Peer Revenue Play credits. Real papers.

Papers

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

Computer Science

cs Watch Computer Science

Monday 14 September

Artificial Intelligence

Converting Sequenced Fuzzy Cognitive Maps to Causal Virtual Worlds with Large Video Generators

Akash Kumar Panda, Olaoluwa Adigun and Bart Kosko

We show how users can create and manipulate causal virtual worlds with large-language-model (LLM) and large-video-model agents. The approach uses feedback fuzzy cognitive maps (FCMs) both to model the granular causal structure of the virtual world and to guide its causal evolution. The local causal rules are partial or fuzzy while the FCM's feedback structure produces global equilibria that define causal scenarios. A sequence of dynamical meta-rules of the form “If $\mathcal{A}$ then $\mathcal{B}$" define the causal scenes of the virtual-world video. The if-part causal pattern $\mathcal{A}$ perturbs the FCM's virtual world at the user's or agent's discretion. The FCM's transient feedback dynamics define the meta-rule's causal arrow of implication. The then-part $\mathcal{B}$ is the resulting equilibrium attractor such as a FCM limit cycle or fixed point. Our algorithm extracts these meta-rules from the FCM and guides the LLM agent to write a script based on the FCM meta-rule sequence. The large video generator converts the meta-rule into a video scene in accord with the flow of the dynamics. We applied the agent-based technique to a simple FCM that describes an undersea world of dolphins and sharks. Google's Gemini 3.1 generated the script and Google's Veo 3.1 generated the dolphin-shark video. The approach is general and can scale by mixing larger FCMs and AI agents to produce more immersive virtual worlds.
Read the full abstract

Robotics

Two-Stage Personalized Gait Phase Estimation in Stroke Survivors During Exoskeleton-Assisted Walking: An Offline Feasibility Study

Hyungseok Ryu and Pilwon Hur

This study evaluated personalized gait phase estimation for stroke survivors using functional inertial measurement unit (IMU) alignment and two-stage sequential adaptation of models pre-trained on healthy gait. The estimator used signals from a thigh-mounted IMU. Heel force-sensitive resistor measurements provided reference phase labels for offline adaptation and evaluation. Stage 1 established a distillation-regularized participant-specific model, and Stage 2 performed conditional refinement using low-rank adaptation. Long Short-Term Memory (LSTM), Temporal Convolutional Network (TCN), and Transformer models were evaluated in five stroke survivors walking with a powered knee exoskeleton using leave-one-subject-out hyperparameter selection and sequential test-then-adapt Stage 2 replay. Relative to the non-adapted baselines, Stage 1+2 reduced the mean participant-wise phase root mean square error by 84.2%, 77.0%, and 60.7%, respectively. The Transformer achieved the lowest final error (2.90 +- 1.13$% of the gait cycle) and heel-strike timing error (23.7 +- 4.5ms). Policy-specific ablations showed that every-cycle updates generally produced the lowest or near-lowest error, whereas conditional updating reduced the update frequency with small accuracy differences. After personalization, alignment produced model-dependent changes in phase error while preserving or improving heel-strike detection and reducing heel-strike timing error for the LSTM and Transformer. Concurrent embedded tests showed that the TCN and Transformer maintained 100-Hz inference during Stage 2 updates without deadline misses, whereas the LSTM missed the 10-ms deadline in 6.6% of inferences. All updates completed within 0.8s. These results support the offline feasibility and embedded computational timing of the proposed framework for exoskeleton-assisted walking.
Read the full abstract

Software Engineering

Cross-Ecosystem Packages As Multilingual: Prevalence, Architecture, and Health

Xiangxi Li, Olivier Nourry, Yoshiki Higo et al. (+1 more)

Modern software development increasingly relies on using multiple programming languages. Some software packages are published to multiple package ecosystems such as NPM for JavaScript and PyPI for Python. Little is known about cross-ecosystem packages, especially regarding how they are structured. In this paper, we conduct a large-scale empirical study of over six million packages across six major ecosystems to understand 1) how prevalent cross-ecosystem packages are among all packages, 2) whether there are distinct source code architectural patterns that cross-ecosystem packages use, and 3) whether there are correlations between architectural patterns and project health metrics from GitHub. Results indicate that cross-ecosystem packages constitute a small but important, growing fraction of packages. We identify five distinct architectural patterns. For example, packages that implement code generation from a shared source file or use language bindings are associated with significantly higher community visibility and development activity. Based on our findings, we provide implications for package adopters, maintainers, and researchers. We envision our taxonomy being used for future investigations into several aspects of software development, such as the trade-offs between focusing on one language and translating to other languages using bindings, templating, and wrappers, versus using native code and native functions to support additional languages.
Read the full abstract

All authors Xiangxi Li, Olivier Nourry, Yoshiki Higo, Raula Gaikovina Kula

Numerical Analysis

efficient matrix-free gauss-newton traveltime tomography on full-metric deformed grids

Zuwei Huang, Pingchuan Ma, Peng Yu et al. (+4 more)

