Machine Learning
AeroChem: Closed-loop Physics-Informed State Space Modeling for Long-term Chemically-Reactive Air Quality Forecasting–Extended Version
Kien Le Trung, Tung Kieu, Dinh Duc Nha Nguyen et al. (+3 more)
Accurate long-term air quality forecasting is challenging due to long-range transport, meteorological variability, and nonlinear chemical reactions underlying secondary pollutant formation. Purely data-driven models often suffer from long-horizon drift and lack physical consistency, while existing physics-informed approaches commonly follow open-loop designs that fuse neural and physical components only at the output level. We propose AeroChem, a closed-loop physics-informed state space framework for chemically reactive air quality forecasting. AeroChem adopts a two-branch co-correction design: a UDE-based process branch provides a structured but imperfect physical prior, while a Mamba-based virtual measurement branch captures long-range temporal context and produces probabilistic virtual observations. Neural Kalman Fusion couples the two branches by correcting the latent physical state at each forecasting step and feeding the posterior state back into the simulator, reducing long-horizon drift. We further introduce HanoiAir, a real-world
dataset integrating pollutant concentrations, meteorology, and emission inventories. Experiments on HanoiAir and a public
benchmark show that AeroChem improves long-horizon stability and sudden-change forecasting.
Read the full abstract ▾
All authors Kien Le Trung, Tung Kieu, Dinh Duc Nha Nguyen, Cuong Do, Bin Yang, Phi Long Nguyen
Sound
PRB-WM: Physics-Regularized Beta World Models for Predictive Link Adaptation on Real Time-Varying Underwater Acoustic Channels
Shengjie Zhong, Zhongliang Zhao, Jingxuan Chen et al. (+5 more)
Adaptive modulation and coding (AMC) improves the spectral efficiency of underwater acoustic (UWA) links, but its feedback is inevitably stale: sound propagates slowly, and by the time channel state information (CSI) arrives, the fast time-varying multipath channel has moved on. Predictive link adaptation therefore needs more than a point forecast: it needs a distribution over each candidate action's consequences. We propose PRB-WM, a physics-regularized Beta world model for predictive per-subcarrier link adaptation on real time-varying UWA channels. A persistence-anchored
stochastic latent-space dynamics model learns how the channel evolves; a counterfactual outcome head evaluates, for every candidate modulation and coding scheme (MCS), a Beta-binomial distribution of bit errors on shared imagined futures; and a chance-constrained receding-horizon model predictive controller maximizes expected spectral efficiency subject to a bounded probability of violating the bit error rate (BER) target. To the best of our knowledge, PRB-WM is the first world model for UWA communications. In closed-loop replay of six measured sea-trial links from the public UWA Channel Library against a 24-method pool spanning the full methodological spectrum, PRB-WM attains a mean goodput 87% above the strongest baseline, ranks first on all six time-varying links at the longest lookahead, and is the only method whose realized frame risk decreases systematically with lookahead, meeting the BER-violation contract where no baseline does. Ablations confirm that rollout sampling dispersion is essential to the chance constraint and that the physics anchor is necessary for trainability.
Read the full abstract ▾
All authors Shengjie Zhong, Zhongliang Zhao, Jingxuan Chen, Dianrun Huang, Zichen Zhao, Yang Liu, Dapeng O. Wu, Tony Q. S. Quek
Human-Computer Interaction
Integrating Feature Understandability into Feature Selection for Human-Centred Tabular Explanations
Nicola Rossberg, Bennett Kleinberg, Barry O'Sullivan et al. (+2 more)
Existing human-centred XAI research predominantly evaluates explanations after they have been generated. However, this fails to provide actionable insights into improving accessibility. This study incorporates human-based feature understandability into feature selection to improve the generation of human-centred explanations. Natural
language explanations for machine learning models trained on tabular data often cite influential features in the input data to explain a given decision. As a consequence, users' ability to understand the produced explanation hinges on their understanding of the cited features. To quantify this natural-
language feature understandability, Rossberg et al. proposed the Feature Understandability Scale, which assigns numerical `understandability scores' to features based on user feedback. To evaluate the degree to which these scores can improve machine learning explanation quality, this study collects understandability scores across two
datasets, proposes an understandability-aware feature selection
algorithm to select features that are both understandable and informative, and trains a random forest based on these feature subsets. The SHAP-based explanations generated by this model are evaluated using user feedback, and changes in explanation quality are assessed. The individual evaluation of the explanations showed that while the understandability-based explanations scored higher on average, the difference was not statistically significant. In contrast, the comparative evaluation found that participants preferred these explanations significantly more frequently than expected at the chance level. It is concluded that the integration of understandability can yield more understandable explanations at minimal cost to classification performance, although changes to quality require elucidation in larger cohorts.
Read the full abstract ▾
All authors Nicola Rossberg, Bennett Kleinberg, Barry O'Sullivan, Luca Longo, Andrea Visentin
Artificial Intelligence
LATCH: LLM-Assisted Timing Closure Harness for Post-Route FPGA Optimisation
Shu Gu, Matthew Youngman, Yuqin Zhao et al. (+5 more)
Post-route FPGA timing closure remains expert-dependent and computationally expensive. We present LATCH (LLM-Assisted Timing Closure Harness), a two-layer framework that separates large
language model (LLM) orchestration from deterministic FPGA implementation and evaluation. Across sixteen designs and seven LLMs, a single-iteration study compares three
agent control granularities - expert-written recipes, direct EDA operations and LLM-constructed procedures - to ask how much control an
agent needs per attempt. Functional-pass rates are 98.2%, 71.4% and 17.9%, respectively; yet direct operations give slightly larger 3.4% median Fmax gains when passing, versus 3.2% for recipes. This exposes a trade-off between execution reliability and timing improvement. Informed by this trade-off, a multi-iteration study fixes the action tier at expert recipes to ask how repeated attempts are best organised, comparing a fitted deterministic heuristic with sequential LLM
reasoning, branching exploration and knowledge base-guided exploration within 12 checkpoints per run. Branching raises mean maximum-frequency improvement from 10.5% (sequential) to 16.0%, and the knowledge base to 20.3%, improving 15 of 16 designs. Characterisation across 2,421 recipe attempts profiled their gain and validation rates, showing hard-block re-placement gives the largest cumulative mean gain at 41.4MHz.
