Sound
How Should We Evaluate Naturalness for Synthetic Speech with a Foreign Accent?
Kentaro Onda, Satoru Fukayama, Daisuke Saito et al. (+1 more)
Recent advances in
speech synthesis technology have enabled the generation of
speech with diverse characteristics. One such characteristic is a foreign accent. In our preliminary experiments, we found that UTMOS, a widely used automatic
speech quality assessment system, tended to assign lower scores to
speech with stronger foreign accents, even though it is produced by a human speaker. This observation raised a question: How do humans evaluate the naturalness of foreign-accented
speech? We conducted a large-scale subjective evaluation involving both native and non-native listeners under different evaluation instructions. The results showed that humans also considered accentedness when evaluating naturalness, but that defining naturalness in terms of human-likeness and selecting raters who have greater exposure to the target accent may enable more appropriate evaluation. This study aims to provide a starting point for future discussions on fairer and more appropriate evaluation of synthetic
speech with a foreign accent.
Read the full abstract ▾
All authors Kentaro Onda, Satoru Fukayama, Daisuke Saito, Nobuaki Minematsu
Computer Vision
PreCoG: Preview-Edit for Efficient Video Correction in Generation-Time
Yilai Liu, Wenqi Pei, Zhifeng Lu et al. (+3 more)
Iterative text-to-
video generation relies on feedback to correct compositional and temporal failures. However, existing methods typically require another full generation run for each correction, repeating computation and potentially disrupting already correct content. We introduce PreCoG, an iterative framework for correcting semantic failures during
video generation. PreQA diagnoses failures from low-cost previews and constructs corrective conditions, while PreEdit edits cached generation trajectories under these conditions, attenuating orthogonal changes to limit disruption of already correct content. PreCoG completes generation only for the selected candidate, reusing its cached trajectory to reduce redundant computation and help preserve semantic consistency between the preview and the final
video. Experiments show that PreCoG achieves the highest VBench and T2V-CompBench scores and approaches VSR's leading VS2 score at $0.56\times$ its inference time. It also outperforms GENMAC on all three quality and
alignment metrics at $0.86\times$ its inference time.
Read the full abstract ▾
All authors Yilai Liu, Wenqi Pei, Zhifeng Lu, Shiyuan Zhang, Zongxi Liu, Hongyang Du
Artificial Intelligence
RoleWorld: Knowledge Transfer in World Modeling with Functional Role Abstractions
Boyuan Xiao, Pu Wang, Ji Feng et al. (+1 more)
World models enable large
language model (LLM)
agents to anticipate action effects and make informed decisions. For generalization, it is desirable for such world models to transfer efficiently to new environments with similar interaction structure and underlying dynamics. Recent approaches encode world dynamics as symbolic rules or executable programs, whose compositional structure in principle affords transfer, but still organize such knowledge around environment-specific objects. To address this limitation, we introduce RoleWorld, a symbolic world modeling approach which uses reusable prototypes and environment-specific parameter values as functional role abstractions to represent how objects behave in interactions. From interaction trajectories, a teacher LLM extracts role prototypes and executable transition rules defined over role instances, together with a skill that guides the actor LLM to use role information in decision making. In a target world, without the teacher, the actor uses this skill together with its current role assignments and parameter estimates, and actively tests a role instance hypothesis through interaction when its uncertainty affects the current decision. Feedback from each action refines role assignments and estimates parameter values online, with no LLM parameter updates and the transition rules held fixed. Experiments on MARS
benchmark show that RoleWorld enables robust generalization across environments with significantly altered object behavior, suggesting that functional role abstractions can serve as an effective component for knowledge transfer in world modeling. Project Page: https://future-item.github.io/RoleWorld.
Read the full abstract ▾
All authors Boyuan Xiao, Pu Wang, Ji Feng, Yao-Xiang Ding
Computation and Language
PreSTO: Predictive Subtree Prefetching for Fast LLM Power Sampling
Nan Jiang, Panagiotis Theodoropoulos and Wei Deng
Power sampling improves large
language model (LLM)
reasoning at test time by sampling from a sharpened version of the base model's distribution. Its sampler, PowerMH, is slow because its Metropolis–Hastings (MH) updates are sequential: each accept/reject decision sets the state from which the next proposal is generated. Prior work reduces this cost by changing the sampler or the model (e.g., sequential Monte Carlo, approximate lookahead,
distillation). We propose Predictive SubTree Prefetching (PreSTO), which accelerates PowerMH by prefetching future proposals and provably leaves its MH transition kernel unchanged. PreSTO views future MH outcomes as a tree of accept/reject decisions: in each model call, it generates the proposals of a prefetched subtree of this tree in one batch, then follows the realized path with the original MH acceptance rule. We also observe that MH reaches only a sparse, nearly unary part of each prefetched subtree, we further design a predictive traversal rule that chooses the subtree to maximize the predicted number of completed transitions. Across seven
datasets and five base LLMs, PreSTO achieves median speedups of $1.71\times$, $1.91\times$, and $2.33\times$ on PowerMH and its follow-ups EntropyCut and MultiTryMH, respectively; on the first two, it makes a median of $3.9\times$ fewer model calls, each only $2.1\times$ longer. On LCB V6 with Qwen3.5-9B, the predictive traversal rule is a further $1.25\times$–$1.37\times$ faster than the default breadth-first traversal.
