Peer Revenue Past citations are no guarantee of future returns

Papers

Fresh from arXiv, typeset properly. Highlighted words trade on the market.

Computer Science

cs Watch Computer Science

Monday 21 September

Networking

Joint Energy Efficiency and Fairness Optimization for D2D Communications in Aerial-Ground Integrated Heterogeneous Networks

Chuan-Chi Lai, Ang-Hsun Tsai and Shang-Long Wu

This study investigates an Aerial-Ground Integrated Heterogeneous network (AGIHN) architecture that combines terrestrial macro base stations and unmanned aerial vehicles (UAVs) serving as aerial base stations to enhance uplink access for macrocell users. To address the complex uplink resource allocation challenge for multiple device-to-device (D2D) communication pairs, we propose a low-complexity Multi-Channel Rate-Fair (MCRF) algorithm. Distinct from traditional exclusive allocation methods, MCRF supports shared reuse, enabling multiple D2D pairs to simultaneously multiplex on the same resource block, thereby significantly improving spectral efficiency. To manage the severe intra-tier interference arising from this non-orthogonal sharing, a heuristic Interference Avoidance (IA) strategy is integrated to ensure the transmission quality of D2D users. The proposed framework jointly optimizes system throughput, user fairness, and energy efficiency without requiring computationally intensive offline training. Simulation results demonstrate distinct performance advantages depending on the reuse mode: Compared to traditional single-channel exclusive reuse schemes, MCRF achieves massive gains, increasing D2D energy efficiency and throughput by approximately 397% and 542%, respectively. Furthermore, relative to multi-channel benchmarks (e.g., MCRR), the proposed algorithm optimizes the efficiency-fairness trade-off, enhancing the fairness index by 7.43% while maintaining a robust fairness score exceeding 0.6 in interference-prone environments.
Read the full abstract

Artificial Intelligence

VLM-in-Sandbox: Visual Workspaces for Agentic Visual Reasoning

Hexiong Yang, Mingrui Chen, Jie Cao et al. (+1 more)

Sandboxed computer environments support multi-step reasoning with tools, executable programs, and persistent files, yet their extension from language models to vision-language models (VLMs) introduces a distinct state-management problem. Visual reasoning produces intermediate image-valued evidence—crops, masks, overlays, zoomed regions, and analytic renderings—that must remain addressable without accumulating unboundedly in multimodal context. We introduce VLM-in-Sandbox, a training-free framework for agentic multimodal reasoning in controlled computer environments. Its Visual Workspace registers generated artifacts in an image ledger, maintains a bounded active visual context, and lets the model explicitly promote selected evidence for subsequent inspection. This separates visual evidence generation, performed by sandbox tools, from visual evidence management. Across seven benchmarks and four base VLMs, VLM-in-Sandbox achieves the highest sample-weighted average accuracy among Vanilla VLM, Append-only Sandbox, and the proposed method. A compiler-matched $2\times2$ study on 1,260 examples further separates model-directed visibility from bounded retention: VLM-in-Sandbox reaches 66.27% accuracy with 18.6% fewer total tokens than the automatic, retain-all control. Over all 6,350 submitted GPT-4.1-mini examples, it produces 302 rescues and 142 regressions relative to Original Append-only. A local vLLM study with prefix caching confirms that the smaller request workload also reduces uncached tokens, time to first token, and end-to-end latency. These results identify explicit visual evidence state as a central abstraction for sandboxed VLM agents.
Read the full abstract

All authors Hexiong Yang, Mingrui Chen, Jie Cao, Ran He

Computer Vision

Dissecting Agentic Forensics: The Role of Triage, Prompting, and Evidence Arbitration in Open-World Fake Image Detection

Xianlong Li, Pietro Bongini, Niccoló Pancino et al. (+3 more)

Image forensics is increasingly an open-world problem: manipulations range from fully synthetic images to localized edits, splicing and swapping, while most forensic detectors remain specialized to a single manipulation family. Agentic AI has recently emerged as a promising solution. In principle, such systems can assess the reliability of individual detectors, identify out-of-scope evidence, and arbitrate conflicting reports. However, it remains unclear which components actually drive performance and whether their benefits persist under distribution shift. To answer these questions, we study a training-free agentic framework built around specialist detectors, per-detector triage, and conflict-aware evidence arbitration. Using six configurations and three multimodal large language model backbones, we dissect the role of triage, prompting, and reasoning quality on both in-distribution and out-of-distribution data. Our results show that naive detector fusion suffers from severe false-positive rates on authentic images. Triage and prompting consistently improve performance by filtering unreliable evidence and exposing detector limitations. However, the dominant factor is represented by reasoning itself: A stronger judge substantially outperforms a weaker one, particularly under distribution shift. Most notably, manipulation recall is nearly saturated across all configurations, indicating that the main challenge of open-world image forensics is not detecting manipulations, but calibrating trust in specialized forensic tools and arbitrating conflicting evidence.
Read the full abstract

All authors Xianlong Li, Pietro Bongini, Niccoló Pancino, Marco Blanchini, Benedetta Tondi, Mauro Barni

