Peer Revenue Play credits. Real papers.

Papers

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

Computer Science

cs Watch Computer Science

Tuesday 15 September

Computer Vision

DecoGS: Adaptive Static-Dynamic Decoupling of 3D Gaussians for Free-Viewpoint Video Streaming

Idil Sulo, Alexey Supikov, Ilke Demir et al. (+1 more)

Streaming 3D reconstruction demands both speed and temporal fidelity, goals that existing methods undermine by updating every Gaussian every frame, even in static regions. We present DecoGS, a method for efficient online training of 3D Gaussians from streaming videos. Unlike prior methods that update the entire scene indiscriminately, DecoGS introduces an adaptive mechanism that selectively focuses optimization on spatiotemporal regions exhibiting motion or photometric changes. This targeted training strategy eliminates redundant updates that cause flickering and drift in nominally static regions, while enabling fast, high-fidelity scene updates. The pipeline further integrates region-aware Gaussian management through gradient gating and efficient visibility filtering to maintain temporal coherence and a compact memory footprint. On N3DV and MeetRoom, DecoGS achieves 34.55 and 31.60 dB PSNR respectively, outperforming all streaming and offline baselines, while rendering at 261 FPS with $70\times$ lower temporal flicker than the best prior method, requiring no large-scale pretraining.
Read the full abstract

All authors Idil Sulo, Alexey Supikov, Ilke Demir, Sainan Liu

Numerical Analysis

A provably convergent MM-GKS variant for large-scale inverse problems

Mirjeta Pasha, Eric de Sturler and Misha Kilmer

For high-quality images with sharp edges, a popular choice for edge-preserving regularization is using a general(ized) $\ell_q$-norm of the gradient of the image. This can be implemented efficiently using the $\ell_2$-norm and a sequence of weighted gradients, with weights derived from the current solution estimate. We can solve the resulting sequence of regularized least squares problems using hybrid Krylov subspace methods, which efficiently compute the regularization parameter using the problem projected on the Krylov subspace. However, each update of the regularization operator requires a new Krylov subspace. The majorization-minimization generalized Krylov subspace method (MM-GKS) addresses this problem by using a single, generalized, Krylov subspace (GKS). Unfortunately, for large-scale problems, if convergence is not fast, MM-GKS has overwhelming memory requirements and computational costs. We propose a variant of MM-GKS that alternately compresses and expands the search space while maintaining strict monotonic convergence. We show that our method provably converges to the minimum of the selected functional, even if the search space dimension is kept very small. This substantially improves on previous theoretical results for MM-GKS, where the convergence proof relies on the basis for the solution space (eventually) spanning the full space. We show that our method can solve large-scale problems efficiently both in terms of memory requirements and computational complexity. We further generalize our proposed method to handle streaming problems, where the data is either not all available simultaneously or needs to be treated as such because of the extreme memory requirements. We use numerical examples from image deblurring, dynamic photoacoustic tomography, and streaming X-ray computed tomography (CT) to illustrate the effectiveness of our proposed methods.
Read the full abstract

Computer Vision

FROD: Feature Matching Residual Denoising Oracle Bone Decipher

Yanbin Hou, Biao Xiong, Guojun Xu et al. (+4 more)

Oracle bone script (OBS), one of the earliest Chinese writing systems, plays an important role in the study of Chinese etymology. Traditional decipherment relies heavily on domain experts who analyze characters through semantic context and structural evolution. To assist this labor-intensive process, we formulate OBS decipherment assistance as a cross-era image translation task and propose FROD (Feature Matching Residual Denoising Oracle Bone Decipher). Although many OBS characters differ substantially from their modern counterparts, they often preserve local topological invariants at the radical level. During training, FROD leverages fast feature matching to provide gated segmentation supervision: paired samples with sufficient matches are processed patch-wise to align fine-grained radicals, whereas low-similarity pairs are trained holistically to avoid mismatched artifacts. In addition, a Residual Denoising Diffusion Model (RDDM) jointly estimates noise and residual signals, thereby reducing the positional drift and stroke disorder commonly observed in standard diffusion models. Finally, a multi-stage font stylization refinement network refines the generated images by eliminating edge noise and stabilizing stroke structures. On our augmented character-disjoint dataset, FROD achieves higher Top-1 recognition accuracy than the evaluated baselines, with a 3.8% absolute gain over OBSD.
Read the full abstract

All authors Yanbin Hou, Biao Xiong, Guojun Xu, Jianwen Xiang, Cheng Tan, Yanchao Yang, Junwei Zhou

Machine Learning

Easy to Catch a Liar, Hard to Clear an Honest One: Language Models Diagnosing a Corrupted Reward Channel from a Verified Record

Arman Nik Khah

An agent that learns from rewards has to trust whatever reports those rewards. When the reports suddenly change, either the world changed or the reporter broke. From the reports alone these are indistinguishable, and reinforcement learning theory shows that no amount of further experience separates them. The prescribed escape is richer data about the reporter itself. We ask whether a frozen language model, handed exactly that data, uses it. We build a two-option game in which a payout swap and a lying reporter produce byte-identical histories. Then we add one verified record: an independent check of one round's real result, printed beside what the reporter said about that round. That single line settles the case. We ask three large models, from two families, to answer one question with one letter. Is the reporter honest or lying? They catch a lying reporter almost perfectly. At the 70B class that holds in every condition we tried; the 32B model slips in one wording. They clear an honest reporter far less often, and how often depends on things that should not matter. Averaged over rounds, letters, and wordings, a 72B model calls an honest reporter a liar 38% of the time when nothing has changed at all, and 58% of the time when the payouts moved. A 70B model from a second family calls an honest reporter a liar 26% and 48% of the time. The failure is not one of reading, because in the situation where nothing changed the same models score 0.96 to 1.00 with the answer printed in the prompt. Which surface feature drives it differs by family. For the Qwen models it is which round the record names, and for Llama it is which letter stands for "honest." Adding the record to a prompt that already states the answer makes Llama less likely to give that answer. We had registered a prediction for that 58% before the run: 35%. The failure is larger than we expected.
Read the full abstract

