Hardware Architecture
OptiPrime: Optimizing Private Inference through Protocol-Hardware Co-design
Jiangrui Yu, Ye Yu, Si Chen et al. (+5 more)
Private deep neural network (DNN) inference based on hybrid homomorphic encryption (HE) and multi-party computation (MPC) can protect user data with a formal guarantee, but at the cost of significant latency overhead due to HE. Customized HE accelerators have been proposed and have achieved orders-of-magnitude speedup for individual HE operations. However, when directly applying a commercial HE accelerator to state-of-the-art HE-MPC frameworks, we observe only limited end-to-end performance gain. This is because HE-MPC frameworks often require wireless transmission of input and output ciphertexts for each HE operation, leading to a severe network communication bottleneck. To overcome this challenge, we introduce OptiPrime, a protocol-hardware co-optimization framework for efficient private DNN inference. OptiPrime features a novel HE protocol for convolutions that substantially reduces the number of transmitted output ciphertexts and mitigates the network communication bottleneck. Meanwhile, as the new protocol introduces complex computation for fewer output ciphertext, we observe new
memory access challenges due to a high volume of weight plaintexts and intermediate ciphertexts. Hence, we further propose a lightweight compression system for the weight plaintexts, reducing
memory traffic by 10 times, as well as a specialized dataflow to maximize on-chip data reuse of intermediate ciphertexts. Extensive experiments show that our framework outperforms the Cheetah baseline by at most 5.7 times on CPUs and 4.2 times with an accelerator.
Read the full abstract ▾
All authors Jiangrui Yu, Ye Yu, Si Chen, Chenqi Lin, Wenxuan Zeng, Junfeng Fan, Mingyu Gao, Meng Li
Computation and Language
Cascade: Hierarchical Recoverability Control for Large Language Model Unlearning
Qingchen Yu, Shiying Duan, Xiaodong Li et al. (+5 more)
Large
Language Model (LLM) unlearning is essential for removing sensitive or copyrighted knowledge while preserving general utility. Existing methods often leave residual knowledge in intermediate representations, which can still be recovered. To address this, we propose Cascade, a hierarchical recoverability control framework that minimizes the internal identifiability of target knowledge. Cascade combines three complementary controls: path-level routing to suppress
privacy-associated activation routes, representation-level compression to reduce
geometric separability, and decoding-level intervention to limit residual recovery. Experiments on TOFU, MUSE-News, and WMDP, including robustness tests with query reformulation and extraction-style
prompts, show that Cascade effectively reduces recoverability while maintaining stable model utility.
Read the full abstract ▾
All authors Qingchen Yu, Shiying Duan, Xiaodong Li, Yuhua Wang, Zhiyu Li, Shiji Zhou, Yifan Sun, Zhaoxin Fan
Computer Vision
Temporally Consistent Graph Extraction and Matching for Longitudinal Angiographic Images
Linus Kreitner, Laurin Lux, Carmen Baumann et al. (+2 more)
Recent advances in angiographic imaging have enabled longitudinal visualization of the microvasculature. Image processing pipelines based on vessel graphs are able to resolve subtle temporal changes at the level of individual blood vessels. However, current strategies for graph extraction, refinement, and matching are highly sensitive, with even minuscule differences in the underlying
segmentation map resulting in substantially different vessel graphs. These artifacts severely inhibit the ability to accurately match sequential vessel graphs of the same subject over time. To address this problem, we propose a strategy that matches graphs before jointly refining them. Specifically, we perform an early matching after basic graph extraction before removing spurious bulges and merging junctions in both graphs using joint information. In experiments with complex retinal vessel graphs, we demonstrate that this strategy results in a higher matched area without graph fragmentation compared to separate or no refinement, respectively.
Read the full abstract ▾
All authors Linus Kreitner, Laurin Lux, Carmen Baumann, Daniel Rueckert, Martin J. Menten
Artificial Intelligence
QART: A Quantum-Classical Hybrid Architecture for Long-Horizon Reasoning – Exploring a Conditional Path toward Quantum Scaling
Lehao Lin, Yuheng Cheng, Guolong Liu et al. (+9 more)
Long-horizon
reasoning is vulnerable to early errors that compromise later decisions. We present QART, the
Quantum-Augmented
Reasoning Transformer, a
quantum–classical hybrid architecture combining a backbone
language model with
quantum encoding, CIM-based QUBO optimization, and
quantum decoding. Semantic information can come from hidden representations or model-generated text; detailed encoding and optimization procedures remain proprietary. Under explicit assumptions, we establish a conditional asymptotic reliability separation from single-trajectory autoregressive LLMs. For a common task family with aligned optimality and acceptance criteria, autoregressive acceptance probability tends to zero when cumulative conditional risk of irreversible errors diverges. QART's task-optimal-path recovery probability remains bounded away from zero if conditional probabilities for optimal-path coverage and semantic fidelity, spectral certification, dynamical reachability, and faithful readout remain uniformly positive under a specified resource schedule. The architecture alone does not imply these bounds. Paired measurements on six long-horizon
benchmarks using DeepSeek V4 Flash, GLM-5.3, and GPT-5.5 xhigh in a Codex
agent environment favor QART in 14 of 15 backbone–
benchmark pairs. Relative gains reach 84.0% on SciCode, 47.6% on $\tau^3$-Bench, and 44.4% on Terminal-Bench 4.0; the DeepSeek V4 Flash configuration regresses by 7.8% on DeepSWE. These results do not directly validate the asymptotic separation. Potential
quantum scaling laws are formulated as conditional hypotheses. A
quantum-advantage interpretation requires a demonstrated CIM
quantum advantage over strong classical solvers and its transfer to end-to-end
reasoning after all system overheads.