Machine Learning

Explainable Neuro-Fuzzy Prediction for Trustworthy Decision-Making in Maritime

Dionisis Kalogeropoulos, Georgia Sovatzidi and Dimitris K. Iakovidis

Predicting when maritime systems require maintenance can be critical, avoiding hazards and costly consequences. To address this problem, this paper proposes an explainable decision-making framework that integrates a neuro-fuzzy prediction model with a two-stage explainable component. The first stage of this component produces feature-attribution explanations, using gradient-based saliency maps, and the second stage extracts local rules using a fuzzy decision tree. The proposed framework is generic and can be integrated into any deep learning-based approach, rendering it explainable. To the best of our knowledge, this is the first fuzzy logic-based framework enabling both feature-level and local rule-based explanations of black box models. This approach aims to foster trustworthiness in decision making through user-understandable machine inferences. The performance of the proposed framework using a deep residual-based neural backbone is evaluated on various general-purpose public benchmark datasets, and its utility in maritime is demonstrated in the context of early fault detection in a naval propulsion system dataset. The results indicate that it can provide predictions outperforming relevant state-of-the-art approaches, with an average AUC-ROC (Area Under the Receiver Operating Characteristic Curve) value, reaching up to 99%, while offering the advantage of explainability.
Read the full abstract

Computation and Language

Mitigating Entity Type Confusion in Cross-Domain NER via Multidimensional Quantification and Reasoning Enhancement

Jingyu Wang, Shijie Wu and Fusheng Jin

Cross-domain Named Entity Recognition (CD-NER) aims to transfer the rich knowledge in the source domain to the target domain. Recent studies adopting decomposition or generation paradigms have achieved significant performance improvements, demonstrating high accuracy in entity span detection. However, during entity type classification, models severely suffer from entity type confusion, the erroneous tendency that models classify entities of one type in the text as another similar but incorrect type. To address this issue, we first propose a Multidimensional Confusion Quantification Model (MCQM) that quantifies a model's confusion extent between entity types from three dimensions: source-target hierarchy analysis, semantic similarity analysis, and explicit data evaluation. Moreover, we propose the Progressive Bidirectional Reasoning Chain (PBRC). PBRC leverages the source-target hierarchy and confusion analysis from the MCQM to prompt the LLM to generate two-stage reasoning information. The two-stage reasoning information is utilized to augment the knowledge of the model, significantly mitigating entity type confusion and improving the model's generalization performance. Experimental results demonstrate that our method achieves new state-of-the-art results on all domains of the CrossNER dataset.
Read the full abstract

Systems and Control

Assessment of the N-1 voltage security of a future Nordic energy system

Luis Kuhrmann, Peiyuan Chen, Lisa Göransson et al. (+1 more)

Capacity Expansion - Energy System Models (CE-ESMs) have been widely used to optimize the decarbonization of future energy systems on national and continental scales. To capture the limitations in electricity trade between different parts of the system investigated, CE-ESMs often include a representation of the transmission grid. However, CE-ESMs usually only include linearized representations of the grid and omit or strongly simplify grid stability requirements. In this work, we evaluate the N-1 voltage security of the electricity system results obtained from a CE-ESM of a decarbonized Nordic energy system in Year 2050, and analyze the effects of different grid code requirements and shunt capacitor and reactor automation on voltage security. For comparison, we evaluate a Year 2022 system based on ENTSO-E data.We show that the CE-ESM results for the Nordic countries are not N-1 voltage-secure and that, depending on the grid code and shunt automation requirements, the contingencies with voltage violations range from 1.1% to 17.4%. Furthermore, the results indicate that both Power Park Module voltage control and shunt extreme voltage automation have strong positive effects on voltage security in the modeled future system. Grid regions with low levels generation, and thus little dynamic reactive power from generators, are found to be the most at risk of being voltage-insecure.
Read the full abstract

All authors Luis Kuhrmann, Peiyuan Chen, Lisa Göransson, Filip Johnsson

Artificial Intelligence

Few-Shot Demonstrations Elicit the Use of In-Context World Representations in LLMs

Kohsei Matsutani, Gouki Minegishi, Core Francisco Park et al. (+3 more)

Large language models (LLMs), when acting as agents, are expected to take observed data in context, infer the latent state space underlying the world, and leverage it for downstream prediction. However, prior work demonstrated that LLMs struggle to use representations learned in context on a graph tracking task, where the model needs to construct a representation of the graph governing data generation process and use it for subsequent predictions. In this paper, we show that extending this to few-shot settings, where each demonstration is generated from a different world with either the same or different graph topologies, enhances its prediction on 6 models from 4 model families. To understand this improvement, we linearly probe a low-dimensional world representation that encodes graph information in the hidden states. Notably, we find that few-shot demonstrations relocate the world representation and increase its predictive use. Specifically, for each model, these world representations shift in directions nearly orthogonal to their original subspace, and interventions on these representations selectively impair performance more than interventions on other subspaces. Consistent with this insight, we show that few-shot demonstrations with observations from different worlds improve performance on ARC-AGI-1&2, web agent tasks, and Othello. Our findings elucidate the role and internal mechanisms of few-shot demonstrations in in-context world modeling. More broadly, our work advances our understanding of how LLM agents learn from in-context observations and provides implications for their further improvement.
Read the full abstract

All authors Kohsei Matsutani, Gouki Minegishi, Core Francisco Park, Takeshi Kojima, Yusuke Iwasawa, Yutaka Matsuo

Robotics

LIBERO-VPro: Benchmarking Closed-Loop Visual Robustness of Robotic Foundation Models

Huiqiong Li, Zhiting Mei, Anirudha Majumdar et al. (+3 more)