Computation and Language

Psychological Effects of Cultural Upheavals from Millions of Song Lyrics Over 100 Years

David M. Markowitz

Cultural upheavals impact many aspects of social life, and many studies have investigated their impact on language patterns. However, few investigations have isolated the impact of upheavals on individuals at scale in popular media. The current work evaluated millions of song lyrics spanning more than a century in search of within-artist and between-artist signals of distress from the Vietnam War, the terrorist attacks of 9/11, and COVID-19. Compared to a five-year baseline, rates of self-references - a marker of psychological distancing - were significantly reduced after the Vietnam War and September 11th. Cognitive processing terms were elevated post-upheaval vs. pre-upheaval, which indicated artists' increased attempts to make meaning from such massive disruptions. Content patterns corroborated these findings as artists wrote more about "life and freedom" (societal conditions) and less about "courtship and nightlife" (interpersonal connection) following the upheavals. Cultural upheavals modify individual and collective verbal behavior, demonstrating their far-reaching impact on society.
Read the full abstract

Machine Learning

Memorisation bias in medical AI

Moritz A. Knolle, Martin J. Menten, Laurin Lux et al. (+5 more)

Medical AI models hold immense potential to improve patient outcomes, but they are also known to unintentionally memorise individual records from their training datasets. While such memorisation has been linked to targeted privacy attacks, its consequences for clinical deployment, where patients may be assessed by a model that saw their historical data during training, remain poorly understood. Here we show that predictions on a patient's unseen future data can change significantly if a model observed that same patient's anonymised historical data during training, a phenomenon we term "memorisation bias". We demonstrate that this bias exists across diverse data modalities and model architectures, and over prolonged time spans: in some cases, memorisation bias persists on future records acquired decades after the historical records used for training. Moreover, in simulated prospective deployment, memorisation bias has asymmetric effects on the diagnostic accuracy of returning data contributors. When a patient returned with a de novo condition absent from their historical records in the training dataset, diagnostic sensitivity decreased significantly compared to an otherwise identical model not trained on their historical data. Conversely, when their health state was unchanged, both sensitivity and specificity were significantly inflated. Our findings reveal a previously uncharacterised risk in medical AI that arises when a model is deployed on patients who contributed to its training data. This exposes a shortcoming of current model development practice: the de-identification measures designed to protect patients' privacy make it difficult to identify returning contributors and exclude them from the AI-assisted interpretation of their own future data. Mitigating memorisation risks may thus require changes to current model training and deployment protocols.
Read the full abstract

All authors Moritz A. Knolle, Martin J. Menten, Laurin Lux, Mélanie Roschewitz, Emma A.M. Stanley, Georgios Kaissis, Daniel Rueckert, Ben Glocker

Software Engineering

Grounding SWE-Agent Decisions in Architecture-0 Design: Navigating Unknown Unknowns through Physical Mapping

Zhongkai Wang and Yan Liu

Autonomous Software Engineering Agents (SWE-Agents) excel in deterministic coding tasks but struggle with Architecture 0, the nascent system design phase plagued by implicit engineering constraints, or Unknown Unknowns (UUs) that are rarely stated explicitly. To investigate how agents navigate UUs, we explore a progressive trajectory across pure-text self-play, tool-augmented feedback, and external physical mapping. Our empirical analysis reveals a cascading chain of failures. Pure-text reasoning inevitably devolves into polite consensus or plausible yet physically impossible fabrications. Attempting to bridge this gap via an early-stage execution sandbox unexpectedly triggers Specification Gaming: agents exploit their autonomy over validation scripts to bypass physical constraints, achieving superficial success without resolving core architectural flaws. To resolve this self-validation trap, we propose the Physical Mapping Guard (PMG). Grounded in the software engineering principle of Separation of Concerns, PMG revokes verification authority from the agent, forcing semantic intents to be evaluated by an external, deterministic Semantic-to-Physical (S2P) mapping engine. Extensive evaluations demonstrate that PMG completely eradicates physical-layer and validation-layer gaming. By precisely isolating residual failures to semantic reinterpretations and auditor overreach, PMG marks a critical step toward genuine affordance grounding in automated architectural design.
Read the full abstract

Numerical Analysis

Toward Pólya's Conjecture: Improving the Individual Li-Yau Bound via Energy Orthogonality