First-arrival traveltime tomography provides a computationally efficient means of imaging subsurface velocity structure, while boundary-conforming deformed grids allow rugged topography to be represented without abandoning a logically structured mesh. In matrix-free Gauss-Newton inversion, however, the linearized full-metric Eikonal transport and its transpose must be applied repeatedly at a fixed background model. Directional sweeping consequently revisits the same state-dependent dependency structure for every Krylov right-hand side. We recast the frozen tangent transport as a directed graph and distinguish loss of the background-traveltime ordering from genuine algebraic cyclicity. Strongly connected components identify the irreducible part of the transport, whereas the remaining dependencies admit exact scalar substitution after reordering. The condensation graph and local block factorizations are constructed once for each frozen source state and then reused for both primal and transpose applications. Numerical experiments on deformed grids and a three-dimensional tomography problem show that the resulting block-triangular formulation preserves the frozen sensitivity action while substantially reducing the repeated transport cost. By eliminating this dominant inner-iteration cost, the proposed method markedly accelerates Gauss-Newton computation and makes full-metric matrix-free inversion on deformed grids practical at much lower cost.
Read the full abstract

All authors Zuwei Huang, Pingchuan Ma, Peng Yu, Takao Koyama, Luolei Zhang, Chongjin Zhao, Mingxin Chu

Systems and Control

Topology-Aware Congestion Pricing: Demand Robust Routing using the Forman-Ricci Curvature

Sheryl Paul, Samuel Williams, Kexin Wang et al. (+2 more)

Congestion pricing is widely used to improve transportation network efficiency where individual decentralized route choices can lead to system-level inefficiencies. Pigouvian tolls achieve the system optimum but depend on demand and can lose effectiveness under demand shifts, particularly on structurally critical bottleneck edges. We propose a topology-aware regularization of the Beckmann potential governing the (Wardrop) equilibrium by augmenting precomputed Pigouvian tolls with an offline structural penalty derived from Forman–Ricci curvature (FRC), which captures bottleneck structures. We prove that the resulting equilibrium is well-defined, that stronger regularization reduces flow on penalized edges, and that efficiency loss depends on how closely the structural penalty approximates optimal Pigouvian tolls. Experiments on eight real-world networks under targeted and uniform demand perturbations show reduced bottleneck flow with near-optimal efficiency. FRC achieves reductions comparable to edge betweenness at substantially lower computational cost, making it a practical, robust complement to classical congestion pricing.
Read the full abstract

All authors Sheryl Paul, Samuel Williams, Kexin Wang, Ruolin Li, Jyotirmoy V. Deshmukh

Information Retrieval

LazFormer: Scaling Transformers for Industrial Recommendation via Transferable Generative Pre-training

Xiaodong Li, Alin Fan, Mingyang Li et al. (+7 more)

Transformers have shown promising performance in LLMs due to their outstanding scalability, several studies have investigated the scalability of Transformers for industrial recommendation. They typically rely on a single ranking model to optimize both sparse and dense parameters from scratch, resulting in substantial computational resource consumption and slow convergence. Fortunately, the pre-training models offer an effective solution to the above issues by providing favorable initialization of both sparse and dense parameters for the subsequent ranking. However, they still face two major limitations: (1) Since the input features used in pre-training and ranking are usually inconsistent, directly transferring dense parameters from pre-training to ranking may lead to negative transfer. (2) Multi-epoch training during the ranking process may result in the overfitting of sparse parameters, while freezing the sparse parameters limits their adaptability to the ranking objectives. To this end, we propose a Scaling Transformer for Industrial Recommendation via Transferable Generative Pre-training, termed LazFormer. Specifically, we first present a generative pre-training module to autoregressively generate sequential features, providing favorable initialization of both sparse and dense parameters for the subsequent ranking. To solve the negative transfer of dense parameters, we propose a transferable residual adapter that injects additional ranking-specific features into ranking in a residual manner. Moreover, a request-aware ranking module integrates long-sequence compression, hybrid sparse attention, and a request-aware paradigm to efficiently model users' long sequences. Besides, we further propose an asymmetric multi-epoch training strategy that resets sparse parameters while continuously accumulating dense parameters across epochs, alleviating the overfitting of sparse parameters.
Read the full abstract

All authors Xiaodong Li, Alin Fan, Mingyang Li, Yan Xiao, Shichao Nie, Junfeng Zhang, Shaochuan Lin, Zhanming Ou, Tao Luo, Xiaoyi Zeng

Machine Learning

LiftGCN: Efficient Energy-Preserving Graph Learning via Joukowski Spectral Lifting for Finite Element Stress Prediction

Chen Zeng and Qiao Wang

Finite element stress fields often exhibit strong local non-smoothness, where stress concentrations near holes, notches, and loading regions induce sharp spatial gradients and high-frequency graph components. Although graph neural networks naturally operate on irregular finite element meshes, conventional message passing is inherently smoothing and progressively attenuates such high-frequency information. Unitary propagation alleviates this problem by preserving spectral magnitudes, but typically relies on matrix functions and high-order approximations with $O(Ked)$ propagation complexity. We propose LiftGCN, an efficient spectrally stable graph network based on Joukowski spectral lifting. LiftGCN maps the real spectrum of a normalized graph operator onto the unit circle through the Joukowski relation and realizes the resulting spectral transformation as a simple second-order recurrence, avoiding matrix exponentials, eigendecomposition, and high-order polynomial truncation. We show that the linear Joukowski backbone has unit-modulus characteristic roots and admits an energy-preserving structure under a positive-definite metric, preventing exponential attenuation of graph-frequency components with depth. Each layer requires only one sparse neighborhood aggregation, yielding $O(ed)$ propagation complexity, while lightweight local nonlinear residuals provide expressive feature transformations. Experiments on finite element stress prediction demonstrate that LiftGCN achieves competitive overall accuracy while improving reconstruction of stress concentrations and local high-gradient structures with substantially reduced computational cost. Our code is available at https://github.com/ChenZeng001/LiftGCN.
Read the full abstract