Robotic foundation models achieve impressive performance on standard manipulation benchmarks, yet these evaluations typically assume clean, timely, and consistent visual observations throughout execution. We introduce LIBERO-VPro, a benchmark for systematically evaluating the closed-loop visual robustness of robotic foundation models by perturbing the visual evidence available during execution. LIBERO-VPro covers four complementary dimensions, including Visual Evidence Degradation, Camera Staleness, Visual Source Consistency, and Task-Relevant Scene Variation, spanning 12 challenge categories, 96 experimental settings, and 3,296 task-condition cases. We evaluate three vision-language-action models and three world-action models over approximately 196,000 simulated episodes, complemented by 200 real-world rollouts on a Franka Research 3. Our results reveal that strong nominal performance can mask substantial weaknesses in visual grounding and adaptation. Models often remain successful despite severe object-level occlusion, yet degrade sharply when local interaction cues are disrupted or familiar spatial priors are violated. They are also highly sensitive to stale or missing observations and struggle when changed task preconditions require behavioral adaptation. Finally, VLAs and WAMs exhibit distinct robustness profiles, showing that visual robustness is multi-dimensional and architecture-dependent. LIBERO-VPro provides a systematic diagnostic framework for developing robotic foundation models that can more reliably ground and adapt their actions under challenging visual conditions.
Read the full abstract

All authors Huiqiong Li, Zhiting Mei, Anirudha Majumdar, Jingjing Chen, Yu-Gang Jiang, Bin Zhu

Software Engineering

A Lean and Spec-Driven AI-Assisted Software Development Lifecycle for Applied AI Education: The AI-SDLC Approach

Andreas Martin and Sandro Schwander

AI coding agents increasingly support software development beyond code completion, including planning, implementation, testing, and repository-level task execution. Their practical use, however, often remains only weakly connected to established software engineering practices. The aim of this work is to develop and evaluate a lightweight, spec-driven lifecycle for governed agentic software engineering. The lifecycle combines established software engineering practices with repository-local guidance through specifications, AGENTS.md, and phase-specific agent skill files. The approach was developed in the context of the FHNW course AI-assisted Software Development and applied by students to business-oriented software use cases. Its educational and practical applicability is explored through a student survey combining closed rating items with open-ended questions. The contribution of this work is a process-oriented framework that enables AI coding agents to operate with bounded autonomy within an explicit, reviewable, and test-oriented software development lifecycle.
Read the full abstract

Artificial Intelligence

LADDER: Graph-Guided Diffusion Language Models for Efficient Multi-Hop Reasoning

Senlei Zhang, Linhao Luo, Qian-Wen Zhang et al. (+4 more)

Graph Retrieval-Augmented Generation (GraphRAG) has remarkably enhanced large language models on complex reasoning by leveraging structured entity topologies. However, existing frameworks heavily rely on standard autoregressive language models where the nature of inherent sequential generation severely hinders overall inference efficiency. Inspired by Diffusion Language Models (DLMs) that offer massive parallelism via continuous refine-in-parallel decoding, we aim to accelerate GraphRAG in the discrete space. However, it remains non-trivial for two challenges. First, partially denoised drafts are highly dynamic and uncertain, making dynamic graph grounding non-trivial. Second, raw denoising states are inherently noisy and unstable, making synchronous graph retrieval and multi-hop aggregation computationally prohibitive. To this end, we present LADDER, a novel framework that bridges diffusion language modeling with GraphRAG through graph-guided parallel decoding. Specifically, (i) we propose an event-driven self-clocking retrieval, inspired by our key insight that 88% of target entities emerge early in the partially denoised state, leading final commitment by an average of 5.7-9.6 steps. This mechanism dynamically triggers graph retrieval only when the set of graph-linkable entities expands, yielding an asynchronous self-clocking policy that bypasses learned gates or heuristic thresholds. (ii) An incomplete-query graph propagation module is designed to process the newly emerging entity queries using a specialized graph foundation model, continuously aggregating multi-hop evidence to sharpen parallel predictions and accelerate overall decoding convergence. Extensive experiments on three challenging multi-hop QA benchmarks show that LADDER raises average exact match from 39.6% to 45.2% while achieving a 4.1x latency reduction.
Read the full abstract

All authors Senlei Zhang, Linhao Luo, Qian-Wen Zhang, Siyu An, Junnan Dong, Shuhao Zhang, Xing Sun

Logic in Computer Science

Garlene: Guarded Recursion in Lean

Sergei Stepanenko, Patrick Bahr and Rasmus Ejlers Møgelberg

Extending the recursion principles of a formal system is an enticing but dangerous endeavour with a well-documented history of leading to consistency bugs. Nakano's guarded recursion is an elegant, type-based approach to soundly extend type theory with a powerful recursion principle. This makes guarded recursion useful for many applications, from programming with infinite structures such as streams to reasoning about advanced programming language features using synthetic guarded domain theory. Sadly, guarded recursion is not directly supported by any major interactive theorem prover, which leaves users of guarded recursion with unmechanised pen-and-paper proofs or mechanisations that depend on unmaintained theorem provers. In this paper, we present an implementation of guarded recursion as an embedded language in Lean consisting of a simply-typed lambda calculus for definitions and a higher-order logic for reasoning. Using Lean's excellent support for metaprogramming, our language allows users to write guarded recursive definitions in an intuitive syntax and to prove properties about them using a dedicated proof mode. We give our language a presheaf model, which we use to prove the soundness of our language and to allow users to export guarded recursive definitions and their theorems into standard Lean developments. To demonstrate the usefulness of our language, we present several case studies for programming and reasoning with guarded recursion.
Read the full abstract