Read the full abstract ▾
Cryptography and Security
Understanding Verification Vulnerabilities in Cross-chain Bridges: An Empirical Study
Yuying Wang, Yi Guo, Jiachi Chen et al. (+2 more)
With the rapid development of blockchain technology, numerous heterogeneous blockchains have emerged, each featuring distinct architectures, consensus mechanisms, and application ecosystems. Cross-chain bridges have consequently become a critical infrastructure component, typically relying on smart contracts to facilitate message passing and asset transfers across heterogeneous blockchains. Unlike single-chain contracts, bridge contracts introduce additional verification logic to validate external-chain data, such as state proofs, message sender identities, and signatures. However, correctly implementing such logic is challenging. We refer to vulnerabilities that violate the security guarantees of cross-chain verification as Cross-chain Verification Vulnerabilities (CVVs). To characterize CVVs, we conduct the first systematic empirical study of this vulnerability class. By analyzing 588 security audit reports from 36 real-world cross-chain bridge projects, we derive 11 CVV patterns and organize them into 5 high-level categories according to the affected verification properties. Following this taxonomy, we construct a CVV
dataset containing 830 vulnerability instances across 786 contract files. The
dataset establishes mappings among audit reports, audited source-code versions, affected source files, and CVV-pattern labels. We then assess existing detection approaches. Current tools provide limited documented coverage of CVV patterns, while only two of four evaluated LLMs outperform an all-pattern constant baseline of 29.3% Macro-F1; the best reaches 51.2%. Together, the limited tool coverage and inconsistent LLM gains motivate detection methods tailored to cross-chain verification semantics.
Read the full abstract ▾
All authors Yuying Wang, Yi Guo, Jiachi Chen, Hanwen Zhang, Yi Sun
Systems and Control
Modelling the Nordic power system expansion with PyPSA-Eur: a comparison with the Nordic Grid Development Perspective 2025
Leonardo Rydin Gorjão and Heidi S. Nygård
We compare the Nordic Grid Development Perspective 2025 (NGDP) with a least-cost transition pathway for the Nordic power system obtained with PyPSA-Eur for the period 2025-2050 under a net-zero CO$_2$ constraint. The model co-optimises generation, storage, and transmission expansion with hourly system operation while constraining the Nordic generation mix to remain consistent with NGDP milestone ranges. Overall, the optimised capacity pathways reproduce the broad NGDP expansion of wind and solar power, with Denmark emerging as the main locus of offshore wind and solar deployment, Finland as a major site for onshore wind expansion, and Norway and Sweden relying more strongly on existing hydropower and nuclear capacity. The main discrepancy between the two pathways does not lie in the broad build-out of variable renewables, but in the timing and role of hydrogen. Whereas the NGDP treats hydrogen as an early and steadily increasing component of industrial demand and system development already from 2030, PyPSA-Eur delays substantial hydrogen deployment until 2045-2050, when it becomes cost-effective primarily as a flexibility and seasonal storage option in a strongly variable-renewable-energy-dominated system. This contrast suggests that early hydrogen build-out in the Nordics is not a robust outcome of cost optimisation alone, but depends strongly on assumptions regarding industrial demand growth, sector coupling, and anticipatory infrastructure planning. We therefore argue that hydrogen remains the principal strategic uncertainty in the Nordic transition, with the NGDP representing a more anticipatory planning perspective and PyPSA-Eur a more conservative least-cost timing of deployment.
Read the full abstract ▾
Computation and Language
Scaling Agentic Data for Long-Horizon Terminal Intelligence
Shun Zou, Ziyu Ma, Yi Zou et al. (+6 more)
Terminal
agents are moving beyond local operations toward completing real-world professional tasks. Short trajectories can demonstrate commands and tool calls, but they do not fully show how
agents accumulate evidence through exploration, use it to inform judgments, continually adjust strategies based on feedback, and turn intermediate results into final deliverables. High-quality long-horizon trajectories capture these agentic behavioral patterns and their connections within a single problem-solving process, providing richer experience for sustained autonomous work. However, environment synthesis may complete or simplify the key work underlying these patterns in advance and thus remove the need for exploration, implementation, and verification that the
agent was meant to perform. To address this, we introduce TerminalHorizon, a fully automated data synthesis engine for long-horizon terminal
agents. Starting from real-world professional work, it uses independent execution to identify key work omitted during construction and uses the resulting evidence to guide environment reconstruction. To extend these patterns across stages, it progressively expands tasks under the same goal, introducing new requirements that build on prior results and call for further exploration and improvement. Using this engine, we construct 1.5K task environments and perform supervised fine-tuning of Qwen3.5-27B on the resulting
dataset to obtain TerminalHorizon-27B. We achieve substantial performance gains on all 12
benchmarks spanning coding-
agent tasks, agentic tasks in real-world production settings, and general
reasoning. Multiple RSI case studies, each with a 12-hour research budget, further demonstrate the model's ability to continue experimenting beyond an initial solution, improve its methods based on feedback, and retain effective improvements in its final deliverables.