Artificial Intelligence

MemRiskBench: Trace-Aware Risk-Preserving Evaluation for Long-Horizon LLM Agents

Jianhua Jiang, Dongbo Yuan and Weihua Li

Long-horizon LLM agents accumulate memory across sessions, creating sparse but high-impact risks: stale facts, conflicting updates, cross-user leakage, revoked-memory reuse, and constraint decay. Standard aggregate scores hide per-risk failure rates–a model achieving 78% average accuracy may still leak data in 4% of episodes–and benchmark compression preferentially discards the rare high-severity events that distinguish a mostly-working model from one that occasionally causes harm. We present MemRiskBench. The primary contribution is a five-category risk taxonomy (plus one documented, unscored category) operationalized by deterministic trace grounded checks, instantiated as a 120-episode scripted benchmark with full trace logging and no LLM-as-judge on the pass/fail path, evaluated on five locally run quantized instruction-tuned models. Second, a risk-preserving subset selector: a coverage-constrained greedy selector on deterministic trace-derived features that retains full ranking (Spearman rho = 0.975, deterministic; CI collapses to a point estimate with zero bootstrap variance), risk coverage (1.0), and high-risk model detection (1.0) at a 20% subset size, reducing compute 5x. Unlike ranking-only subset selectors, this selector additionally preserves risk-type coverage and high-risk detection using trace-grounded deterministic features that do not require an LLM judge. All episodes, traces, the scoring implementation, and the selector are released to support reproducible evaluation and risk assessment of deployed LLM agents
Read the full abstract

Data Structures and Algorithms · Cross-listed from math.PR

The threshold for online balancing of i.i.d. binary vectors

Dylan J. Altschuler and Konstantin Tikhomirov

Consider the task of online vector balancing for stochastic arrivals $X_1,\ldots,{X_T}$, where the $X_i$ are independent uniformly random $d$–sparse binary vectors in $\{0,1\}^n$. This is a random analogue of the online Beck–Fiala problem. We show that uniformly for $2\le d\le n/2$ and $T = \Theta(n)$, the optimal online prefix discrepancy $\max\limits_{t\leq T}\left\|\sum_{i=1}^t\sigma_i X_i\right\|_\infty$ is of order \[ \Theta\big(\max\{\sqrt d,\log\log n\}\big). \] The upper bound is achieved by an efficient online algorithm. Thus, for $d\le(\log\log n)^2$, the optimal discrepancy is $\Theta(\log\log n)$ and is independent of the sparsity up to constant factors, whereas above this scale it is $\Theta(\sqrt d)$, matching the order of the offline discrepancy. This identifies the threshold at which sparsity begins to govern the online discrepancy of the random Beck–Fiala model.
Read the full abstract

Computer Vision

PhysBrain 1.5: From Vision-Language Models to Physical Foundation Models

DeepCybo Team, Yu Bin, Haipeng Cao et al. (+51 more)

We present PhysBrain 1.5, a unified model for understanding physical environments, generating actions, and predicting future states. Motivated by the physical loop of observation, interaction, and environmental change, we bring these capabilities into a common learning framework. Starting from a general vision–language model, we encode language responses, end-effector motion, and dense visual targets as discrete sequences and jointly optimize them with autoregressive next-token prediction. Pre-training draws its embodied supervision entirely from human interaction videos, using task-centered episodes to pair semantic and spatial context with recovered motion and subsequent observations. We then adapt the model through supervised fine-tuning on a mixture of human demonstrations, robot trajectories, and simulated experience. Across 28 embodied understanding benchmarks, our 8B model achieves an average score of 72.5, setting a new open-source state of the art and performing on par with leading proprietary models such as GPT-6-Astra and Gemini 3.6 Flash. It achieves the best open-source results on 14 benchmarks while retaining general multimodal capabilities. Beyond these understanding evaluations, qualitative examples show the model's ability to produce end-effector trajectories and predict future scenes through spatially aligned RGB, depth, and robot-mask outputs.
Read the full abstract

All authors DeepCybo Team, Yu Bin, Haipeng Cao, Zheng Chang, Kai Chen, Youning Chen, Kailin Deng, Yichao Du, Xiaotong Fu, Haoyang Ge, Yunlong Guo, Chenliu Hao, Jiyan He, Xuguo He, Yakun Hou, Kai Hu, Cong Huang, Tuopusen Huang, Yu Huang, Hong Li, Peize Li, Shijie Lian, Xiaopeng Lin, Yun Lin, Haibao Liu, Haochen Liu, Qiuzhi Liu, Shengcai Liu, Zhiqiang Liu, Tao Luo, Peng Ren, Shuo Ren, Chaoyi Ruan, Zhaolong Shen, Yukun Shi, Qiyuan Su, Yuxuan Tian, Yining Wang, Changti Wu, Hao Wu, Xueyin Xu, Ruoqi Yang, Zhaoyang Yang, Hang Yuan, Zhaoyang Zeng, Hanwen Zhang, Ruimeng Zhang, Yao Zhang, Yibo Zhang, Yuxiang Zhang, Zhirui Zhang, Ziyi Zhang, Zubin Zheng, Zishen Zhuang

Machine Learning

Learning to Solve Stochastic Controls with Unknown Drifts and Running Rewards: Theory, Algorithms and Convergence

Jin Ma, Gaozhan Wang, Jianfeng Zhang et al. (+1 more)

