Computational Engineering
FinRegQA-EU: Corruption-Based Preference Data for Grounded EU Financial Regulatory Question Answering
Aulia Kharis Rakhmasari, Fan Yu, Alexander Hoyle et al. (+1 more)
Large
Language Models (LLMs) struggle with region-specific factual knowledge, particularly in financial regulation. While
benchmarks such as CFinBench, provide broad coverage of financial knowledge in other regions, no comparable resource exists for European financial regulation. We close this gap by proposing an end-to-end pipeline for evaluating and improving LLMs on European financial regulatory question answering. Our
dataset is grounded in the official Q&A corpora of the European Banking Authority (EBA) and the European Securities and
Markets Authority (ESMA). We evaluate candidate answers with a pointwise LLM-as-a-Judge protocol using three judges from distinct model families, retain only unanimously judged pairs, and sharpen the rejected side through a taxonomy of regulatory failure modes : law swaps, article swaps, hallucinated citations, and hallucinated text. By fine-tuning on the resulting preference pairs exposes a divergence at the core of our findings: supervised fine-tuning attains the highest judge score of any method yet got the lowest rule-based Citation F1. SFT is producing longer answers with three times as many citations, most of them unsupported. DPO and GRPO offer the better trade-off with more concise answers and the highest citation F1 among fine-tuned models. Standard LLM-as-a-Judge evaluation rewards citation density as evidence of grounding and cannot detect when those citations are fabricated. Thus, we detect a blind spot that matters wherever answers must be verifiable. We release the
benchmark and evaluation stack at https://github.com/auliakharis/FinRegQA-EU.
Read the full abstract ▾
All authors Aulia Kharis Rakhmasari, Fan Yu, Alexander Hoyle, Elliot Ash
Artificial Intelligence
When Upstream Messages Override Correct Answers: A Controlled Study of Multi-Agent LLM Collaboration
Yaxin Gong, Gangyi Zhang, Chongming Gao et al. (+7 more)
Multi-
agent LLM systems rely on message passing among specialized
agents to accomplish complex tasks. However, an upstream
agent may provide useful information or an incorrect answer that causes a downstream
agent to override a correct answer supported by its own evidence. Prior work has not clearly separated the benefits of communication from the damage caused by incorrect messages. We study this problem with controlled experiments across five
benchmarks and five receivers, keeping the downstream task and evidence fixed while comparing answers under three conditions: no message, the upstream
agent's original message, or a message with the opposite conclusion. Our experiments reveal three key findings. First, messages often help when the downstream
agent would otherwise answer incorrectly. Second, messages can also hurt: when the downstream
agent would answer correctly without a message, an incorrect upstream message changes the answer in up to 32% of cases. Third, in 94% of audited harmful cases, the downstream
agent copies the upstream's specific wrong answer–a pattern we term answer substitution. Removing unreliable messages recovers part of the lost accuracy, suggesting that communication should be selective based on upstream reliability and the evidence already available to the downstream
agent.
Read the full abstract ▾
All authors Yaxin Gong, Gangyi Zhang, Chongming Gao, Leyang Shen, Chenxiao Fan, Jiakai Wang, Dong Wang, Yang Liu, Wenjie Wang, Xiangnan He
Signal Processing
Multivariate signal restoration via Multifold Graph Learning
Haruki Yokota and Yuichi Tanaka
We propose a method for restoring noisy and incomplete multivariate signals by learning multifold graphs. Spatial relationships among channels can be utilized to recover missing values and suppress noise. However, these relationships can vary across frequency components and observation windows while retaining common connectivity patterns. We refer to the graphs associated with individual components and windows as multifold graphs. We model multifold graphs as nonnegative combinations of shared prototype graphs. We formulate signal restoration and multifold graph learning as a joint optimization problem and solve it by alternating optimization. We unroll the resulting
algorithm into a neural network with trainable regularization weights, step sizes, and filter coefficients. The network is trained in a self-supervised manner. Synthetic experiments show improved graph estimation accuracy over the compared methods. On real-world weather data, the proposed network achieves competitive completion performance with substantially fewer trainable parameters than a self-
attention-based model.
Read the full abstract ▾
General Relativity and Quantum Cosmology
Holographic dark energy in Einstein-Cartan spin cosmology
Yongjun Yun and Jungjai Lee
We show that, in Einstein-Cartan theory, the torsion scalar modifies the
dust-like equation of state of non-interacting
holographic dark energy with the Hubble radius as the infrared cutoff, enabling late-time
cosmic acceleration within the low-
redshift domain of validity, which is not realized in the corresponding model in general relativity. Using the same
holographic dark energy background, we further derive the torsion-induced modification of the
cosmic distance duality relation, $d_L=d_A(1+z)^2(1+\eta)$. In the late-time universe, the magnitude of the deviation parameter, $|\eta|$, is small but non-vanishing, reflecting the cumulative effect of torsion along the light-propagation path.