Read the full abstract ▾
All authors Shu Gu, Matthew Youngman, Yuqin Zhao, Cristian Sestito, Ali Siddique, Ramesh Krishnamurthy, Danial Chitnis, Themis Prodromakis
Computer Vision
Adaptive Interaction Network for Human Motion Prediction During Human-Robot Collaboration
Mengyuan Liu, Yangting Lin and Qiongjie Cui
Human motion prediction during human-
robot collaboration is critical for achieving safe and efficient interactions in shared environments. Unlike previous studies that have primarily focused on humans and objects, we focus on the
robot-aware human motion prediction task, which explicitly models the influence of
robots on human motion. This task presents new challenges, such as capturing human-
robot heterogeneity and modeling complex spatial interactions. To address these issues, we develop an adaptive interaction network (AINet) model that consists of two branches: a primary branch that predicts future human motion and an auxiliary branch that estimates
robot trajectories. The two branches are jointly optimized and coupled via a Local-Global Spatial Interaction (LGSI) Module, which effectively captures fine-grained and global contextual dependencies between human and
robot motion sequences. Then, we introduce an Adaptive Weighted Aggregation (AWA) Module to dynamically fuse motion features using context-dependent weights, thereby increasing adaptability across diverse scenarios. Furthermore, we adopt a coarse-to-fine prediction strategy, in which a coarse pseudo-trajectory is first predicted, followed by the refinement of detailed human poses based on that trajectory. Extensive experiments on three challenging
datasets reveal that our proposed method achieves superior performance, validating its effectiveness in human-
robot collaboration scenarios. Our code is available at: https://github.com/LyTingHub/AINet.
Read the full abstract ▾
Social and Information Networks
The Effect of Expertise Signaling when Sharing Medical Information in Opinion Dynamics
Moyi Li, Chuqiao Yan, Jesus Jair Reyes Gutierrez et al. (+2 more)
Social media heavily influences health decisions, yet few opinion dynamics models account for how information is delivered. This work investigates how signaling source expertise shapes trust and long-term opinion formation. Through an online experiment, we find that adding a professional title to the sender's display name significantly increases a post's perceived credibility. Incorporating these findings to create a data-driven opinion dynamics model, we prove that (1) connecting users through some paths to an expert guarantees consensus with experts' opinion, while (2) higher rates of expertise signaling accelerate reaching consensus. Simulations show that (3) convincing even 20% of users to signal their title reduces consensus time to nearly one-third in Erdos-Renyi networks and (4) higher title adoption brings average opinion much closer to that of experts in scale-free and real-world networks. Altogether, our work highlights expertise signaling as a viable intervention to promote validated medical information online.
Read the full abstract ▾
All authors Moyi Li, Chuqiao Yan, Jesus Jair Reyes Gutierrez, Aleksandra Urman, Stefania Ionescu
Computer Vision
Shunyuan Bai, Yuchen Ren, Le Yang et al. (+3 more)
With the advancement in
language modeling, research on
adversarial images has recently shifted from image classifiers to
vision-
language models (VLMs). Despite the new, text-
prompt-driven nature of VLMs, we find that existing VLM adversaries have largely overlooked the dynamics of text
prompts. In a typical use case,
adversarial images can protect visual
privacy by rejecting VLMs from answering questions about the image. However, existing protections are
prompt-agnostic, i.e., indiscriminately rejecting any question, including those for potential legitimate use of the image. To address this limitation, we propose
Prompt-Adapted (ProAda)
adversarial images, which are optimized to balance the rejection of harmful
prompts and the correct response of legitimate
prompts. In particular, to achieve a more accurate
adversarial direction, the text
prompt is also iteratively updated with a simple classifier judging whether the harmfulness of the
prompt remains. Extensive experiments on visual-
privacy-related
datasets validate that ProAda can reject over 90% of harmful
prompts while allowing over 90% of legitimate ones, demonstrating superior overall performance compared to existing
prompt-agnostic VLM adversaries. In addition, our ProAda achieves competitive overall cross-model transferability and improved robustness against countermeasures.
Read the full abstract ▾
All authors Shunyuan Bai, Yuchen Ren, Le Yang, Chenhao Lin, Chao Shen, Zhengyu Zhao
Multiagent Systems
AgentCue: Statistical Summaries for Guiding Decentralized Multi-Agent Self-Organization
Guojun Zhu, Xinyou Chen, Kejian Zhang et al. (+2 more)
Multi-
agent systems (MAS) combine multiple
agents to solve complex tasks, and recent MAS scale to more than a thousand
agents. At this scale, decentralized MAS remove the central orchestrator that assigns sub-tasks, and the
agents, which we call workers, self-organize through their own choices of sub-tasks and collaborators on a shared board. As workers keep adding participation and collaboration records, however, the information explodes: workers spend more and more effort on reading the records of other workers, and self-organization loses efficiency. In the statistical view, we represent the execution history of an MAS by two continually updated networks, a collaboration network among workers and a participation network between workers and task types. We then propose AgentCue, a method built on a new latent space model that places workers and task types in a shared latent space. Each time the networks are updated, the estimated parameters of the latent space model form a compact and interpretable statistical summary, and workers use the statistical summary to choose sub-tasks and collaborators without repeated searches of the shared board. We establish the identifiability of the latent space model and non-asymptotic error bounds for the estimates under network increments, and we show that a fixed number of gradient updates after each network update suffices for the same error rate. Experiments on LongBench v2 Multi-Doc QA show that AgentCue achieves competitive effectiveness, efficiency, and interpretability.