Read the full abstract ▾
All authors Shun Zou, Ziyu Ma, Yi Zou, Yong Wang, Lin Chen, Zehui Chen, Guanhua Chen, Xiangxiang Chu, Feng Zhao
Robotics
Grounded-Dreamer: Robot Learning from World Model Synthetic Data with Physical Grounding
Feng Jiang, Shu Chen, Yuanfei Wang et al. (+7 more)
Scaling
robot manipulation policies requires large amounts of diverse, action-labeled data, yet collecting such data in the real world remains expensive and difficult to scale. Existing methods either depend on human teleoperation, rely on simulation with limited visual realism, or use human
videos that lack embodiment-specific annotations. In this paper, we introduce Grounded-Dreamer, a framework for synthesizing physically grounded
robot manipulation data with
video world models while avoiding human teleoperation demonstrations. Grounded-Dreamer combines the visual realism of generative
video models with simulator physics engines. Starting from a small set of real images depicting
robot task initial states, our method automatically reconstructs task-relevant objects and camera geometry, aligns them in simulation, and collects physically valid trajectories. These trajectories are used to post-train both a
video world model and an inverse dynamics model, enabling the generation of visually realistic
robot manipulation
videos and corresponding
robot actions from real images. To filter physically implausible rollouts, Grounded-Dreamer replays generated trajectories in the reconstructed simulation and retains only those that successfully complete the tasks. The real-world
robot policies are trained solely on the grounded synthetic trajectories without any human demonstrations. Empirical results in real-world tasks demonstrate that Grounded-Dreamer can synthesize physically grounded data and substantially facilitate policy learning without requiring human teleoperation effort.
Read the full abstract ▾
All authors Feng Jiang, Shu Chen, Yuanfei Wang, Yuan Li, Zhenhao Shen, Jiaqi Liang, Yang Chen, Lei Wei, Chen Xie, Ruihai Wu
Networking
Configuration Migration Planning through Decoupled Modeling and Searching
Dan Wang, Peng Zhang and Ratul Mahajan
Executing large network configuration changes, called migrations, is slow and error-prone today; operators must manually devise a safe order for updating devices that does not disrupt traffic and meets operational intents (e.g., low total time). We develop Smoothie, a versatile migration planning framework that, unlike existing tools, can support diverse operational intents. Inspired by automated planning, it achieves versatility by decoupling the encoding of network safety and intents from the search for a viable plan. Smoothie uses symbolic simulation for general and scalable safety encoding, after which it can use a range of planners, including existing off-the-shelf planners and a new one we developed for optimized parallel plans. We demonstrate Smoothie's versatility and
benchmark its performance using diverse migration scenarios on many
topologies. It finds both sequential plans and parallel plans, and the parallel ones compress up to thousands of configuration updates into no more than 3 steps. Its versatility does not come at the expense of performance: finishing most planning tasks in less than 1 hour.
Read the full abstract ▾
Robotics
Low-Latency Mapless ESDF Queries for MAV Reactive Collision Avoidance
Leonard Freißmuth, Cedric Le Gentil, Helen Oleynikova et al. (+1 more)
Reactive collision avoidance in unknown, cluttered environments must perceive obstacles and correct motion within milliseconds. Existing methods rely on maps for high-rate collision queries, but their acceleration structures require pre- processing. That cost is amortized in long-horizon planning, where a map serves millions of queries; reactive planning, however, is a near-field, short-horizon problem with potentially only hundreds of queries per measurement, where building a map may not pay off. We propose a mapless, Graphics Processing Unit (GPU)-accelerated Euclidean Signed Distance Field (ESDF) query with negligible pre-processing that operates directly on posed depth images, with resolution set by pooling the image rather than by a voxel size. On an embedded GPU it is simultaneously more accurate and lower in total latency than every voxel-grid configuration we measured between 2 cm and 20 cm, at one to two orders of magnitude less
memory at matched resolution. With our query integrated into a Model Predictive Controller (MPC), simulated runs in
laser-scanned forests at up to 9 m/s collide in 0.4 % through dense branches, against 5.9 % with the best voxel grid and 5.5 % with the best mapless baseline at our resolution, whose failures we attribute to voxel resolution and total latency respectively. We deploy the system onboard at two forest sites and fly at commanded speeds of up to 4 m/s.
Read the full abstract ▾
All authors Leonard Freißmuth, Cedric Le Gentil, Helen Oleynikova, Stefan Leutenegger
Computation and Language
SOAR: Source-Aware Reinforcement Learning with Precise Credit Assignment for Search Agents
Shengze Huang, Zihao Tang, Jinluan Yang et al. (+11 more)
Reinforcement learning (RL) for search
agents often suffers from evidence fabrication, a failure mode where
agents bypass external information ($E_{ext}$) and fabricate an incorrect answer. We argue that this fabrication arises from an over-reliance on unreliable internal knowledge ($E_{int}$) as shortcuts due to the inherent opacity of
reasoning trajectories. To address this, we propose SOAR (SOurce-Aware Reinforcement learning), a paradigm that transforms monolithic
reasoning into source-explicit trajectories. SOAR (i) disentangles $E_{ext}$ and $E_{int}$ into parallel, observable streams via a Source-Aware Workflow, and (ii) incorporates Source-Consistent Reward to guide the policy
evolution. By making information-source attribution explicit, SOAR enables precise credit assignment between different knowledge streams. Evaluations show that SOAR outperforms baselines on 3B and 7B backbones by 7.3% and 5.4%, while reducing evidence fabrication by 74.8%. These confirm that SOAR significantly improves performance on knowledge-intensive
benchmarks while effectively mitigating evidence fabrication, fostering more faithful and grounded
reasoning with enhanced robustness.
