Artificial Intelligence
DARS: Dual-Level Credit Assignment RL with Structured Reasoning for Instruction-Based Image Editing
Haoxiang Cao, Jiajiong Cao, Xuanpu Zhang et al. (+2 more)
Instruction-based image editing uses a planner-renderer pipeline: a
vision-
language model (VLM) first converts the instruction into an edit plan, and a
diffusion model then executes that plan. Training such systems with only final-image rewards is inefficient because a poor edit does not reveal whether additional optimization should place more emphasis on the planner or the renderer, and even planner-dominant cases remain difficult to localize within a free-form
reasoning trace. We present DARS, a reinforcement learning framework for dual-level credit assignment in this two-stage setting. Across modules, multi-plan multi-render rollouts estimate between-plan and within-plan reward variability for soft module routing, while rollout mean rewards provide hardness estimates for an adaptive curriculum. Within the planner, a four-field structured
reasoning output enables a prefix-gated reward and
token-level advantage reweighting, turning outcome-level feedback into localized supervision. Experiments on five
benchmarks show that DARS outperforms a Joint~RL baseline with the same backbone, data, reward model, and rollout budget, with the largest gains on
reasoning-intensive edits.
Read the full abstract ▾
All authors Haoxiang Cao, Jiajiong Cao, Xuanpu Zhang, Changqian Yu, Chaoqun Wang
Cryptography and Security
Chameleon: Robust Defense Against Tor Website Fingerprinting via Many-to-Many Traffic Morphing
Yuwen Cui, Kai Wei, Kehan Shen et al. (+4 more)
Website fingerprinting (WF) attacks can infer users' browsing activities from encrypted Tor traffic by exploiting side-channel features. Although many WF defenses have been proposed, we find that most existing defenses create learnable web trace mapping features. We further show that robustness against
adversarial training does not necessarily imply robustness against defense-aware autoencoder (DAAE)-based attacks. To address these limitations, we present Chameleon, a robust WF defense based on many-to-many randomized traffic morphing. Chameleon selects morphing candidates with high intra-class diversity and low inter-class disparity. Chameleon randomly maps each webpage trace to multiple candidates, and allows different webpages to share morphing targets, thereby increasing
adversarial uncertainty. For practical Tor deployment, Chameleon introduces a radix-trie-based synchronization mechanism that enables pluggable transport (PT) endpoints to identify consistent morphing traces using packet-direction prefixes, together with trace mutation and normalized prefix matching to reduce overhead. We evaluate Chameleon against six state-of-the-art defenses and five WF attacks on three public
datasets in closed- and open-world settings. Compared with Adaptive Tamaraw, Chameleon reduces
adversarial-training-based attack accuracy by up to 36.74% while reducing bandwidth and time overhead by 34.12% and 60.38%, respectively. Under DAAE-based RF attacks on GTT23, Chameleon limits attack performance to 35.19% F1-score while Adaptive Tamaraw only limits it to 88.22% F1-score. In the real-world PT bridge evaluation, Chameleon substantially reduces the effectiveness of strong WF attacks while incurring only 16.25% time overhead.
Read the full abstract ▾
All authors Yuwen Cui, Kai Wei, Kehan Shen, Ning Wang, Zhuo Lu, Yao Liu, Guangjing Wang
Numerical Analysis
Numerical Study of a Surface Growth Model with Singular Noise
Dirk Blömker, David Buchberger and Johannes Rimmele
We study a
stochastic model for epitaxial thin-film growth driven by spatially rough additive noise in a regime where the noise is singular and regularization via truncation in
Fourier space is used to give a meaning to the solution, leading to a vanishing nonlinearity in the limit. In order to study this phenomenon numerically, the nonlinearity is discretized by a spectral Galerkin projection, while time integration is performed with an exponential Euler scheme. For roughness stronger than space-time white noise, we derive strong error estimates in $L^p(\Omega;C([0,T];\mathcal H^1))$ that display explicitly the interaction between the spatial cut-off, the time step, and the decay of the nonlinear current. We also quantify the growth of the truncated
stochastic convolution and the corresponding vanishing rate of the nonlinearity. Numerical experiments illustrate the transition from persistent hill formation to noise-dominated dynamics as the roughness parameter increases.
Read the full abstract ▾
Computer Vision
G3Ego: Gaze-Guided Graphs for Egocentric Action Understanding
Marko Haralović, Akash Ramakrishnan and Estefania Talavera Martinez
Egocentric action understanding is often addressed using large
video models pretrained on extensive exocentric
datasets. However, many first-person actions depend on a small number of hand-object interactions involving only a few relevant entities. We propose G3Ego, a graph-based framework for
egocentric action understanding that uses gaze as a structural cue to identify action-relevant entities in the scene. From sparsely sampled frames, G3Ego constructs action scene graphs from
vision-
language descriptions, grounded objects, and hand cues, and then prunes irrelevant entities using the camera wearer's gaze. The resulting graph
embeddings are temporally aggregated for action recognition and anticipation. Unlike prior work that uses gaze primarily as an auxiliary modality or
attention signal, G3Ego incorporates gaze directly into graph construction, producing efficient and interpretable representations focused on action-relevant interactions. Experiments on EGTEA Gaze+ and MECCANO show that G3Ego achieves competitive performance compared with
video-based approaches and consistently improves Macro-F1 under class-imbalanced evaluation, while avoiding reliance on computationally expensive
video pretraining. These results demonstrate the effectiveness of gaze-guided graph representations for
egocentric action understanding.