Yifan Wang and Hehu Xie

We establish two complementary lower-bound mechanisms for individual eigenvalues of the Dirichlet Laplacian. First, energy orthogonality yields a frequency-dependent cap on the Fourier density of a finite spectral projection. Combining this cap with the standard $L^2$ Bessel estimate and a radial-capacity bathtub principle gives, on every open set of finite positive measure in $\mathbb R^n$ with $n\geq2$, \[ \lambda_k\geq c_n(2\pi)^2\omega_n^{-2/n}|\Omega|^{-2/n}k^{2/n}, \qquad \frac{n}{n+2}<c_n<1. \] The constant $c_n$ is characterized by a scalar equation, with $c_2=0.5383068077\ldots$. This estimate preserves Weyl scaling and strictly improves the individual consequence of the Li-Yau sum inequality, although it does not improve the sharp leading coefficient in that sum inequality. Second, we retain part of the spectral deficit discarded when an eigenvalue sum is bounded by its largest term. A lower bound for the counting function, integrated through the exact first Riesz-mean identity, leads to a strictly monotone scalar equation. Its unique positive root is no weaker than the volume-only bound, and we give necessary and sufficient criteria for strict improvement over both that baseline and any independent lower bound. Quantitative estimates of Jiang-Lin provide an explicit implementation on bounded Lipschitz domains. The final comparisons and numerical example distinguish improvements within this framework from stronger estimates available under additional geometric or spectral assumptions.
Read the full abstract

Computer Vision

InfoTaxa: Information-Calibrated Label-Free Clustering for Fine-Grained Visual Taxonomy

David Ahmedt-Aristizabal, Mohammad Ali Armin and Lars Petersson

Label-free clustering of frozen pretrained visual embeddings offers a scalable route to biodiversity monitoring, but image-only fine-grained taxonomy exhibits a consistent coarse-to-fine failure mode: clusters recover broad taxonomic structure yet plateau at species level. We study this behaviour on BIOSCAN-5M through an information-calibrated clustering analysis. BioCLIP~2 features with UMAP and HDBSCAN reach $0.79$ AMI at family and $0.67$ at genus, substantially improving over the prior image baseline and remaining competitive with oracle-$K$, graph-based, and learned clustering heads on the same frozen features. To diagnose whether the remaining plateau is method-limited or information-limited, we introduce InfoTaxa, which combines clustering efficiency—the fraction of probe-estimated image information recovered by an unsupervised partition—with paired DNA as an audit signal only, not an inference input. The density pipeline recovers approximately $0.90$ and $0.81$ of the image-available information at order and family, respectively. Held-out late-fusion probes show that adding DNA to the image embedding reduces species-level prediction error by approximately two bits. Robustness analyses cover multiple image encoders, described-species and rare-class subsets, probe diagnostics, and held-out-species coarse-rank generalisation and same-species retrieval. Thus, in the tested setting, species-level label-free clustering is both clustering-limited and representation-limited: improved clustering may recover additional image-exposed structure, but cannot close the DNA-audited information gap alone.
Read the full abstract

Computational Engineering

emgforge: an automated end-to-end pipeline for simulating surface EMG on MRI-based volume conductors

Dimitrios Halatsis, Noura Ezaz-Nikpay, Pranav Mamidanna et al. (+1 more)

Simulated electromyograms are used to understand what an electrode records, to test decomposition and estimation algorithms on signals with known ground truth, and to train learning-based decoders. Most simulators fix the geometry to a cylinder or a slab, or stop at the lead field and leave the rest to the user. We present emgforge, an open pipeline that takes a labelled MRI segmentation of a limb to surface EMG in one command: a tetrahedral mesh with conductivity tensors aligned with each muscle's fibres; one reciprocal finite-element solve per electrode, valid for every fibre of every muscle; fibre beds that are straight or follow the muscle's shape; a motor-unit pool obeying the size principle; motor-unit action potentials on any electrode layout; and a motoneuron-pool and twitch layer that turns a drive or a movement into interference EMG and force. We describe the pipeline stage by stage, and at each stage we show, with an example, why the choice was made. The step that turns a lead field into a single-fibre action potential – direct line-source synthesis – is checked against a closed-form solution ($r = 1.0000$, zero lag), and the whole chain against fifty checks with numeric criteria from the physiological literature. We then use the pipeline for four studies: what an electrode sees as a function of depth, fat, spacing and montage; whether fibre geometry changes the signal; how much crosstalk a grid over one muscle receives from its neighbours; and how interference EMG scales with drive. The code, the validation suite and three datasets with ground truth are released.
Read the full abstract

All authors Dimitrios Halatsis, Noura Ezaz-Nikpay, Pranav Mamidanna, Dario Farina

Information Theory

The Gaussian Multiuser Channel Capacity Region

John M. Cioffi

This work characterizes a Gaussian multiuser-channel capacity-region using receiver-subset message atoms, Gaussian single-user equivalents, and successive decoding. A memoryless multiuser-channel model specifies both the channel conditional distribution and the independent-use input distribution. For all linear Gaussian channels, independent Gaussian user signaling and receiver-local worst-case-noise/MMSE-GDFE transformations provide a single-user-equivalent basis for the complete capacity-region construction. Each user distributes its input autocorrelation among a finite set of receiver-subset atoms, whose rate sums satisfy the applicable receiver constraints. Minimum-energy and weighted-rate-sum designs optimize these allocations, while fixed-allocation linear programs determine feasible atomic rates and synchronized time-shared successive-decoding implementations. The resulting framework includes Gaussian multiple-access, broadcast, and interference channels, with numerical examples illustrating their rate regions and receiver designs.
Read the full abstract

Computer Vision

Probe-VAD: Ordinal Likelihood Probing for Training-Free Video Anomaly Detection

Jiawei Gu, Qilin Zhao, Tengkuo Guo et al. (+6 more)

