying deployment computation to this depth even when less computation may suffice. Achieving depth elasticity, i.e., reliable decisions across recurrent depths with adaptive computation at deployment, therefore remains a key challenge. To address this, we propose FlexLoop, a novel post-training framework that converts pretrained fixed-depth looped policies into depth-elastic policies. FlexLoop keeps training on the original RL objective to preserve full-depth capability while performing adjacent-depth policy
distillation to progressively transfer decision quality from deeper to shallower recurrent steps. The resulting policy supports reliable inference across recurrent depths and enables state-wise adaptive inference through recurrent-depth consistency. Experiments on $30$ online and offline long-horizon goal-conditioned environments show that FlexLoop preserves full-depth performance while making shallower depths effective. Keeping competitive performance, FlexLoop reduces average recurrent depth by up to $\bf{43\%}$ and achieves up to $\bf{1.34\times}$ wall-clock speedup in a stress test.
Read the full abstract ▾
All authors Xun Wang, Ruishuo Chen, Yu Chen, Zhuoran Li, Longbo Huang
Computer Vision
PACER: Progressive Availability-Conditioned Evidence Routing for Radiology Report Generation under Incomplete Clinical Context
Yulong Chen, Yadong Liu, Haoyu Cao et al. (+3 more)
Radiology report generation (RRG) increasingly incorporates heterogeneous clinical evidence, such as multi-view radiographs and previous reports, whose availability varies across examinations. However, accommodating different input combinations does not ensure effective evidence use: generated reports may still omit or inaccurately describe clinically relevant findings. To address this problem, we propose PACER, a Progressive Availability-Conditioned Evidence Routing framework for structured incomplete-context RRG that follows a Refine-Calibrate-Commit pipeline. It first refines observed visual representations through endpoint-preserving patchwise routing across frozen encoder depths, incorporating complementary cues while retaining the pretrained terminal representation. It then calibrates the
language-model prefix according to the observed evidence and availability state, adapting the shared generator's conditioning as the available source set changes. Finally, it generates polarity-structured clinical commitments before the report in the same autoregressive trajectory, providing structured clinical context for subsequent generation. Experiments demonstrate state-of-the-art clinical efficacy across all four MIMIC-RG4 settings and strong MIMIC-CXR performance, while maintaining competitive
language-generation quality.
Read the full abstract ▾
All authors Yulong Chen, Yadong Liu, Haoyu Cao, Sen Xu, Yueying Wang, Jie Wen
Robotics
Model-Informed Safe Reinforcement Learning for Bipedal Locomotion via Step-to-Step Prediction
Victor Paredes and Ayonga Hereid
Humanoid robots promise versatile mobility in cluttered, human-centric environments, but real deployment demands principled safety. Classical model-based gait generators yield interpretable motions but often lack the robustness and adaptability of modern reinforcement learning (RL) based approaches. We propose a model-informed reinforcement learning framework anchored to the analytical Angular Momentum Linear Inverted Pendulum (ALIP) template. We provide a step-to-step safety certificate for ALIP stepping via a discrete exponential control barrier function (DECBF) and use it as (i) a training-time shaping signal and (ii) a runtime action filter that minimally adjusts swing-foot placement to satisfy template-level constraints. Full-order safety is evaluated empirically on the Digit
humanoid in MuJoCo with a whole-body controller stack. Compared to an unconstrained baseline, our approach reduces safety-violation events in the reported external-disturbance trial, while larger lateral-velocity transients reveal a safety-tracking tradeoff.
Read the full abstract ▾
Robotics
Trajectory-Safe Orienteering for Human-Robot Shared Environments
Songqun Gao, Elena Basei, Marco Roveri et al. (+2 more)
Orienteering problem (OP) has wide real-world applications and also great potential in human-
robot collaboration. However, existing approaches struggle to simultaneously ensure safe and feasible trajectories while achieving high-quality task execution in shared workspaces. To this end, this work studies the OP with time windows and variable profits (OPTWVP). A two-stage DEcoupled discrete-Continuous Optimization with Service-time-guided Trajectory (DeCoST) approach is proposed to effectively solve OPTWVP in shared spaces. Meanwhile, the safety-aware time windows of nodes and the discretized workspace are introduced to ensure collision-free trajectories between the end effector and the human. Preliminary results validate the effectiveness of DeCoST in generating collision-free trajectory plans while preserving the quality of orienteering tasks.