Read the full abstract ▾
Computer Vision
Artificial Intelligence for Workflow Analysis in Colorectal Surgery: A Multicentric, Cross-Procedural Development and Generalization Study
Pietro Mascagni, Julia Alekseenko, Pooja P Jain et al. (+10 more)
Minimally invasive colorectal surgeries (MIS-CRS) are characterised by significant variability and inconsistent outcomes. ColoWorkflow, a tool for the
video-based assessment (VBA) of MIS-CRS workflow, was recently validated. However, manual VBA is time-consuming, limiting implementation. This study presents AI-ColoWorkflow, a deep learning model for automated
surgical workflow analysis across MIS-CRS. Operative
videos of MIS-CRS were collected from 4 centres and a publicly available
dataset. Phases and steps were manually annotated according to ColoWorkflow. A deep learning model combining a fine-tuned DINOv3
vision transformer for per-frame visual feature extraction with a hierarchical multi-stage temporal convolutional network was jointly optimized for phase and step recognition. The model trained on pooled multicentric data, namely AI-ColoWorkflow was compared against centre-specific and procedure-specific models on a held-out test set. The following metrics were used for evaluation: macro F1 score, balanced accuracy, precision, and recall. AI-ColoWorkflow achieved a macro F1 of 73.01% $\pm$ 10.27 (balanced accuracy 73.43%) for phase recognition and 39.82% $\pm$ 7.06 (balanced accuracy 38.65%) for step recognition. The global model outperformed centre- and procedure-specific models in most experiments except procedure-specific step recognition. In the generalization analysis, mean F1 was 48.42% for phase recognition. AI-ColoWorkflow can reliably recognize MIS-CRS phases. A single model trained on pooled, multicentric, multi-procedural data generalises at least as well as and often better than centre- or procedure-specific models for phase recognition in MIS-CRS, while procedure-specific step models retain advantages for certain procedure types, motivating hybrid training strategies for future
surgical AI development.
Read the full abstract ▾
All authors Pietro Mascagni, Julia Alekseenko, Pooja P Jain, Marta Goglia, Andrea Balla, Ludovica Baldari, Gianfranco Silecchia, Claudio Fiorillo, Vincenzo Tondolo, Salvador Morales-Conde, Luigi Boni, Sergio Alfieri, Nicolas Padoy
Computation and Language
FormalTCS: Benchmarking End-to-End Frontier Formal Theoretical Computer Science Research of Large Language Models
Dingzirui Wang, Xuanliang Zhang, Keyan Xu et al. (+2 more)
Large
language models (LLMs) have shown growing potential for automated theoretical computer science (TCS) research, yet existing
benchmarks remain far from realistic research settings. We introduce \ourbenchmark, an expert-validated
benchmark for evaluating LLMs on frontier, end-to-end TCS research. \ourbenchmark contains $143$ instances drawn from papers accepted to STOC, FOCS, SODA, and COLT in 2025-2026, preserving paper-specific definitions, assumptions, and proof dependencies, with expert-verified Lean formalizations and proofs. Evaluations of leading LLMs reveal that current models remain far from reliably completing the full research pipeline. In particular, autoformalization is the sharpest bottleneck: the best model achieves only $11.5$ on translating natural-
language claims into formal
theorem statements, compared with $28.6$ Pass@8 when proving human-provided formal statements. Building on \ourbenchmark, we further develop an automated TCS research framework that generates, formalizes, filters, and proves new claims. Of $64$ generated claims, only $6$ ultimately pass expert evaluation and proof verification, indicating that beyond formalization, limited research taste remains another major barrier to autonomous TCS research.
Read the full abstract ▾
All authors Dingzirui Wang, Xuanliang Zhang, Keyan Xu, Qingfu Zhu, Wanxiang Che
Information Theory
The Generalized Random Access Problem for Linear Codes
Anina Gruica, Antonio Petrillo and Ferdinando Zullo
Random access is a central requirement in DNA-based storage systems: one would like to recover selected information symbols without sequencing the whole encoded object. A recent combinatorial model associates to a generator
matrix $G\in F_q^{k\times n}$ the random variable $\tau_i(G)$, measuring the number of sampled columns needed to recover the information vector $e_i$. We study the cardinality-based extremal and finite-
geometric aspects of simultaneous multi-symbol recovery. For a nonempty set $I\subseteq[k]$, let $\tau_I(G)$ denote the number of random column samples needed until all vectors $e_i$, $i\in I$, lie in the span of the observed columns. This variable interpolates between the singleton random access problem and the full-recovery problem underlying coverage depth. For each $m$, we introduce uniform worst-case and average parameters over all requested sets $I$ with $|I|=m$. Using the known subset-counting formula for $E[\tau_I(G)]$, we establish general upper and lower bounds for these parameters. In particular, the lower bounds are expressed through order statistics of the singleton recovery variables and specialize to the known singleton bounds when $m=1$. For systematic MDS encoders, we record an equivalent form of the known multi-symbol expectation formula and derive monotonicity and asymptotic consequences. For simplex encoders in arbitrary dimension, we obtain closed formulae in terms of Gaussian binomial coefficients; the full-recovery endpoint agrees with the known coverage-depth formula for simplex codes. Finally, in dimension three we study balanced quasi-arcs and compare their values with the simplex and MDS
benchmarks.