Emerging Technologies

Beyond HBM-on-GPU: Thermal Design Envelope for 3D Volumetric DRAM-on-GPU Integration

Yukai Chen, Melina Lofrano, Khakim Akhunov et al. (+12 more)

The scaling of GPUs for AI and HPC workloads is increasingly constrained by the capacity, bandwidth, and thermal limits of both 2.5D HBM-GPU and direct-stacked 3D HBM-on-GPU integration. This work establishes the thermal design envelope for 3D volumetric DRAM-on-GPU integration, in which vertically oriented DRAM dies and interleaved cooling cavities reshape heat flow and memory interfacing above the GPU. Using a package-level thermal model anchored to a consistent HBM-on-GPU baseline and driven by a realistic reticle-scale non-uniform GPU power map, we quantify the key parameters governing thermal feasibility. Stack height is the dominant limiter of peak temperature, while cooling-cavity conductivity shifts the feasible region, and mold insertion and stack orientation further modulate thermal behavior. A distributed memory-controller and network-on-chip tier introduces only a moderate thermal penalty. Although die-level parallelism increases bandwidth, the reduction in simulated training time saturates once execution becomes compute-bound. These results define a bounded co-design space across bandwidth, capacity, and thermal constraints for 3D volumetric DRAM-on-GPU integration.
Read the full abstract

All authors Yukai Chen, Melina Lofrano, Khakim Akhunov, Jonas Svedas, Arjun Singh, Nathan Laubeuf, Diksha Moolchandani, Anshul Gupta, Matthew Walker, Zsolt Tokei, Geert Van der Plas, Dwaipayan Biswas, Herman Oprins, Julien Ryckaert, James Myers

Software Engineering

Evaluating the effectiveness of class-level LLM-generated test suites in Python

Bilal Al-Ahmad, M. Harshvardhan, Khaled El-Fakih et al. (+1 more)

Context: Large language models (LLMs) can generate unit tests quickly, but high structural coverage does not establish that those tests execute reliably or detect faults. Existing evidence often treats coverage as the principal outcome and rarely compares prompt strategies and models through mutation testing at class level. Objective: This study examines how prompt strategy and model choice shape the executability, structural coverage, fault-detection effectiveness, and structural quality of LLM-generated Python test suites relative to human-written suites. Method: We evaluate multiple prompt strategies across a diverse set of current LLM configurations on the ClassEval benchmark. The evaluation combines execution outcomes, line and branch coverage, Cosmic Ray mutation scores, and structural quality indicators. Primary analyses treat successful execution as a prerequisite; paired comparisons use only classes shared by the relevant executable subsets. Results: Structural coverage is consistently near its ceiling and offers little discrimination among configurations. Executability varies substantially. The proposed prompt performs strongly for mutation score, but no prompt dominates across models. Model choice explains more variation than prompt choice, and their interaction shows that prompt effectiveness depends on the selected model. Human and LLM suites are evaluated on unequal executable subsets, so their relative mutation scores do not establish superiority. Conclusion: Reliable assessment of LLM-generated tests should treat executability as a gate and combine coverage with mutation testing and structural quality indicators. In practice, model selection should precede prompt tuning.
Read the full abstract

All authors Bilal Al-Ahmad, M. Harshvardhan, Khaled El-Fakih, Anas AlSobeh

Numerical Analysis

Morley element for the linear strain gradient elasticity problem

Xiao Li, Shudan Tian and Hua Wang

We establish a discrete $H^1$-Korn inequality for finite element spaces satisfying a second order weak continuity condition. This implies that classical $H^2$-nonconforming elements satisfy the discrete Korn inequality. Based on this result, we develop a stabilized Morley finite element method for linear strain gradient elasticity using only piecewise quadratic polynomials. Thanks to the discrete $H^1$-Korn inequality, this method does not require any penalty parameter. We prove that the method is robust with respect to both $\lambda$ and $\iota$. Numerical experiments confirm the theoretical results.
Read the full abstract

Systems and Control

An Algebraic Observer for State-Affine Systems

Romeo Ortega, Alexey Bobtsov, Anton Pyrkin et al. (+1 more)

We present a new systematic method to design an algebraic swapping lemma observer for nonlinear systems which are affine in the state. Four are the main features of the new observer: (i) Far superior transient performance compared to standard asymptotically convergent observers; (ii) structural simplicity - its construction relies solely on basic linear filtering and a single matrix inversion; (iii) applicability to non-uniformly-completely-observable systems, for which classical methods are not applicable; (iv) straightforward extension to the cases of unknown time-varying parameters and measurement delay. The core idea exploited in the paper is to combine the construction of a generalized parameter estimation-based observer with a simple filtering technique to derive the algebraic observer. The resulting design is shown to apply to a class of state-affine systems satisfying a weak generic condition. Moreover, it is established that for time-invariant systems, this condition is always satisfied globally.
Read the full abstract

All authors Romeo Ortega, Alexey Bobtsov, Anton Pyrkin, Olga Zarina

Machine Learning

Pharmacokinetic State Space Models for Unbiased Prediction of Haemodynamic Collapse