We study continuous-time and possibly high-dimensional stochastic control problems where drift coefficients and running reward functions are unknown. Due to these missing model primitives, we take the exploratory, reinforcement learning (RL) framework of Wang, Zariphopoulou, and Zhou(2020) with relaxed controls and entropy regularization. The objective is to develop theoretically grounded, efficient and scalable RL algorithms to learn both the optimal value functions (which also solve the exploratory HJB equation) and optimal exploratory feedback control policies. When the diffusion coefficients do not contain control, we employ probabilistic representations of both the optimal value function and its gradient based on an auxiliary state process depending only on the diffusion part of the original dynamics. With a delicate analysis on some properly defined mappings and their fixed points, this leads to the introduction of our policy iteration algorithms and their convergence. We demonstrate the performance of our algorithms through various numerical examples. Finally, we study a special control-dependent diffusion case where probability representation of the Hessian is called for.
Read the full abstract

All authors Jin Ma, Gaozhan Wang, Jianfeng Zhang, Xunyu Zhou

Graphics

Opacity Is Not Just Opacity

Chunran Zhang and Tianrui Li

Web graphics travel with content across pages and themes, where changing backgrounds can require recoloring and maintenance. Opacity already makes a fixed object's appearance depend on its background, yet is usually understood only as how much the object obscures it. In fact, opacity controls the scaling of the object-background color difference; transparency is only one effect of this relationship. Zero places the output at the background and one at the source color, but difference scaling need not stop at either position. We retain the compositing expression and extend the coefficient domain from $[0,1]$ to the real numbers: negative values reverse the difference, whereas values above one expand it in the same direction. We focus on same-direction expansion for reusing Web graphics across backgrounds. Each object carries a fixed source color and coefficient, while the actual background determines the enhancement direction. Background-adaptive contrast enhancement thus becomes part of the object's compositing properties, reducing the design and maintenance of separate color variants. The implementation reuses the original equation without increasing the per-pixel arithmetic operation count within the same pipeline. Enumerating all 8-bit sRGB source colors on 16 predefined light and dark canvases, a fixed $\alpha=1.1$ increases the contrast ratio in 99.8145% of combinations. Without changing source colors, 4.8346% of all combinations newly reach the $3:1$ contrast threshold. Output validation and timing across three browsers demonstrate implementation in the same WebGL pipeline, with no sustained additional runtime observed.
Read the full abstract

Artificial Intelligence

Towards a knowledge-enhanced single-cell foundation model

Hanqing Zhang, Jie Bao, Mei Ma et al. (+7 more)

Single-cell foundation models (scFMs) increasingly rely on large-scale transcriptomic pretraining, yet expanding pretraining data can yield diminishing gains while substantially increasing computational cost. Our data scaling analyses showed that incorporating biological knowledge, including cell-level text annotation and gene-level regulatory information, provided additional scaling dimension than simply increasing data size. Motivated by this observation, we present scKITE, a simple yet effective scFM that integrates cell-annotation and gene-regulatory supervision into a shared transcriptomic Transformer encoder through lightweight auxiliary decoders. These decoders are used only during pretraining and subsequently discarded, yielding a general-purpose encoder enriched with biological knowledge for downstream applications. With only 179,067 pretraining samples, i.e., less than 0.5% of those used by previous strong scFMs, scKITE outperformed these models across diverse downstream tasks, highlighting knowledge-enhanced pretraining as a promising paradigm for biologically grounded scFMs.
Read the full abstract

All authors Hanqing Zhang, Jie Bao, Mei Ma, Shuai Liu, Jiaying Ma, Jiaguan Liu, Jiaxiao Li, Zhenbo Li, Wenwen Gong, Zhijun Ca

Computation and Language

Online Language Adaptive Sampling for Better Distributed Cross-lingual Gains

Quang Phuoc Nguyen, Félix Gaschi, David Anugraha et al. (+2 more)

Realignment is a promising approach for improving the cross-lingual transfer ability of multilingual language models, particularly for extremely low-resource languages (LRLs). However, existing realignment methods rely on uniform and random sampling of parallel sentences across languages, which may be suboptimal under limited batch sizes. In practice, models may benefit from seeing certain languages more frequently, especially those that are poorly aligned, and the optimal distribution can evolve throughout training. In this work, we propose a simple yet effective adaptive sampling strategy that assigns trainable sampling probabilities to each language. Languages that contribute more to the realignment loss are sampled more frequently in subsequent batches, and the optimal distribution can evolve throughout training. Our method employs an inner-outer optimization loop with a small overhead, leading to consistent performance improvements and, more importantly, distributing the gains across languages. We observed a $+0.67$ average performance increase on all tasks with XLM-R, and $+0.60$ with Gemma 2 9B compared with uniform realignment. Furthermore, our method is robust across different models. Code available at https://github.com/felixgaschi/multilingual-alignment-and-transfer.
Read the full abstract

All authors Quang Phuoc Nguyen, Félix Gaschi, David Anugraha, Santiago Martínez Novoa, En-Shiun Annie Lee

Machine Learning

HiGFRL: Hierarchical Graph Fusion-Driven Reinforcement Learning for Dependency-Aware Task Scheduling in Heterogeneous Cloud