Read the full abstract ▾
Computer Vision
Socialality Anchors: Towards Group-bounded Trajectory Prediction
Ziqian Zou, Conghao Wong, Qinmu Peng et al. (+1 more)
Trajectory prediction is a key component for understanding human behavior patterns in dynamic scenes. Researchers have devoted substantial efforts to modeling social interactions, especially group-wise interactions, since group membership often reflects shared intention, coordinated motion, and stable mutual adaptation, thus providing a persistent and semantically meaningful social prior for
forecasting. However, existing group modeling methods may rely on a fixed threshold and infer groups mainly from
agents' relative positions within the observation window, overlooking the fact that grouping rules should be
agent-specific, temporally coherent, and context-adaptive across diverse personalities, culturalities, and evolving interaction contexts. Inspired by human social perception that alternates between interpersonal distance in boundary-sensitive situations and relative speed consistency in dynamic interactions, we propose Socialality, a human-inspired trajectory prediction framework with interpretable Socialality anchors and an extended grouping window for stable, context-aware grouping inference. Concretely, Socialality introduces a duo-scalar-controlled grouping kernel Socialality that jointly leverages historical observations and short-term future trajectory previews to learn
agent-specific grouping rules, and employs a group-wise perception mechanism to model in-group and out-of-group interactions in an intuitive and explainable manner. Furthermore, we conduct extensive experiments on standard
benchmarks to demonstrate the performance gains of Socialality, and provide qualitative analyses and statistical studies of anchor distributions to verify the interpretability and stability of the proposed Socialality anchors.
Read the full abstract ▾
All authors Ziqian Zou, Conghao Wong, Qinmu Peng, Xinge You
Computer Vision
RoXDrive: Closed-Loop Reinforcement Learning for End-to-End Autonomous Driving via Action-Faithful Rollouts
Hongbin Lin, Chaoda Zheng, Yiming Yang et al. (+11 more)
End-to-end autonomous driving policies are commonly trained via imitation learning on logged demonstrations without observing the consequences of their own actions, leading to causal confusion in closed-loop real-world deployment. To address this issue, reinforcement learning (RL) post-training offers a promising alternative by leveraging world models as interactive training environments to enable future scene generation for policy improvement. Nevertheless, existing approaches either rely on reconstruction-based simulators, offering limited counterfactual interaction, or adopt synthetic simulators to enable long-horizon closed-loop interaction at the cost of a substantial sim-to-real gap. Recently,
video world models have exhibited the ability to generate realistic multi-step future rollouts but may not faithfully reflect action conditions, resulting in action-
vision mismatch. In this paper, we introduce RoXDrive, a plug-and-play closed-loop RL framework that enables reliable policy optimization by identifying action-faithful world-model rollouts, consisting of two stages: 1) Model pre-training: In addition to imitation-based policy pre-training, we devise an Action-
Vision Faithfulness Evaluator for inverse dynamics estimation with our geometry-aware auxiliary trajectory supervision, enabling long-horizon assessment of whether visual dynamics faithfully reflect the conditioning ego actions. 2) Action-faithful RL post-training:
Agents iteratively interact with world models to form long-horizon scene rollouts, retaining only action-faithful ones for dense safety-aware scoring and scene-level closed-loop RL post-training. Extensive experiments on nuScenes and an in-house
dataset with over 130K training scenarios demonstrate consistent gains across planners, reducing safety violations by 27.6% with DiffusionDrive on nuScenes and 33.7% with Qwen3-VL on the internal data.
Read the full abstract ▾
All authors Hongbin Lin, Chaoda Zheng, Yiming Yang, Xiangyu Li, Shijia Chen, Jinhao Deng, Kangjie Chen, Dongbin Zhang, Jie Feng, Yu Zhang, Xianming Liu, Shuguang Cui, Boyang Wang, Zhen Li
Computation and Language
Rethinking Multimodal Fake News Detection in the Generative AI Era
Wenbin Shen, Guoxuan Qin, Guangxu Yao et al. (+3 more)
Generative content is increasingly entering the production and dissemination of news, transforming fake news from manually fabricated or simply manipulated material into complex forms in which native and generated content jointly participate. Existing
multimodal fake news detection research primarily focuses on veracity assessment and rarely characterizes how generativity differences affect the reliability of evidence. In contrast, AIGC detection primarily determines whether content is generated or modified by generative models, but it does not by itself establish whether the underlying news event is true. To bridge the separation between these tasks in data and evaluation, we construct Weibo26, a
multimodal fake news detection
dataset for generative-content scenarios. On this basis, we propose the Generativity-Aware Hierarchical
Reasoning (GAHR) framework, which combines global judgment with local correction so that generativity information participates in news-veracity
reasoning. Experiments on multiple existing fake news detection
benchmarks and Weibo26 show that GAHR achieves competitive veracity-detection performance while effectively identifying generative content.
Read the full abstract ▾
All authors Wenbin Shen, Guoxuan Qin, Guangxu Yao, Baodong Wang, Yuanbo Rui, Zhichao Lian
Cryptography and Security
Does the Unsafe Gradient Survive a Conversation? On the Fragility of Gradient-Based Jailbreak Detection in Multi-Turn Dialogue
Omar Sheta, Rinku Deuja, Hadi Masoudi et al. (+1 more)
Safety-aligned
language models are commonly deployed as multi-turn assistants, which lets adversaries spread unsafe intent across several user turns instead of a single
prompt. Gradient-based jailbreak detectors such as GradSafe were developed for single
prompts: they score an input by the
alignment between its induced gradient and a fixed unsafe reference direction, and their effectiveness in multi-turn dialogue remains unclear. We conduct a controlled evaluation of gradient-based jailbreak detection in multi-turn settings. We extend GradSafe with a Context Window Scanner that applies the detector to fixed-size windows of user turns and uses the maximum window score as the conversation-level score. We evaluate different window sizes, attack families, benign conversation distributions, and target models. The results differ sharply between synthetic and realistic benign settings. Against synthetic benign conversations, the detector achieves an ROC-AUC of 0.98 on human-authored multi-turn jailbreaks. On WildChat benign conversations, ROC-AUC drops to 0.76, and a threshold calibrated on synthetic data flags more than 90% of benign conversations as unsafe. Under realistic benign distributions, single-turn windows give the highest separability, whereas longer windows and accumulated contexts reduce performance. The detector is also sensitive to the attack-generation method and target model: successful Crescendo attacks receive scores comparable to or lower than benign conversations, and Qwen2.5-7B-Instruct yields near-random separability with a different optimal window size. These findings show that gradient-based signals can support multi-turn jailbreak detection, but reliable deployment requires calibration on realistic benign conversations, short-window scoring, length-aware thresholds, and evaluation across attack types and model architectures.