Rithin Nagaraj, Sudiksha Chindula and Bhaskarjyoti Das

An Intraoperative Hypotension (IOH) event is a frequent complication during administration of general anaesthesia with serious downstream consequences, yet clinical management remains reactive and not predictive. Existing predictive models, however, ignore drug infusion history as a valuable signal for prediction despite its direct pharmacological relevance. Our model achieves an Area Under the Receiver Operating Characteristic curve (AUROC) of 0.7360 and an Area Under the Precision-Recall Curve (AUPRC) of 0.1794, representing a 2.73-fold lift over the random guessing AUPRC baseline (0.0657), with the removal of propofol and remifentanil effect-site concentrations resulting in a 13.9% AUPRC drop compared to the full model. This is consistent with the hypothesis that pharmacokinetic trajectories encode impending haemodynamic changes before they manifest in the Mean Arterial Pressure (MAP). Additionally, this paper shows that training without lead-gap filtering degraded AUROC by 16.7%, empirically confirming that unfiltered models learn to detect ongoing hypotension rather than predict future events. Finally, a Mamba-based architecture achieves the aforementioned high prediction performance while maintaining a constant memory footprint across a range of sequence lengths, unlike the quadratic VRAM overhead typical of vanilla Transformers, making it the more practical choice for continuous intraoperative deployment.
Read the full abstract

Computer Vision

LiAuto-MindViT: A Hybrid Vision Backbone with Adaptive Bidirectional Mamba

Lifu Mu, Shuai Chen, Wen Zheng et al. (+7 more)

While Mamba-based models have shown strong potential for long sequence modeling, adapting them to vision is challenging due to the requirement of local neighborhood correlations and multi-directional spatial contexts for visual understanding. In this paper, we present LiAuto-MindViT, a novel hybrid vision backbone that synergizes the strengths of CNNs, Mamba, and Transformers. The core of our design is the Adaptive Bidirectional Mamba (ABM), which eliminates the directional bias of unidirectional SSMs through bidirectional selective scanning with learnable alpha blending, enabling content-adaptive directional fusion without the overhead of exhaustive multi-path routing. To further accelerate inference, we propose a deployment-friendly Reparameterized ConvSE (RepConvSE) module that leverages structural reparameterization to reduce latency and memory access overhead. Extensive experiments demonstrate that LiAuto-MindViT achieves state-of-the-art performance on image classification, object detection, and semantic segmentation while enabling efficient inference through reparameterization.
Read the full abstract

All authors Lifu Mu, Shuai Chen, Wen Zheng, Haoyi Sun, Xueyang Fu, Pengfei Yu, Ning Mao, Tao Wei, Zhou Pan, Kun Zhan

Numerical Analysis

Autoencoders vs. Numerical Analysis–Informed Manifold Learning for Navier–Stokes Flows

Alessandro Della Pia, Lucia Russo, Ioannis Kevrekidis et al. (+1 more)

Autoencoders (AEs) have become a dominant approach to nonlinear latent-space construction in data-driven reduced-order modelling (ROM), with their decoders lifting latent representations back to the ambient state space. Their prominence, however, has overshadowed an established alternative: manifold-learning methods grounded in classical numerical analysis. We revisit this alternative using Parsimonious Diffusion Maps (PDMs), benchmarking them against Proper Orthogonal Decomposition (POD)-based ROMs and several convolutional AE architectures for the two-dimensional incompressible flow past a rotating cylinder —a bifurcating Navier-Stokes (NS) system organized by a codimension-2 Bogdanov-Takens point and its associated Hopf, saddle-node, and homoclinic bifurcations. Our approach uses PDMs to identify a parsimonious and interpretable set of intrinsic latent coordinates and to estimate their dimension directly from data. Gaussian process regression then learns the latent dynamics, while convex K-nearest-neighbor (K-NN) interpolation in PDMs space constructs the pre-image map, for which we establish pointwise consistency. The resulting nonlinear ROM substantially outperforms POD-based ROMs and achieves reconstruction and prediction accuracy comparable to —and, in some bifurcating regimes, better than— that of AE-based ROMs. At the same time, latent-variable learning with PDMs requires orders of magnitude less computational time than AE training.
Read the full abstract

All authors Alessandro Della Pia, Lucia Russo, Ioannis Kevrekidis, Constantinos Siettos

Computer Vision

AlignMorph: Tuning-Free Diffusion Image Morphing via Explicit Semantic Transport

Wuyi Liu, Xu Han, Yuren Chen et al. (+3 more)

Image morphing aims to produce a smooth and semantically consistent transition between two input images. Existing diffusion-based morphing methods either require expensive per-pair optimization or rely on implicit spatial alignment, which easily fails under large layout discrepancies. To address these limitations, we propose AlignMorph, a novel tuning-free diffusion framework guided by the principle of transport-then-denoise. We explicitly decouple geometric alignment from generative denoising to avoid structural entanglement. Our framework consists of two core components. (1) Global Semantic Transport, which achieves diffusion-compatible semantic alignment via entropic optimal transport and reliability-aware latent warping; and (2) Coordinate-Aligned Generation, which uses a symmetric bi-phase attention handoff to maintain consistent spatial coordinates throughout denoising. Without any tuning, AlignMorph effectively eliminates ghosting and achieves superior structural coherence and temporal smoothness on morphing benchmarks. Code is available at https://github.com/51xOne/Alignmorph.
Read the full abstract

All authors Wuyi Liu, Xu Han, Yuren Chen, Yige Mao, Zishuo Peng, Xianzhi Li

Machine Learning

A Distributional Optimisation Perspective on Combining Models in Deep Learning

Congye Wang, Yan Lin, Zheyang Shen et al. (+2 more)