Read the full abstract ▾
All authors Guojun Zhu, Xinyou Chen, Kejian Zhang, Sanguo Zhang, Doudou Zhou
Artificial Intelligence
Weak Segmentation-Guided GAN for~Realistic Color Edition
Vincent Auriau, Emmanuel Malherbe and Matthieu Perrot
Editing the color of images in a realistic way finds many applications such as changing the perception of an image, data augmentation or film post processing. The design of an automatic tool is a complex and long addressed challenge. In particular, two properties are difficult to meet altogether: generating realistic results without artifacts and the possibility to precisely choose the future color. Conventional methods using segmentation and histogram matching maximize the controllability but also introduce a lack of realism or are complex to automate. On the contrary, GANs that specialize in realism are difficult to control. To overcome these challenges, we propose a novel GAN architecture leveraging any differentiable segmentation model. We demonstrate the genericness of our framework that presents state of the art results on different use cases. It generates images that look realistic while offering a precise color control.
Read the full abstract ▾
Machine Learning
DR-APO: Decoupled-Representation Advantage-Guided Policy Optimization from Continuous Control to Embodied Navigation
Runhua Zhang, Yingjie Niu and Chao Li
Policy representations in reinforcement learning have expanded beyond Gaussian policies to
diffusion and flow-matching based generative policies. However, existing RL methods remain representation-specific, lacking a unified optimization interface for emerging generative policies. In particular, extending likelihood-based objectives to multi-step generative policies couples optimization to their internal generation process, where accumulated likelihood ratios can weaken the update signal. Meanwhile, generative-policy-specific methods often rely on multi-candidate generation and critic-based selection, improving overall return while providing limited improvement to the policy itself. We introduce DR-APO (Decoupled-Representation Advantage-Guided Policy Optimization), which decouples policy improvement from policy representation through advantage-guided target improvement and representation-compatible direct action fitting, providing a shared optimization principle for Gaussian,
diffusion, and flow policies. Across five MuJoCo-v5 tasks, DR-APO remains competitive with SAC for Gaussian policies and achieves the best aggregate policy-only performance for both
diffusion and flow-matching policies. NavDP post-training improves the Success Rate (SR) from 70.33% to 89.55% in simulation and from 25% to 65% in real-world navigation. These results demonstrate a unified policy-improvement principle across Gaussian,
diffusion, and flow policies, from continuous-control learning to embodied-policy post-training.
Read the full abstract ▾
Artificial Intelligence
When 1+1 Backfires: Rethinking Relevance-Diversity Balancing for Sample-Aware Visual Token Reduction
Yihang Huang, Peisong Wen, Chenhao Zhou et al. (+2 more)
Visual
token compression has emerged as a critical technique for reducing the inference cost of
Vision-
Language Models. Existing methods select
tokens based on text relevance, visual diversity, or a fixed combination of both—treating the relevance-diversity balance as a universal constant independent of the input. We conduct a systematic analysis to challenge this assumption. At the
dataset level, grid-searching the optimal relevance-diversity weight per
benchmark reveals substantial cross-task variation. More critically, we further maximize per-sample answer likelihood to recover sample-level oracle weights, finding that their distributions not only differ markedly across
benchmarks but also exhibit high within-
benchmark variance. Based on these observations, we propose SAVER, a framework for Sample-Aware relevance-diversity balanced Visual
tokEn Reduction. We first derive a
Geometric Intent Prior (GIP) from the spatial concentration of text-relevant
tokens to infer a sample-specific relevance-diversity weight, and then apply this weight to jointly select
tokens via a Weighted Text Centroid (WTC) for relevance scoring and a Visual Marginal Coverage Gain (VMCG) for diversity. SAVER requires no additional training and achieves sample-aware balancing entirely at inference time. Extensive experiments demonstrate that SAVER consistently outperforms state-of-the-art baselines across diverse
benchmarks, retaining 96.5% of full-model performance on LLaVA-1.5-7B with only 11.1% of the original visual
tokens, and further generalizing to LLaVA-NeXT and Mini-Gemini.
Read the full abstract ▾
All authors Yihang Huang, Peisong Wen, Chenhao Zhou, Difu Feng, Qianqian Xu
Formal Languages and Automata
Conditional Membership in Regular Languages
Antoine Amarilli, Sebastien Felipe Labbe and Charles Paperman
We study a formulation of regular
language membership as a promise problem, which we dub conditional membership: we fix a promise
language $P$ and a target
language $T \subseteq P$, we are given a word $w$ which is promised to belong to $P$, and we must determine whether $w$ belongs to $T$. We study the deterministic worst-case query complexity of this task, when the length $n$ of $w$ is known in advance and where each query examines the $i$-th position of $w$ for some $1 \leq i \leq n$ and returns the $i$-th letter $w_i$ of $w$. Our goal is to characterize the asymptotic complexity as a function of the word length $n$, depending on the fixed
languages $P$ and $T$. Our main result is to show that the complexity of this task admits a trichotomy between three regimes: $O(1)$ queries, $\Theta(\log n)$ queries, and $\Theta(n)$ queries. We further show that the trichotomy criterion is decidable, namely, it is PSPACE-complete to decide which regime applies, given nondeterministic automata $A_P$ and $A_T$ respectively representing $P$ and $T$.