Read the full abstract ▾
All authors Omar Sheta, Rinku Deuja, Hadi Masoudi, Minghong Fang
Machine Learning
An Effective, Reliable, and Robust Framework for Human Activity Recognition Using Wearable Sensors
Nafees Ahmad, Ho-fung Leung, Muhammad Adil Abid et al. (+1 more)
Human Activity Recognition (HAR) through wearable sensors greatly improves the quality of human life through its multiple applications. For HAR, multi-sensor channel information is vital for optimal performance. Current work states that applying an
attention neural network to prioritize discriminatory sensor channels helps the model classify activity more precisely. However, obtaining discriminatory information from multisensory channels is not always trivial, such as when collecting data from older hospitalized patients. In this context, existing HAR methods struggle to classify activities, particularly activities with similar natures. Moreover, HAR models predominantly suffer from overfitting due to the small size of available
datasets, which leads to poor performance. Data augmentation (DA) is a viable solution to this problem. However, available DA methods have various drawbacks, including the possibility of being domain-dependent, resulting in distorted models for test sequences. To address these HAR problems, we propose a novel framework, ALAE-TAE-CutMix+, which focuses on two aspects. First, it enhances the latent information across each sensor channel and learns to exploit the relation among multiple latent features and the ongoing activity. Consequently, the discriminatory feature representations of each activity is enriched. Second, a new augmentation strategy is introduced to address the shortcomings of existing multi-sensor channel data augmentation. We then extend the framework to create a further enhanced version, namely ALAE-CIE-TAE-CutMix+, which learns to capture the interactions between the features of each pair of sensor channels. We find that although the first framework performs slightly better than the latter, the latter is nonetheless more reliable and robust. Both frameworks significantly outperform SOTA approaches on the four HAR
datasets from diverse domains.
Read the full abstract ▾
All authors Nafees Ahmad, Ho-fung Leung, Muhammad Adil Abid, Sadia Shakil
Artificial Intelligence
Automated Screw Planning for Reduced Pelvic Fractures Based on Statistical Shape Models and Deep Learning
Yang Gao, Sutuke Yibulayimu, Yanzhen Liu et al. (+2 more)
Percutaneous iliosacral screw fixation is an important minimally invasive treatment for unstable pelvic fractures. Because the sacroiliac region has complex anatomy and narrow screw corridors, the accuracy and safety of screw placement directly affect
surgical outcomes. Accurate and reliable preoperative screw planning is therefore essential to improve
surgical success and reduce intraoperative risks. Conventional preoperative planning typically requires surgeons to determine screw trajectories through manual measurements, a labor-intensive process that depends on subjective clinical experience. To address these challenges, we propose a fully automated pipeline for preoperative iliosacral screw planning in patients with pelvic fractures. Using patient-specific three-dimensional anatomy, the pipeline automatically identifies safe screw corridors and generates individualized insertion trajectories to support clinical preoperative planning. We evaluated the proposed pipeline on 200 clinical cases of pelvic fractures. Compared with conventional manual measurements, the safety margin of the safe insertion corridors increased by 2% across the four screw types, the mean planning time decreased by more than 90%, and the clinical acceptance rate reached 95%.
Read the full abstract ▾
All authors Yang Gao, Sutuke Yibulayimu, Yanzhen Liu, Zian Zhao, Yudi Sang
Disordered Systems and Neural Networks
Locking transition in coupled disordered systems
Guy Bunin
When a system of many interacting constituents is extended across space, every region carries the same disordered landscape, and it is unclear whether distant regions settle into the same state. We study copies of the Random Energy Model (REM), sharing one disorder realization, coupled along a chain. A first-order transition separates a phase with short-range correlations, from a locked phase in which the entire chain occupies the lowest-energy state with probability one, even at positive temperature. No intermediate ordering lengths occur. In the Generalized REM the chain locks either to the lowest-energy state or to the lowest free-energy valley.
Read the full abstract ▾
Networking
DSWM: Decomposed Spatio-Temporal World Model for Demand-Driven UAV Base Station Repositioning
Shengjie Zhong, Zhongliang Zhao, Jingxuan Chen et al. (+4 more)
Uncrewed aerial vehicle base stations (
UAV-BSs) are expected to cover traffic demand that shifts across space and time, yet most repositioning schemes either re-solve an optimization problem per slot or learn reactive policies without an explicit demand model. We cast demand-driven fleet repositioning as latent-space decision-time planning and propose DSWM, a decomposed spatio-temporal world model: an agentic controller that perceives the demand field through a rolling observation window, retains operational context in a latent recurrent state, reasons about candidate motions by imagined rollouts under an uncertainty penalty, and coordinates the fleet through replanned first actions. DSWM learns a recurrent state-space model shaped by an exponential-moving-average (EMA) based latent predictive objective with variance regularization. It attaches a differentiable service simulator that replays the association, probabilistic line-of-sight channel, and Shannon rate chain inside latent rollouts. Planning uses a cross-
entropy method whose imagined demand is anchored on the current observation window with mixing coefficient $\rho=0.95$. On a unified pipeline over three real
datasets (Milan CDR (call detail record), Shanghai Telecom, YJMob100K) and 14 methods including five reproduced IEEE baselines, DSWM attains weekday served ratios of 0.889, 0.908, and 0.898, ranking first among non-ablated configurations on every
dataset. On Milan it improves over the strongest non-learning baseline (Greedy, 0.780) by 0.109, a margin that comes from decision-time use of observations rather than prediction accuracy.