Combining predictions from different models can improve performance at machine learning tasks, but the training of the individual models and the rule used to combine them are typically chosen separately, and by ad hoc means. Recent advances in distributional optimisation (i.e. where the optimisation occurs over the set of probability distributions) offer an opportunity for principled joint training, viewing the collection of models as a discrete distribution whose support points are to be optimised, but the potential of these methods is not well-understood. In this paper we (1) cast two standard combination strategies - ensembles and low-rank adapter averaging - as entropy-regularised distributional optimisation, observing that the resulting objective is convex in the ensemble case but not in the adapter-averaging case, so that existing convergence guarantees for mean field Langevin dynamics transfer only to the former; (2) assess existing and novel algorithms for this task, including a functional variant of variational gradient descent; and (3) report an empirical study spanning synthetic classification tasks and fine-tuning of large language models on a commonsense reasoning benchmark.
Read the full abstract

All authors Congye Wang, Yan Lin, Zheyang Shen, Matthew A. Fisher, Chris. J. Oates

Artificial Intelligence

Brain-Token Learning: Microstate-Based Tokenization and Multi-Scale Interaction for Long-Horizon EEG Sequence Modeling

Weishan Ye, Yue Pan, Li Zhang et al. (+2 more)

Electroencephalography (EEG) provides a non-invasive window into dynamic brain activity, yet modeling long-horizon EEG sequences remains challenging due to their high temporal complexity, substantial variability across subjects, and the lack of biologically meaningful sequence representations. Existing tokenization strategies, such as fixed-window and patch-based representations, discretize EEG signals according to artificial temporal boundaries, which may disrupt intrinsic brain-state dynamics. In this work, we propose Brain-Token Learning, a neuroscience-inspired framework that introduces Brain Tokenization for long-horizon EEG sequence modeling. Instead of partitioning EEG signals into predefined temporal segments, Brain Tokenization represents EEG as sequences of recurrent microstate-derived brain tokens, where each token corresponds to a quasi-stable large-scale brain state with variable temporal duration. Based on these biologically grounded tokens, we further develop a multi-scale token interaction module consisting of Latent State Aggregation and State Transition Modeling to jointly capture global brain-state context and local microstate transitions. We evaluate Brain-Token on five heterogeneous EEG datasets, including the newly collected long-horizon NeuroLong dataset and four affective or clinical EEG datasets (SEED, DEAP, MDD, and NSSI). Extensive experiments demonstrate that Brain-Token consistently outperforms conventional CNN/LSTM architectures, Transformer-based models, and domain adaptation methods across diverse EEG scenarios. Further analysis verifies the effectiveness of microstate-based tokenization and multi-scale interaction for learning robust and interpretable EEG representations. These results establish Brain-Token as a biologically grounded tokenization paradigm for long-horizon EEG sequence modeling.
Read the full abstract

All authors Weishan Ye, Yue Pan, Li Zhang, Gan Huang, Zhen Liang

Machine Learning

The Undetected Damage of Quantization on Retrieval and How to Fix It

Luca Zhou, Alessandro Zirilli, Daniele Solombrino et al. (+2 more)

We show that a quantized model that keeps its classification accuracy still changes $14$ to $46\%$ of its top-1 retrieval results, and that aggregate ranking metrics reveal only part of this damage. We tie this failure to the gap between the two highest model scores and use that gap to decide when to trust a quantized answer and where additional precision should be spent. We show that the top-1 result is guaranteed to survive quantization only when this gap exceeds twice the largest rounding error. In classification, the scores are logits, and training compares the correct class against every other class, which encourages this gap. In retrieval, the scores are query-document similarities, and training compares each positive only against sampled negatives, so nothing separates the top-1 item from the second. This gap can be measured without labels. Before deployment, it predicts which models will break under quantization, and at deployment time it tells, per input, whether the quantized answer still matches the full-precision answer. Most classification inputs have a gap wide enough to trust the quantized answer, but few retrieval queries do. That gap motivates a different fix in each task. In retrieval, spending extra bit-width on the layers whose quantization moves the gap most recovers up to three-quarters of an extra bit's benefit for half its cost. In classification, routing the few low-gap inputs to full precision recovers most of the lost accuracy at a fraction of the cost.
Read the full abstract

All authors Luca Zhou, Alessandro Zirilli, Daniele Solombrino, Roberto Dessì, Emanuele Rodolà

Robotics

Performance-Preserving Online Adaptation in Social Navigation via Diffusion Steering

Haruto Nagahisa, Kohei Matsumoto, Yuki Hyodo et al. (+1 more)

In social navigation, modeling the complex interactions between humans and robots is difficult, and deep reinforcement learning has therefore been actively studied. However, because simulation alone cannot fully reproduce diverse scenarios, robot dynamics, and the social conventions that vary across deployment environments, fine-tuning in the deployment environment is promising. In doing so, learning that preserves the base model's performance is required, so as not to compromise the primary objective of navigation, namely avoiding pedestrians and reaching the destination. In this study, we propose a method that applies diffusion steering via reinforcement learning (DSRL), which trains only the noise policy while keeping the diffusion policy fixed, thereby achieving learning that preserves performance. Furthermore, we integrate diffusion-based RL policies trained with multiple seeds to construct the base policy, improving learning performance. Our evaluation shows that, compared with other methods, the proposed method enables efficient learning while preserving performance, and we confirm flexible behavior control through adaptation to social conventions, as well as its effectiveness on a physical robot through hardware-in-the-loop simulation.
Read the full abstract