Read the full abstract ▾
All authors Songqun Gao, Elena Basei, Marco Roveri, Luigi Palopoli, Daniele Fontanelli
Robotics
ARS: Agentic Reward System for Robot Learning
Sheng Hu, Weiyi Lu, Lingbing Zeng et al. (+5 more)
Progress reward modeling is the problem of estimating how a
robot's behavior changes task progress over time. Reliable estimation requires distinguishing meaningful state changes from failed attempts and task-irrelevant actions. We introduce the Agentic Reward System (ARS), an inference framework for progress reward modeling with general-purpose
vision-
language models (VLMs), without additional reward-model training. Given an offline trajectory and a task instruction, ARS uses adaptive visual inspection for both event proposal and verification. A subagent proposes a task-relevant event timeline, which a primary
agent verifies and revises before estimating per-frame progress. ARS can incorporate optional terminal outcome labels and visual references to inform its judgments. It can also audit progress estimates from external reward models. We evaluate ARS with a 27B VLM on a controlled semantic-mismatch
benchmark and downstream policy learning in simulation and on a real
robot. The
benchmark reveals that several evaluated reward baselines assign spurious progress to wrong-object manipulation even in simple pick-and-place scenes. ARS better suppresses these errors and outperforms these baselines in simulation policy learning. We further demonstrate that ARS supports long-horizon policy learning from mixed-quality offline experience on real-
robot multi-screw fastening in a full-scale laboratory replica of an industrial washing-machine assembly line. These results suggest that structured inference and verification can improve the usefulness of general-purpose VLMs for
robot reward modeling. Code is at https://github.com/midea-ai/ars
Read the full abstract ▾
All authors Sheng Hu, Weiyi Lu, Lingbing Zeng, Gan Weng, Weiwei Zhang, Kai Xie, Xiaofeng Mou, Yi Xu
Networking
Deconstructing BLE Multi-hop: a Model-based Approach to Quantifying the Challenges
Bozheng Pang, José Alamos, Thomas C. Schmidt et al. (+1 more)
Bluetooth Low Energy (BLE) was originally designed for point-to-point communication, but BLE multi-hop networks have attracted academic and industrial interest. Multi-hop communication, however, introduces desynchronized nodes to the network due to the difference in individual clocks. In this paper, we study the impact of clock drift on a BLE multi-hop network. The aim is to find out if a BLE multi-hop network can be properly set up, why, and how. For this goal, we develop a mathematical model to quantify the collision probability among BLE connections managed by a single device. We provide a simplified version of the model for constrained deployment. The impact of clock drift and our mathematical model are validated through practical experiments. Afterward, we find that a BLE multi-hop network cannot eliminate the impact of clock drift in most cases. Moreover, from a long-term point of view, the collision between BLE connections occurs with a fixed frequency. We further analyze the limitation of using BLE to form multi-hop networks, and propose possible solutions, such as
topology limitation, changes to BLE stack or hardware. This paper is a clear and quantitative problem statement on the limitations of using BLE in multi-hop networks.
Read the full abstract ▾
All authors Bozheng Pang, José Alamos, Thomas C. Schmidt, Matthias Wählisch
Statistical Methodology
Risk-Calibrated Balancing for High-Dimensional Causal Extrapolation
Fenglin Yang, Haoran Lei, Yan Chen et al. (+1 more)
In observational causal inference,
covariate balancing is widely used to reduce source-target
covariate shift, but under weak overlap in high dimensions, stronger balance can induce concentrated weights and increase variance. Balance measures how well the target
covariate distribution is represented, but does not by itself determine how reliably the counterfactual mean can be estimated. We develop risk-calibrated balancing for the average treatment effect on the treated, which applies ridge augmentation to any normalised base weights and selects its penalty using conditional prediction risk of the counterfactual mean. Under a random-effects predictive model, we derive an exact finite-sample decomposition of this risk into residual
covariate imbalance and weight-induced variance. For design-independent base weights under proportional asymptotics, we characterise how limiting risk depends on source and target covariance geometry, population mean shift, and weight concentration. For
covariate-adaptive base weights, we develop a uniformly consistent target-aware risk
estimator whose minimiser attains vanishing scaled oracle excess risk. Simulations show that the high-dimensional risk predictions remain informative for adaptive balancing and that target-aware tuning generally reduces excess target risk. Empirical analyses of job-training and single-
cell perturbation data show that risk-calibrated balancing generally improves on the corresponding base
estimators, with larger gains under weaker overlap.