Read the full abstract ▾
All authors Lehao Lin, Yuheng Cheng, Guolong Liu, Yao Li, Xuning Tan, Xiyuan Zhou, Ruixi Zou, Shi Wang, Huan Zhao, Wenxuan Liu, Haifeng Wu, Junhua Zhao
Numerical Analysis · Cross-listed from physics.comp-ph
An energy stable and accuracy-preserving finite volume scheme based on the SAV method with application to wall-distance computation
Xiaorui Xu and Qian Wang
A novel semi-implicit second-order finite volume scheme integrating the scalar auxiliary variable (SAV) approach is proposed for solving the pseudo-time Eikonal equation in wall-distance computation. Unconditional energy stability under zero boundary conditions is rigorously proved, eliminating the dependence of the time step on the grid scale and enabling large-time-step computation. The scheme is a priori accuracy-preserving, and its discretization
matrix forms an M-
matrix, thereby guaranteeing strict non-negativity of the numerical solution inherently. The framework extends readily to any non-conservative scalar equation and, being independent of the specific finite-volume reconstruction, is compatible with schemes of arbitrary order of accuracy. A vanishing artificial viscosity is introduced to smooth the solution without compromising formal accuracy, and upwinding is incorporated through directional weighting in the weighted least-squares (WLS) reconstruction. Numerical experiments confirm that the scheme achieves the designed accuracy and permits stable computations with uniformly large time steps. For complex configurations such as a three-element airfoil and the three-dimensional ONERA M6 wing, accurate results are obtained on high-aspect-ratio grids, with relative errors in the computed wall distance below 3% relative to the search-based reference, except near
geometric singularities.
Read the full abstract ▾
Artificial Intelligence
Bridging Learned Visual Perception and Symbolic Belief-Space Planning
Guy Azran, Michael Navat and Sarah Keren
In partially observable settings,
agents must act without full knowledge of the world state and rely on uncertain state-estimation pipelines. Obtaining grounded and verifiable symbolic plans under such uncertainty remains a key challenge. Recent work has integrated
Vision-
Language Models (VLMs) to bridge perception and symbolic
reasoning, following two main paradigms. The first, VLM-as-planner, maps images directly to action sequences, and the second, VLM-as-grounder, grounds observations into symbolic predicates used as the initial state by off-the-shelf planners. Both approaches ignore uncertainty in the planning process, compromising robustness. We introduce a third paradigm, VLM-as-probabilistic-grounder, a novel approach that captures the uncertainty of VLM predicate groundings as a probability distribution over symbolic states. This enables planning in belief space and producing robust plans under uncertainty. Experiments in simulated household
robot settings show improved robustness and task success over deterministic grounding, underscoring how our approach leverages foundation models for reliable planning under uncertainty.
Read the full abstract ▾
Social and Information Networks
WCCS: Efficient Wedge Conductance Community Search over Large Temporal Bipartite Graphs (Full Paper)
Longlong Lin, Wei Chen, Pingpeng Yuan et al. (+3 more)
Bipartite graphs are ubiquitous for modeling complex interactions between two distinct entity types across numerous practical applications such as e-commerce, academic networks, and social systems. Despite significant progress in community search over bipartite graphs, most prior work is limited to static settings and ignores the rich temporal dynamics present in real-world networks. Moreover, existing methods typically adopt edge-centric measures and strict consecutivity constraints, failing to capture higher-order interactions and frequent yet non-consecutive activities. More importantly, they often neglect the crucial community-quality requirements of both internal cohesiveness and external sparsity, failing to identify critical nodes or including many irrelevant nodes. To address these dilemmas, we propose the novel problem of Wedge Conductance Community Search (WCCS), which aims to identify a query-dependent community that is not only structurally and temporally cohesive but also well-separated from the rest of the network over non-consecutive timestamps. We formalize WCCS by generalizing the classical $(\alpha,\beta)$-core to a higher-order $(\alpha,\beta,\tau)$-wedge core, and by proposing a novel temporal wedge conductance metric that explicitly balances internal density and external sparsity. To solve WCCS efficiently, we first develop an online priority-driven filter-and-expand framework with several effective
pruning techniques and a powerful
geometric slope optimization for rapid temporal wedge conductance calculation. Subsequently, to further improve scalability, we propose an offline compressed index to accelerate search. Finally, comprehensive experiments on seven real-world
datasets demonstrate the effectiveness, efficiency, and scalability of our solutions compared to eight competitors.