Read the full abstract ▾
All authors Shengjie Zhong, Zhongliang Zhao, Jingxuan Chen, Xianbin Cao, Xinmei Qiang, Dapeng O. Wu, Tony Q. S. Quek
Computer Vision
GlassFormer: Learning Real-time Glass Segmentation using Radar-Depth Fusion
Suhani Grover, Astik Srivastava, Viswas Dinesh et al. (+2 more)
Transparent surfaces are ubiquitous in built environments, yet they remain a persistent failure case for robotic perception. RGB cameras perceive the background behind glass rather than the surface itself, while depth sensors such as
LiDAR, time-of-flight, and RGB-D often return invalid or background measurements in transparent regions. As a result, systems that rely solely on optical sensing may misinterpret glass walls, doors, or mirrors as free space, compromising safe and reliable
navigation. Existing glass
segmentation approaches address this by learning visual cues such as reflections, boundaries, and semantic context from RGB images. While effective under favourable lighting and viewing conditions, these cues degrade in low-light environments, under glare, or when glass surfaces are featureless or partially occluded. In this work, we propose a
multimodal framework that fuses millimetre-wave radar with RGB-D sensing for real-time transparent surface
segmentation. Radar reflects strongly off glass surfaces, providing a
geometric cue that remains reliable precisely where
vision and depth fail. We exploit this cross-modal inconsistency to generate a radar-guided spatial prior, which is integrated into a lightweight
transformer-based
segmentation network, GlassFormer, via cross-modal
attention. We report results on a mixed-condition test split covering all scene types and a dedicated low-light split designed to stress
vision-only methods. GlassFormer achieves 0.88 mIoU on the mixed split, and 0.59 mIoU on the low light split, demonstrating substantial robustness gains over
vision-only baselines while maintaining real-time performance on resource-constrained platforms.
Read the full abstract ▾
All authors Suhani Grover, Astik Srivastava, Viswas Dinesh, Avinash Sharma, K. Madhava Krishna
Machine Learning
RolloutFaith: Auditing Persistent Internal Interventions in Visual World Model
Junchi Yao, Ziyi Wang, Youling Huang et al. (+1 more)
Interpretability methods such as probes, activation patches and learned editors are designed to reveal or modify a model's current computation. World models pose a harder requirement: because their predictions become inputs to later predictions, a useful internal correction must survive after editing stops. We therefore propose RolloutFaith, a framework that measures semantic improvement both in the prediction produced at intervention time and over later autonomous predictions under fixed events, actions, noise, and information budgets. We evaluate ten fitted editors on three world models across Crafter, Cartpole, and CoinRun. We also use Reference Activation Patching, which replaces a model activation with the paired activation computed from the real observation, to measure the correction available at the chosen interface. This reference intervention improves later predictions in all nine model and task combinations and outperforms the best fitted editor in eight, yet its sustained gain decreases with horizon in five of nine combinations. Current fitted editors recover only limited and inconsistent long term effects. By restoring individual state components to their untouched values, we find that persistent effects travel through the newest generated frame in DIAMOND, recurrent
memory in DreamerV3, and both in STORM. These findings suggest that training should reward future consequences. To test this hypothesis, we propose Delayed LoReFT, which optimizes the same low rank intervention through four frozen future transitions and improves sustained intervention effects to some extent.
Read the full abstract ▾
All authors Junchi Yao, Ziyi Wang, Youling Huang, Lijie Hu
Computer Vision
Does the VGGT Family Need All Its Layers?
Fengyi Zhang, Holger Caesar, Xiangyu Sun et al. (+3 more)
Which layers of a feed-forward geometry model are needed to preserve both camera poses and dense 3D structure? We study layer redundancy in VGGT, $\pi^3$, and VGGT-$\Omega$: 3,018 pruned configurations, scored on seven camera-pose and dense-geometry metrics across four indoor and outdoor
datasets. Four findings follow: (i) Removable layers cluster in two redundancy regions: a dominant early region and a narrower late one, while deletions spanning the intervening layers are consistently more disruptive. This recurring pattern holds across models,
datasets, and metrics, and contrasts with the middle-to-late redundancy commonly reported in the literature. (ii) Within these regions, we observe that the joint degradation from deleting two intervals is approximately the sum of their individual degradations, reducing the number of model evaluations for
pruning search from $O(L^4)$ to $O(L^2)$, where $L$ is the aggregator depth. (iii) We find that CKA provides a cheaper representation-based proxy for interval degradation, offering a practical trade-off between
pruning quality and calibration cost. (iv) Closed-form linear calibration recovers accuracy after
pruning without end-to-end retraining. A least-squares analysis shows that using a shared map for special and patch
tokens generally incurs excess reconstruction loss, motivating
token-aware recovery. Recovery maps fitted on just 100 calibration scenes generalize to held-out scenes and unseen
datasets. The resulting models reduce aggregator parameters by up to 44% while maintaining accuracy comparable to their intact counterparts. Code and experimental results will be available at our project page: https://xian-bei.github.io/vggt-family-layer-redundancy/
Read the full abstract ▾
All authors Fengyi Zhang, Holger Caesar, Xiangyu Sun, Zheng Zhang, Zi Huang, Yadan Luo
High Energy Physics (Phenomenology)
An Operator Analysis of Radiative Muon Decay
Arvind Rajaraman and Chao-Hsiang Sheu
New physics beyond the Standard Model (SM) may induce new four-
fermion interactions. We investigate the sensitivity of radiative
muon decay, $\mu^-\to e^-\bar\nu_e\nu_\mu\gamma$, to such four-
fermion interactions of mass dimension seven and eight. For each operator, we calculate its interference with the SM amplitude and obtain an analytic expression for the decay rate. We apply these to a log-likelihood comparison for a
benchmark sample of $10^5$ events, and find that these operator contributions can be distinguished from the SM prediction at characteristic coefficient magnitudes between $10^{-9}$ and $10^{-8}$.