Tiangang Li, Shi Ying and Xiangbo Tian

Online scheduling of dependency-aware tasks in heterogeneous cloud clusters is a fundamental yet challenging problem due to the complex interplay between DAG topologies and multi-dimensional resource constraints. While DRL has shown promise, existing GNN-based approaches often struggle to efficiently model high-order topological dependencies and suffer from loose coupling between task and resource states, leading to myopic scheduling decisions. To address these limitations, we propose HiGFRL, a Hierarchical Graph Fusion-Driven Reinforcement Learning framework. HiGFRL constructs a novel three-level state representation comprising a Static Hypergraph, a Dynamic Global Graph, and a Local Bipartite Graph to explicitly model the interplay between task dependencies and real-time cluster dynamics. Specifically, we design a fusion-driven dual-network architecture to optimize RL decision-making, where a Context Fusion Allocator integrates local bipartite matching features with fused global context to execute precise task-to-node allocation, and a Global State Evaluator leverages the global dynamic graph representation to accurately estimate expected long-term cumulative reward. Furthermore, we incorporate a topology-prior-guided hybrid reward mechanism that distills static topological priors into the learning process to accelerate convergence. Extensive experiments using real-world Alibaba cluster traces demonstrate that HiGFRL significantly outperforms heuristics and DRL baselines. Specifically, in challenging large-scale high-load scenarios, HiGFRL reduces the Makespan by up to 32.55%, and optimizes the average task flow time and average task wait time by 13.58% and 13.79%, respectively. Experimental results confirm that HiGFRL not only significantly improves cluster throughput but also ensures superior QoS by substantially reducing queuing delays. Code Release:https://github.com/igeng/HiGFRL.
Read the full abstract

Computation and Language

A Corpus-Aligned Uthmani-to-Standard Quranic Word Mapping and a Deterministic Recitation Validator

Yahya Mohamed Elnawasany

Quranic text is distributed in two orthographic forms that are byte-level distinct: the Uthmani script used in every printed mushaf, and the Standard (Imla'i) Arabic form that every mainstream Arabic NLP tool is built for. The gap is concentrated in one Unicode character, U+0670 (superscript alef), which appears in some of the most frequently recited words in the Quran and is silently mishandled by general-purpose Arabic normalizers. We release a 2,290-pair, corpus-aligned Uthmani-to-Standard word mapping constructed by aligning the complete 6,236-verse Quran across both orthographic forms, together with a seven-step text normalization pipeline built on it. Normalizing both forms of all 6,236 verses through that pipeline yields identical strings for 90.9% of verses, and we characterize the residual divergence rather than assert that it is closed. On top of the normalized text, we build a deterministic, LLM-free Quranic recitation validator using a four-layer verse-matching search (exact, morphological, relaxed, fuzzy) and word-error-rate-graded feedback across five severity tiers. The validator scores 98.4% (122/124) on a 124-case suite emitted by the released test harness, and both failures share one mechanism: a single substitution error can make a different verse an exact match. A full-corpus census additionally quantifies an inherent text-only ambiguity affecting 16.5% of verses, and on 34 recitation transcripts drawn from a deployed Arabic ASR system the validator identifies the correct verse in every case. We release the mapping, the script that builds it, the validator, and the evaluation harness under open licenses; every number in this paper except the deployment measurement, whose transcripts are not ours to publish, is reproduced by running them.
Read the full abstract

Computer Vision

MoVT: Video-Augmented Motion Tokenizer for Text-to-Motion Generation

Beibei Jing, Tianle Guo, Youjia Zhang et al. (+5 more)

Text-driven 3D human motion generation models face significant challenges in responding to diverse and unconstrained textual prompts, primarily due to the limited availability of 3D motion training data. To address this, we introduce MoVT, a novel framework that effectively leverages the extensive range of human action videos to enhance text-to-motion generation. At the core of our approach is the cross-modal augmented motion tokenizer, which projects discrete 3D motion tokens into the 2D domain. This projection allows us to enrich the motion codebook with complex, real-world motion patterns derived from videos. The enriched discrete tokens are then mapped back to the 3D domain, resulting in aligned 3D and 2D codebooks with an enhanced capacity to represent intricate motions. These enhanced codebooks are integrated into a generative masked transformer, which predicts masked motion token indices in a modality-agnostic manner. This enables the use of text-index pairs, generated from the 2D codebook and annotated motion videos, to further enhance the generator. Extensive empirical evaluations show that MoVT performs favorably against prior state-of-the-art methods across multiple key metrics.
Read the full abstract

All authors Beibei Jing, Tianle Guo, Youjia Zhang, Zikai Song, Yawei Luo, Junqing Yu, Tao Guan, Wei Yang

Computation and Language

Can We Triage LLM Translation Errors in Classical Texts Without Human References? Source Novelty, GEMBA Scoring, and Budgeted Review through Pali-to-English Translation

Máté Metzger

As large language models become capable translators of classical texts, a key challenge is deciding which outputs need expert review when no human reference exists. This study tests reference-free error triage through Pali-to-English translation. Three LLMs translated 15,493 passages. Five signals were compared: source novelty, source-candidate embedding distance, peer-translation disagreement, English-to-Pali backtranslation, and no-reference GEMBA scoring. Signals were calibrated on a 3,000-item reference-informed LLM-adjudicated sample and checked against a 500-item author-adjudicated anchor. Human references supported calibration and validation only; they were never used to compute the risk signals. Source novelty was a useful source-side risk prior but not a per-candidate error detector. Peer disagreement and backtranslation provided secondary signal. The strongest method was no-reference GEMBA scoring by a panel of models generally regarded as stronger than the translators: reviewing the top 10% by GEMBA risk captured 81.6% of panel-major errors in the calibration set. GEMBA also remained the best reference-free signal against the author anchor. A same-tier panel, with self-scoring excluded, remained useful but performed worse, indicating that evaluator strength matters beyond the prompt alone. A budgeted workflow is proposed, combining source novelty, peer disagreement, and stronger candidate-aware judging to allocate human review. Transfer to other classical languages, including Latin, Ancient Greek, and Sanskrit, remains to be tested.
Read the full abstract