Read the full abstract ▾
All authors Longlong Lin, Wei Chen, Pingpeng Yuan, Ruikun Luo, Qiangqiang Dai, Rong-Hua Li
Robotics
Artificial Intelligence-Enabled Space Robot Operations: Technologies, Challenges and Prospects
Zeyuan Huang, Gang Chen, Zixuan Hao et al. (+7 more)
Space
robots are increasingly expected to perform long-duration, contact-rich, and multi-stage operations with limited human intervention. Recent advances in artificial intelligence (AI),
robot learning, and
embodied foundation models provide new opportunities to improve the autonomy and adaptability of such systems, but their transfer to space is constrained by scarce mission data, space-specific dynamics and sensing conditions, limited onboard resources, and stringent safety requirements. This article reviews artificial intelligence-enabled space
robot operations (AI-SRO) from a capability-building perspective. We first summarize representative operational scenarios, autonomy trends, and space-specific constraints. We then establish a three-layer technical framework comprising capability foundations, capability formation, and capability deployment/
evolution. Within this framework, we review simulation environments,
datasets and
benchmarks; task and environment understanding, state perception, decision-making and planning, and action execution; and onboard deployment, ground-to-space adaptation, continual learning, and capability transfer. Finally, we propose key research directions toward trustworthy simulation and data, open-world
multimodal cognition, long-horizon safe decision-making, physically constrained policy learning, and space computing infrastructures.
Read the full abstract ▾
All authors Zeyuan Huang, Gang Chen, Zixuan Hao, Guoqin Tang, Junyi Zong, Guoyou Ban, Jiale Wang, Haoyang Lv, Chaoqian Ren, Sitong Liu
Computer Vision
VOR-Bench: A Human Perception-Driven Benchmark for Video Object Removal
Haonan Huang, Tianrui Qiu, Xianghao Zang et al. (+10 more)
Despite its crucial role in
video object removal (VOR), existing evaluation paradigms face two critical limitations: questionable references and a misalignment between tradi- tional metrics and human preference. To address these challenges, we introduce VOR- Bench, which advances VOR evaluation through three integrated components. First, we present the VOR
Dataset (VORD), the first
benchmark dataset providing both paired edited
videos and graffiti masks. Its unique strength lies in a diverse data spectrum, which encompasses model-generated, tool-rendered, and camera-captured data, ensuring robust assessment across real-world scenarios. Second, we develop rMPAF, a realistic Motion- capable Paired-
video Acquisition Framework. By combining the strengths of image- based object removal and fine-tuned
video generation models, rMPAF automatically generates realistic, motion-coherent paired
videos. Finally, we propose three evaluation dimensions and introduce VOR-MDSM, the first perception-driven VLM-based scoring model specifically designed for mask-guided VOR. It bridges the gap between arithmetic metrics and human perception by covering the essential visual attributes and matching nuanced human judgment. Extensive experiments demonstrate that VOR-Bench yields evaluation results that align closely with human perception, achieving a remarkable cor- relation (h̊o} > 0.9) with subjective assessments. We will release VOR-Bench along with its documentation to ensure full reproducibility.
Read the full abstract ▾
All authors Haonan Huang, Tianrui Qiu, Xianghao Zang, Yinan Du, Zhixiang He, Chi Zhang, Hao Sun, Zhongjiang He, Tianwei Cao, Xuchong Zhang, Hongbin Sun, Kongming Liang, Zhanyu Ma
Networking
A Mechanical Antenna for Improving Capacity Fairness in Dynamic Multi-Station Scenarios
Akihito Taya, Yuuki Nishiyama and Kaoru Sezaki
While indoor Internet of Things (IoT) and sensor networks increasingly rely on Wi-Fi access points (APs) to collect high-bandwidth data streams from multiple devices, conventional APs rely on static
antenna deployments, whose fixed orientations are often suboptimal in dynamic propagation environments. To overcome this limitation, this paper proposes a mechanical Wi-Fi
antenna control system that adaptively optimizes its 3D
antenna orientation for dynamic multi-station scenarios. The proposed system autonomously actuates its physical
antennas in response to perceived
radio environments by combining state-specific black-box optimizers and capacity-based environment change detection. The evaluation results show that the proposed system improves channel capacity under dynamic station combinations, avoids unnecessary re-optimization under transient blockages, and triggers re-optimization after sustained environmental changes such as continuous blockage and device relocation.
Read the full abstract ▾
Computational Engineering
Online adaptive non-intrusive model reduction via manifold interpolation and subspace updates: application to FSI convergence acceleration
Azzeddine Tiba, Florian de Vuyst and Iraj Mortazavi
We introduce a novel online adaptive non-intrusive reduced-order modeling strategy for parameterized dynamical systems involving parameter and time-dependent reduced bases. The proposed framework is based on a unified Grassmann
manifold formulation combining three key components: interpolation of local reduced subspaces for unseen parameters, geodesic online subspace updates driven by incoming high-fidelity snapshots, and a latent-space regression strategy relying on Grassmann-distance weighting and Procrustes
alignment to consistently aggregate predictions from multiple local models. The adaptive reduced-order model is embedded in a partitioned fluid-structure interaction framework, where it predicts fluid interface forces to provide accurate initial guesses for the nonlinear coupling iterations, thus achieving computational speedups with no loss of accuracy. The reduced basis and the regression operators are adapted independently during the simulation and without requiring the storage of high-dimensional streaming data, preserving computational efficiency while substantially improving predictive capabilities. Numerical results on reference FSI test cases demonstrate superior accuracy with respect to static and global reduced-order models, leading to a significant reduction in the number of fixed-point iterations required for convergence. The proposed framework offers a flexible and fully non-intrusive approach for the efficient simulation of nonlinear parameter-dependent multiphysics problems.