Read the full abstract ▾
Numerical Analysis
High Performance Computing of SDRE models with Discrete Kalman Filtering for Robust $H_{\infty}$-Controls
Yunfeng Cai, Tiexiang Li, Wen-Wei Lin et al. (+1 more)
State-dependent Riccati equation (SDRE) control requires repeated online solution of continuous-time algebraic Riccati equations (CAREs). A projected-channel $H_\infty$ formulation preserves the physical actuator and sensor dimensions of under-actuated, partially observed systems. We derive a computable sufficient attenuation bound for positive-semidefinite stabilizing Riccati solutions and construct an update that enforces their spectral-radius coupling condition. A discrete Kalman recursion supplies the scheduling state estimates. The two CAREs arising in controller synthesis are solved by a structure-preserving doubling
algorithm (SDA) or a warm-started Newton–Kleinman iteration equipped with a doubling Lyapunov solver. Numerical studies use a twelve-state F-16 model with complete aerodynamic forces, moments, and trim, together with quadrotor spiral tracking. With instantaneous command updates, all three CARE backends give essentially the same closed-loop response. In the tracking simulations, measured computation times determine when new control inputs are applied, and the previous inputs are held during computation. SDA and Newton reduce airspeed and pitch errors in all six paired aircraft tracking runs. In the faster quadrotor task with limited computational resources, SDA and Newton complete all paired runs, while runs using MATLAB icare terminate early.
Read the full abstract ▾
All authors Yunfeng Cai, Tiexiang Li, Wen-Wei Lin, Junxin Zhang
Statistical Methodology
BRP-GABLE: An Interpretable Rule-Based Prediction Framework for Multiple Outcome Types
Yulong Li, Ke Wan, Toshio Shimokawa et al. (+1 more)
Interpretable prediction models are important in biomedical research, where predictive accuracy must often be balanced against the ability to examine predictor-outcome relationships. Automatic Binary Logistic Estimation (ABLE) provides interpretable rule-based representations by constructing additive models using threshold rules. However, the original method is restricted to binary outcomes, and its greedy forward construction follows a search path, making candidate rules dependent on earlier selections and potentially excluding alternative structures. We extended ABLE to binary, continuous, and time-to-event outcomes using outcome-specific fitting criteria, yielding Generalized ABLE (GABLE). We then propose bootstrap rule pooling for GABLE (BRP-GABLE), which applies GABLE rule generation to bootstrap samples to explore alternative search paths, pool distinct rules, and perform a single global LASSO selection over the pooled rules and truncated linear terms. Unlike conventional bagging, bootstrap-specific models are not averaged, and resampling is used to diversify the candidate rule space before constructing a final model. Simulations showed that BRP-GABLE consistently improved predictive performance compared with GABLE and provided competitive prediction with relatively simple rule structures. Application to overall survival demonstrated its use for clinically interpretable prediction. BRP-GABLE provides a flexible framework for constructing sparse and interpretable predictive models across multiple outcome types.