Read the full abstract ▾
Robotics
Design and Analysis of a Nonlinear Parallel Mechanism Coupling for Dynamic Humanoid Legs
Rohit Kumar, Heiner Peters, Felix Wiebe et al. (+5 more)
Humanoids increasingly demand lightweight leg mechanisms for agile, dynamic, and energy-efficient locomotion. Reducing distal inertia through proximal actuation has thus become a common design goal. Yet, compact transmissions that preserve torque capability and efficient force transmission remain hard to achieve. This paper presents a novel series-parallel leg design combining a knee parallel mechanism, an ankle parallel mechanism, and a nonlinear knee-ankle coupling where all actuators placed closer to the hip. As the knee flexes, the coupling passively assists ankle dorsiflexion for foot clearance and, as it extends it assists plantarflexion for push-off, redistributing ankle load through the knee transmission. We derive the coupling's nonlinear transmission models and validate them in simulation and on hardware. The design shows that the shared transmission lets both joints draw on each other's actuator capacity by easing the knee's peak torque demand under load and the ankle's peak speed demand during fast motion. %Together With the leg's proximal actuator placement, the leg achieves an effective reflected mass of 0.37kg at the foot for a 6kg leg, demonstrating very low distal leg inertia for dynamic humanoid
robots.
Read the full abstract ▾
All authors Rohit Kumar, Heiner Peters, Felix Wiebe, Franek Stark, Janne Janzen, Dennis Mronga, Shubham Vyas, Frank Kirchner
Computation and Language
MixLID: Token-Level Language Identification in Mixed-Language Text
Seongtae Hong, Youngjoon Jang, Seungyoon Lee et al. (+2 more)
Processing multilingual text requires both identifying a broad range of
languages and distinguishing the
language of each
token in inputs containing multiple
languages. We introduce MixLID, a
token-level
language identification model supporting 111
language-script combinations. MixLID follows a two-stage training process: it first learns to distinguish individual
languages using the
language labels of monolingual examples, then continues training on mixed-
language data. The second stage uses concatenated examples from existing code-switching data alongside augmented examples created through word substitution based on correspondences between English source words and loanwords. For monolingual identification, MixLID outperforms all baselines in both accuracy and macro F1 on four
benchmarks within the
language coverage shared with each baseline. For mixed-
language identification, it outperforms the baselines in identifying the
language of individual
tokens on every evaluated
language pair. MixLID achieves high performance across a broad range of
languages in both monolingual and mixed-
language settings. The model is publicly available at https://huggingface.co/nlpai-lab/MixLID.
Read the full abstract ▾
All authors Seongtae Hong, Youngjoon Jang, Seungyoon Lee, Jungseob Lee, Heuiseok Lim
Computer Vision
Detecting Chain-of-Thought Hijacking in Backdoored Multimodal Large Reasoning Models
Zhifang Zhang, Qi Wei, Weitong Chen et al. (+5 more)
Chain-of-thought (CoT)
reasoning enables
multimodal large
reasoning models (MLRMs) to solve complex visual problems, but also exposes them to CoT hijacking: an adversary implants a backdoor through poisoned fine-tuning so that a visual trigger induces a hijacking turn, redirecting an otherwise faithful
reasoning chain to an attacker-chosen answer. However, since the hijack acts within the
reasoning chain, existing
multimodal backdoor defenses designed for MLLMs that answer directly struggle to detect it. Moreover, inspecting the chain itself does not reliably expose the hijack, since the hijacking turn can resemble honest self-correction in form. In this paper, we find that honest
reasoning tends to revise its answer at high-
entropy "aha moments", whereas a hijack can overturn a confident answer through a near-deterministic turn. To quantify this contrast, we formalize this phenomenon as belief inertia, the cumulative next-
token entropy of a
reasoning span minus the answer-belief revision it induces, with markedly lower values for hijacked spans than for honest
reasoning spans. Since hijacking
tokens are also image-dependent, we further improve detection by restricting the measure to image-dependent spans, yielding visual belief inertia (VBI). Building on this, we propose InertiaGuard, a training-free, test-time detector that flags a trace when its VBI falls below a threshold calibrated on a small set of clean traces. Across various attacks and
benchmarks, InertiaGuard achieves higher detection performance than existing baselines, while generalizing to different model architectures and trigger types.
Read the full abstract ▾
All authors Zhifang Zhang, Qi Wei, Weitong Chen, Olaf Maennel, Wei Emma Zhang, zuomin ren, Lei Feng, Miao Xu
Machine Learning
DEFlow: Deep Equilibrium Flow Maximum-Entropy Reinforcement Learning
Ruslan Ageev, Huaze Tang, Runqing Miao et al. (+2 more)
Expressive flow policies can represent multiple high-value actions, but sampling them with few integration steps while retaining tractable action densities remains challenging. We introduce DEFlow, a deep
equilibrium flow policy that replaces explicit Euler sampling with implicit Euler integration and solves all intermediate actions jointly as an
equilibrium system. We combine implicit differentiation with a discrete change-of-variables formula for the final-action density, enabling off-policy training within soft actor-critic without backpropagating through solver iterations. DEFlow achieves an average relative improvement of approximately 10% in mean successful coverage over the strongest baseline across four Multi-Goal docking variants. It also achieves the highest mean time-averaged return on four of five manipulation tasks, while remaining broadly competitive across five MuJoCo tasks. These results support implicit flow policies for tasks requiring both diversity and precision, at the cost of additional nonlinear and linear solves. Primary
Read the full abstract ▾
All authors Ruslan Ageev, Huaze Tang, Runqing Miao, Jiarong Li, Wenbo Ding
Machine Learning
Towards Modality-Agnostic Seizure Classification: A Unified Deep Learning Framework for Heterogeneous EEG and Intracranial EEG Signals
Ramya Sundaram, Muhammad Aslam Jarwar, M Uma et al. (+2 more)
Seizure prediction and detection, essential for clinical treatment of epilepsy, remain the crucial task of this neurological disease.