Read the full abstract ▾
Computer Vision
Multi-modal Knowledge Preserving Adapter for Embedding Backward Compatibility
Jaeseok Byun, Gukyeong Kwon, Han-Kai Hsu et al. (+4 more)
Upgrading
embedding models typically requires expensive database re-indexing, as new query
embeddings are incompatible with existing database
embeddings. While Backward Compatible Training (BCT) mitigates this by enforcing compatibility during training, existing approaches often require updating the backbone model. This is impractical because of significant training cost, the risk of performance regression, and limited access to proprietary model weights. We introduce Multi-modal Knowledge Preserving Adapter (MKP-Adapter), the first adapter-only BCT approach for Multi-modal Large
Language Models (MLLMs) that requires no backbone updates. We identified that the primary challenge in adapter-only BCT is preserving the knowledge of the new
embeddings while enforcing backward compatibility. Hence, we propose a multi-level preservation loss that maintains the
geometric structure of the
embedding spaces throughout BCT. Furthermore, a focal re-weighting strategy is integrated to prioritize learning from challenging samples. Experiments demonstrate that our method achieves strong backward compatibility across diverse multi-modal
benchmarks (image, text, visual document, and
video retrieval tasks) and model types. Notably, MKP-Adapter is trained solely on pre-extracted
embeddings and requires only negligible additional latency relative to the original backbone forward pass, highlighting its efficiency.
Read the full abstract ▾
All authors Jaeseok Byun, Gukyeong Kwon, Han-Kai Hsu, Meher Gitika Karumuri, Zhikang Zhang, Hao Yang, Davide Modolo
Computer Vision
Accelerated Decoding of Centroid Positional Encoding for Instance Segmentation
Carmelo Scribano, Filippo Muzzini, Nedyalko Prisadnikov et al. (+6 more)
Beyond model inference, the decoding stage, which converts raw network outputs into task-level representations, constitutes a significant portion of the execution cost. Despite its practical impact, prediction decoding has received comparatively little
attention and is often implemented using generic CPU routines or inefficient GPU kernels, limiting the benefits of advances in model efficiency. In this work, we investigate the decoding overhead associated with a recent sinusoidal centroid encoding for Instance
Segmentation, in which each pixel regresses a positional
embedding of its instance centroid. This approach allows flexible
segmentation without predefined proposals, but extracting instance masks from dense
embeddings incurs a high computational cost. We present an optimized CUDA-based implementation of the decoding
algorithm tailored to this encoding, explicitly addressing challenges related to parallelization, synchronization, and
memory access on modern GPUs. Our solution significantly reduces decoding overhead and improves End-to-End inference latency, outperforming both CPU-based approaches and naive GPU implementations. The results demonstrate that efficient decoding is essential to fully exploit the advantages of advanced output representations and highlight the importance of jointly designing encoding schemes and their decoding
algorithms for real-time computer
vision systems.
Read the full abstract ▾
All authors Carmelo Scribano, Filippo Muzzini, Nedyalko Prisadnikov, Mohammad Mahdi, Yuqian Fu, Giorgia Franchini, Danda Pani Paudel, Marko Bertogna, Luc Van Gool
Computer Vision
NeuroTS-Net: Multi-Class Semantic Segmentation of Pediatric Brain Tumors in Multi-Modal MRI
Darius Peteleaza, Razvan-Gabriel Dumitru, Bogdan Neamtu et al. (+3 more)
Pediatric
brain tumors are a leading cause of cancer-related mortality in children, and their small, rare, and often low-contrast subregions make accurate manual delineation challenging. Reliable automated
segmentation is therefore needed to support diagnosis, treatment planning, and response assessment. Accordingly, we introduce NeuroTS-Net, a three-dimensional encoder-decoder convolutional neural network architecture for multi-class semantic
segmentation that incorporates a dual-scale raw-detail stream, adaptive low-resolution context selection, and detail-preserving multipath downsampling. These components preserve fine intensity and boundary information while efficiently modeling broader tumor context. NeuroTS-Net was trained on the BraTS 2026 pediatric
dataset without external data or pretrained weights and evaluated against nnU-Net and MedNeXt under the same experimental protocol. NeuroTS-Net outperformed the baseline methods, achieving whole-tumor and tumor-core Dice scores of 0.938 and 0.937 on the internal validation set and 0.927 and 0.926 on the official challenge validation set. The code is open-sourced at: https://github.com/maenstru56/NeuroTS.