Read the full abstract ▾
Networking
Using Zone-Disjoint Multi-Path Routing Algorithm for Video Transmission over Ah-Hoc Networks
Ali Asghar Khavasi and Nastooh Taheri Javan
Finding multi-path routes in ad hoc networks due to their grid
topology seems to be a trivial task, but because of CSMA/CA effects in these networks found paths are not completely disjoint unless an appropriate
algorithm have taken into account. If such an
algorithm provided and designed carefully it could improve multi-path
video transmission over these kinds of networks. By using node-disjoint paths, it is expected that the end-to-end delay and BER in each case should be independent of each other. However, because of natural properties and medium access mechanisms in ad hoc networks the end-to-end delay and also BER between any source and destination depends on the pattern of communication in the neighborhood region. In this case some of the intermediate nodes should be silent to reverence their neighbors and this matter increases the end-to-end delay. To avoid this problem, multi-path routing
algorithms can use zone-disjoint paths instead of node-disjoint paths. In this paper we demonstrated a new multi-path routing
algorithm that selects zone-disjoint paths that in addition used for
video multi-path transmission over ad hoc networks. It is shown that by using this new
algorithm along with choosing an appropriate scheme for
video transmission over discovered paths, our approach receives enhanced results comparing previously used
algorithms.
Read the full abstract ▾
Neural and Evolutionary Computing
Petri Net Description of Biological Neural Circuits for Fast Hardware Prototyping
Carlo daCunha, Rodrigo Pena and Marcos Turqueti
Current approaches to simulating biological neural
circuits, whether on general-purpose hardware or dedicated neuromorphic platforms, remain constrained by fixed-timestep numerical integration, hardware-imposed precision limits, and an inability to guarantee timing correctness for event-driven spiking dynamics under real-time constraints. Here, we propose a Petri net description of biological neural
circuits that overcomes these limitations by modeling
neurons, synapses, and spike events as a T-timed Petri net with formally verifiable timing semantics, enabling deadline-guaranteed real-time execution and analytically tractable correspondence to continuous-time leak-integrate-and-fire dynamics, independent of the underlying integration timestep. To test the model, we present the results of three simulated microcircuits: feedback inhibition, lateral inhibition, and hierarchical feature detector. The Petri
neuron reproduces the expected dynamical signatures of each
circuit while providing formally bounded timing guarantees throughout, with worst-case response times matching analytical predictions across all three cases.
Read the full abstract ▾
Cryptography and Security
Trustworthy mobile edge caching: a blockchain approach to mitigate malicious nodes and incentivize cache sharing
Motahare Ebrahimi, Nastooh Taheri Javan, Seyedakbar Mostafavi et al. (+1 more)
As mobile network traffic continues to grow, content caching on edge servers is critical for reducing latency. However, challenges such as malicious edge servers that may delete or manipulate cached content, along with the limited capacity of these servers, need to be addressed. To overcome the capacity limitations, helper mobile nodes can contribute their cache resources. However, due to their selfish behavior, an incentive mechanism is necessary to encourage resource sharing. Additionally, these helper nodes can also be malicious. This paper proposes a blockchain-based trust management mechanism that addresses these challenges by accurately identifying trustworthy edge servers and mobile nodes. The proposed mechanism calculates both direct and indirect trust using smart contracts, ensuring that malicious nodes are effectively filtered out. Trustworthiness is determined based on mobile node satisfaction with the quality of service, and trust data is securely stored on the blockchain. To combat node selfishness, a reward mechanism is introduced to incentivize cache sharing. Furthermore, a blockchain-based authentication mechanism protects against node impersonation. Our approach optimizes trust, cache capacity, and cost efficiency while considering mobile node mobility, energy consumption, and computational power constraints during the consensus process. Simulation results show that the proposed method can accurately distinguish between honest and malicious servers, even with a 10% noise in data.
Read the full abstract ▾
All authors Motahare Ebrahimi, Nastooh Taheri Javan, Seyedakbar Mostafavi, Fatemeh Pakzaban
Computer Vision
PelviNeXt: A Modality-Agnostic Hybrid Network for Pelvic Imaging in Women's Health
Siam Tahsin Bhuiyan, Rashedur Rahman, Sefatul Wasi et al. (+5 more)
Women's health remains substantially under-resourced in medical imaging research, with pelvic pathologies such as polycystic ovary syndrome (PCOS) and pelvic fracture both suffering from a scarcity of public, well-annotated
benchmark data despite their clinical importance. We introduce PelviNeXt, a modality-agnostic hybrid architecture combining a dense convolutional feature extractor, hierarchical channel-spatial
attention (H-CBAM), a multi-scale fusion module (MSFM), and talking-heads multi-head self-
attention (TH-MHSA), applied without modification to both pelvic ultrasound and X-ray inputs. While benchmarking PelviNeXt on PCOSGen, the only gynaecologist-annotated public PCOS ultrasound
dataset, we identified extensive exact and near-duplicate contamination within and across the
dataset. We audit this contamination via perceptual hashing, publicly release a deduplicated version of the
dataset, and establish the first integrity-audited evaluation protocol and baseline for PCOSGen under 5-fold cross-validation. On the only publicly available pelvic fracture X-ray
dataset (PXR150), PelviNeXt exceeds previously reported state-of-the-art results across accuracy, recall, specificity, and AUROC. Ablation studies confirm that each architectural component contributes to performance on both tasks. Our results demonstrate that a single architecture, applied without task-specific modification, can serve as a reliable foundation for pelvic imaging across modalities in data-scarce, under-researched areas of women's health.