EEG and iEEG are widely used to analyze epilepsy due to its capability of capturing discriminative
brain activities at high time resolution. However, existing works generally analyze either
EEG or iEEG seizure activity separately, where
EEG analysis has been well-researched, while more and more works consider iEEG for its higher specificity at the spatial level and signal quality. Currently, most of the existing seizure prediction systems are single-modal in nature, which limits its application to a variety of clinical conditions. Therefore, a common framework to analyze seizures with both
EEG and iEEG signals needs to be developed. This paper presents a new framework of
multimodal seizure classification integrating the heterogeneous
EEG and iEEG recordings from different subjects and sources. A specific framework, called Unified
Multimodal Signal Harmonization (UMSH), is developed for harmonizing signals with varied sampling rates and recording conditions. Moreover, to handle the extremely class-imbalanced problem in the data sets, we use a Conditional Generative
Adversarial Network (cGAN) based data augmentation technique to generate synthetic samples to balance the class distribution. The proposed framework uses the EEGNet-
Vision Transformer (EEGNet-ViT) as the feature extraction and classification network to learn the local discriminative patterns as well as global contextual information in the
multimodal seizure data. Experimental results demonstrate the effectiveness of the proposed framework for robust seizure classification, emphasizing the potential of integrated
EEG-iEEG
multimodal learning in advancing next-generation epilepsy monitoring and clinical decision-support systems.
Read the full abstract ▾
All authors Ramya Sundaram, Muhammad Aslam Jarwar, M Uma, Sunder Ali Khowaja, Qurat-Ul-Ain Mastoi
Computer Vision · Cross-listed from eess.IV
Uncertainty-Aware Cortical Surface Reconstruction and Spherical Registration for Heterogeneous Brain MRI
Jesper Duemose Nielsen, Karthik Gopinath, Andrew Hoopes et al. (+4 more)
Surface-based cortical analysis is useful in many applications as it is a natural way to model the highly folded structure of the cerebral cortex, allowing quantities such as
curvature and thickness to be easily calculated. Existing deep learning (DL) methods have focused on 1x1x1 mm3 T1-weighted (T1w) scans, thus replicating classical pipelines. Here we present a neural network that is trained exclusively on synthetic scans with random contrast and resolution. Consequently, it can be applied to almost any kind of
magnetic resonance imaging (MRI) scan. In addition, our model provides vertex-wise uncertainty estimates of the predicted surface as well as a spherical registration to fsaverage space. Our model performs on par with other state-of-the-art DL methods on 1x1x1 mm3 T1w scans and outperforms the only other method capable of estimating cortical surfaces from low resolution, non-T1w scans. The predicted uncertainty, moreover, correlates with overall scan quality on low resolution scans and highlights areas of poor surface reconstruction on 1x1x1 mm3 T1w scans, suggesting that it can be used for quality control. Finally, the predicted spherical registrations prove comparable to other DL and classical registration methods. These qualities, when combined with the fast inference time, will provide the ability to analyze large, existing databases of clinical MRI scans, with the potential for finding disease-specific patterns that would otherwise be infeasible in a research setting.
Read the full abstract ▾
All authors Jesper Duemose Nielsen, Karthik Gopinath, Andrew Hoopes, Adrian Dalca, Axel Thielscher, Juan Eugenio Iglesias, Oula Puonti
Software Engineering
Software Testing Meets Bayesian Workflow: A Literature-Driven Artifact Study of Probabilistic Programs
Oleg Jarma, Maja Dall, Raúl Pardo et al. (+2 more)
Automated testing is an effective software quality assurance method, but it is rarely used for probabilistic models. This is despite the heavy use of probabilistic programming for data analytics in research and engineering, where the consequences of errors are dire. A key obstacle is the specification of testable correctness properties for probabilistic models, known as the oracle problem. Like machine learning, probabilistic programming is used precisely where no analytical specification exists: had we been able to write one, we would have written an
algorithm instead of fitting a model. An alternative is partial, proxy correctness specifications. The statistics literature already offers many, but as quality guidelines that require human judgment: comparing plots, visually analyzing shapes of distributions, assessing whether parameter values are ”far” or ”close enough”. These guidelines are not systematically automated. In this work, we elicit, implement, and study testable correctness properties of probabilistic models. We extract 17 broadly applicable properties for probabilistic models from one of the most widely used textbooks in
Bayesian data analysis, Statistical Rethinking by McElreath. For each property, we select and implement a test oracle, and study its utility for automatic testing, using a population of 59 probabilistic models from academic and industrial sources. We find realistic use cases (models under test) for all the properties. We observe that the vast majority of tests are not flaky in practice, despite the theoretical potential for flakiness. To the best of our knowledge, we are the first to investigate the effectiveness of mutation testing for probabilistic models, showing that standard mutation operators do not capture faults tracked by the probabilistic properties.