Read the full abstract ▾
All authors Darius Peteleaza, Razvan-Gabriel Dumitru, Bogdan Neamtu, Arpad Gellert, Mariana Sandu, Claudiu Matei
Computer Vision
GRACE: Geometry- and Ray-Aware Camera-Efficient Multi-View Pedestrian Tracking
Taigo Sakai, Hiroki Kouno, Naoki Kato et al. (+1 more)
Reducing the number of cameras reduces the deployment cost but removes views that correct BEV responses stretched away from true pedestrian positions by projection and short score drops that can split tracks} in Bird's-Eye View (BEV) tracking. We introduce GRACE, a camera-efficient multi-view tracker with three components. Volumetric-Guided Fusion combines homography-based BEV features with features lifted through 3D space. Ray Conditioning exposes each camera's viewing direction to the fusion network. Its tracking component, BEV Track Recovery (BTR), uses low-confidence detections only to continue existing tracks. The same detections cannot start new tracks. With two WildTrack cameras, GRACE improves MOTA from 83.54 for TrackTacular, our baseline, to 91.07.
Read the full abstract ▾
All authors Taigo Sakai, Hiroki Kouno, Naoki Kato, Kazuhiro Hotta
Computer Vision
SPEAR NeXT Causal Latent Forecasting Across Multiple Horizons for Spectral Temporal Earth Representation Learning
Rajiv Ranjan, Udaiveer Singh, Shashank Tamaskar et al. (+1 more)
Earth observation is inherently dynamic, yet temporal information in many foundation models is learned through reconstruction, invariance, or retrospective sequence summarization. SPEAR NeXT is introduced as a compact pixel-wise
multimodal spectral temporal foundation model in which temporal self supervision is formulated as past only, multi horizon latent Earth state prediction. Instantaneous states are first encoded by the pretrained SPEAR model from optical, radar, and environmental observations into compact 32 dimensional
embeddings. Their temporal
evolution is then modeled by a causally masked Trans former that predicts multiple future latent states from pre ceding observations. Relative temporal order is represented using Rotary Position
Embeddings, while month and year
embeddings encode seasonal phase and interannual con text.
Read the full abstract ▾
All authors Rajiv Ranjan, Udaiveer Singh, Shashank Tamaskar, Dharmendra Saraswat
Computer Vision
tcnerv:dual-domain temporal context modeling for implicit neural video compression
Xuezhi Xiang, Yixin Zhao, Heqi Xiang et al. (+2 more)
Video compression aims to minimize reconstruction distor tion under a constrained bit rate. Existing
video implicit neural representations (INRs) often decode frames independently, leaving intermediate features unconditioned on previous reconstructions and content
embeddings without explicit temporal prediction. We propose TCNeRV, which exploits reconstructed context in both feature and
embedding domains. Its multi-scale temporal-context fusion (MTCF) module injects gated historical features at multiple decoder scales, while temporal
embedding-residual coding (TERC) predicts each content
embedding and codes only its residual. With approximately 3M parameters, TCNeRV achieves an average PSNR of 36.08 dB on the UVG
dataset, outperforming HNeRV-Boost by 2.20 dB. It reduces BD-rate by 22.06%, 66.73%, and 29.85% relative to HM, DCVC, and HiNeRV, respectively, demonstrating competitive rate-distortion performance with limited model capacity.
Read the full abstract ▾
All authors Xuezhi Xiang, Yixin Zhao, Heqi Xiang, Jiayao Liu, Shanjun Zhang
Formal Languages and Automata
Mining DTA with SMT by Exploiting Simple Elementary Language and Timed Augmented Prefix Acceptor
Ziran Wang, Jie An and Naijun Zhan
Timed automata, which extend finite state automata by introducing clock variables, serve as a popular formalism for specifying and analyzing the timed behaviors of real-time systems. Extracting the timed behaviors of a black-box, safety-critical system is crucial for designing and analyzing its real-time requirements, yet it remains challenging. In this paper, we address this problem by generating a deterministic timed automaton (DTA) consistent with a given set of system behaviors, comprising both positive and negative examples. To this end, we adapt the formalism of simple elementary
languages (sEL) and introduce the timed augmented prefix tree acceptor (tAPTA). Our approach proceeds as follows: First, we preprocess samples by translating them into sEL, which discards redundancy and detects conflicts; then, we rewrite the resulting sELs in an incremental form and construct a tAPTA to further simplify the samples; finally, we encode the search for a DTA that accepts the simplified tAPTA as an SMT formula. We evaluate our approach on randomly generated
benchmarks and a scheduling case study. The results demonstrate the effectiveness of our simplification method in reducing the size of the encoded SMT formula and the efficiency of our approach in mining a DTA.