Artificial Intelligence

Geometric Flow enhanced Graph Coarsening

Chaoqun Fei, Guoxuan Li, Tinglve Zhou et al. (+2 more)

Recently, researchers have proposed a graph pooling operation, akin to the pooling process in conventional convolutional neural networks (CNN), aimed at reducing the computation cost of Graph convolutional neural networks (GCNNs). While most GCNN-based methods treat graph pooling as a node clustering problem and propose learning a cluster assignment matrix, existing clustering-based pooling methods tend to focus solely on the rough topology information of graphs, neglecting the exploitation of higher-order mutual connections among neighbors. In terms of message passing on graph, the ease of information passing on edges reflects the closeness between neighboring nodes, which significantly relies on the interconnectivity among neighbors. In this study, we address this gap by considering such local connection information and introducing a novel graph pooling method named RicciPool. We introduce discrete graph curvature, particularly Ollivier-Ricci curvature, as a measure of higher-order connectivity around an edge. Subsequently, we construct an Ollivier-Ricci flow formula to reweigh edge weights, leveraging the crucial information provided by Ricci curvature, particularly vital for extracting clusters in graphs. Building upon this foundation, we utilize the spectral clustering technique to learn a new cluster assignment matrix. Experimental results on multiple bioinformatics protein datasets and social networks underscore the effectiveness of our proposed method.
Read the full abstract

All authors Chaoqun Fei, Guoxuan Li, Tinglve Zhou, Chuanqing Wang, Yangyang Li

Machine Learning

High-Probability Nash Regret for Decentralized Learning in Markov $\alpha$-Potential Games: Episodic and Fully Online Asynchronous Algorithms with Applications to Markov Congestion Games

S. Rasoul Etesami

We study decentralized learning of Nash equilibria (NE) in infinite-horizon discounted Markov games under bandit feedback, focusing on Markov $\alpha$-potential games. We develop KL-projected natural policy gradient (NPG) algorithms in two settings: an episodic setting with frozen policies during sampling and a fully online setting in which players receive a single realized cost sample per time step and update their policies asynchronously along a continuing trajectory. We establish finite-time high-probability NE regret bounds of order $\widetilde O(T^{-1/4})$ and $\widetilde O(T^{-2/15})$ for the episodic and fully online settings, respectively, up to fixed approximation terms. Crucially, our bounds eliminate the distribution-mismatch coefficient, which can scale prohibitively with the size of the state space, while accommodating potential approximation, estimation-oracle bias, and transition sensitivity. We further identify a state-wise potential structure that yields sharper guarantees with additive dependence on the potential approximation error $\alpha$. We specialize the framework to independent-resource Markov congestion games (IMCGs), establish their approximate-potential and transition-sensitivity properties, and construct decentralized estimation oracles from realized costs. As an application, we introduce strategic online job scheduling on stochastic machines and obtain a scalable decentralized algorithm for learning stable dispatching policies. Overall, our results provide the first finite-time high-probability NE regret guarantees for fully online asynchronous decentralized learning in Markov $\alpha$-potential games, remove distribution-mismatch coefficients from the regret bounds, accommodate fixed estimation-oracle bias, and provide scalable decentralized learning with finite-time guarantees for IMCGs.
Read the full abstract

Sound

CAL-MOS: Bridging Layers with Adapters for Robust MOS Prediction Across Speech Foundation Models

Alef Iury Siqueira Ferreira, Pedro Lustosa Rege Botelho, Fernanda Silva et al. (+5 more)

Speech Quality Assessment (SQA) is essential for modern speech technologies, and recent non-intrusive SQA predictors increasingly rely on Speech Foundation Models (SFMs). However, because SFMs expose representations from many layers, it remains unclear which depths are most informative for MOS prediction and how multi-layer information should be combined reliably across backbones and datasets. We benchmark ten SFMs on four MOS datasets under three regimes: full fine-tuning, last-layer probing with a frozen encoder, and naive cross-layer weighted aggregation. We find that the best layer is strongly backbone- and dataset-dependent, and that naive weighted fusion can be unstable across settings. We further evaluate a layer-calibrated aggregation variant that applies per-layer adapters before pooling, which improves the robustness of multi-layer fusion and narrows the gap to full fine-tuning while keeping the backbone frozen.
Read the full abstract

All authors Alef Iury Siqueira Ferreira, Pedro Lustosa Rege Botelho, Fernanda Silva, Daniel Casanova, Rafael Faustino, Frederico Oliveira, Arlindo Galvão Filho, Anderson da Silva Soares

Numerical Analysis

A time explicit multiscale framework for heterogeneous elastic wave propagation based on multipoint stress discretization