Read the full abstract ▾
All authors Shengze Huang, Zihao Tang, Jinluan Yang, Xin Yu, Zhenghao Lin, Xiao Liu, Zengxuan Wen, Yeyun Gong, Haizhen Huang, Weiwei Deng, Feng Sun, Qi Zhang, Fei Wu, Kun Kuang
Human-Computer Interaction
How Anthropomorphic Attitudes Toward Agents Divide User Behavior, and How Design Should Change
Tingyu Cao, Yan Tang, Keer Hu et al. (+6 more)
Studies of conversational
agents rely on interviews, surveys, lab tasks, or taxonomies. Whether anthropomorphic naming splits those patterns, and whether replies should change, lack field evidence. We report a field study of a desktop assistant (May-August 2026; n=257). Stance is an anthropomorphic assistant name (118 users; 45.9%). Behavior comes from a 128-unit sparse-autoencoder codebook, identity tags, and opening lexicons. Ranks differ by stance (Spearman rho=+0.249 vs. null mean +0.382; p=.0419). Teacher and tutoring identities covary with renaming, an introverted task-only orientation against it; renamers greet more and command less; confiding shows the codebook's largest gap. We revise the
agent: greet and receive affect on relational openings, execute directly on tasking. In 1,744 judgments (n=129), renamers chose the revised reply far more often than default-name users on being treated as a person and having affect received, less robustly on willingness to continue, and neither judged it worse on task interference.
Read the full abstract ▾
All authors Tingyu Cao, Yan Tang, Keer Hu, Bomingxuan Zhu, Ruyi Zou, Huaze Tang, Yuanbo Tang, Shao-Lun Huang, Yang Li
Computer Vision
From Glance to Focus: Mitigating Recognition Laziness in MLLMs for Fine-Grained Recognition
Yutong Yang, Zhuqi Liu, Mouxing Yang et al. (+1 more)
Multimodal Large
Language Models (MLLMs) generally fall short of expectations in Fine-Grained Visual Recognition (FGVR), although they exhibit promising FGVR foundations, i.e., visual perception and broad category knowledge. Most existing studies seek to remedy this deficiency by adopting domain-specific post-training, at the risk of compromising generalization to unseen domains. Different from these efforts, in this paper, we revisit the FGVR mechanism underlying MLLMs from both the empirical and theoretical perspectives and uncover an inference-time phenomenon termed FGVR Laziness. In brief, FGVR Laziness refers to the insufficient association between visual cues and category concepts under certain candidate category lists and recognition guidance, leaving the FGVR foundations of MLLMs largely under-utilized. To mitigate FGVR Laziness, we propose Laziness-resIstant Visual rEcognition (LIVE), a training-free framework which jointly refines candidate lists and recognition guidance to elicit the latent FGVR capability of MLLMs. Specifically, LIVE first performs query-adaptive candidate inference to derive a compact yet reliable candidate list. Meanwhile, LIVE constructs category-specific FGVR skills by mining the intra-category characteristics and inter-category differences. Finally, LIVE selectively invokes detailed skill guidance according to recognition uncertainty and category confusion, shifting MLLM-based FGVR from a cursory glance to a focus on associating discriminative visual cues with category concepts. Extensive experiments on 13
benchmarks against 24 state-of-the-art methods spanning fine-grained category recognition, action recognition, and general category recognition, verify the effectiveness and generalizability of LIVE across different MLLM backbones. The code will be released upon acceptance.
Read the full abstract ▾
All authors Yutong Yang, Zhuqi Liu, Mouxing Yang, Xi Peng
Artificial Intelligence
Quality, Not Just Outcome: A Structural Scoring Framework for Selecting Coding-Agent Trajectories for Supervised Fine-Tuning
Sida Li, Yuanxin Liu, Shicheng Li et al. (+4 more)
Open coding
agents are commonly trained through supervised fine-tuning on interaction trajectories whose final patches pass the
benchmark test suite. However, this outcome-level filtering criterion ignores process quality: trajectories that eventually succeed may still contain inefficient interaction patterns such as repetitive file inspection, unstable tool usage, or delayed modification behavior, all of which become part of the imitation target. We propose TQS (Trajectory Quality Score), a structural scoring framework for coding-
agent trajectories that operates directly on trajectory structure, requires no LLM judge, and runs in linear time. TQS characterizes trajectory quality through structural signals organized around structured convergence: information focus, intent–action
alignment, and policy dynamics. Using 155,144 successful trajectories from a public open-license corpus, we rank trajectories by TQS and fine-tune coding
agents on filtered subsets. Models trained on top-ranked trajectories consistently outperform those trained on random or bottom-ranked subsets on SWE-Bench-Verified. Our results suggest that process-level trajectory quality is an important factor in coding-
agent supervision and that structural trajectory filtering provides an effective and scalable alternative to LLM-based data selection.
Read the full abstract ▾
All authors Sida Li, Yuanxin Liu, Shicheng Li, Linli Yao, Xu Sun, Haoli Bai, Xiaohui Li
Social and Information Networks
Les Misérables Dialogue: A film-based network representation of social communication
Theodora Moldovan, Georgios Panayiotou and Davide Vega
In this work, we revisit the classic Les Misérables
benchmark network from the perspective of social communication. Using the 1998 film adaptation of the novel, we construct the publicly available Les Misérables Dialogue temporal text network, which explicitly distinguishes speakers, addressees, and other recipients of each utterance, along with its content and timing. Using the ten social dimensions model, we also derive multilayer network representations of the network, in which layers correspond to distinct relational dimensions. Beyond the network
dataset, this work offers a general methodology for building similarly rich communication
datasets from similar narrative sources.