Video anomaly detection (VAD) aims to localize anomalous events in untrimmed videos. Vision-language models (VLMs) provide rich visual understanding for training-free VAD, but existing approaches impose restrictive interfaces between visual understanding and anomaly scoring. Caption-based pipelines compress visual evidence into text, potentially discarding subtle cues, while direct numerical generation forces the model to express its judgment through a small set of predefined scores. Such interfaces can obscure subtle differences in anomaly severity, causing visually distinct clips to receive similar representations or scores and thereby limiting the resolution of anomaly ranking. We propose Probe-VAD, an ordinal binary-probing framework that directly probes severity preferences from a frozen VLM. Given raw video clips, Probe-VAD queries ten ordered severity thresholds and extracts constrained YES/NO continuation likelihoods. Their normalized preferences form a cumulative severity profile, from which tail evidence is aggregated into a continuous anomaly score, with isotonic projection enforcing ordinal consistency. Experiments on public VAD benchmarks demonstrate superior performance with low computational cost. Probe-VAD provides a simple interface for translating frozen VLM visual understanding into continuous, rank-sensitive anomaly scores without task-specific training or caption-based compression. Code is available at: https://github.com/yvestine/COVAS-VAD.
Read the full abstract

All authors Jiawei Gu, Qilin Zhao, Tengkuo Guo, Zhiming Zhong, Shuangqing Zhang, Fan Lyu, Fang Zhao, Guo-Sen Xie, Caifeng Shan

Robotics

FluxVLA Engine: A One-Stop VLA Engineering Platform for Embodied Intelligence

Yinhao Li, Weixin Mao, Zihan Lan et al. (+22 more)

Vision-language-action (VLA) models, world-action models (WAMs), and offline reinforcement learning methods are rapidly expanding the design space of embodied policies, yet turning these algorithms into reliable robot systems remains constrained by fragmented data formats, training stacks, evaluation protocols, inference runtimes, and embodiment-specific interfaces. We present $\mathrm{FluxVLA}$ Engine, an open, configuration-driven platform that turns heterogeneous embodied-policy components into a reproducible data-to-deployment workflow. Rather than introducing another policy model, $\mathrm{FluxVLA}$ standardizes interfaces for datasets, visual-language and world models, action heads, reward- or advantage-weighted learning, distributed training, simulation evaluation, optimized inference, and robot operators. The engine further integrates compositional dual-arm simulation, scalable automatic data generation, and model-decoupled human-in-the-loop rollout, takeover, correction collection, and reward annotation. For responsive physical execution, it combines Real-Time Chunking (RTC) with accelerated inference backends, lightweight remote GPU serving, and configurable trajectory post-processing. Together, these capabilities connect offline learning, simulation validation, online correction, and real-robot execution through shared and auditable contracts. $\mathrm{FluxVLA}$ therefore targets the engineering bottlenecks separating promising embodied-learning algorithms from reproducible evaluation and dependable deployment. Code is available at https://github.com/FluxVLA/FluxVLA
Read the full abstract

All authors Yinhao Li, Weixin Mao, Zihan Lan, Jikun Rong, Qirui Hu, Yiming Zhang, Weipeng Deng, Bowen Shen, Minzhao Zhu, Yiming Mao, Yan Yang, Chenguang Cui, Hongyuan Chen, Xu Huang, Zheyi Zhao, Pinxi Shen, Bozhen He, Zhen Fu, Yifan Wang, Zexin Zhang, Ang Gao, Haoyu Chen, Chengqi Shi, Wenda Wu, Hua Chen

Human-Computer Interaction

[MM/AI] Mental Models in Human-AI Interaction: Methods and Challenges in the Generative and Agentic AI Era (Workshop)

Téo Sanchez, Bhada Yun, Prerna Ravi et al. (+6 more)

The mental model construct is widely used in HCI to refer to the knowledge structure people hold in order to reason about and interact with computing systems. Yet it is often operationalized intuitively: the construct is often used interchangeably with related concepts (e.g., folk theories, sensemaking) and methods of studying it (e.g., through elicitation) are many and diverse, with each method resting on distinct assumptions about what counts as a mental model. Generative and agentic AI systems may further complicate mental model formation and elicitation as such systems are opaque by design and increasingly act on users' behalf across files, applications, and on the web. Together, these challenges may hinder the commensurability of research on people's mental models of AI systems. The MM/AI workshop calls for a critical reassessment of how we understand and study mental models in human-AI interaction research. It aims to foster theoretical and methodological exchange on mental models in human-AI interaction, identify open challenges, and develop directions for future research. We invite short papers on users' or stakeholders' mental models of AI systems, particularly contributions that reflect on the conceptual and methodological foundations of the construct. The half-day workshop combines lightning talks, hands-on elicitation exercises, and structured discussions on key questions concerning the future of the mental model for human-AI interaction research.
Read the full abstract

All authors Téo Sanchez, Bhada Yun, Prerna Ravi, Laura Schütz, Anna Neumann, Robin Shing Moon Chan, April Yi Wang, Qiaosi Wang, Sumit Asthana

Cryptography and Security

Cross-Domain Inference for Human Localization: Applying Wi-Fi RSSI Data to CSI-Trained Models

Ariel Duschanek-Myers, Thomas Welsh and Helmut Neukirchen

Wi-Fi signal data can be used to compromise the privacy of individuals. While many existing approaches rely on Channel State Information (CSI), collecting this data on typical IoT devices often requires elevated operating system permissions and specialized drivers. Consequently, this paper investigates the feasibility of utilizing Received Signal Strength Indicator (RSSI) data to predict human locations. RSSI was selected because it is accessible even on devices with limited user permissions, and therefore is more applicable to a wider array of IoT devices. To bypass the tedious process of obtaining training data needed to train an RSSI-based model, an existing Wi-Fi pose prediction project was used in this research. However, that project assumed CSI data as input. Therefore, we investigate the feasibility of cross-domain inference, i.e., feeding RSSI data into that existing CSI-based model. We collected an RSSI dataset, synchronized with video ground-truth of a person moving within a room, to evaluate the model's performance. This evaluation confirmed that RSSI data can predict locations with approximately 80% confidence when human movement is present. This demonstrates that a model trained on CSI data can be used to evaluate low-granularity RSSI data consisting of decibel-milliwatt (dBm) values to roughly locate people in the collection space. These results imply that a wide range of IoT devices can be used for privacy invasion in Wi-Fi-dense environments.
Read the full abstract