Read the full abstract ▾
All authors Fenglin Yang, Haoran Lei, Yan Chen, Jin-Hong Du
Computation and Language
CARDAMOM: A Micro-Dialectal Arabic Speech Dataset for ASR
Bashar Talafha, Samar M. Magdy, Aisha Alansari et al. (+36 more)
We present Cardamom, a micro-dialectal Arabic
speech dataset designed to support fine-grained evaluation and adaptation of automatic
speech recognition (ASR) systems. Community-curated by native speakers familiar with the represented varieties, Cardamom contains approximately 40 hours of transcribed YouTube
speech spanning 21 micro-dialects across Egypt, Jordan, Lebanon, Mauritania, Palestine, and Saudi Arabia. Each segment is annotated with one or more operational micro-dialect labels, code-switching information, and utterance-level perceived gender, enabling analysis of sub-country variation that is obscured by conventional country-level labels. We describe the collection and annotation process, motivate the micro-dialect inventory linguistically, and
benchmark four
multilingual ASR systems in zero-shot and adapted settings. The strongest zero-shot system obtains 43.47% aggregate WER, with particularly high error rates on Mauritanian and Lebanese varieties; adaptation on Cardamom reduces its WER to 35.21%. Audio-based identification experiments further highlight the difficulty of fine-grained micro-dialect recognition: across three training seeds, a dedicated classifier obtains 46.85% accuracy and 31.95% F1. Cardamom provides a resource for studying localized dialectal variation and developing Arabic
speech systems with broader regional coverage.
Read the full abstract ▾
All authors Bashar Talafha, Samar M. Magdy, Aisha Alansari, Alaa Alkhawaldeh, Abdurrahman Juma, Sharaf Makahleh, Nour Gamal, Omar Attia, Hanaa Kurdi, Najwa Rizk, Maysa Anaya, Hessah Altimyat, Layal Alhazmi, Shumukh Alotaibi, Hajar Alhadaris, Rayan Alomari, Rahaf Almalaq, Malak Alkhorasani, Sara alghamdi, Rahaf Alshamrani, Nsrin Ashraf, Ibrahim Jaradat, Nada Qardahji, Yasmin Zaraket, Elmoukhtar Brahim, Sidi Ebeidy, Oumoulmouminin Mahmoud, Yahjeb Bouha Khatraty, Meya Haroune, Mohammad Ghaddar, Mohamad Eldirany, Rashed Alamoush, Tala Chhaytle, Nuha Albadi, Yahya El Hadj, Hamzah Luqman, Fadi A. Zaraket, Mustafa Jarrar, Muhammad Abdul-Mageed
Computer Vision
When Does an Image Determine the Answer? Benchmarking Visual Answerability across Charts and Scenes
Sungguk Cha, Mintae Kim, Youngsub Han et al. (+2 more)
Reliable visual question answering requires correct answers when evidence is sufficient and abstention when it is not. We introduce a
benchmark that connects complete-question evaluation with explicit evidence for its labels across PlotQA charts, CLEVR rendered scenes, and GQA photographs. Each question groups original and edited images, presented independently; success requires every supported answer and every required abstention to be correct. For chart missing-information labels, executable witnesses establish that admissible complete charts give different answers but identical pixels after masking. Scene labels follow source programs and edits, with a residual-cue analysis for photographs. Across 72,000 responses from six model configurations, the highest observed complete task success rates are 57.0%, 43.5%, and 33.7%, respectively. On charts, the strongest configuration achieves 96.2% per-view decision accuracy, yet 265 of its 835 groups with every decision correct still contain incorrect answers. Evaluating supported answers and necessary abstentions together exposes failures that answerability decisions alone conceal.