Read the full abstract ▾
Systems and Control
Extended Neighborhood Message Passing for Inference in Loopy Factor Graphs
Kuilong Yang, Zengfu Wang and Hua Lan
Belief propagation (BP) is widely used for inference on probabilistic graphical models but often suffers from non-convergence and poor accuracy on loopy factor graphs, yielding inexact variance estimates in the Gaussian case. Generalized BP (GBP) improves accuracy but relies on manual design or application-specific heuristics for region-graph construction. We propose extended neighborhood message passing (ENMP), which automatically constructs extended neighborhoods of variable nodes from the bipartite factor graph
topology, capturing loop-induced correlations without manual region design. The framework applies to general distributions on factor graphs with a tunable accuracy-complexity trade-off. In the exact regime, message updates converge to the unique fixed point of the ENMP equations in finitely many iterations, yielding exact marginals; in the approximate regime, ENMP provides approximate marginals. For Gaussian factor graphs, we derive closed-form update rules enabling exact variance estimation in the exact regime, addressing the long-standing inaccurate variance estimates of loopy Gaussian BP. We evaluate ENMP on densely loopy Gaussian factor graphs from power-grid
benchmarks and on a discrete Ising factor graph. Results show accuracy improves with neighborhood size, with exact marginals achieved on several systems in both settings. On larger Gaussian systems, ENMP outperforms regularized Gaussian BP (sGaBP-m) in both mean and variance estimation accuracy.
Read the full abstract ▾
Artificial Intelligence
VIGOR: Verifiable Industrial Geometry Optimization and Repair in Scene Programs
Fuqiang Wang, Zheng Guo, Xiaoming Wu et al. (+5 more)
Large
language models (LLMs) increasingly generate structured layouts and executable scene programs from natural-
language instructions. However, executability does not imply engineering feasibility: an industrial scene program may execute successfully while its final state still violates coupled boundary, collision, clearance, aisle, or structural constraints. We identify this mismatch as the executability-engineering-feasibility gap, where locally plausible placements can remain globally infeasible because corrections to one device may introduce violations elsewhere. To make this gap measurable in a controlled setting, we construct an execution-grounded industrial scene-program
dataset with 1,749 constructible scenarios, complete executable programs, and 94 final-state
geometric checks per scenario. We further propose VIGOR, which combines supervised scene-program generation with execution-grounded verification and staged
geometric refinement. Supervised fine-tuning establishes complete program generation, local projection resolves independently correctable violations, and joint conflict-graph repair coordinates residual multi-object conflicts while preserving structural relations. Experiments show that VIGOR achieves 96.86% Complete Feasibility and an Overall score of 91.20, outperforming the strongest evaluated baseline by 10.42 points in Overall. These results show that, under controlled industrial layout conditions, reliable scene-program generation requires not only executable programs, but also explicit verification and coordinated resolution of coupled engineering constraints.
Read the full abstract ▾
All authors Fuqiang Wang, Zheng Guo, Xiaoming Wu, Hanlin Kong, Nayu Liu, Chuanting Zhang, Daojun Liang, Jingxuan Wei
Artificial Intelligence
Competence-Aware Orchestration for LLM-Based Multi-Agent Systems
Songmiao Wang, Yuchen Wang, Chenglin Yu et al. (+2 more)
LLM-based multi-
agent systems (MAS) have emerged as a promising paradigm for enhancing complex
reasoning through role specialization and collaboration, yet a key challenge remains: how can collaboration be adapted to a backbone's competence on the current query? This problem matters because more collaboration is not always better–richer coordination may help on difficult cases, but it also incurs additional
token cost and redundant interactions. We propose a two-stage competence-aware framework for automatic MAS orchestration. It first models the LLM backbone's task-conditioned competence for the current query, and then uses this signal to adapt role activation and the communication graph. Across six
benchmarks, our method achieves an average score of 93.81%. Experiments with six LLM backbones of varying competence levels further show that our method adjusts collaboration according to the inferred competence: for higher-competence backbones, it improves average accuracy from 87.22 to 89.97 while reducing
token cost by 36.26%; for lower-competence backbones, it yields a further average gain of 4.58 points over existing methods. The same trend also holds on unseen backbones.
Read the full abstract ▾
All authors Songmiao Wang, Yuchen Wang, Chenglin Yu, Hongxia Yang, Ming Li
Computer Vision
Measurable Semantic 3D Gaussian Splatting with Joint Region and Depth Supervision for Interactive Building Inspection
Yi Zhang, Tian Tan and Ray Kai Leung Su
Image-based 3D reconstruction provides a scalable representation for building inspection and maintenance. However, photorealistic reconstruction alone does not fully provide the
geometric measurability, semantic structure, and interactive information access required for engineering applications. This study proposes a measurable semantic 3D Gaussian Splatting (3DGS) framework with region and depth supervision for interactive building inspection from multi-view imagery. Mask-based region supervision suppresses irrelevant backgrounds and focuses optimization on target regions. Point-wise depth supervision guides Gaussian centers toward physical surfaces using reference geometry derived from multi-view stereo (MVS) point clouds, providing
geometric anchors for measuring physical dimensions and areas. A semantic Gaussian field associates learnable class features with individual Gaussian primitives, enabling semantic rendering and component-level inspection. These capabilities are operationalized through AEC-SplatTwin, an interactive building inspection platform supporting real-time visualization, semantic analysis, quantitative measurement, and
multimodal large
language model (MLLM)-assisted interaction. On the synthetic
UAV-inspection QuakeCity and smartphone-captured HKUPB
datasets, the framework reduces Gaussian-center depth MAE by 58.1% and 86.8%, while its semantic field achieves mIoU values of 0.8529 and 0.8642. On HKUPB, the mean relative errors for height, width, and area measurements are 0.33%, 1.07%, and 0.60%. These results show that the proposed framework extends 3DGS beyond visual reconstruction into a measurable, semantically structured, and interactive engineering representation for building inspection.