All authors Haruto Nagahisa, Kohei Matsumoto, Yuki Hyodo, Ryo Kurazume

Computer Vision

NeuIDO: Neural Intrinsic Dynamics Operator for Physics-Informed 4D World Models

Jiajing Lin, Xin Zhang and Jianhua Sun

World models aim to capture environmental dynamics and predict future trajectories, showing growing potential for embodied intelligence. Physics-informed 4D generation integrates physical simulation to predict 3D object interactions, offering a promising pathway toward world models. However, this paradigm relies on manually imposed dynamical assumptions rather than internalizing world dynamics, and thus still leaves a gap toward a true world model. To bridge this gap, we propose NeuIDO, a novel world dynamics modeling framework that learns a unified intrinsic dynamics representation from visual observations, advancing physics-informed 4D generation toward a world model. Specifically, we formulate world modeling as a neural operator learning problem and introduce a two-stage training strategy to learn a generalizable mapping from the visual observation distribution to the intrinsic dynamics distribution. Building on this observation-dynamics mapping, NeuIDO enables zero-shot dynamics inference directly from videos and can be further aligned with complex real-world dynamics via few-shot adaptation. Extensive experiments demonstrate that NeuIDO effectively unifies the intrinsic dynamics underlying diverse visual observations into a shared representation and rapidly infers dynamics in novel scenes.
Read the full abstract

Computer Vision

AnalogDepth: Multi-view Geometry from FPV drones under Analog Video Transmission

André Amorim and Pedro F. Proença

Analog video transmission (VTX) remains widespread in FPV drones due to low latency, weight and low cost. However analog VTX suffers from complex spatially structured image degradation which differ fundamentally from digital image corruption (e.g. AWGN) used in standard training augmentation. This work shows that this type of noise severely degrades the accuracy of Depth Anything 3 (DA3), a state-of-the-art feed forward visual geometry foundation model. To address this gap, we present AnalogDepth, a parameter-efficient training pipeline that adapts DA3 to analog FPV imagery using student-teacher knowledge distillation with Low-Rank Adaptation (LoRA) injected into the DINOv2 backbone. Rather than synthesizing noise analytically, we build a noise bank from static FPV recordings under diverse conditions and compare real-noise injection against PSD-matched Gaussian synthesis and AWGN as baselines. Experiments on six real FPV flight sequences across three indoor scenes show that training with our noise bank consistently reduces per-frame depth RMSE and 3D reconstruction Chamfer distance compared to the pretrained DA3 baseline and both Gaussian noise variants. These results demonstrate that replicating the spatial structure of real analog transmission noise is critical for effective adaptation.
Read the full abstract

Computation and Language · Cross-listed from eess.AS

Morpho-VITS: Variational Inference with Morphological Modeling for End-to-End Speech Synthesis of a Tonal Bantu Language

Antoine Nzeyimana

Text-to-speech models for Bantu tonal languages are challenged by a tonal system that is rooted in both the lexis (i.e., the inventory of words, stems, and affixes) and the grammar (i.e., morpho-syntax). To complicate matters, the standard writing systems of these languages often omit tone markings and syllable duration information, which must be disambiguated by the reader based on context. Motivated by linguistic descriptions of Bantu language tone systems, we propose an end-to-end text-to-speech model that augments the text encoding mechanism with a morpho-syntactic prior. We replace the standard phoneme encoder in the VITS architecture with a morpheme sequence encoder and a phoneme-to-morpheme attention network. We posit that, by using this explicit morphological modeling, we can capture the information required to produce the correct tone. Experiments conducted on the Kinyarwanda language, a tonal and morphologically complex Bantu language, reveal substantial TTS improvement from this morphological modeling. Specifically, the proposed method significantly improves the naturalness, intonation, and intelligibility of the produced synthetic voices.
Read the full abstract

Computer Vision

HappyWorld-Bench

Zhiqi Bai, Junai Cai, Yixin Chen et al. (+33 more)

Evaluating world models requires assessing both the quality of the worlds they generate and their consistency and responsiveness under exploration, interaction, and modification. We introduce HappyWorld-Bench, a comprehensive benchmark that evaluates whether generated worlds remain reliable as agents interact with them. Our design is built on a hierarchical capability framework of six world capabilities (W1-W6), from generative construction to unified world modeling, instantiated across three independent evaluation tracks: video world models, spatial world models, and embodied world models. HappyWorld-Bench comprises 1,138 video prompts, 300 spatial scenes, and 254 embodied test cases. Across all three tracks, we build and operate HappyWorld-Arena to organize human A/B comparisons and derive model-level Elo ratings, which complement newly designed automated metrics that capture behavioral correctness. We evaluate 14 video world models, 9 spatial systems, and 8 embodied candidates under this unified framework. Results reveal remaining reliability gaps across all three tracks: video models exhibit reduced consistency during extended rollouts and revisits, spatial models achieve at best 70.14% placement accuracy and 73.33% edit execution, and embodied models struggle to preserve state across multi-step actions and respond precisely to altered action conditions and physical rules. These findings highlight the need to evaluate world models not only by visual quality, but also by state consistency and the correctness of their responses to actions and interventions.
Read the full abstract