Xiang Zhong, Eric T.Chung and Shubin Fu

Simulating elastic wave propagation in heterogeneous media presents significant mathematical and computational challenges, since resolving fine-scale material variations requires extremely fine spatial discretizations, while mixed stress–displacement formulations typically lead to large saddle-point systems that are not well suited for efficient time integration. Moreover, conventional multiscale reductions generally produce nontrivial coarse mass matrices, thereby requiring additional linear solves at every time step and diminishing the advantages of explicit schemes. To address these difficulties, we develop a time explicit multiscale method based on a multipoint stress control volume discretization. The central innovation is a unified spatial–temporal reduction strategy that simultaneously removes two dominant algebraic bottlenecks: the complex global fine-scale mixed solve and the repeated coarse-scale mass solve arising in conventional multiscale time stepping. More specifically, the stress and auxiliary rotation variables are eliminated locally, leading to a symmetric positive definite reduced stiffness operator, upon which a multiscale space is constructed using a density-weighted local spectral problem. The associated projected mass bilinear form preserves the physical mass inner product and gives an identity mass matrix under a density-orthonormal auxiliary basis, leading naturally to an explicit central-difference scheme. We establish discrete energy stability under a coarse-scale CFL condition and derive convergence estimates for both the density-weighted displacement and the locally recovered stress. Numerical experiments in heterogeneous media validate the theoretical results and demonstrate the effectiveness of the proposed method for elastic wave propagation.
Read the full abstract

Machine Learning

Cloud Workflow Scheduling Based on Graph Attention-Driven Hierarchical Reinforcement Learning

Zongjin Li, Shaohan Feng, Chunxi Yang et al. (+1 more)

Dynamic cloud workflow scheduling must balance deadline satisfaction, container utilization, and energy consumption while dealing with stochastic task-execution speeds, placement-dependent communication, and coupled task and container decisions. Workflows are naturally modeled as directed acyclic graphs (DAGs), but conventional vector- or matrix-based states do not fully capture their dependency topology. To better represent task urgency and structural relationships, we assign predicted sub-deadlines to tasks and use a multi-head graph attention network (GAT) to extract dependency information from the evolving DAGs. Based on these representations, we develop a Graph Attention-Driven Hierarchical Reinforcement Learning (GA-HRL) framework and model the scheduling process as an event-driven hierarchical semi-Markov decision process (SMDP). Workflow arrivals and task completions trigger scheduling events. At each scheduling event, the Task Scheduling (TS) agent first processes the currently ready tasks by assigning them to admissible existing containers or requesting new ones. The requested containers are then processed by the Container Scheduling (CS) agent for host placement before the environment advances. The two agents are trained alternately using separate Proximal Policy Optimization (PPO). Experiments on the 2018 Alibaba cluster trace show that GA-HRL maintains competitive workflow success rate and, in settings where success is comparable, generally achieves higher container utilization and lower energy consumption. Under the largest speed variation, it trades a small success-rate margin for substantially lower energy. Simulation code is available at: https://github.com/zongjin130/GA-HRL.
Read the full abstract

All authors Zongjin Li, Shaohan Feng, Chunxi Yang, Wenbo Wang

Numerical Analysis · Cross-listed from math-ph

Boundary transmission and excursion geometry in the Lorentz mirror model: a numerical study

Jian Gu and Qin Hao

We study boundary transmission and excursion geometry in the planar Lorentz mirror model through finite-volume numerical experiments. Cylinder penetration quantiles grow approximately linearly with circumference over the simulated range, with a systematic upward drift in the normalized quantiles when vacancies are present. Estimated slab-transmission probabilities yield exponential confinement bounds with quantified statistical confidence at the tested widths. Planar excursions conditioned to reach a distant boundary exhibit transverse ranges proportional to the exit radius, while their repeated-visit fractions vary strongly with mirror density. Endpoint-label collision probabilities substantially exceed a general gluing lower bound, although they account for only part of the observed same-column crossing probability. Finally, rerouting at repeated vertices preserves the exit while substantially shortening the sampled paths. These findings characterize finite-volume transport and excursion geometry without determining an asymptotic scaling exponent or resolving infinite-plane localization.
Read the full abstract

Systems and Control

The Heavy Chain PDE: Rapid Stabilization by Backstepping

Miroslav Krstic

We consider boundary stabilization of a heavy chain hanging from a moving trolley with no tip load. Because the tension vanishes at the free end, the wave speed vanishes there; in Riemann coordinates the model becomes a degenerate $2\times2$ hyperbolic system in which the coupling is singular and the free-end reflection is generated in the domain rather than by a boundary condition. We construct a Volterra backstepping transformation that maps this system to the same chain with uniform damping of an arbitrarily prescribed rate and an elastic restraint at the trolley, yielding exponential convergence of displacement, velocity, and strain to zero. The singular kernel equations are solved by selecting their bounded Frobenius branch at the free end, which replaces the missing boundary datum, and the four kernels are generated by a globally convergent power series. The transformation is boundedly invertible on the energy space, with inverse obtained by reversing the prescribed decay rate. The result extends the radial backstepping structure developed for parabolic equations on disks and balls to a degenerate hyperbolic system.
Read the full abstract

Computer Vision

ThreshGuide: Class-Aware Labeled-Guided Thresholding for Semi-Supervised 3D Abdominal Multi-Organ Segmentation

Hongyu Liu, Yinlong Wang, Lusha Li et al. (+1 more)

Pseudo-labeling is a strong paradigm for semi-supervised medical image segmentation, yet its effectiveness is highly sensitive to confidence thresholding. In abdominal multi-organ segmentation, a fixed global threshold is particularly suboptimal because organ classes differ substantially in size, appearance, and learning difficulty. In this work, we propose ThreshGuide, a class-aware threshold adaptation framework that uses labeled data to guide pseudo-label selection on unlabeled data. Built upon a standard teacher-student architecture, the teacher model evaluates labeled samples during training to estimate class-aware threshold targets by maximizing an error-aware Fe̱ta} criterion that balances precision and coverage. These targets are then smoothed with an exponential moving average (EMA) and used to filter unlabeled voxels in a class-dependent manner. Experiments on FLARE2022 and AMOS2022 show that ThreshGuide performs competitively overall, yielding clear improvements specifically on hard-to-learn organs.
Read the full abstract