Read the full abstract ▾
All authors Siam Tahsin Bhuiyan, Rashedur Rahman, Sefatul Wasi, Halima Khatun, Ashraful Islam, AKM Mahbubur Rahman, Saadia Binte Alam, M Ashraful Amin
Computer Vision
DPC-Net: Dual-Prior Collaborative Network for All-in-One Image Restoration
Zhaokun He, Kangbiao Shi, Axi Niu et al. (+4 more)
All-in-One Image Restoration (AiOIR) aims to handle diverse degradations within a unified model. However, existing methods often overlook image semantics in degradation modeling and lack low-level visual priors during reconstruction, leading to structural distortions and semantic inconsistencies. To address these issues, we propose a novel Dual-Prior Collaborative Network (DPC-Net), which achieves high-quality restoration by jointly exploiting degradation-semantic coupled priors and low-level visual priors. Specifically, degraded images are fed into a Degradation-Aware Network (DAN) to extract degradation-semantic coupled features. To this end, a
Vision-
Language Model (VLM) supervises DAN by constraining its features distribution, introducing image semantics into the encoding of degradation patterns. A Degradation-Semantic Modulation Module (DSMM) further translates this guidance into degradation-semantic coupling and propagates coupled representations to the decoder. During decoding, knowledge bases provide low-level visual priors, and the Dual-Prior Collaborative Reconstruction Module (DPCR) integrates dual-prior information to guide degradation removal while preserving structure and semantics, producing high-fidelity restored images. Extensive experiments on multiple restoration
benchmarks demonstrate that DPC-Net achieves superior performance against state-of-the-art AiOIR methods.
Read the full abstract ▾
All authors Zhaokun He, Kangbiao Shi, Axi Niu, Jian Jin, Peng Wu, Wei Dong, Qingsen Yan
Programming Languages
Formal Performance and Compile Time Guarantees for Compiler Optimization Heuristics
Nikil V. Shyamsunder
Modern optimizing compilers rely on heuristic search
algorithms for NP-hard optimization problems, which can result in poor generated-code performance and long or unpredictable compile times. These are considered bugs by users, but verified compilers rarely reason beyond semantic preservation. We propose verifying performance and compile time properties of compiler passes. As a proof-of-concept, we formulate inline expansion using a cost model estimating instruction-cache performance. We mechanize this in Rocq, prove semantic preservation of the inlining transformation, and verify the
algorithm's monotone improvement, convergence-time bound, and performance bounds for intermediate and final solutions.
Read the full abstract ▾
Computer Vision
Joonas Järve, Halil Ibrahim Aysel, Tarun Khajuria et al. (+1 more)
We present a novel view on feature
evolution in
Vision Transformers (ViTs) by visualizing the training process over two dimensions – network depth (layer) and training time (epochs). We employ Sparse Autoencoders (SAEs) to extract candidate sparse features from CLS-
token representations and compare their activation profiles across epoch–layer pairs. This allows us to study feature-level dynamics that are not directly visible from representation-level similarity measures. Furthermore, we demonstrate how this framework of feature
evolution allows us to describe feature migration, the change in the layer where a feature is most detectable during training. Our experiments show that migration is concentrated early in training, occurs more often toward earlier layers than toward deeper layers, and declines as feature organization stabilizes. We further find that deeper layers stabilize earlier and more strongly than shallow layers. The results show that our approach can be employed as a tool for understanding how ViTs learn and evolve.
Read the full abstract ▾
All authors Joonas Järve, Halil Ibrahim Aysel, Tarun Khajuria, Meelis Kull
Multiagent Systems
Multi-Agent Orchestration with the Common-Sense Reasoning Capabilities of LLMs for Autonomous Driving
Mehdi Azarafza, Faezeh Pasandideh, Ali Ehteshami Bejnordi et al. (+2 more)
Autonomous vehicles require robust perception and decision-making capabilities to operate in diverse and unseen scenarios. While reinforcement learning and rule-based methods can provide effective control and safety mechanisms, their performance may degrade in situations requiring contextual
reasoning. Large
Language Models (LLMs) have demonstrated strong capabilities in understanding
multimodal information and generating contextual
reasoning, however, their use for direct vehicle control can introduce latency and
hallucination risks. To address these limitations, a hybrid framework is proposed. This system uses an orchestrator to coordinate PPO-trained reinforcement learning and PID control, with LLM common-sense
reasoning applied throughout the framework. LLM
reasoning is further employed iteratively to refine the RL reward function for dynamic driving environments. The proposed framework is evaluated in highly randomized CARLA scenarios under diverse environmental and traffic conditions. The results demonstrate the potential of integrating LLM-based
reasoning with conventional autonomous driving methods while retaining structured control and safety mechanism.