Numerical Analysis · Cross-listed from eess.SP

Frame bounds and bandwidth tiling for time-causal bandpass wavelets

Jens E. Pedersen, Tony Lindeberg and Peter Gerstoft

Wavelets and frames that provide strong guarantees for signal representations are a cornerstone in signal processing theory, but have long been restricted to non-causal settings. Recent work extended wavelet analysis to time-causal systems that operate on streaming signals, with exact reconstruction and time-recursive implementations. However, the frame guarantees that make such representations reliable under noise and quantization are uncharacterized. We derive closed-form frame bounds and conditioning on band-limited domains, together with peak frequencies, constant-Q bandwidth tiling, and spectral decay rates for time-causal bandpass wavelets. Our work provides design rules for the scale ratio and channel count, which we validate numerically against discrete implementations of the causal wavelets in terms of recursive filters.
Read the full abstract

Robotics

TIO-Former: Ultra-Lightweight 6-Directional ToF-Inertial Odometry for Nano-UAVs via a Streaming Causal Transformer

Yang Liu, Yifan He, Wenhao Zhao et al. (+9 more)

Autonomous nano-UAV navigation requires accurate ego-motion estimation under stringent size, weight, power, and computing (SWaP-C) constraints, where visual sensors and LiDARs exceed payload limits, optical flow degrades in low-texture scenes, and inertial-only state estimation is susceptible to accumulated drift. While multi-zone time-of-flight (ToF) arrays provide a lightweight metric complement, 6-DoF estimation from merely 384 ranges per frame is challenged by invalid returns, anisotropic observability, and temporal computational scaling. We propose TIO-FORMER, a camera-free, optical-flow-free, and mapless range-inertial odometry framework driven by an IMU and an ultra-lightweight (15 g) payload of six orthogonal 8 x 8 ToF arrays. Our frontend pairs consecutive range grids with a bilateral gated difference, while IMU-guided cross-attention dynamically routes directional features conditioned on platform kinematics. A Streaming Causal Transformer couples an uncompressed Local KV cache with compressed Chunk-FIFO memory, maintaining bounded inference cost and memory footprint independent of flight duration. In real-flight evaluations, TIO-FORMER reduces open-loop position error by 54.4% compared to nano-UAV optical flow and by 66.4%-89.1% over learned inertial baselines. We also evaluate performance across multiple environments and robustness under severe sensing degradation. Deployed on an edge RISC-V companion computer, TIO-FORMER achieves a P95 latency of 10.466 ms and peak resident memory of 6.324 MiB (less than 5 percent system RAM), demonstrating that sparse range sensing provides practical geometric anchoring for resource-constrained micro-aerial robots. Code is available at https://github.com/Ly041021/TIO-Former.
Read the full abstract

All authors Yang Liu, Yifan He, Wenhao Zhao, Xiangyu Mo, Yang Xu, Hao Wei, Mingze Ma, Huan Li, Yifan Wu, Fei Gao, Zipeng Dai, Xin Zhou

Machine Learning

MyoFlow: Anchor-Tied Rectified Flow for HD-sEMG Gesture Recognition Across Sessions and Subjects

Chenhao Wu, Dingjie Peng, Zhihe Zhang et al. (+6 more)

High-density surface electromyography (HD-sEMG) gesture recognition supports prosthetic control, assistive robotics, and rehabilitation, but electrode re-donning and physiological variability cause distribution shifts that degrade accuracy across sessions and subjects. Generative HD-sEMG models primarily synthesize signals for augmentation; although diffusion models enhance representation learning, prediction still relies on a separate classifier. To tie learned dynamics to the decision rule, we propose MyoFlow, the first discriminative flow-matching framework for HD-sEMG recognition across sessions and subjects. It recasts classification as anchor-tied transport: a domain-conditioned rectified flow moves encoded windows toward gesture anchors that serve as transport targets and define the nearest-anchor decision geometry, enabling zero-shot recognition without an independent head. On the Hyser dataset, MyoFlow improves mean cross-session and cross-subject accuracy over the strongest diffusion-based baseline by 4.24% and 6.37%, respectively, and achieves 91.71% mean zero-shot accuracy and 97.39% mean few-shot accuracy across multiple days on the CEMHSEY dataset.
Read the full abstract

All authors Chenhao Wu, Dingjie Peng, Zhihe Zhang, Satoshi Funabashi, Satoshi Konishi, Wuqiang Yang, Hiroshi Onoda, Hironori Washizaki, Jiang Liu

Artificial Intelligence

End-to-End Latency-Minimizing and Load-Balanced Request Scheduling for Edge LLM Inference in Agentic AI Services

Zhen Li, Jun Cai, Haoran Gao et al. (+2 more)