Read the full abstract ▾
Robotics
TEMPO: Learning Temporal Context for Dynamic Robot Manipulation
Zhenyang Feng, Jimin Heo, Erik B. Sudderth et al. (+1 more)
Vision-
language-action (VLA) models have achieved impressive performance in quasi-static manipulation, but struggle in dynamic manipulation tasks because they operate on a single observation at inference time. We identify two representational failures that underlie this limitation. The first is motion ambiguity, where a single observation does not include scene dynamics and therefore cannot anticipate the future state of moving objects. The second is state aliasing, where visually similar observations from different points in a task require different actions. We argue that these failures persist regardless of model scale and inference latency, showing that the bottleneck is missing temporal context rather than model capacity. Based on this insight, we propose TEMPO, which augments a pretrained VLA with two temporal inputs: a motion summary extracted from a frozen
video foundation model to resolve motion ambiguity and a compact proprioceptive history to resolve state aliasing. TEMPO requires no modification to the backbone and adds minimal compute overhead at training or deployment. Across four dynamic manipulation tasks, it improves Bottle Handover success from 44% to 74% and is the only method that solves state aliasing. Probing and ablation studies confirm that each temporal signal independently addresses its corresponding failure. We further release TEMPO-Bench, a
benchmark of over 50k annotated frames for evaluating motion-aware
robot perception in both regression and multiple-choice formats. Project Website: https://tempo-
robot.github.io/
Read the full abstract ▾
All authors Zhenyang Feng, Jimin Heo, Erik B. Sudderth, Unnat Jain
Numerical Analysis
Mixed precision solvers for the all-at-once Runge–Kutta discretization of the heat equation
Santolo Leveque, Luca Bergamaschi, Ángeles Martínez et al. (+1 more)
We study the effect of mixed precision on the numerical integration of the heat equation discretized with a Runge–Kutta method in time. A full space-time discretization is applied, which results in a very large and sparse linear system to be solved for the numerical approximations and the Runge–Kutta stages of all time steps. The linear system is solved by applying a suitable preconditioned iterative method that can be run in parallel. In order to speed up the solution process, the preconditioner is applied using a mixed precision framework. Sequential results show the robustness of the preconditioner, even when applied in mixed precision. Finally, we present numerical evidence of the improved performance of the mixed precision strategy when applied in a parallel environment, achieving up to a 50% reduction in CPU time.
Read the full abstract ▾
All authors Santolo Leveque, Luca Bergamaschi, Ángeles Martínez, Erin Carson
Performance
Strong aggregation of the Markov chains associated with matching models based on the automorphism group of their compatibility graphs
Moyi Yang and Jean-Michel Fourneau
We extend the analysis of strong aggregation to general compatibility graphs, focusing on item counts rather than positions, and exploring generalized greedy matching disciplines. We prove that under a condition of
automorphism-based transition consistency, the associated Markov chain is strongly aggregable for an arbitrary graph with a non-trivial
automorphism group. Furthermore, we extend our analysis to non-greedy matching disciplines, distinguishing scenarios where compatible items can or cannot coexist within the same state. This result is illustrated with a simple compatibility graph with a rich
automorphism structure: the odd rings. For all scenarios, we investigate the strong aggregation properties of the resulting Markov chains. This work enhances the theoretical understanding of lumpability in
stochastic matching models and provides a foundation for analyzing complex graph structures.
Read the full abstract ▾
Computation and Language
Reduplicative constructions in Mandarin: Socio-emotional profiling through distributional semantics
Chaoyi Wu, Yu-Hsiang Tseng and R. Harald Baayen
Mandarin Chinese has two productive reduplicative constructions that repeat either two-character base words or their constituents (e.g., `in good health', `discuss a bit'). Their varied meanings have been described as realizing plurality, valence coloring, sound symbolism and pragmatic functions. The aim of this study is twofold. A first goal is to clarify whether it is possible to come to a more precise understanding of the variegated semantics of Mandarin reduplication by using word
embeddings from distributional semantics. A second goal is to explore how useful
embeddings are for understanding the details of a semantically complex word-formation process. We show that the
embedding space recovers the semantic and grammatical properties of reduplications previously identified in the literature, validating Tencent
embeddings for morphological investigation. Semantic profiling revealed that reduplicative constructions are often strongly represented on multiple dimensions. The two patterns exhibit clear semantic and pragmatic differentiation in distributional space. Procrustes analysis clarified that the overall organization of the base-word space is largely preserved in the reduplication space, with local mismatches highlighting regions of discourse-pragmatic reorganization. Taken together, these results show that high-dimensional word
embeddings can recover established linguistic generalizations, and capture the semantic versatility of Mandarin reduplication and constructional transparency.
Read the full abstract ▾
Computer Vision
Measuring Annotation Efficiency for Handwritten Devanagari Recognition: Sample-Complexity Curves for Four Pretraining Regimes
Manglesh Kumar Pandey and Sumit Kumar Banshal
To train handwritten text recognition systems we need word images and their corresponding transcriptions, and these transcriptions are produced manually. For a script that can be read by only a small number of specialists, this manual transcription is a limitation, because the trained models are supposed to save the time of those same specialists. A relevant question therefore arises: how many transcriptions are needed before a recogniser becomes useful, and how much of that cost can pretraining remove? In this study the answer is measured directly for handwritten Devanagari. We keep the recogniser, optimiser and evaluation protocol the same and change only the number of real transcribed words used for fine-tuning across nine budgets from 10 to 4,000 and four initialisation regimes, with six seeds at every point. The resulting curves are then converted into annotation-equivalent terms. A CER of 0.50 is reached by supervised synthetic pretraining using only 81 transcribed words, whereas random initialisation requires 355, which gives a label multiplier of 4.40 [3.56, 4.99]. There is a zero-shot reference point as well: with no real transcribed words at all, this pretraining is worth about 136 of them. This advantage gets smaller as the target accuracy improves, and at the most demanding target we measure, it cannot be distinguished from no saving at all. A fourth arm in which only the encoder is transferred separates the effect of the pretraining method from that of transfer scope, and masked image modelling is observed to transfer negatively over a bounded range of budgets. We emphasise that the scarcity in this study is constructed by subsampling a large corpus.