Read the full abstract ▾
All authors Mehdi Azarafza, Faezeh Pasandideh, Ali Ehteshami Bejnordi, Stefan Henkler, Achim Rettberg
Human-Computer Interaction
Navigating and Retrieving Information in Immersive Model-Based Design Reviews: An Exploratory Study
Victor Romero, Romain Pinquié and Frédéric Noel
Digital engineering uses many models from different perspectives, creating a connected set of digital artefacts across a product's life cycle. Designers seeking a holistic view must navigate numerous models and views, requiring domain-specific software,
languages, and representations. This can lead to getting lost in scattered information and the cognitive burden of mentally integrating details across diagrams. To overcome these issues, we developed the virtual environment GraphXplore. GraphXplore enhances perceptual and conceptual integration by linking all relevant visual items from different perspectives into an interactive, layered 3D graph displayed in virtual reality, providing a holistic view of the system. We compared GraphXplore with a conventional on-screen setup using a PowerPoint slide deck with model screenshots viewed on a desktop PC. In an experiment with N=33 volunteers (mainly industrial product design postgraduates and professors), we conducted a baseline usability study focused on fundamental information
retrieval tasks for model-based design comprehension, as identifying basic model elements is the fundamental prerequisite in design reviews. Our findings indicate that for simple
retrieval tasks, the correctness of answers, completion time, recall score, and perceived confidence are comparable in both environments. However, the virtual environment demonstrated practical advantages, achieving a "good" average System Usability Scale (SUS) score of 73.1 compared to the slide setup's borderline score of 66.4. Furthermore, GraphXplore users reported a lower perceived cognitive workload (mean NASA-TLX score of 43.8) compared to the traditional setup (50.4). Future work will enhance this experiment to yield empirical results across massive industrial
datasets, refine GraphXplore, and extend to new design review objectives.
Read the full abstract ▾
Computer Vision
ID-VTG: Image-Disambiguated Video Temporal Grounding
Minghang Zheng, Jingli Wei, Hongyi Yang et al. (+1 more)
Video Temporal Grounding (VTG) faces significant challenges when natural
language queries must distinguish between multiple events involving visually similar entities, particularly when relying on fine-grained visual attributes that are difficult to describe accurately in words alone. To address this, we introduce Image-Disambiguated
Video Temporal Grounding (ID-VTG), a task that leverages
multimodal queries combining a reference image and a text description to precisely localize segments where a specific instance performs a described action. To facilitate research, we construct two
benchmarks: IDVTG-Gym, focusing on fine-grained, compositionally ordered gymnastics actions with athletes in similar uniforms; and IDVTG-InternVid, an open-world
dataset featuring diverse entities (e.g., humans, animals, fictional characters) and significant temporal distractors. Methodologically, we propose the Visually-Guided Disambiguation Aggregation (VGD-Agg) framework based on a dual-branch fast-slow architecture. The fast branch efficiently generates preliminary event proposals, while the slow branch performs fine-grained frame-level matching between
video frames and the reference image. We enhance discriminability via two learnable
tokens: a Compare
Token, which represents hard negatives to probe for the presence of the target instance (as referred to by the query image), and a Depress Value, which represents text-irrelevant events. Proposals that the Compare
Token identifies as lacking the target instance are pushed toward the Depress Value, thus easing disambiguation via the text query. Extensive experiments validate our approach, which achieves state-of-the-art results on the proposed
benchmarks. Code is available at https://github.com/oceanflowlab/ID-VTG.
Read the full abstract ▾
All authors Minghang Zheng, Jingli Wei, Hongyi Yang, Yang Liu
Information Theory
RMWorld: Task-Aware Radio World Models with Value-of-Information Guided Multi-Trial Learning for Multi-UAV Communication Control
Xiucheng Wang, Nan Cheng and Junxi Huan
Reliable multi-
UAV communication control depends on predicting which aerial links will serve traffic before measurements are available.
Radio world models (
radio WMs) make such planning tractable, but their errors are nonuniform: a globally accurate model may still fail along high-demand corridors or association boundaries where rate errors reverse control decisions. This mismatch creates a learning challenge. Link queries must reduce decision-relevant channel uncertainty, while counterfactual trials must be filtered so that biased rollouts do not corrupt the policy. Existing acquisition and model-based control treat these budgets separately, valuing uncertainty, coverage, or optimistic return rather than risk reduction. We present RMWorld, a task-aware
radio-WM framework that couples value-of-information channel calibration with credibility-diversity multi-trial selection. A biased propagation formula is corrected by a
Bayesian residual, and each link is valued by its exact one-label reduction in locally linearized task-integrated posterior rate variance. Counterfactual branches are selected by a task-gated log-determinant objective, followed by conflict projection and fixed-batch validation. We derive the variance-reduction identity, prove posterior task-risk equivalence and the submodular greedy guarantee, and establish a scoped first-order non-interference result. Across 100 paired 3GPP trials RMWorld reaches 0.949~bit/s/Hz task-weighted RMSE, and across 30 severe-load DeepMIMO trials it reduces median backlog by 0.967 versus Ensemble UCB at 37.5% more offline rollouts.