Read the full abstract ▾
Information Theory
Structure-Aware Online Optimization of the Age of Information with Unknown System Statistics
Yoshiaki Inoue, Michel Mandjes and Liron Ravner
Timely information dissemination is essential in modern communication systems, where low informational latency is critical for networked control, monitoring, and real-time decision-making. The Age of Information (AoI) has emerged as a fundamental metric for quantifying information freshness at the receiver. A key challenge in AoI optimization is selecting the update generation rate: infrequent updates lead to stale information, whereas overly frequent updates increase queueing delays. We develop a structure-aware, data-driven framework for adaptive AoI optimization modeled as single-server queues with unknown system statistics. Our key idea is to exploit analytical representations of the AoI gradient, which depend on a finite-dimensional collection of system quantities that can be estimated from observations collected during system operation. This reduces the online learning problem to estimating the quantities required by the gradient, rather than learning the AoI objective as a black box. We propose an online
stochastic approximation
algorithm that jointly estimates these quantities and optimizes the update generation rate. We prove almost sure convergence of the
algorithm to the optimal update generation rate under mild regularity and moment conditions, despite the temporal dependence induced by the underlying queueing process. We demonstrate the framework in four representative incomplete-information settings, including FCFS queues with unknown service characteristics or hidden background traffic, a preemptive LCFS system with partial observations, and a generate-at-will system with threshold waiting.
Read the full abstract ▾
Information Theory
A Ray-Traced Digital Twin for 5G NR Positioning with OpenAirInterface
Nima Chaharbaghi, Florian Kaltenberger, Bartosz Podrygajlo et al. (+2 more)
Evaluating 5G positioning on a physical testbed ties every measurement to one propagation environment and one
antenna layout, so any question about an alternative deployment requires a new field campaign. We present a ray-traced digital twin of the GEO-5G testbed at EURECOM that drives an unmodified OpenAirInterface (OAI) 5G stack with per-
antenna channels computed by Sionna-RT over a 3D model of the site. The distributed gNB
antennas are modelled as independent
radio devices rather than as elements of a compact array, which preserves the per-
antenna absolute delays on which time-difference-of-arrival (TDoA) positioning depends. With them preserved, the twin drives OAI's SRS-based UL-TDoA pipeline to metre-level accuracy consistent with that reported for the physical deployment. We then use the twin to answer a question the physical testbed cannot. Widening the carrier truncates the tail of the horizontal error distribution without improving a typical position, and leaves the vertical error untouched, because the latter is limited by the array geometry rather than by the measurement. That limit is predictable from the
antenna coordinates alone, and a height-diverse layout reduces the RMS height error by a factor of four.
Read the full abstract ▾
All authors Nima Chaharbaghi, Florian Kaltenberger, Bartosz Podrygajlo, Rakesh Mundlamuri, Roberto Verdone
Computation and Language
Neurograf v1: An End-to-End Romanian-First Language Model Family
Ionut Adrian Rotaru
We present Neurograf v1, an experimental end-to-end Romanian-first
language-model pipeline developed to investigate the feasibility of training
language models from scratch for a lower-resource European
language. The pipeline comprises RoSfera, a 635 GB Romanian corpus containing 175.7 million documents; an 80k byte-level BPE tokenizer; five decoder-only models ranging from 160M to 6B parameters, trained on 131 billion
tokens; three instruction-tuned assistants; and two contrastively trained
embedding models. Training and evaluation were conducted using computing infrastructure at ELI-NP/IFIN-HH. The model family exhibits consistent scaling of validation loss and increasing Romanian factual and cultural knowledge with model size. On the 1,000-question WWTBM
benchmark, Neurograf-6B achieves 69.89% accuracy on Romanian-context questions, while Neurograf-3.2B reaches 67.38%. Compute-optimal analysis yields a parameter-scaling exponent of approximately 0.423. Neurograf v1 serves as an experimental demonstrator rather than a production system. The study identifies practical challenges involving diacritic preservation, corpus quality, data composition, and tokenization efficiency, while demonstrating the feasibility of developing Romanian-first base models, instruction-following assistants, and semantic
embedding models within a unified training pipeline.
Read the full abstract ▾
Multiagent Systems
The Limits of Manipulation within Personalized Incentive Policies
Andrea Araldo, Alessa Mayer, Ravi Seshadri et al. (+1 more)
Demand management policies aim to shift individual behavior toward sustainable choices (e.g., goods, transport modes). Personalized incentive policies tailor subsidies to
agents' needs and constraints, but personalization also exposes the regulator to
agents' strategic manipulative behavior. The extent to which
agents can profitably manipulate such policies remains poorly understood, which limits their applicability. This paper establishes analytically the conditions under which manipulation benefits the
agent. We formalize a Stackelberg game in which an
agent may simulate a different profile to extract higher incentives from a regulator. Previous work typically assumes that the regulator would instantaneously classify
agents into the simulated user profile. In contrast, we explicitly model the regulator's process of learning the
agent profile, based on observed past behavior. This makes manipulation harder, since it forces the
agent to consistently behave according to a simulated profile, thus renouncing following their true preferences. Manipulative
agents thus incur a Cost of Manipulation, which has typically been neglected. By accounting for it, we get a counterintuitive finding: although classification uncertainty reduces personalization accuracy, it may benefit the regulator by deterring manipulation. We establish an upper bound on the
agent's gain from manipulation, which becomes stricter as profiles become harder to distinguish for the regulator. Simulations on the London Passenger Mode Choice
dataset illustrate this deterrence effect. The framework can therefore be used to stress-test the robustness of personalized incentive policies before deployment.