Read the full abstract ▾
All authors Oleg Jarma, Maja Dall, Raúl Pardo, Mahsa Varshosaz, Andrzej Wąsowski
Artificial Intelligence
Double-Rollout Reinforcement Learning with Sampling-based Reward Estimation
Haifeng Qian, David Mosallanezhad, Christian Munley et al. (+2 more)
Reinforcement learning with verifiable rewards (RLVR) implemented with Group Relative Policy Optimization (GRPO) has driven substantial progress in training
reasoning language models. However, verifiable outcome rewards provide an imperfect measure of
reasoning quality: a correct final answer may not be supported by the
reasoning trace, whereas an incorrect rollout may contain a nearly correct
reasoning trajectory. We present empirical evidence for this mismatch and hypothesize that the resulting reward noise contributes to instability in reinforcement learning for both
reasoning accuracy and
token efficiency. To address this credit assignment challenge, this paper proposes double-rollout reinforcement learning. For each sampled rollout, we truncate its
reasoning trace, sample multiple continuations from the truncated prefix, and replace the original reward with the mean continuation reward, yielding a more robust estimate of
reasoning quality. This double-rollout
algorithm incurs only a moderate increase in compute cost and yet reaches substantially higher accuracies across math and coding tasks and across Qwen and Nemotron models than baseline
algorithms with fewer RL steps. For example, using only DAPO data it trains Nemotron-3-Nano-30B-A3B to reach 95.4% on AIME 2026, versus 91.5% by GRPO and substantially above state of the art for this model size, within 30 RL steps. When combined with length-based rewards, the same
algorithm further improves the accuracy-efficiency Pareto frontier over existing efficiency optimizations. These findings suggest that the double-rollout reward estimation is an effective and cost-efficient way to improve both the accuracy and
token efficiency of
reasoning RL.
Read the full abstract ▾
All authors Haifeng Qian, David Mosallanezhad, Christian Munley, Adithya Renduchintala, Oleksii Kuchaiev
Distributed Computing
Prorsa: Unleashing the Potential of Prefill-Decode Disaggregation in Agentic Reinforcement Learning
Chiheng Lou, Xiangwei Deng, Bangjun Xiao et al. (+4 more)
Agentic reinforcement learning (RL) is commonly used to enhance the capabilities of large
language models (LLMs) in solving complex multi-turn tasks. During rollout, agentic RL exhibits a workload pattern distinct from that of traditional RL: multi-turn interactions repeatedly introduce prefill requests, causing prefill and decode workloads to coexist throughout rollout. This workload makes prefill-decode (PD) disaggregation, a design widely used for online LLM serving, promising for speeding up agentic RL rollout. This paper shows that PD disaggregation can improve rollout efficiency by (a) mitigating interference among data-parallel
attention modules, (b) enabling stage-specific parallelism, and (c) reducing end-to-end trajectory completion time. However, a fixed prefill-decode allocation may fail to sustain these benefits as workload composition varies across tasks and over time. We therefore present Prorsa, an agentic RL framework for prediction-guided prefill-decode resource allocation. Prorsa observes the lifecycle of every trajectory to forecast short-horizon prefill and decode demand. These forecasts then guide worker allocation decisions and trigger role switching of rollout engines, aligning prefill and decode capacity with anticipated workload demand. Across synchronous and asynchronous agentic RL settings, Prorsa achieves end-to-end rollout speedups of 1.11x-4.05x over prefill-decode colocation.
Read the full abstract ▾
All authors Chiheng Lou, Xiangwei Deng, Bangjun Xiao, Xiaodong Ji, Yikai Zhao, Xin Jin, Hailin Zhang
Computer Vision
JtT: Rethinking Point Trajectory Diffusion for Diverse and Rigid Motion from an Image
Gabrijel Boduljak, Yushi Lan, Christian Rupprecht et al. (+1 more)
We study forecasting rigid-body motion from a single image: generating diverse and physically plausible future trajectories for arbitrary points in a scene, without building rigidity into the architecture or relying on
geometric inputs such as depth. Like
video generators, recent trajectory generators fail at this task, even in simple synthetic Kubric scenes, despite scaling up model size and training on real data. We show how to solve this with the right architecture and parameterization. Our model, JtT, is a simple
diffusion transformer that operates directly in coordinate space and decodes arbitrary and dense query patterns, without the trajectory VAEs or fixed grids assumed in prior work. Through a systematic study of the design space of point trajectory
diffusion, we find that diffusing per-frame velocities is the only parameterization that captures rigidity, that it must be paired with the right timestep schedule, and that adding full-resolution RGB at the query points resolves the boundary failures of prior methods. However, evaluating such 2D models rigorously is itself non-trivial. To our knowledge, we are the first to observe that physical plausibility and diversity do not improve together during training: larger models, as used in prior work, memorize the single ground-truth future per training image, becoming more rigid while covering fewer possible futures. Yet prior work has paid little
attention to this, so we show how model rankings depend on model size, metric, and stopping time, and adopt a stricter, checkpoint-averaged evaluation protocol. Under this protocol, JtT improves over prior methods on both distributional and rigidity metrics and approaches ground-truth rigidity, with only about 50M parameters.
Read the full abstract ▾
All authors Gabrijel Boduljak, Yushi Lan, Christian Rupprecht, Andrea Vedaldi
Machine Learning
HyBRA-EEG: Hyperbolic Global-Local Brain-Region Aggregation for Self-Supervised EEG Representation Learning
Xin Liu, Feng Lu and Wei Li
Electroencephalography (
EEG) representation learning is challenged by noisy signals, inter-subject variability, and heterogeneous electrode montages in different
datasets and recording settings. Recent self-supervised
EEG pretraining methods improve transferability by converting heterogeneous recordings into unified
token or sequence representations, but channel-aware designs may still encode montage- or
dataset-specific regularities. We propose HyBRA, a self-supervised framework based on
hyperbolic global-local
brain-region aggregation. HyBRA maps heterogeneous channel observations into a fixed regional
token space by combining electrode coordinates, region priors, and feature-dependent
hyperbolic distances. A channel-evidence injection branch preserves fine-grained discriminative cues during aggregation. The resulting
tokens are processed by a Region-Time
Transformer and pretrained with masked reconstruction of latent features and region-level signals. HyBRA outperforms the compared methods in average balanced accuracy on six
benchmark datasets. Under a controlled six-fold evaluation on OpenBMI-MI, HyBRA matches CSBrain in balanced accuracy, improves AUROC by 1.84 percentage points and AUPRC by 5.23 percentage points, and uses 96.8% fewer parameters. Matched comparisons on TUAB and TUEV show higher balanced accuracy for
hyperbolic matching than for Euclidean distance or cosine similarity.