Read the full abstract ▾
Machine Learning · Cross-listed from stat.ML
Discrete Diffusion Inference-Time Control with Nested Sequential Monte Carlo
Lohithsai Yadala Chanchu, Hany Abdulsamad and Christian A. Naesseth
We study inference-time control for text generation in discrete
diffusion language models, where the goal is to steer sampling toward sequence-level rewards without retraining. Prior work in this domain has focused on particle-based methods such as best-of-$n$ sampling and bootstrap sequential Monte Carlo, which may suffer from overoptimism and weight degeneracy, respectively. We address these limitations using nested sequential Monte Carlo methods. We formulate nested SMC (NSMC) and fully-adapted nested SMC (FA-NSMC) for Feynman–Kac steering, identifying and correcting errors in prior formulations that lead to biased final estimates. We evaluate these methods on toxicity and fluency steering tasks, showing that NSMC and FA-NSMC consistently outperform best-of-$n$ and bootstrap SMC.
Read the full abstract ▾
Computer Vision
ArmorOCR: Grounded Adversarial Visual Perception via Observation-Transferred Self-Distillation
Linhan Cao, Siyuan Li, Jun Lan et al. (+8 more)
Large
multimodal models (LMMs) have demonstrated strong OCR recognition capabilities, yet remain vulnerable to
adversarial visual text that is readable to humans but challenging for models to localize and recognize. Existing OCR
benchmarks mainly focus on natural or document-style text, while
adversarial OCR evaluations remain limited in scale, task coverage, or region-aware evaluation. In this paper, we formulate
adversarial OCR as a grounded OCR perception task and introduce AdvSpot, the first
benchmark for grounded
adversarial OCR evaluation. AdvSpot comprises 390 images with region-level annotations, spanning 5 primary categories and 13 fine-grained
adversarial OCR types. To address this challenge, we propose ArmorOCR, a two-stage training framework for robust
adversarial OCR perception. ArmorOCR first acquires missing
adversarial OCR perception from privileged transformed observations through On-Policy Self-
Distillation (OPSD), and then refines grounded OCR perception through Group Relative Policy Optimization (GRPO) with task-conditioned rewards for localization, recognition, full spotting, and visual question answering (VQA). Experiments on our AdvSpot, other
adversarial OCR
benchmarks, and general OCR
benchmarks demonstrate that ArmorOCR consistently improves
adversarial OCR perception while preserving competitive general OCR capability.
Read the full abstract ▾
All authors Linhan Cao, Siyuan Li, Jun Lan, Liangbo He, Guannan Li, Xiaolei Huang, Jun Jia, Shuheng Zhou, Huijia Zhu, Weiqiang Wang, Wei Sun
Systems and Control
Performance-Guaranteed Reference Tracking With Power Directionality Constraints: Application to Controlled Stochastic Watersheds
Jonathan Shell, Sepehr Moalemi, Branko Kerkez et al. (+1 more)
Modern stormwater infrastructure faces increased demands that require a corresponding increase in capacity. Traditionally, these demands have been met by constructing new infrastructure assets, which is a costly endeavor. More recently, many system operators have achieved great success in employing feedback control techniques to improve system performance. However, the resulting closed-loop system exhibits power directionality constraints that introduce nonlinear constraints in feedback synthesis. In this work, we develop a
stochastic control synthesis procedure with provable performance bounds on mean-square reference tracking for a general class of problems in which power directionality constraints arise. The proposed method is then applied to a flood mitigation example using a numerical model of a real-world smart water system. The key result is an extension of the performance-guaranteed control (PGC) framework, which was originally designed for disturbance rejection, to accommodate reference tracking control objectives.
Read the full abstract ▾
All authors Jonathan Shell, Sepehr Moalemi, Branko Kerkez, Jeff Scruggs
Cryptography and Security
Privacy-Preserving Detection of Rare Disease-Associated Cell Subsets via Secure Multi-Party Computation
Ş. Selcan Magara, Esther Havemann, Debora Jutz et al. (+2 more)
The detection of rare disease-associated
cell subsets from high-dimensional single-
cell measurements is critical for understanding diseases such as leukaemia and viral infections. CellCnn, a convolutional neural network (CNN) designed for this task, has demonstrated the ability to identify phenotype-associated
cell populations at frequencies as low as 0.01%. Training such models reliably requires patient cohorts that are larger and more diverse than any single institution can typically assemble, and the underlying single-
cell data is too sensitive to share across institutional boundaries under existing
privacy regulations. We propose a secure multi-party computation (MPC) framework that enables the training and inference of CellCnn entirely on secret-shared data. This ensures that neither the participants nor the computing servers ever observe raw patient data or intermediate values. Evaluated on
benchmark single-
cell datasets for cytomegalovirus infection (CMV) and acute myeloid leukaemia (AML), our implementation preserves accuracy close to its plaintext counterpart while outperforming the prior
privacy-preserving baseline. In contrast to earlier
privacy-preserving approaches that removed components such as ReLU activations and bias terms, our method retains these key parts of the CellCnn architecture and supports accurate analysis without exposing raw patient data.