Read the full abstract ▾
Computer Vision
TecoPrompt: Temporal-Conservative Prompt Learning for Vision-Language Models
Zeyi Shao, Haowen Hua, Jiaxin Zhang et al. (+3 more)
Prompt learning adapts
vision-
language models, such as CLIP, by adjusting a small set of context
tokens. However, under few-shot supervision, even moderate label noise can disrupt
prompt optimization. To address this issue, we propose TecoPrompt, a closed-loop robust
prompt-learning framework that revisits optimal transport (OT) pseudo-labeling from a temporal perspective. TecoPrompt employs an entropic OT plan in the CLIP semantic space to obtain globally consistent label candidates. It verifies the reliability of these candidates by examining trajectory stability: a noisy label is only rewritten if the OT candidate remains unchanged within a K-epoch temporal stability window and passes a confidence gate based on Exponential Moving Average (EMA). This approach helps reduce confirmation bias. The rewritten labels are then integrated back into
prompt training using a tri-group objective that includes three loss functions aligned with clean, mid, and noisy subsets. Experiments on seven
datasets with synthetic symmetric and asymmetric noise, as well as Food101N, demonstrate significant performance improvements. For example, on the OxfordPets
dataset, with 50% asymmetric noise, TecoPrompt achieves an accuracy of 0.843, up from 0.775.
Read the full abstract ▾
All authors Zeyi Shao, Haowen Hua, Jiaxin Zhang, John See, Zeyd Boukhers, Cong Yang
Systems and Control
Two-stage Coordinated Energy Management of Train Operation and Wayside Energy Storage System for Rail Power Supply Systems
Fei Liu, Niklas Biedermann, Stefan Östlund et al. (+1 more)
The increasing electrification of railway power supply system (RPSS) intensify the operational and economic challenges at the railway power system interface. Energy storage systems (ESSs) can provide fast and flexible support to mitigate short term power spikes and to improve the energy management. However, achieving coordinated operation is challenged by the tight coupling among electrical railway operation and ESS dispatch under time-varying traction demand and network limits. This paper proposes a two-stage coordinated energy management method for electrified RPSSs that jointly optimizes railway system operation, train trajectories and ESS dispatch while explicitly accounting for traction power flow constraints. First, a day-ahead operation stage determines the train operating profiles and the ESS setting decisions to establish the baseline operating plan. Then, an intra-day rolling optimization stage based on adaptive weight economic-model predictive control (AWC-MPC) updates ESS dispatch under refreshed forecasts of traction demand and renewable output. A real Swedish railway case is utilized to minimize the energy purchase cost and the ESS cost while reducing peak grid power, demonstrating its practical applicability with 35.7% peak grid power demand and 28.8% total system cost reduction.
Read the full abstract ▾
All authors Fei Liu, Niklas Biedermann, Stefan Östlund, Qianwen Xu
Human-Computer Interaction
The Evolution of Coordination in a Collective Intelligence System: 25 Years of English Wikipedia and the Emergence of Generative AI
Neal Reeves, Maja Świeczkowska, Amy Rechkemmer et al. (+1 more)
English Wikipedia is one of the largest examples of collective intelligence on the Web, sustained not only by article production but also by volunteer coordination and governance. While prior research has examined coordination work in Wikipedia, less
attention has been paid to how participation in these spaces has evolved over time. Drawing on a longitudinal analysis spanning nearly 25 years of English Wikipedia, we examine editing patterns across five namespaces covering content, discussion, and governance. We find that participation in coordination spaces has declined relative to content production, particularly in governance areas, with a shrinking core of editors performing an increasing share of this work. Using Markov-based session metrics, we also find that editing has become more specialised, with editors moving less frequently between namespaces. Motivated by recent governance debates around generative AI, we conclude by investigating whether the availability of LLMs has altered these long-term trends. While short-term changes are visible, we find little evidence that generative AI fundamentally changed existing trajectories of coordination and participation.
Read the full abstract ▾
All authors Neal Reeves, Maja Świeczkowska, Amy Rechkemmer, Elena Simperl
Computation and Language
A Data-free Universal Prior over Syntactic Structures
Fermín Moscoso del Prado Martín
The probabilities of syntactic structures in human
languages are assumed to emerge fully from
language-specific experience. Here, I show that a universal prior over syntactic structures emerges from a model of human
language production, in which words are progressively integrated into syntactic structure. Without fitting any parameters to specific
language data, the resulting prior assigns higher probabilities to attested than to random dependency trees in all 138 typologically diverse
languages examined. These prior probabilities correlate positively with those estimated from corpora in 33 of 34
languages. The results indicate that part of the probability structure of syntax can arise independently of
language-specific learning. This identifies human
language production as a possible cognitive source of universal statistical structure in
language, while providing a data-independent structural bias for probabilistic models, including large
language models.