Read the full abstract ▾
Computer Vision
Code-Interactive Visual Reasoning for Financial Candlestick Understanding
Chenxi Zhang, Youwei Pang, Xiaoqi Zhao et al. (+4 more)
Financial candlestick understanding requires locating visual elements, aligning them across trading dates and panels, and combining observations through numerical and financial
reasoning. Answer accuracy alone does not reveal whether predictions are supported by chart evidence. We introduce Code-Interactive Financial Candlestick
Reasoning and present Fin-Thinker, a model based on Qwen3.5-9B that generates and executes code to acquire evidence and perform computations. The model uses the returned observations to guide subsequent
reasoning. To train these capabilities, we construct FinKLine-32K with 32,184 replay-verified code-observation trajectories collected through teacher-guided student exploration. These include successful solutions with and without error recovery. Our three-stage training framework combines foundational visual-code fine-tuning, financial process supervision of successful
reasoning and corrective continuations, and execution-feedback reinforcement learning. For evaluation, we introduce FinKLineBench with 1,200 questions across 138 financial task types to assess answer correctness, code execution, and evidence grounding separately. On FinKLineBench, Fin-Thinker improves strict accuracy by 13.1 and 33.2 percentage points over the best-performing direct-answer baseline among those evaluated and its base model with sandbox access, respectively. Training-stage ablations further show that financial process supervision and execution-feedback reinforcement learning yield successive improvements in both answer accuracy and GPT-5.6-judged grounded accuracy.
Read the full abstract ▾
All authors Chenxi Zhang, Youwei Pang, Xiaoqi Zhao, Ziliang Gan, Rongjunchen Zhang, Shanshan Feng, Hao Wang
Machine Learning
OctMole: Multiscale 3D Molecular Generation with Hierarchical Spatial Flows
Yu-Tong Jin, Yi-Yang Tian, Qiwei Ye et al. (+1 more)
Generating accurate 3D molecules requires jointly determining a variable number of atoms, their identities, and geometry across spatial scales: global shape emerges coarsely, whereas chemical bonds demand fine local precision. Existing atom-based
diffusion and flow models operate largely at a single scale, while dense spatial fields become costly at high resolution. We introduce OctMole, a multiscale octree flow framework for 3D molecular generation. A hierarchical occupancy flow progressively resolves sparse molecular support from coarse to fine, and a joint atom flow assigns atom types and continuous in-
cell offsets to occupied leaves. This decomposition combines efficient global structure with subcell
geometric precision, while
cell corruption improves robustness to generated support. On QM9 and GEOM-DRUG, OctMole achieves strong chemical, distributional, and
geometric quality, with particularly clear gains over Uni-3DAR on GEOM-DRUG and substantial efficiency gains over dense 3D generation. As an additional capability, intermediate occupancy states and selected regions provide spatial conditioning without task-specific retraining, supporting multiscale shape conditioning, regional editing, linker generation, and shape interpolation. Code and pretrained checkpoints are available at https://github.com/octree-nn/octmole and https://huggingface.co/Disembo/octmole, respectively.
Read the full abstract ▾
All authors Yu-Tong Jin, Yi-Yang Tian, Qiwei Ye, Peng-Shuai Wang
Machine Learning
Characterizing and Mitigating Distributional Bias in Physics-Informed Generative Models
Tanja Bien, Samir Darouich, Lluís Pastor-Pérez et al. (+3 more)
Physics-informed generative models augment a data-fitting objective with residual penalties that encourage physical constraints to hold in generated samples. However, improving constraint satisfaction need not improve fidelity to the data distribution. We study this conflict in residual-regularized
diffusion models and identify two possible consequences. First, the same prediction error can incur different residual costs near different feasible states, preferring states with lower residual sensitivity (avoidance). Second, this preference can extend to feasible states outside the data support, where the residual also vanishes (leakage). Motivated by this analysis, we propose a data-anchored penalty that weights prediction errors by the residual Jacobian at the clean training sample and normalizes the resulting magnitude. This removes the incentive to relocate to less sensitive states without changing the model architecture or sampling procedure. Experiments on a controlled synthetic system, three PDE systems, and molecular transition-state generation with flow matching demonstrate the benefits of anchoring. Code is available at https://github.com/TanjaBien/anchored_
diffusion.
Read the full abstract ▾
All authors Tanja Bien, Samir Darouich, Lluís Pastor-Pérez, Vinh Tong, Loay Mualem, Mathias Niepert
Sound
LLM-HB: Language-Aware LLM-Guided Hotword Biasing for Code-Switching ASR
Yuxuan He, Genshun Wan, Pengcheng Li et al. (+3 more)
Code-switching (CS)
speech, characterized by
language alternation within a single utterance, is prevalent in multilingual communities and poses challenges to automatic
speech recognition (ASR) due to rapid
language transitions. We propose LLM-HB, a
language-aware large
language model-guided hotword biasing framework for code-switching ASR (CS-ASR). The framework incorporates a mixture-of-experts (MoE) adaptor and an auxiliary
language prediction head to better capture and differentiate multilingual representations, while hotwords are injected through LLM-based prompting. Experiments on the ASRU2019 code-switching challenge test set demonstrate that LLM-HB achieves a 20.30% relative reduction in mixed error rate (MER) over the baseline, reaching 5.85% MER under a 15-distractor hotword setting. To the best of our knowledge, this is the first work to integrate LLM-guided biasing into code-switching ASR. We further release the extracted ASRU2019 hotword list to support future research.