Read the full abstract ▾
All authors Andrea Araldo, Alessa Mayer, Ravi Seshadri, Amir Brudner
Artificial Intelligence
DP-MIND: Differentially private memory-guided Long context Inference
Zhihao Liu, Yitian Cheng, Shuang Liu et al. (+3 more)
LLM-as-a-Service has become a dominant paradigm for accessing large
language models without requiring local deployment. However, the process raises severe
privacy concerns when user queries may include sensitive or confidential contexts. Differential
privacy (DP) provides a principled approach to protecting such inputs, but existing DP inference methods are primarily designed for short- or moderate-context settings and struggle with million-
token-scale inputs due to limited context capacity and severe utility degradation under DP perturbation. In this paper, we propose DP-MIND, a
memory-guided framework that scales differentially private inference to million-
token contexts. DP-MIND enables private long-context inference by locally perturbing the input and processing it chunk by chunk with a compact
memory that preserves task-relevant information across the sequence. To make this
memory robust to DP noise, we optimize the
memory construction policy directly on perturbed inputs using reinforcement learning, guided by both final answer correctness and
memory consistency. We further recover perturbation-corrupted answer spans through a local denoising module without exposing the original context to the external model. We provide theoretical
privacy analysis of DP-MIND and further conduct extensive empirical analysis across multiple long-context
benchmarks with context lengths up to the million-
token scale, demonstrating that DP-MIND consistently outperforms existing DP and long-context inference baselines in both scalability and utility.
Read the full abstract ▾
All authors Zhihao Liu, Yitian Cheng, Shuang Liu, Rui Wen, Yuke Hu, Zhan Qin
Artificial Intelligence
Looking Ahead and Back: Anticipatory Generative Modeling for Road-Network Trajectories
Zhenhao Huang, Li Sun and Philip S. Yu
Trajectory generation underpins urban applications such as traffic management and urban planning. Within road networks, vehicle movement along road segments is largely deterministic, whereas transitions at intersections are critical–multiple outgoing paths may appear equally plausible, yet they can lead to substantially different downstream routes. Existing generative methods such as
diffusion models simulate location sequences and fail short of next transition selection, even producing trajectories that drift off the road network. To fill this gap, we advocate a fundamental shift: moving beyond location simulation toward behavior modeling on the road network. In this paper, we revisit trajectory generation through the lens of generative route planning, and introduce a new graph-constrained generative paradigm, Anticipatory Generative Modeling, which resolves next transition selection by incorporating the Anticipation of how the future route may unfold toward the destination. Concretely, we propose a novel generative model named Foresight that formulates a probabilistic model for an "anticipate–select–update–re-anticipate" loop that enables longer-term foresight while continuing sequential generation along the historical trajectory. Extensive experiments demonstrate that Foresight wins state-of-the-art baselines.
Read the full abstract ▾
Networking
PCM: Programmable Congestion Management for Terabit RDMA NICs
Mikhail Khalilov, Timo Schneider, Tommaso Bonato et al. (+10 more)
Datacenter congestion control (CC) and load balancing (LB) evolve rapidly as workload demands change, but deployment depends on RDMA hardware and transport interfaces. Emerging programmable RDMA engines tie policy code to vendor APIs. Operators must therefore port each policy for every platform they deploy. We address this with PCM, a programming model that separates portable congestion management from platform integration on datacenter NICs. Developers write event-driven handlers that they can debug in simulation and reuse on real hardware. PCM exposes flow telemetry as signals and uses triggers to support per-event reactions and coarser responses to accumulated feedback. Vendors provide optimized backends that map signals and output controls to native NIC mechanisms with defined feedback and control semantics. We demonstrate PCM's expressivity by implementing eleven well-known datacenter CC and LB
algorithms. We deploy PCM across four distinct datapaths: an Ultra Ethernet simulator, CPU-based UCCL, and on-NIC offloads on NVIDIA ConnectX-8 and Microsoft 1P. On CX-8, PCM-Swift achieves processing capacity equivalent to one reaction per three 4 KiB packets at 800 Gbit/s, using one-fifth of the NIC's hardware threads. In UCCL, it matches native Swift's 1.56 Tbit/s goodput with 64 KiB chunk-level control. PCM's design informed ongoing Ultra Ethernet work toward a portable congestion management interface.