Read the full abstract ▾
All authors Yulong Li, Ke Wan, Toshio Shimokawa, Kensuke Tanioka
Computer Vision
On-Policy Visual Evidence Distillation
Shaohang Wei, Feifan Song, Guangyue Peng et al. (+9 more)
Visual
agents solve problems by interleaving
reasoning with image operations, and on-policy
distillation (OPD) provides guidance from a strong teacher on student-generated interaction trajectories. However, image operations change the evidence available for subsequent
reasoning, so local errors in evidence acquisition (Acquire), reading (Read), or answer grounding (Ground) can propagate through the trajectory and lead to incorrect answers. Existing
multimodal OPD methods primarily construct or contrast auxiliary views of the original image to strengthen supervision, without explicitly modeling the connections between student actions, resulting observations, and subsequent
reasoning. This limits their ability to provide corrections tailored to different failure stages. We introduce Reflection on Visual Evidence (ReVuE), an on-policy
distillation method for visual
agents. ReVuE compares multiple student-generated trajectories for the same query, summarizes the observed visual evidence, and diagnoses the first failure across the Acquire, Read, and Ground stages. The resulting reflections provide training-time context for the teacher. We group and reweight
token-level
distillation losses according to how strongly these reflections affect the teacher's predictions. This design translates trajectory-level evidence diagnosis into targeted
token-level supervision, guiding students to improve their visual evidence acquisition and
reasoning. Across 11
benchmarks spanning the Qwen2.5-VL and InternVL3.5 model families, ReVuE outperforms all evaluated OPD baselines in weighted-average scores for perception, mathematical
reasoning, and general tasks. ReVuE also reduces redundancy in
reasoning and tool calls while improving tool-call accuracy and task accuracy. Code is available at https://github.com/sylvain-wei/ReVuE
Read the full abstract ▾
All authors Shaohang Wei, Feifan Song, Guangyue Peng, Wenhao Yu, Wei Li, Wen Luo, Yang Xu, Yufan Shen, Luke Mao, Yang Du, Asher Qin, Houfeng Wang
Computer Vision
You Cannot Recover What Was Never Measured: Quantifying the Information Ceiling of Ultra-Low-Field MRI Super-Resolution
Prathamesh Pradeep Khole, Shreya Handa, Utkarsh Gupta et al. (+1 more)
Generative super-resolution models can turn portable 64 mT MRI into images that look like 3T scans, and the field evaluates them with PSNR, SSIM, and pixelwise uncertainty, most often on pairs built by synthetically degrading high-field images. Prior work acknowledges that these models hallucinate and that the problem is ill posed, but to our knowledge no study measures how much information about the individual subject the real low-field scan actually contains. We measure it. Using paired 64 mT and 3T scans of the same subjects from three public
datasets, and a measurement protocol validated on tests whose correct answer is known in advance, we find that, judged over the whole
brain, real 64 mT scans carry structure specific to the individual only down to approximately 3 to 4 mm half-pitch in plane, and coarser still through plane. Standard synthetic degradations preserve subject information roughly 1 mm beyond this ceiling, so models trained and benchmarked on synthetic pairs are evaluated on information that real scanners never record. We then test trained
diffusion models and a publicly released external model on real paired acquisitions; 24 trained runs of five architectures (GAN,
diffusion, and
transformer families) give the coverage of the audit. On every subject where faithfulness can be measured, fine output detail is no more correlated with the subject's own 3T scan than with a stranger's, while sample-variance uncertainty does not distinguish fabricated structure from reconstruction difficulty. Because PSNR and SSIM score resemblance to a reference rather than whether detail belongs to the subject, a
benchmark scored by them cannot tell recovery from fabrication. Code for the measurement protocol will be released so that recoverability claims can be tested for newer models.
Read the full abstract ▾
All authors Prathamesh Pradeep Khole, Shreya Handa, Utkarsh Gupta, Razvan Marinescu
Quantum Physics
Ordering controlled by the measurement-feedback interval in quantum Boltzmann samplers
Peng Wang, Yu-Xuan Zhang, Hai-Tao Ding et al. (+1 more)
We show that the measurement–feedback interval alone can induce ordering in a
quantum Boltzmann sampler with fixed programmed couplings and a fixed local dissipative rule. At zero environmental dephasing, repeated projective measurements remove transverse coherence regenerated during relaxation, thereby enhancing the local longitudinal response. We derive the exact finite-interval Markov kernel for successive measurement records and obtain the ordering threshold in the Curie–Weiss limit. For couplings below the
equilibrium Curie–Weiss threshold, shortening the readout interval drives a continuous transition to an ordered stationary state even though the programmed Boltzmann distribution remains disordered. The stationary response and equation of state map exactly onto those of a continuously interacting model with dephasing, while the linear relaxation rates remain distinct at matched static response. Exact finite-size stationary calculations reveal the transition through bimodal magnetization distributions and mean-field critical scaling.
Read the full abstract ▾
All authors Peng Wang, Yu-Xuan Zhang, Hai-Tao Ding, Leong-Chuan Kwek
Artificial Intelligence
ARC-KV: Amortizing Anchor Search for Reconstruction-Based KV Cache Compaction
Zheyu Shen, Guanhua Wang, Dezhan Tu et al. (+5 more)
Long-context large
language model inference is bottlenecked by KV caches that grow linearly with sequence length. This burden is especially severe for long, reusable context prefixes, whose cache must serve many downstream queries. Reconstruction-based methods such as
Attention Matching achieve strong downstream task performance with compact KV caches. However, iterative anchor search dominates the compaction cost of OMP-based
Attention Matching. This motivates our selective amortization principle of learning a reusable anchor-selection policy across contexts while retaining context-specific reconstruction. In this work, we propose ARC-KV, a novel reconstruction-based KV cache compaction method that follows this principle. To this end, we first train a value-aware indexer to select real-key anchors in a single scoring pass. ARC-KV then applies convex-hull-constrained key merging and fits an
attention-mass bias and compact values against the full cache. At inference time, ARC-KV builds the compact cache once per context using the frozen indexer and reuses it for all subsequent queries. Extensive experiments demonstrate that ARC-KV outperforms reported compaction methods in most settings across QuALITY, RULER, and LongBench on Llama-3.1-8B-Instruct. In particular, at 10% KV retention on QuALITY, ARC-KV improves accuracy from 0.6409 to 0.6474 over
Attention Matching while reducing compaction time by a factor of 25.73, from 959.8 s to 37.3 s.