Read the full abstract ▾
All authors Sungguk Cha, Mintae Kim, Youngsub Han, Byoung-Ki Jeon, Sangyeob Lee
Computer Vision
SentZero: An Enhanced Sentence-Centric Vision-Language Pretraining for Multi-Task Zero-Shot Chest X-Ray Analysis
Hangyul Yoon, Hyungyung Lee, Edward Choi et al. (+1 more)
Vision-
language (VL) pretraining using paired chest X-ray (CXR) images and radiology reports has shown strong potential for medical image understanding. However, existing methods often remain dependent on task-specific finetuning because radiology reports are lengthy, clinically dense, and difficult to align with simple zero-shot
prompts. Recent sentence-level approaches partially address this limitation using clinical phrases extracted by large
language models (LLMs), but they largely overlook the intrinsic characteristics of radiology discourse. In particular, limited positive-pair diversity constrains further gains, while clinically equivalent sentences frequently recur across patients, creating false negatives in contrastive learning. To address these issues, we propose SentZero, an enhanced sentence-centric VL pretraining framework for zero-shot, multi-task CXR analysis. SentZero introduces LLM-based abstract-level sentence structuring and mapping to expand positive-pair diversity, together with an additional loss term to mitigate false negatives. We further introduce sentence-conditioned residual modulation of visual
embeddings, enabling visual features to adapt to the semantic characteristics of each input sentence. Across diverse downstream tasks and
datasets, SentZero improves zero-shot generalization and outperforms prior multi-task zero-shot methods.
Read the full abstract ▾
All authors Hangyul Yoon, Hyungyung Lee, Edward Choi, Eunho Yang
Machine Learning
Learn Here, Move Less Elsewhere: Input-Conditioned Plasticity from Retained-Domain Activation Atlases
Jiangtao Lin, Bangyang Wei, Yihang Ding et al. (+2 more)
Task-specific fine-tuning can rewrite a
language model's answers beyond the training task, complicating updates that must preserve existing behavior. We introduce ATLAS, which turns retained-domain representations into an input-dependent rule for task adaptation. An activation atlas supplies local reference centers and directional filters to a shared low-rank residual. Target supervision learns the residual, while retained geometry shapes its action throughout training and inference. On Qwen3-8B, ATLAS achieves lower mean retained-output Kullback-Leibler (KL) divergence than all seven published baselines at shared coding-performance requirements, with consistent advantages across multiple training seeds. Structural comparisons identify the contributions of retained reference states and directional conditioning, and answer-level analyses show fewer rewritten mathematical answers and more stable commonsense choices. Experiments spanning five backbones and two retained domains further demonstrate coding gains with reduced retained-output movement. With compact storage and modest decoding overhead, ATLAS provides a practical mechanism for acquiring specialized skills while maintaining continuity in existing responses.
Read the full abstract ▾
All authors Jiangtao Lin, Bangyang Wei, Yihang Ding, Siyi Liu, Yuhan Dong
Strongly Correlated Electrons
Electronic and topological properties of Ce-based honeycomb ferromagnet Ce$_2$Zn$_6$Ge$_3$
Yanen Huang, Zihan Yang, Jiawen Zhang et al. (+7 more)
Ce$_2$Zn$_6$Ge$_3$ is a rare example of the Ce-based honeycomb ferromagnet. Here, we report its
Fermi surface and topological properties by
quantum oscillations via the magnetoresistance and tunnel diode oscillator (TDO) based measurements, in combination with the density functional theory (DFT) calculations. Four fundamental frequencies are observed in the
quantum oscillations, and their angle dependence is more compatible with the DFT calculations assuming that the 4$f$-electrons are localized, suggesting a localized nature of ferromagnetism in Ce$_2$Zn$_6$Ge$_3$. Furthermore, the observations of negative longitudinal magnetoresistance and non-zero Berry phase, as well as the existence of two pairs of Weyl points near the
Fermi level as revealed from the calculated electronic structures, provide strong evidence for nontrivial
topology in Ce$_2$Zn$_6$Ge$_3$. These findings suggest that Ce$_2$Zn$_6$Ge$_3$ could provide a unique platform to study magnetism,
topology,
quantum criticality and their interplay.
Read the full abstract ▾
All authors Yanen Huang, Zihan Yang, Jiawen Zhang, Yuwei Zhou, Lubin Wang, Gang Li, Michael Smidman, Chao Cao, Yu Liu, Huiqiu Yuan