Large language model (LLM)-powered agentic AI services increasingly demand low-latency inference, motivating the deployment of LLMs across distributed edge servers. However, heterogeneous communication and computing capabilities, together with dynamically evolving inference states, make the edge server selection for each incoming request time-varying and tightly coupled across slots. In this paper, we investigate an online request scheduling framework for edge LLM inference that jointly minimizes long-term average end-to-end latency and regulates workload distribution across heterogeneous edge servers. Two main challenges arise in this context. First, conventional latency models cannot accurately capture the fine-grained dynamics of multi-stage LLM execution. Second, the latency consequence of a scheduling decision is observed only after request completion, making immediate decision evaluation difficult. To address these challenges, we develop a cross-slot inference model that captures transmission, prefill, iteration-level decoding, and key-value (KV) cache evolution for each diverse request, and characterize server workload through a KV cache memory-time consumption metric. We propose the LYREO approach that transforms the long-term load-balancing constraint via Lyapunov optimization and employs reward redistribution with sequencebased return prediction to convert delayed outcomes into timely learning signals for earlier decisions. Simulations under various configurations demonstrate that LYREO consistently achieves lower latency and more balanced load distribution than representative learning-based and heuristic baseline schemes.
Read the full abstract

All authors Zhen Li, Jun Cai, Haoran Gao, An Li, Tan Li

Systems and Control

Data-Driven Policy Iteration Without an Initial Stabilizing Policy: A Finite-Horizon Bootstrap Method

Jiacheng Wu and Yang Zhu

This article investigates data-driven policy iteration (PI) for continuous-time linear systems without requiring an initially stabilizing policy. Standard infinite-horizon PI is not self-starting because its policy-evaluation step is well posed only when the feedback gain is stabilizing. However, verifying this property is difficult when the system matrices are unknown. To remove this requirement, we develop a finite-horizon bootstrap method. The key idea is to perform policy evaluation over a compact interval for a shifted system, where the evaluation equation is well defined for arbitrary bounded time-varying policies. We show that, for a sufficiently long horizon, the initial-time optimal gain of the shifted finite-horizon problem, when applied as a constant feedback gain, achieves a prescribed stability margin for the original system. We then derive a data-driven implementation from an off-policy identity evaluated along trajectories of the original plant. We use basis-function approximations to reconstruct the finite-horizon value matrix and policy, and we characterize the resulting error through a perturbed policy-improvement recursion. A data-driven Lyapunov certificate is further introduced to verify admissibility of the candidate gain before it is used to initialize infinite-horizon PI. Numerical studies of a batch reactor and a two-mass-spring system demonstrate the effectiveness of the proposed bootstrap method.
Read the full abstract

Computer Vision

EventEgoHands++: Event-based Egocentric 3D Hand Mesh Reconstruction with Real Dataset

Ryosei Hara, Wataru Ikeda, Masashi Hatano et al. (+1 more)

3D hand mesh reconstruction is a challenging yet essential task for downstream applications, including human-robot interaction and AR/VR. Although conventional cameras have been widely adopted for this task, methods that rely on them struggle in low-light environments and under severe motion blur. To address these limitations, event-based cameras have recently attracted attention for their high dynamic range and high temporal resolution. However, applying event cameras to egocentric hand reconstruction remains challenging because camera wearer's motion produces dense background events that obscure hand-specific signals. Although the first egocentric event-based approach mitigates this issue using hand segmentation, its binary hand mask does not distinguish between left and right hands. As a result, the model lacks instance-level hand information and predicts both hands even when only one or neither hand is present. This limitation leads to incorrect inter-hand relationships and degraded reconstruction accuracy. In this paper, we propose EventEgoHands++, a framework for event-based 3D hand mesh reconstruction from an egocentric viewpoint. The proposed method incorporates a Hand Detector that estimates instance-level bounding boxes and masks for both the left and right hands. Moreover, we introduce Adaptive Attention, which dynamically gates the attention based on these detection results to accurately learn the spatial relationship and mutual interactions between the hands. To train and evaluate our framework, we extend the synthetic N-HOT3D dataset and newly construct EEH-R, the largest real-world event-based egocentric hand dataset to date, comprising approximately 1M annotated frames captured in environments including low-light conditions. Extensive experiments on both synthetic and real datasets demonstrate that our method consistently outperforms the baselines.
Read the full abstract

All authors Ryosei Hara, Wataru Ikeda, Masashi Hatano, Mariko Isogawa

Robotics

Fleet-To-Lab: A Transfer Learning Framework For Lunar Rover Slippage Estimation Via Model Fusion

Riccardo Viviano, Saki Omi, Andrej Orsula et al. (+1 more)

Accurate wheel slip estimation is essential for autonomous lunar rover mobility and navigation. Machine Learning models trained on terrestrial data generalize poorly to lunar terrain, and real lunar datasets are scarce due to the limited number of missions and costly data acquisition. We present Fleet-to-Lab, a transfer learning framework that leverages proprioceptive data collected by previously deployed heterogeneous lunar rovers to mitigate the Earth-Moon domain gap in slip estimation for a future deployable unit. We fuse several heterogeneous expert models into a single architecture, using a modest dataset collected after the rover deployment. We propose AcoMerge, a new hybrid swarm-intelligence algorithm that performs model fusion by searching for an optimal combi- nation of expert parameters. Experiments conducted in a high- fidelity physics simulation show balanced accuracy and macro- F1 improvements compared to deep model fusion baselines. AcoMerge exhibits competitive performance with joint training on deep architectures, while achieving higher macro-F1 and balanced accuracy on a smaller model. Overall, our framework shows model fusion as a possible transfer learning alternative for slippage estimation in space robotic missions with limited data.
Read the full abstract

All authors Riccardo Viviano, Saki Omi, Andrej Orsula, Miguel Olivares-Mendez

Numerical Analysis

Error Bounds for Boundary-Stopped Positive Cubature Schemes for Hamilton–Jacobi–Bellman Equations