Read the full abstract ▾
All authors Zheyu Shen, Guanhua Wang, Dezhan Tu, Mengchi Zhang, Yanjia Li, Adnan Aziz, Chunqiang Tang, Ang Li
Audio and Speech Processing
WenetSpeech-Min: A Large-Scale Minnan Speech Corpus with Dual Transcriptions for Dialectal Speech Processing
Haoyu Zhang, Chunjiang He, Hongtao Li et al. (+17 more)
Progress in dialectal
speech technology is hindered by the scarcity of large-scale, real-world corpora. For Minnan
speech, existing resources remain limited, and few provide paired Minnan and Mandarin transcripts at scale. To address these gaps, we introduce WenetSpeech-Min, an open-source corpus comprising around 10,000 hours of Minnan
speech collected from diverse online media, with paired Minnan and Mandarin transcripts for every utterance. We further establish an automatic
speech recognition (ASR)
benchmark covering both Minnan and Mandarin transcripts and a text-to-
speech synthesis (TTS)
benchmark using Minnan transcripts, with manually verified evaluation sets for both tasks. To assess the effectiveness of the corpus, we train ASR and TTS models on WenetSpeech-Min and compare them with representative systems on the proposed
benchmarks. The resulting models outperform the evaluated open-source models on most metrics and achieve competitive performance against commercial systems. We will release the corpus,
benchmarks, and models to facilitate reproducible research on Minnan
speech technology.
Read the full abstract ▾
All authors Haoyu Zhang, Chunjiang He, Hongtao Li, Zeyu Zhu, Qituan Shangguan, Chengyou Wang, Jingbin Hu, Ziyu Zhang, Bingshen Mu, Yanbo Wang, Shuai Wang, Jinhui Ye, Chengdong Liang, Binbin Zhang, Pengcheng Zhu, Chuang Ding, Qianze Feng, Qingyang Hong, Liumeng Xue, Lei Xie
Astrophysics of Galaxies
Morphological Identification of Dynamical Regimes in MHD Turbulence with ScaleAware-JEPA
Mengke Zhao, Guang-Xing Li and Keping Qiu
The morphology of turbulent interstellar gas reflects the coupled action of
turbulence,
magnetic fields, and self-
gravity, but density amplitude alone does not uniquely specify dynamical state. We use ScaleAware-JEPA to learn multiscale structural coordinates from density alone and test whether these learned coordinates organize dynamical states more clearly than density-based conditioning. Clump-like, filament-like, and diffuse-like latent neighborhoods show an ordered progression in turbulent velocity scaling that is not reproduced by density-selected populations. Velocity and
magnetic fields are withheld during training and used afterward as post-training physical diagnostics: MHD states occupy ordered but overlapping regions of the learned representation, and dimensionless dynamical balances vary coherently across the full latent atlas. These results show that a representation learned from density morphology can acquire a geometry that is systematically organized by established MHD diagnostics. Multiscale morphology therefore provides a useful coordinate for dynamical state beyond density amplitude alone.
Read the full abstract ▾
Computer Vision
Motion Concept Unlearning in Video Diffusion Models
Ping Liu and Chi Zhang
Text-to-
video (T2V)
diffusion models can generate realistic depictions of actions such as kicking, stabbing, and shooting, raising safety concerns that motivate targeted concept erasure. Although concept erasure has been extensively studied for static concepts in text-to-image and T2V models, erasing motion concepts remains largely unexplored. We present a systematic study of motion concept erasure in
video Diffusion Transformers (DiTs). Through causal interventions, we show that text-conditioning
attention carries concept-specific motion information and supports selective intervention, whereas perturbing temporal positional encoding suppresses both target and non-target dynamics. We further find that directly adapting ESD, a representative weight-level image erasure method, to a
video DiT yields modest and uneven motion suppression: reducing its erasure training loss does not by itself remove the concept signal from the difference between the conditional and unconditional predictions, which classifier-free guidance (CFG) then scales at every denoising step. From these findings, we derive three requirements for motion concept erasure: concept specificity, spatial selectivity, and temporal naturalness. Each determines one component of MUTE (Motion concept Unlearning in Text-to-
video gEneration): at each denoising step, MUTE extracts a concept direction through
token neutralization, derives a spatial gate from the direction's intrinsic structure, and subtracts the resulting correction from the velocity output before CFG is applied. MUTE is training-free and requires no weight modification. Experiments on 20 motion concepts show that MUTE outperforms representative
prompt-level, weight-level, and inference-time baselines on Wan2.1-T2V, and the same formulation transfers to CogVideoX, supporting its applicability across distinct T2V
attention architectures.
Read the full abstract ▾
Fluid Dynamics
Radial flow of an Oldroyd-B fluid: theoretical and simulation results in the ultra-dilute limit
Ron Lottem and Evgeniy Boyko
Pressure-driven radial flows of viscoelastic fluids are common in various industrial applications, such as injection molding and extrusion. It is well known that viscoelastic rheology can significantly impact the hydrodynamic features of non-Newtonian flows. However, these hydrodynamic features remain not fully understood compared to those observed in Newtonian flows. We analyze the pressure-driven radial flow of an Oldroyd-B fluid between parallel plates and present a theoretical framework together with finite-element numerical simulations for determining the flow rate-pressure drop relation. Unlike previous theoretical studies restricted to the weakly viscoelastic limit of low Deborah ($De$) numbers, we apply lubrication theory and consider the ultra-dilute limit, which allows us to study viscoelastic radial flows at order-one Deborah numbers. Using the one-way coupling between the Newtonian velocity profile and elastic stresses, we derive closed-form expressions for the conformation tensor and pressure drop in the ultra-dilute limit. We show that the pressure drop monotonically increases with $De$, identify the physical mechanisms governing this increase, and delineate the range of validity of the ultra-dilute approximation. We further reveal that the low-$De$ asymptotic analysis of the pressure drop may fail to accurately capture finite-element simulation results, even at low Deborah numbers, owing to its inability to satisfy the inlet elastic stresses. In contrast, our theoretical predictions based on the ultra-dilute limit are in excellent agreement with the finite-element simulation results, enabling us to elucidate the pressure drop behavior for order-one Deborah numbers.