Read the full abstract ▾
All authors Ş. Selcan Magara, Esther Havemann, Debora Jutz, Ali Burak Ünal, Mete Akgün
Machine Learning
SAE-Xplainers: Rule-Based Feature Interpretation for Extreme Earth Events
Hugo Porta, Emanuele Dalsasso, Chang Xu et al. (+2 more)
The emergence of large-scale Weather and
Climate (W&C)
datasets offers new opportunities for modeling extreme Earth events (ExEE) and their impacts using deep learning. However, their adoption in operational settings remains limited by the lack of models' interpretability. While for conventional text and image modalities, tools such as Sparse Autoencoders (SAEs) have proven effective for extracting human-understandable concepts, their use for the analysis of ExEE remains challenging due to the nature of W&C data. To address this, we introduce (i) a geographic location-based modulation of the inputs of SAE to capture the local semantic meaning of environmental patterns, and (ii) an ensemble of rule-based SAE-Xplainers to interpret the resulting high-dimensional features derived from complex, multi-modal environmental predictors. We evaluate our method on three ExEE types: the prediction of fires, and the detection of tropical cyclones and atmospheric rivers. We show that SAE input modulation improves both reconstruction performance and feature utilization, and that our SAE-Xplainers enable faithful interpretation of complex climatic patterns by unfolding them into human-understandable rules that are consistent with the scientific literature, while also supporting the identification of feature absorption.
Read the full abstract ▾
All authors Hugo Porta, Emanuele Dalsasso, Chang Xu, Theo Gnassounou, Devis Tuia
Computation and Language
When Text and Numbers Disagree: Evidence Arbitration in Large Language Models
Mattia Carletti, Edward Phillips, Fredrik K. Gustafsson et al. (+5 more)
Large
language models (LLMs) are increasingly used in settings where textual summaries, numerical observations, and external tool outputs may provide conflicting evidence. We study how LLMs arbitrate between such sources when they support opposing decisions. To do so, we introduce a controlled synthetic
benchmark in which latent risk trajectories generate both numerical time series and natural
language summaries, allowing us to construct conflicts where exactly one evidence source is aligned with the ground-truth label. This design lets us independently manipulate modality, temporal recency, source reliability, and evidence provenance. Across open-weight instruction-tuned models, we find that arbitration behaviour is systematic rather than random: models exhibit distinct text-versus-number preferences, follow temporal recency more consistently than explicit reliability cues, and can over-rely on external forecasts even when they conflict with direct contextual evidence. These results suggest that current LLMs often rely on heuristic arbitration strategies when integrating heterogeneous evidence, highlighting a failure mode for tool-augmented decision systems.
Read the full abstract ▾
All authors Mattia Carletti, Edward Phillips, Fredrik K. Gustafsson, Patitapaban Palo, Lei Clifton, Danielle Belgrave, Xiao Gu, David A. Clifton
Artificial Intelligence
DECOWAM: Decoupled Whole-Body World-Action Model for Legged Mobile Manipulation
Siyuan Ma, Boshi Zhang, Yutian Zhang et al. (+4 more)
Mobile manipulation requires a
robot to predict how locomotion and arm motion jointly alter future observations and control. Existing world-action models, developed largely for fixed-base platforms, do not explicitly distinguish camera ego-motion from base and arm actions. Here we introduce DECOWAM, a whole-body world-action model that separates these factors through dedicated conditional interfaces. DECOWAM freezes an adapted FastWAM backbone and trains residual adapters, an action-equivalent future bottleneck distilled from privileged observations, adversarially separated base and arm latents, and base-velocity conditioning for
video prediction. We further introduce ARMDOG, a real-
robot dataset that synchronizes
video, whole-body state and action, and
language. On a fixed replay protocol, DECOWAM improved both future-
video and action prediction over FastWAM, reducing action MSE by 21.7% with 25.95M trainable adaptation parameters. Across 79 closed-loop trials per method, it achieved the highest observed whole-body coordination and base-displacement robustness among the compared systems, while task completion remained comparable to the strongest baseline. These results show that embodiment-aware factorization can support parameter-efficient joint visual prediction and whole-body control under moving viewpoints.
Read the full abstract ▾
All authors Siyuan Ma, Boshi Zhang, Yutian Zhang, Qinglian Wu, Jiaqi Zhai, Dong Wei, Qiaojun Yu
Computer Vision · Cross-listed from eess.IV
Flow Matching-Based PET Image Reconstruction
Fumio Hashimoto, Ziqian Huang, Tatsuya Yokota et al. (+1 more)
Generative models have shown strong potential for positron emission
tomography (PET) image reconstruction. Although
diffusion model-based reconstruction methods have demonstrated promising performance, they often require many reverse sampling steps with data-consistency updates incorporated into the sampling process. Flow matching offers an attractive alternative because it can directly estimate clean images from intermediate states, allowing data-consistency refinement to be separated from flow propagation. In this work, we proposed flow matching-based PET image reconstruction methods. We first established PET-FlowDPS by incorporating Poisson likelihood guidance with an expectation-maximization (EM)-based preconditioner into the FlowDPS framework. We then proposed a model-based PET reconstruction method that used a pretrained flow matching model as a prior, in which the flow-based prior, PET data refinement, and
stochastic propagation were interpreted within an approximate
Bayesian framework. Experimental results using [$^{\text{18}}\text{F}$]FDG
brain PET
datasets showed that the proposed method achieved better bias-variance trade-offs across different dose levels compared with other reference methods. These results demonstrated the potential of flow matching as a generative prior for quantitative PET image reconstruction.