Haoran Xu and Xingye Yue

We derive error bounds for a boundary-stopped positive cubature scheme for degenerate parabolic Hamilton–Jacobi–Bellman equations with Dirichlet data on bounded domains. The scheme balances antipodal branches at their first boundary contacts and uses a control-dependent effective time. Its stopped-barrier remainder is \(O(\tau\Delta t^{\gamma/2})\), and the total mass of interpolated branches is at most \(2\tau/\Delta t\), where \(\tau\) is the effective time. After division by the effective time, these estimates give a consistency bound that is uniform as \(\tau\to0\). Under a common strict boundary barrier and the stated mesh conditions, interior consistency, coefficient shaking, switching, and localized comparison yield \[ \|(u-u_h)^+\|_\infty\le C(\Delta t^{1/4}+h\Delta t^{-1/2}), \qquad \|(u_h-u)^+\|_\infty\le C(\Delta t^{1/10}+h^{1/2}\Delta t^{-1/4}). \] Thus \(\Delta t\asymp h^{10/7}\) gives an \(O(h^{1/7})\) maximum-norm bound. The analysis applies to any fixed centrally symmetric positive degree-two cubature and permits rank-deficient diffusion. Numerical examples examine parallel heat loss to a cold wall and control-dependent, rank-deficient diffusion.
Read the full abstract

Distributed Computing

DS2-Based Cross-Data-Space Interoperability for Precision Agriculture

Katerina Kyriakou, Ilias Syrigos, Ioannis Moutsinas et al. (+2 more)

Despite the strategies of modern precision agriculture to leverage the integration of legacy agricultural systems, the challenges of IoT data fragmentation, farmers' sovereignty preservation, and limited interoperability still persist. This paper presents our work, conducted within the Horizon Europe DS2 project (DataSpace, DataShare 2.0), that applies an interoperability-oriented framework supporting participants of different agricultural data spaces to share data products and services under secure, sovereign, and transparent methods. The suggested methodology follows a layered reference architecture, where each layer consists of independent operational modules that facilitate the inter-sector data exchange between DigiAgro and AgroScience Data Spaces. The result of this work is an automated ecosystem for sharing diverse farm IoT measurements, satellite images and metrics, weather forecasts, and analytics services across distinct data spaces, aiming to generate accurate recommendations on crop practices, such as irrigation schedules, that farmers and agronomists will rely on to increase crop production while maintaining sustainability.
Read the full abstract

All authors Katerina Kyriakou, Ilias Syrigos, Ioannis Moutsinas, Panagiotis Tzimotoudis, Thanasis Korakis

Machine Learning

LoopSpec: Pipelined Self-Speculative Decoding for Looped Transformers

SangLyul Cho, Langqing Cui, Sehoon Kim et al. (+2 more)

Looped Transformers achieve strong performance with compact parameter sizes by repeatedly applying a shared stack of Transformer blocks across recurrent depths. However, they incur higher decoding latency than standard Transformer models of comparable parameter size because shared weights are accessed at every recurrent depth. To improve decoding efficiency, self-speculative decoding is particularly well suited to Looped Transformers, as their intermediate recurrent states can directly provide draft predictions without an auxiliary draft model. We therefore propose LoopSpec, a training-free self-speculative decoding framework tailored for Looped Transformers. LoopSpec extracts draft tokens from early recurrent states and operates in a pipelined manner, overlapping draft generation of future tokens with target verification of the current token. To improve draft accuracy without excessive compute overhead, we introduce a selective second proposal from deeper recurrent depth while ensuring lossless decoding under both greedy and sampling regimes. Furthermore, we derive the optimal proposal depths in closed form and show the prediction matches measurement. Across reasoning and coding benchmarks, LoopSpec achieves up to 6.83$\times$ inference speedup across diverse Looped Transformers.
Read the full abstract

All authors SangLyul Cho, Langqing Cui, Sehoon Kim, Dongsu Han, Insu Han

Computer Vision

Multimodal Cultural Heritage Architectural Style Classification for Residential Buildings in the UAE Based on CLIP Embeddings and SVM

Ahmed Ammar Kubba, Manar Abu Talib, Iman Ibrahim et al. (+1 more)

The analysis and classification of cultural heritage architectural styles remain challenging due to the complexity of visual images of buildings, which are highly relied on in traditional CNN-based classification approaches in comparison to textual descriptions, and the relative lack of non-western region-specific datasets. This paper addresses this gap by proposing a multimodal machine learning framework to analyze and classify Emirati residential architecture using OpenAI's CLIP model. We integrate visual features from images and textual features from expert descriptions into a unified 512-dimensional embedding, followed by dimensionality reduction with UMAP for visualization and unsupervised clustering using K-Means. Cluster labels, which are derived from manual analysis of the K-Means clusters, are used to train an SVM classifier for automated architectural style classification. Our approach achieves a classification accuracy of 98% across eight identified style clusters, higher than every other study in the literature, demonstrating the effectiveness of combining visual and textual modalities. Overall, this paper highlights the potential of using multimodal AI to support architectural heritage analysis, offering scalable and interpretable tools for exploring regional architectural identities.
Read the full abstract

All authors Ahmed Ammar Kubba, Manar Abu Talib, Iman Ibrahim, Qassim Nasir

Artificial Intelligence

MOCC-R1: Reinforcing Reasoning-Response Consistency for Multimodal Counselor Response Generation

Wenjie Zheng, Qiming Xie, Jianfei Yu et al. (+1 more)