Read the full abstract ▾
All authors Mikhail Khalilov, Timo Schneider, Tommaso Bonato, Siyuan Shen, Marcin Chrapek, Yehor Kozyr, Alberto Merino, Rip Sohan, Surendra Anubolu, Mohan Kalkunte, Ahmad Ghalayini, Abdul Kabbani, Torsten Hoefler
Machine Learning · Cross-listed from stat.ML
Fast Gradient-Based Approximation of Continuous Dynamic Time Warping
Pierre Houedry, Romain Tavenard, Nicolas Courty et al. (+1 more)
Dynamic Time Warping (DTW) is a common choice for measuring the discrepancy between time series. It proceeds by finding an optimal warping between timestamps through dynamic programming, which can be slow and is not differentiable. Consequently, several variants have been proposed. Among them, Soft-DTW proposes a smooth formulation of DTW, amenable to gradient computation, while Continuous-DTW (CDTW) introduces a continuous formulation through parametrizable warping functions. Yet, computational costs remain high for both methods and impractical for large
datasets in modern machine learning pipelines. This paper revisits CDTW in several ways. After establishing its differentiability under mild conditions, we introduce FastCDTW, which is an efficient approximate solver with two different computational strategies: an exact closed-form scheme for piecewise-linear warping functions, and an unbiased Monte Carlo
estimator for smooth ones, such as implicit neural networks. Both strategies provide gradients with respect to the warping function and the input time series, and the resulting
algorithm is GPU-friendly. We demonstrate its benefits through its integration into more complex learning problems, including time series averaging, classification and deep domain adaptation.
Read the full abstract ▾
All authors Pierre Houedry, Romain Tavenard, Nicolas Courty, Romaric Gaudel
Artificial Intelligence
Locate, Judge, Read: Role-Specialized Tool Agents over a Knowledge-Point Index for Open-Domain Multimodal Document QA
Wenlin Lin and Fanzhe Wei
Question answering over large heterogeneous document collections requires first finding the right passages and then reading them, yet current
retrieval-augmented
agents give one model both kinds of tools and let it schedule itself. We present KnowForge, a pipeline separated by job: a hybrid-
retrieval knowledge-point index; a Locator
agent that can only search; a code-scheduled bridge judge that forces the missing second hop; a typed, size-bounded evidence pool that merges every search's ranking; a Deep Reader
agent that can only read text, images and tables; and a synthesizer with a format checker. With a self-hosted Qwen3.6-35B-A3B (3B active), KnowForge reaches F1 47.5 on the full open-domain M3DocVQA (2,441 questions, 3,368 PDFs), +11.0 over the published M3DocRAG system and +7.1 over one-shot retrieve-and-answer on the same index and model, and 53.5 with DeepSeek-V4-Flash. On MultiHop-RAG it reaches 73.5 accuracy, above the strongest published RAG and GraphRAG results (71.2); on the single-document MMLongBench-Doc it lifts the same model from 34.8 to 47.0, level with GPT-4o reading page images (46.3). Per-job ablations on the full
benchmarks attribute the gain: the Deep Reader is worth 3.8, 9.8 and 0 points on the three corpora, tracking how visual each is; merging both
agents into one with all tools and twice the rounds loses 1.9 F1 because it keeps searching instead of reading; a round-budget sweep shows a step at four Locator rounds and a plateau beyond; query latency scales with model calls rather than corpus size. We serve the three indexed
benchmarks as read-only knowledge bases (free registration) and release all
prompts and the runner code: https://github.com/metask-ai/knowforge-bench
Read the full abstract ▾
Operating Systems
Characterizing CPU-GPU Memory Sharing over Unified Memory Architecture
Jinrong Yang, Zimeng Wang, Rong Chen et al. (+1 more)
Unified
Memory Architecture (UMA) enables the CPU and GPU to share a single physical
memory. However, its complexity and opacity often drive applications back to inefficient copying or to incorrect direct access that sacrifices performance or even correctness. This paper presents a comprehensive study of CPU-GPU
memory sharing on UMA, covering correctness and performance across data-plane transmission and control-plane coordination on four platforms. It yields four findings that guide libumsh, a portable library that delivers correct and efficient
memory sharing across platforms and extends to emerging ones (e.g., NVIDIA DGX Spark). Applied to nine real-world systems, libumsh reduces data-plane time by 16-75% and control-plane overhead by 7-90%.
Read the full abstract ▾
All authors Jinrong Yang, Zimeng Wang, Rong Chen, Haibo Chen
Machine Learning · Cross-listed from stat.ML
Why Heavy-Tailed Weight Spectra Predict Model Quality
Joseph Wilson, Chris van der Heide, Liam Hodgkinson et al. (+3 more)
A solid understanding of the predictive success of deep neural networks (DNNs) remains elusive. For example, while many data-dependent metrics exist that seek to predict model quality of DNNs, these metrics may be expensive to compute for large
datasets and/or may be impossible to compute when training
datasets are not released. A practical and effective predictor of model quality involves analyzing DNN weight
matrices, as prior work has established that heavy-tailed spectral distributions in trained weight
matrices can be strongly predictive of model quality. However, such metrics lack a rigorous statistical justification. In this work, we aim to understand why these metrics perform well, from a statistical perspective. To do so, we employ a probabilistic framework to derive the marginal likelihood for a DNN, evaluated using only the final layer weights. Across large-scale convolutional DNNs and LLMs, we find that this marginal likelihood predicts model quality. To understand the role heavy-tailed spectra play in predictive performance, we derive the limiting log-marginal likelihood for spectra that follow the (heavy-tailed) High-Temperature Marchenko-Pastur (HTMP) distribution. We show that this limiting quantity is convex in a heaviness parameter, and we derive an optimal heaviness that empirically predicts over-fitting for large-scale DNNs.
Read the full abstract ▾
All authors Joseph Wilson, Chris van der Heide, Liam Hodgkinson, Zhichao Wang, Fred Roosta, Michael W. Mahoney