Read the full abstract ▾
Machine Learning
Can Deep Learning Achieve Cross-Physics Mapping?
Pengfei Zhu, Julien Lecompagnon and Mathias Ziegler
Can deep learning translate physical fields governed by fundamentally different equations? We address this question by introducing Cross-Physics Mapping (CPM), an operator-learning framework for mappings between heterogeneous physical domains. We formulate sufficient conditions for such mappings through compatible latent representations and propose a dimensionless scaling principle that aligns the characteristic
evolution scales of the source and target systems without assuming their dynamical equivalence. As a representative test, paired
diffusion and wave fields are generated independently from their respective
parabolic and
hyperbolic equations while sharing the same latent geometry, material heterogeneity, excitation, and dimensionless scale. Seven architectures-ResUNet, DeepONet,
Fourier, latent, wavelet, U-shaped, and Galerkin neural operators-are evaluated for both
diffusion-to-wave and wave-to-
diffusion mappings. The results reveal a strong directional asymmetry.
Diffusion-to-wave reconstruction is more challenging because it requires recovering wavefront, phase, and time-of-flight information attenuated by
diffusion; U-NO performs best in this direction, achieving a relative $\ell_2$ error of $0.307$ and an $R^2$ of $0.905$. Wave-to-
diffusion mapping is considerably more stable, with GNO attaining a relative $\ell_2$ error of $0.154$ and an $R^2$ of $0.935$. Neural operators generally outperform the conventional convolutional baseline, highlighting the nonlocal nature of cross-physics transformations. These findings demonstrate that deep learning can establish useful mappings between distinct physical modalities on a shared latent
manifold, while the achievable accuracy remains fundamentally constrained by the direction-dependent information content of the governing physics.
Read the full abstract ▾
Artificial Intelligence
CoAdapt: An LLM-based Framework for Adaptive Collaborative Perception in IIoT Robotic Swarms
Houssam Hajj Hassan, Antonia Maria Masucci, Lynda Zitoune et al. (+1 more)
Industrial IoT environments increasingly deploy autonomous mobile
robots for tasks such as material handling, product assembly, or infrastructure inspection. In such deployments, collaborative perception enables
robots to share
LiDAR observations and collectively construct a richer model of their environment than an individual
agent could produce alone. However, industrial environments are dynamic spaces where
robot positions shift continuously, network bandwidth fluctuates, and the marginal contribution of
robots to perception quality varies at runtime. Existing collaborative perception approaches are designed for static participation assumptions and cannot adapt to these dynamics without sacrificing either detection precision or communication efficiency. This paper presents CoAdapt, an adaptive collaborative perception framework for IIoT robotic swarms in which a Large
Language Model (LLM) serves as a runtime fusion controller, jointly deciding which
robots participate in the fusion process and which fusion
algorithm to apply based on the current spatial configuration and network state. The LLM reasons over structured natural
language descriptions of the scene derived from raw
LiDAR point clouds, requiring no taskspecific training and generalizing to unseen swarm
topologies. Evaluated on the OPV2V
benchmark across 25 scenarios, our approach achieves a 38% reduction in communication cost while maintaining detection precision comparable to static baseline approaches.
Read the full abstract ▾
All authors Houssam Hajj Hassan, Antonia Maria Masucci, Lynda Zitoune, Salah-Eddine Elayoubi
Information Retrieval
Efficient Swing Computation for Retrieval in Large-Scale Recommender Systems
Runhao Jiang and Renchi Yang
Given a user-item graph $G$, a query item $v_q$ and a target item $v_t$, the Swing score $sw(v_q, v_t)$ of the item pair $(v_q, v_t)$ leverages the user-item-user interaction structure to evaluate their similarity. This measure is found to be highly effective in item-to-item (i2i)
retrieval task and finds extensive applications in industrial-scale recommender systems. However, existing solutions towards computing Swing scores are either prohibitively expensive due to their quadratic time complexity w.r.t. the item degree, or rely on truncation heuristics that yield unsatisfactory quality, rendering them impractical particularly on graphs with billions of interactions. In this paper, we present ASC and $K$-ASC, two novel and efficient
algorithms for approximate and top-$K$ Swing queries, to address the aforementioned limitations. Specifically, these
algorithms provide rigorous theoretical guarantees in probabilistic relative and additive errors of Swing values. The basic idea of ASC is to combine two randomized
algorithms, GNS and USS, in a simple yet non-trivial way to adaptively process high- and low-degree query items with minimal runtime cost. In particular, $K$-ASC offers practical efficiency and effectiveness for top-$K$ queries through a filter-refinement paradigm with carefully-designed heuristics. Extensive experiments over eight real
datasets demonstrate that ASC and $K$-ASC can achieve orders of magnitude speed-up over competitors in terms of computational time while offering the same approximate and top-$K$ query result quality, and in particular, $K$-ASC is highly efficient on massive graphs including the billion-edge Yambda and MAG
datasets.
Read the full abstract ▾