Multimodal counselor response generation (MCRG) aims to generate an appropriate counselor response from multimodal dialogue histories. Progress is limited by two gaps: first, existing datasets rarely capture sustained, human-recorded counseling interactions conducted by qualified counselors; Second, existing methods do not explicitly optimize consistency between counseling reasoning and the generated response, potentially undermining the reliability of MCRG systems. Thus, we introduce MOCC, a multimodal counseling conversation corpus containing over 200 hours of interactions involving 154 credential-verified counselors. Based on MOCC, we propose MOCC-R1, a two-stage framework for optimizing reasoning-response consistency. Cold-start supervised fine-tuning trains the model to generate a structured trajectory consisting of client-state understanding, a response intent that links a counseling principle to a planned action, and the final response. Reinforcement learning (RL) then rewards grounded plan coherence and plan execution, encouraging the inferred state and plan to be supported by the dialogue context and the response to realize that plan. Experiments demonstrate the effectiveness of the proposed MOCC-R1.
Read the full abstract

All authors Wenjie Zheng, Qiming Xie, Jianfei Yu, Rui Xia

Performance

Discovering Performance Archetypes: Critical-Path-Aware Pattern Analysis and Regression Detection

Kaveh Shahedi, Heng Li, Maxime Lamothe et al. (+1 more)

Software performance analysis and prediction requires integrating multiple signals, as code structure alone cannot capture runtime behavior shaped by execution frequency, resource contention, and I/O patterns. We present a critical-path-aware performance analysis methodology that automatically discovers recurring performance patterns by synthesizing static code features, dynamic execution traces, and kernel-level resource data. In a preliminary study across six real-world C/C++ applications (SQLite, OpenSSL, Zstandard, FFmpeg, cURL, and jq), we first empirically confirm that static complexity metrics explain only 10.4% of the variance ($\rho^2$) in critical path execution time, quantifying a gap that, while theoretically expected, had not been measured systematically across applications. Motivated by this finding, we analyze nearly 80,000 critical execution paths and address two research questions. First, we discover 13 distinct performance archetypes: recurring behavioral patterns that appear consistently across different applications, independent of their domain or implementation. Five of these patterns are near-universal and appear in at least five of the six applications studied. Notably, three of these archetypes are present in all six applications, and together, these common patterns account for 56.4% of all observed paths. Each archetype maps to specific resource profiles and optimization strategies that transfer across domains. Second, we leverage these archetypes within a multi-signal regression detection framework that triangulates path structure, resource consumption, and archetype deviations, achieving an F1-score of 0.867 and a 60.4% improvement over resource-only methods.
Read the full abstract

All authors Kaveh Shahedi, Heng Li, Maxime Lamothe, Foutse Khomh

Machine Learning

IRENE: A Convolutional GRU Ensemble Model for Radar Precipitation Nowcasting over Italy

Alessandro Camilletti, Gabriele Franch, Elena Tomasi et al. (+1 more)

We present IRENE (Italian Radar Ensemble Nowcasting Experiment), a deep learning model for probabilistic short-range precipitation nowcasting over the Italian domain at \SI{1}{km} spatial and 5 min temporal resolution. IRENE adopts an encoder–forecaster architecture built on multi-scale Convolutional Gated Recurrent Units (ConvGRUs), trained on the national radar composite produced by the Italian Civil Protection Department (DPC). An importance-sampling scheme focuses training on precipitation-relevant events, while the almost-fair Continuous Ranked Probability Score (afCRPS) is adopted as the primary probabilistic loss function. Two additional training configurations are proposed: an adversarial (GAN) variant, IRENE-GAN, designed to improve the spatial sharpness of the generated forecasts, and a spectrally constrained variant, IRENE-GAN-RAPSD, in which the adversarial objective is complemented by an explicit penalty on the radially averaged power spectral density. The three configurations are evaluated against the stochastic extrapolation method STEPS and the pre-trained deep learning model DGMR. All IRENE configurations attain a lower Continuous Ranked Probability Score than both benchmarks at every lead time and rank histograms closer to uniformity, indicating better probabilistic skill and ensemble calibration. In terms of ensemble-mean mean absolute error the advantage is confined to the first 90 min, beyond which the strongly damped DGMR fields and, to a lesser extent, STEPS become competitive. Spectral analysis shows that the adversarial training removes the progressive loss of small-scale variance exhibited by IRENE, at the cost of an excess of fine-scale power at long lead times that the spectral penalty only partially controls.
Read the full abstract

All authors Alessandro Camilletti, Gabriele Franch, Elena Tomasi, Marco Cristoforetti

Robotics

Fingers as Legs: Learning Self-Supported Locomotion and Manipulation with an Anthropomorphic Hand

Amirhossein Kazemipour, Hehui Zheng and Robert Katzschmann

A walking robotic hand must use the same fingers to move its body, support its weight, and interact with the environment. We show how an anthropomorphic hand can learn these skills while retaining its finger design and position controller. Onboard power and computation make the platform self-contained. Our reinforcement learning approach accounts for the hand's unequal fingers, with training in a simulator calibrated from hardware measurements. In simulation, the hand moves faster with our reward formulation than with tuned rewards originally designed for quadrupeds. On hardware, task-specific policies enable untethered crawling, steering, and fall recovery. While supporting its own weight, the hand also executes successive keyboard commands without vision and pushes an object to targets using overhead visual feedback. These results demonstrate a compact mobile manipulator that reuses its fingers for locomotion and interaction, without a separate locomotion mechanism.
Read the full abstract