All authors Zhiqi Bai, Junai Cai, Yixin Chen, Jingrun Du, Tao Feng, Wei Gong, Siyuan Huang, Xiao Lin, Jiaheng Liu, Jun Luo, Yongzhe Lyu, Liya Ma, Zenan Meng, Lin Qu, Wenbo Su, Jiaming Wang, Qinghe Wang, Shaofei Wang, Yanghai Wang, Zequn Wang, Ziming Wang, Hu Wei, Jiangtao Wu, Ruiqi Wu, Jiaxin Xie, Yuchi Xu, Ze Xu, Chengting Yu, Liangyu Yuan, Gang Zeng, Yawen Zeng, Xingyao Zhang, Zizheng Zhang, Bo Zheng, Jiancheng Zhu, Song-Chun Zhu

Computer Vision · Cross-listed from astro-ph.IM

Scale-Vector Alignment: A Scale-Aware Framework for Spatially Resolved Morphological Similarity in Astronomical Images

Mengke Zhao, Guang-Xing Li, Keping Qiu et al. (+1 more)

Astronomical maps made with different tracers are not expected to have identical morphology. Excitation, optical depth, chemistry, radiation, and ISM phase alter the response of a tracer, and the resulting differences can depend on both position and spatial scale. We propose scale-vector alignment, a scale-aware method based on Constrained Diffusion Decomposition (CDD). CDD decomposes an image into localized scale components; at each position, their amplitudes define a scale vector that describes how the measured intensity is distributed over spatial scale. We define the pixel-wise similarity $\Spix(x,y)$ as the normalized alignment of two local scale vectors. The normalization removes the overall amplitude, so $\Spix$ compares relative scale composition rather than absolute flux. We also define the scale-wise similarity $\Sscale(l)$ by comparing the two CDD component maps at each spatial scale. Spatial shifts are used to construct an empirical shifted reference distribution for $\Spix$. In Orion~A, the tracer with the highest similarity to the dust-derived column-density map changes from $^{12}$CO to $^{13}$CO to C$^{18}$O toward higher column density. In NGC~6334I(N), the line–continuum similarity decreases locally around the brightest compact structures, where radiative-transfer effects can alter the observed line morphology. In NGC~3627, CO is most similar to 21~$\mu$m emission, and $\Sscale$ reaches its maximum at an intermediate sub-kpc scale. The method measures where two tracers have similar multiscale structure and at which scales their spatial distributions agree. The implementation is publicly available at https://github.com/meng-ke/Scale-Vector-Alignment.
Read the full abstract

All authors Mengke Zhao, Guang-Xing Li, Keping Qiu, Shanghuo Li

Machine Learning

SupportCal: Label-Free Calibration of Post-Trained LLMs via Reference Support and Corroboration

Linhan Luo, Lequan Lin, Dai Shi et al. (+3 more)

Post-training often improves task performance but can degrade confidence calibration, leaving post-trained language models (PoLMs) more overconfident than their corresponding pretrained language models (PLMs). Because task-specific labeled calibration data can be costly or unavailable, the corresponding PLM provides a natural label-free reference for post-hoc calibration. Prior agreement-gated PLM-referenced calibration fits a scalar temperature using only examples on which the PoLM and its PLM reference agree, excluding disagreement examples because direct alignment can drive the fitted temperature excessively high and induce under-confidence. We revisit this binary treatment. A controlled reintroduction diagnostic reveals a non monotonic aggregate effect: admitting a moderate fraction of disagreement examples can improve calibration, whereas the benefit diminishes as unit weight inclusion approaches the full disagreement set. We introduce SupportCal, a label-free post-hoc method that retains agreement examples at unit weight and assigns disagreement examples continuous weights based on the own-base PLM's relative support and corroboration from pretrained references selected from a size-compatible candidate pool. We further characterize when the resulting weighted objective admits a finite optimal temperature. Across MedMCQA and MathQA, SupportCal yields lower mean ECE than the agreement-only baseline for nearly all evaluated target-model configurations; supplementary TweetEval Sentiment results show the same pattern on a fixed-label classification task.
Read the full abstract

All authors Linhan Luo, Lequan Lin, Dai Shi, Feng Chen, José Miguel Hernández-Lobato, Junbin Gao

Artificial Intelligence · Cross-listed from q-bio.BM

Adapting Boltz-2 with limited experimental activity data improves early enrichment in virtual screening

Kairi Furui and Masahito Ohue

Virtual screening aims to prioritize active compounds from large chemical libraries within a limited experimental budget. When applying Boltz-2 to virtual screening, a key challenge is how to use limited experimental data from the target assay to improve the prioritization of active compounds. We investigated whether fine-tuning the Boltz-2 affinity heads with a small number of binary activity labels could improve early enrichment of active compounds in hit discovery. We compared fine-tuning with 40-300 labels in a retrospective evaluation on eight MF-PCBA targets. With 300 activity measurements, fine-tuning increased the number of actives in the top 1% by a geometric mean of 1.77-fold across the eight targets and improved average precision (AP) by 2.14-fold relative to the control without fine-tuning. We also investigated whether rescoring a subset of candidates could retain the improvement in hit recovery by reranking only the top-ranked Boltz-2 candidates with the fine-tuned head. Restricting rescoring to approximately 10% of the evaluation set retained hit recovery comparable to full rescoring. These findings show that affinity-head fine-tuning with limited activity labels improves early enrichment with Boltz-2 and that this benefit can be retained when rescoring a restricted set of candidates.
Read the full abstract