All authors Hongyu Liu, Yinlong Wang, Lusha Li, Hui Meng

Human-Computer Interaction

The Dynamic Organization of Sustained Human-AI Cognition: From Construct-Level Change to Relational Structure

Zijian Ru

As generative artificial intelligence becomes a routine participant in writing, learning, information retrieval, analysis, decision making, and problem solving, human-AI cognition research must address not only whether AI changes psychological constructs, use intensity, or task performance, but also how human cognitive activity is organized beneath similar aggregate indicators. This article proposes a dynamic cognitive organization framework that shifts analysis from construct-level change to relational organization anchored in the person's current task-cognitive state under sustained AI participation. The framework distinguishes five relational dimensions: execution locus, cognitive governance, representational reorganization, process organization, and reachable cognitive space; it also proposes a path-specific recursive principle whereby interaction outcomes, costs, and experiences may selectively reweight future probabilities of different organizational pathways. Five sets of testable propositions follow: the same overall AI-use intensity can correspond to different cognitive organizations; similar immediate outcomes can arise from different organizations with different predictive value for proximal subsequent outcomes; longitudinal organizational change need not track overall AI-use intensity; expansion of reachable cognitive space and displacement of pre-existing or emerging human-originated pathways may coexist within one episode; and recurrent cognitive organizations may redistribute cognitive practice opportunities, with accumulated differences potentially corresponding to different developmental trajectories in strategies, habits, and abilities. The contribution is an analytic level and five-dimensional relational structure for describing, comparing, measuring, and testing process differences that aggregate indicators or construct-level analyses do not uniquely determine.
Read the full abstract

Systems and Control

Stabilization of a Heterodirectional Bradytachic (1D, 2D) PDE Pair

Miroslav Krstic

A scalar hyperbolic PDE, actuated at one boundary, is coupled with a fast PDE in two spatial dimensions: transport in the axial coordinate and in an internal coordinate, and possibly diffusion in the internal coordinate. Backstepping designs exist for coupled hyperbolic systems, for their ensembles, and for their continua, but in all of these the second variable of the fast subsystem carries no transport or diffusion; when it does, no design is available, and from a scalar input no exact control of the two-dimensional state is to be expected. The pair is stabilized here by time-scale separation: in the quasi-steady limit the two-dimensional subsystem collapses into a spatial Volterra operator inside a one-dimensional reduced plant, backstepping applies there, and the two-dimensional subsystem is left to be a stable boundary layer. One theorem establishes exponential stability of the pair for every time-scale ratio below an explicit threshold, uniformly in the internal diffusion coefficient down to the pure-transport case.
Read the full abstract

Networking

Burst-mode timing recovery based on fourth-power phase detector for passive optical networks

Ji Zhou, Haide Wang, Xiaofeng Zhang et al. (+5 more)

Driven by the ever-increasing capacity demands, 50G passive optical network (50G-PON) is ready for practical application. It is highly challenging to realize 50GHz burst-mode analog components; therefore, based on 25GHz burst-mode analog devices, burst-mode digital signal processing (DSP) is introduced to achieve the reception and processing of 50Gb/s on-off keying burst signals. To optimize the power consumption and area of the DSP chip, a one-sample-per-symbol (1-SPS) analog-to-digital converter has been applied in 50G-PON. One of the main challenges is implementing burst-mode timing recovery (BM-TR) for the 1-SPS burst signal in 50G-PON. In this paper, we first propose a BM-TR based on the fourth-power phase detector (4PPD) for 50G-PON. We mathematically verify that 4PPD can directly compute the timing phase offset (TPO) from the 1-SPS signal without using training sequences, allowing for immediate BM-TR initialization within 20 cycles to prevent long convergence times. After the initialization, the feedback loop structure tracks the TPO changes based on the sign of 4PPD, the loop filter, and the numerically controlled oscillator. In conclusion, training-sequence-free 4PPD-based BM-TR achieves low burst overhead via fast convergence and is particularly effective for handling burst signals in 50G-PON.
Read the full abstract

All authors Ji Zhou, Haide Wang, Xiaofeng Zhang, Zhiyang Liu, Miao Yu, Changyuan Yu, Liangchuan Li, Xiangjun Xin

Robotics

Comparing Trajectories from Positions Alone: Curvature-Based Time Alignment and Drift Error Metric

Effie Daum, Daniele De Martini, Claire Dune et al. (+1 more)

In field robotics, acquiring independent large-scale reference trajectories more accurate than the evaluated estimates remains an open challenge. The domain is widely reliant on Absolute Trajectory Error (ATE) and Relative Pose Error (RPE), computed with automated tools, that rest on assumptions and evaluation parameters rarely made explicit. When unreported, the errors can be misleading and hinder fair comparisons. This paper introduces a trajectory-evaluation protocol for standardized and reliable accuracy assessment in state estimation, localization, and Simultaneous Localization And Mapping (SLAM). The approach combines a novel temporal alignment method based on curvature signals with an error metric normalized by travelled distance. We explicitly account for temporal synchronization, sampling alignment, and extrinsic calibration, quantifying their influence through a sensitivity analysis. The proposed protocol contributes to more rigorous, reproducible, and standardized trajectory evaluation.
Read the full abstract

All authors Effie Daum, Daniele De Martini, Claire Dune, François Pomerleau