Read the full abstract ▾
All authors Fumio Hashimoto, Ziqian Huang, Tatsuya Yokota, Kuang Gong
Robotics
Planning-Oriented End-to-End Autonomous Driving: Architectures, Evaluation, and Emerging Paradigms
Yanchen Guan, Xingcheng Liu, Bin Rao et al. (+7 more)
End-to-end autonomous driving has evolved from camera-to-control regression toward planning-oriented systems that use structured representations, trajectory-level outputs, and increasingly realistic evaluation protocols. This survey reviews this transition across behavior cloning, conditional imitation learning, privileged
distillation, BEV and vectorized planning, unified perception-prediction-planning architectures, world-model-based planners, and
vision-
language-action systems. We argue that the key distinction in modern end-to-end driving is not whether intermediate representations are used, but whether they are learned, supervised, and evaluated to support safe, feasible, and route-compliant planning. To organize the literature, we synthesize existing methods along four axes: input representation, planning output, supervision signal, and evaluation protocol. We further examine the
benchmark shift from open-loop trajectory matching to closed-loop simulation, non-reactive real-log evaluation, long-tail testing, and human-preference-aware metrics. Our analysis highlights that architectural progress is difficult to interpret without
benchmark-consistent evaluation, and that displacement-based open-loop metrics alone provide limited evidence for safe and human-aligned driving. We conclude with open challenges in uncertainty-aware planning, learner-expert mismatch, runtime safety assurance,
language-action grounding, world-model validation, and reproducible benchmarking.
Read the full abstract ▾
All authors Yanchen Guan, Xingcheng Liu, Bin Rao, Chengyue Wang, Guofa Li, Yunjian Li, Lishengsa Yue, Zhiyong Cui, Chengzhong Xu, Zhenning Li
Hardware Architecture
ODEONN: A Digital ODE Solver Architecture for Oscillatory Neural Networks
Bram F. Haverkort and Aida Todri-Sanial
Oscillatory Neural Networks (ONNs) are an alternative computing paradigm for AI and combinatorial optimization problems. However, digital architectures are often designed for specific applications of ONNs. This work introduces a modular and scalable architecture called ODEONN that is generic to multiple applications of ONNs, and to the best of our knowledge, is the first fully digital ONN to also support complex-valued coupling. Additionally, an approximation of the sine function is introduced that uses half of the hardware resources compared to standard methods. The performance of ODEONN is compared with a full-precision software simulation, where a performance degradation of less than $2\%$ is shown. Therefore, we conclude that the fixed-point quantization and the approximated waveform affect the accuracy of computation by only a small amount. Furthermore, ODEONN shows a 45$\times$ reduction in energy-delay product over the software simulation running on conventional hardware.
Read the full abstract ▾
Cryptography and Security
A Meta-Study on Replication Papers in Usable Security & Privacy
Christian Mack, Benjamin Berens, Hanna Algedri et al. (+4 more)
The field of usable security and
privacy research is a young and expanding field, which is still developing standards for its research, e.g. regarding replications. We used a mixed-method approach, in order to get a better understanding of the current state of replications in the field of usable security and
privacy: (1) we examine the Call for Papers of 13 venues spanning security,
privacy, and human-computer interaction; (2) we conduct a systematic search for papers reporting replicated user studies published across these venues between 2016 and 2025, yielding 24 relevant publications; (3) we categorized these 24 papers employing the replication taxonomy proposed by Olszewski et al. (2025); (4) we distributed a survey to the authors of these papers to understand their motivations for conducting replications. Our analysis reveals four key insights: (A) Calls for Papers would benefit from clearer guidelines for authors and reviewers regarding replication work; (B) determining what modifications were made relative to the original study proves difficult when reading replication papers; (C) strict exact replications do not exist in our sample. Approximately two-thirds of the 24 studies altered multiple aspects of the original work; (D) temporal and contextual changes affecting results emerged as one of the most frequently cited motivations for replication. Based on these findings, we offer practical recommendations for venues, researchers, and peer reviewers to strengthen replication practices in usable security and
privacy research.
Read the full abstract ▾
All authors Christian Mack, Benjamin Berens, Hanna Algedri, Tobias Hilt, Daniela Reimer, Peter Mayer, Melanie Volkamer
Computer Vision
BeyondMasks: Evaluating Causal and Physical Consistency in Video Object Removal
Yigit Ekin, Enes Sanli, Aykut Erdem et al. (+2 more)
Recent advances in generative
video models have significantly improved visual realism in
video object removal, yet evaluation protocols still focus on masked region fidelity, treating removal as local inpainting. In real scenes, object removal is a causal intervention: eliminating an object also requires removing its induced physical effects, such as shadows, reflections, illumination changes, translucency, and dynamic traces. Existing
benchmarks lack aligned clean references or remain limited to simplified synthetic settings, preventing systematic evaluation of causal consistency. We introduce BeyondMasks, a paired
benchmark for causally consistent
video object removal, consisting of temporally aligned synthetic and real world
video pairs with clean background references. The
dataset spans diverse photometric,
geometric, volumetric, and dynamic interactions, and supports both mask based and instruction driven editing. We further propose CORE, a structured
vision language model based evaluation protocol that jointly measures object disappearance and after effect consistency, aligning more closely with human judgments than existing metrics. Benchmarking state of the art methods reveals systematic failures in removing secondary physical effects despite high masked region fidelity, exposing a gap between visual plausibility and causal correctness. BeyondMasks reframes
video object removal as causal scene consistency rather than local reconstruction and provides a unified framework for its evaluation.
Read the full abstract ▾
All authors Yigit Ekin, Enes Sanli, Aykut Erdem, Erkut Erdem, Aysegul Dundar