Read the full abstract ▾
All authors Yuxuan He, Genshun Wan, Pengcheng Li, Gongping Huang, Jianqing Gao, Yanmin Qian
Computer Vision · Cross-listed from stat.ML
Variational Filtering for Bayesian Last Layers with an Independent Binary Probit Surrogate
Dimitrije Markovic, Conor Heins, Alexander Tschantz et al. (+1 more)
Modern deep classifiers trained by gradient descent need many passes over the data to become accurate, and even then are not always well calibrated; post-hoc temperature scaling corrects calibration after training but cannot influence training-time accuracy or convergence. We propose a variational filtering
algorithm for the last layer of deep classifiers, whose parameters are treated as the latent state of a linear-Gaussian state-space model. Each mini-batch is assimilated by an exact prediction step followed by a closed-form variational update, made conjugate by an independent binary probit (IBProbit) surrogate for the categorical likelihood. The filter's process noise stabilises the updates under feature drift and keeps the predictive distribution from collapsing to a point estimate, allowing the same procedure to be used for linear probing on a frozen backbone and for full-network fine-tuning. We evaluate on DINOv3 backbones against two baselines tuned under an identical protocol: AdamW with cross-
entropy and post-hoc temperature scaling, and Variational
Bayesian Last Layers (VBLL). As a linear probe on frozen features, IBProbit attains the best accuracy and negative log-likelihood on all five downstream tasks at the largest backbone, and on two of the five at the smallest. In out-of-distribution detection with CIFAR probes on the largest backbone, IBProbit reduces the false-positive rate at 95% true-positive rate by a factor of 1.4 to 3.2 relative to the better of the two baselines, on all three
dataset pairs. When the whole network is fine-tuned on ImageNet-1k, IBProbit reaches the final performance of the cross-
entropy baseline in half the wall-clock time.
Read the full abstract ▾
All authors Dimitrije Markovic, Conor Heins, Alexander Tschantz, Christopher L. Buckley
Computer Vision
CineRecon: Benchmarking Frontier Models for Agentic Cinematic Reconstruction
Jialei Wang, Zehan Wang, XiaoYang Wu et al. (+6 more)
Reconstructing reference
videos as editable dynamic 3D scenes is an important path toward controllable
video generation for filmmaking: these scenes provide modifiable, renderable visual proxies that enable explicit control over scene layout, subject actions, and camera behavior. To evaluate
agents' ability to reconstruct editable dynamic 3D scenes from dynamic reference
videos, we introduce CineRecon, a
benchmark comprising 50 reference
videos and 360 annotated evaluation clips. The reference
videos span film, real-world footage, and games. Given a complete
video, an
agent uses tools to construct, animate, render, and refine its reconstruction. We evaluate this task under three representation settings: Proxy, Simplified, and Detailed. These settings increase
geometric and appearance requirements while retaining the same requirements for spatial relations, camera behavior, and subject dynamics. This design tests whether
agents can reproduce the events in a
video when detailed appearance is unnecessary, and how performance changes as representation requirements increase. For evaluation, we construct checklists that associate observable properties and events with specific entities and times. A
vision-
language judge compares timestamp-aligned reference and rendered frames across 11 categories, grouped into camera, static, and dynamic consistency dimensions. We evaluate 12 models using their corresponding
agent harnesses and find failures across all three dimensions. Subject motions and interactions remain difficult to reproduce even under the Proxy setting.
Read the full abstract ▾
All authors Jialei Wang, Zehan Wang, XiaoYang Wu, Ziang Zhang, Siyu Chen, Jiaer Huang, Yujia Zhang, Tianyu Pang, Hengshuang Zhao
Systems and Control
NANO: A Unified Optimization Framework for Nonlinear Gaussian Filtering
Zhenxuan Ma, Haoning Wang, Wenhan Cao et al. (+1 more)
Conventional Gaussian filtering typically approximates nonlinear models or their statistical moments and retains the Kalman update structure. The resulting approximation errors can affect both state estimates and their uncertainty. This paper presents the Natural Gradient Gaussian Approximation (NANO) framework for nonlinear filtering. Both prediction and measurement update are formulated as optimization problems over Gaussian distributions, with the entire Gaussian distribution serving as the optimization variable. The framework integrates observation losses, distributional discrepancies, natural-gradient optimization, and finite-step update rules, providing a unified formulation for constructing different filters. Natural-gradient iterations account for the geometry of the Gaussian family and jointly update the distribution parameters. The framework incorporates the existing NANO-P method using the Kullback-Leibler divergence and introduces NANO-W using the Wasserstein distance. NANO-P maintains covariance positive definiteness through a positive-semidefinite
curvature approximation, while NANO-W uses a covariance transport update that accommodates indefinite
curvature. Their update rules and sufficient conditions for covariance positive definiteness are established within the common framework. Through these two realizations, the proposed framework achieves the best estimation accuracy among the evaluated methods on each of six
benchmarks. Runtime evaluations further assess its computational feasibility for practical applications.
Read the full abstract ▾
All authors Zhenxuan Ma, Haoning Wang, Wenhan Cao, Shengbo Eben Li