Read the full abstract ▾
Artificial Intelligence
Where Does Staleness Accumulate? Pool Aware Effective Staleness Control for Asynchronous RL in LLM Post-Training
Chenliang Li, Neiwen Ling, Zijun Wei et al. (+1 more)
Fully asynchronous reinforcement learning (RL) improves resource utilization in large
language model post-training by overlapping rollout generation with policy optimization, but it also introduces policy lag as trajectories are generated and queued while the trainer continues to update. We study how this lag accumulates over a trajectory's lifetime and how it can be controlled without sacrificing the wall-clock benefits of asynchronous execution. We decompose trajectory staleness into Generation Staleness, accumulated before rollout completion, and Waiting Staleness, accumulated after a completed trajectory enters the pool. Motivated by this decomposition, we introduce PACE (Pool-Aware Control of Effective Staleness). PACE converts excess pool occupancy into an adaptive rejection budget and ranks completed trajectories using an effective-staleness score that combines Waiting Staleness with prefix-aware Generation Staleness. This avoids penalizing long or interrupted rollouts solely because they span multiple policy versions. In single-turn mathematical
reasoning, PACE improves the six-
benchmark average validation accuracy by 18.7% over unfiltered asynchronous RL at the same wall-clock budget and matches synchronous RL performance with 47.1% less GPU time. PACE also improves validation performance in multi-turn tool-integrated
reasoning, outperforming both synchronous and unfiltered asynchronous RL. Further experiments with the mixture-of-experts model and an alternative RL
algorithm support its applicability across model architectures and training
algorithms.
Read the full abstract ▾
All authors Chenliang Li, Neiwen Ling, Zijun Wei, Alfredo Garcia
Artificial Intelligence
The Default Trap: Rethinking Plan Evaluation in Tool-Using LLM Agents
Xueqi Li, Jingjie Ning and Yibo Kong
An executor can respond strongly to a change in a supplied plan's priority while showing a small change in the same information-selection probability when a default-aligned whole plan is removed. We call the risk of interpreting the latter as weak responsiveness to alternative priorities the default trap. We compare paired plans that prioritize different information targets with a shared no-plan reference. An accounting identity relates these distinct behavioral contrasts. Across 3,200 decision windows on 160 selected Retail, Airline, and AgentDojo tasks, switching priorities strongly redirects two models' choices, while the two plan-versus-default contrasts differ. In 2,160 additional windows, reversing account-list order shifts default target selection by 63.3-98.3 percentage points; priority-switching effects remain 96.7-100.0 points in either order. A separate 3,240-window component study finds strong control under single priority sentences, with effects of additional text varying by group and direction. Finally, 1,080 full-task episodes yield observed success differences of -19.4 to +8.3 points relative to no plan. All Retail and Airline success intervals include zero; AgentDojo results describe four fixed application worlds. These findings support joint reporting of priority responsiveness, presentation-dependent defaults, and task success and cost.
Read the full abstract ▾
Artificial Intelligence
Calibrate the Decisions That Change the Future: On-Policy Post-Training Quantization for Multimodal Large Language Models
Wenxiao Fan, Jingling Fu, Lichen Ma et al. (+6 more)
Post-training quantization (PTQ) lowers deployment cost for
multimodal large
language models, but calibration typically reconstructs fixed sequences with local objectives. This overlooks autoregressive feedback: a quantization-induced
token change redirects the prefix and changes future states. Yet on-policy coverage alone is insufficient because many decision mismatches barely affect future generation. We propose OnPTQ, an on-policy framework that calibrates on trajectories visited by the current quantized policy. On shared prefixes, OnPTQ identifies quantization-eroded boundaries, evaluates competing
tokens through short counterfactual rollouts, and combines current discrepancy with branch consequence into a Decision–Consequence risk. The risk prioritizes critical states, while context anchoring and trajectory refresh preserve
multimodal behavior and keep calibration aligned with the updated policy. We further derive a Decision–Consequence bound linking behavioral deviation to current policy discrepancy and action-conditioned future-value span. Across
vision–
language and omni-modal Qwen models under multiple low-bit settings, OnPTQ improves downstream performance and yields fewer correctness flips against the corresponding Dense/FP16 references, without changing the deployed inference graph.
Read the full abstract ▾
All authors Wenxiao Fan, Jingling Fu, Lichen Ma, Yu He, Luohang Liu, Jinbao Xue, Ke Zhang, Junshi Huang, Kan Li
Optimization and Control
Optimal Cuts and Optimal Faces of Exact Max-Cut Semidefinite Relaxations
Avinash Bhardwaj, Chen Chen and Vishnu Narayanan
An exact Max-Cut semidefinite relaxation can have optima outside the convex hull of optimal cut
matrices. We study when this hull equals the optimal face and how to recognize equality. For rational weights, the unique optimal dual slack is recoverable in
polynomial time, but its kernel may contain directions no optimal
matrix uses. Under strict complementarity, recognition and recovery of all optimal cuts on equality instances take deterministic
polynomial time. At dual rank one, this hypothesis is unnecessary. Recognition is
polynomial-time Turing equivalent to exact rational semidefinite feasibility, even on simple unweighted graphs. Testing whether a supplied cut
matrix is the unique optimum is many-one equivalent, even on connected simple graphs with a unique optimal cut. NP-completeness of recognition would imply NP equals coNP. Replication realizes doubly nonnegative
matrices with positive diagonal and rational kernel as sign-spanned optimal dual slacks, preserving rank, complete positivity, and cp-rank.
Read the full abstract ▾