Numerical Analysis
Entropy-Based Local Characteristic Decomposition
Shaoshuai Chu, Michael Herty and Alexander Kurganov
Local characteristic decomposition (LCD) is widely used in high-order numerical methods for
hyperbolic systems of conservation laws to reduce spurious oscillations appearing in the computed solutions. The LCD implementation requires a representative average interface state, typically obtained using arithmetic or Roe-type averages of the nearly grid values. We propose an
entropy-based LCD (ELCD), in which the states in the two
cells adjacent to an interface are considered together with several nearby states in phase space. Among these candidates, we select the state that locally minimizes the
entropy and use it as an average interface state for linearizing the flux Jacobian. We incorporate the ELCD into several second-order finite-volume and fifth-order finite-difference schemes. Numerical experiments for the two-dimensional Euler equations of gas dynamics show that the schemes, which utilize the ELCD procedure generally resolve complex wave structures more sharply than their counterparts, which use the arithmetic averages.
Read the full abstract ▾
Numerical Analysis
A Fictitious Domain Formulation with Bubble Enrichment
Stefano Berrone, Lorenzo Neva, Stefano Scialò et al. (+1 more)
The fictitious domain method offers a powerful alternative to circumvent complex mesh generation process by
embedding the complex physical domain into a simpler, non-matching background mesh. Among the various strategies to enforce the boundary condition on such a mesh, one possibility is to impose it weakly through a Lagrange multiplier. Existing approaches following this strategy typically require two independent uniform meshes for the domain and the boundary, whose mesh sizes are related by a prescribed ratio. In this work, we relax this requirement by constructing the boundary mesh directly from the trace of the background triangulation. To recover the uniform discrete inf-sup condition under this weaker mesh assumption, we enrich the discrete space of the solution with bubble functions. Our main result is the construction of a suitable operator that allows us to prove this uniform discrete inf-sup condition, thereby establishing the stability of the resulting scheme. As a consequence, we derive optimal a priori error estimates and provide a numerical experiment to validate the theoretical results.
Read the full abstract ▾
All authors Stefano Berrone, Lorenzo Neva, Stefano Scialò, Fabio Vicini
Computational Engineering · Cross-listed from cond-mat.mtrl-sci
The Roadmap of Inorganic Computational Materials Databases: Capabilities, Credibility, Coverage, and the Open Frontier
Miao Liu, Jianghao Jin, Tenglong Lu et al. (+4 more)
Computational materials databases have become central infrastructure for data-driven discovery of inorganic materials, yet their growth remains strikingly uneven across property families. This perspective synthesizes a systematic survey of mainstream density functional theory (DFT) software, the computational cost and credibility of nineteen material-property families, and the coverage of existing computational databases, into a coherent picture of where the field stands and where it should go. We show that the ecosystem of first-principles codes is methodologically mature: for nearly every property of technological interest, at least one production-grade code can compute it.The binding constraint is no longer methodological capability but the economics of trust - which properties can be computed cheaply enough, and accurately enough, to be harvested at database scale. Mapping database coverage onto a Gartner-style readiness cycle reveals a sharp divide: ground-state structure, energetics, elasticity, and
topology have reached routine production, while nine property families - including NMR/EPR parameters, core-level spectra, electron-
phonon properties, thermal conductivity, and
quantum transport - remain without any systematic computational database. We argue that these blank zones define the scientific opportunity of the next decade, and we propose a three-horizon roadmap: consolidating coverage and interoperability in the near term, industrializing mid-cost properties through surrogate-accelerated workflows in the medium term, and conquering the high-cost frontier through machine-learned interatomic potentials, autonomous computing infrastructure, and community governance in the long term.
Read the full abstract ▾
All authors Miao Liu, Jianghao Jin, Tenglong Lu, Jianguo Si, Yin Shi, Sheng Meng, Weihua Wang
Artificial Intelligence
MetaRTL: Meta-path Attention Enhanced Relational Table Learning
Ken Zhong, Weichen Li and Zheng Wang
Relational table learning has gained increasing
attention with the widespread use of relational databases. Existing methods typically rely on deep GNN or HGNN stacks, leading to high computational costs and limited performance on large real-world databases. We propose MetaRTL, a two-stage framework for scalable and expressive relational table learning. In the first stage, MetaRTL obtains initial table
embeddings via lightweight pre-training. In the second stage, it performs non-parametric message passing to derive meta-path features, which are then aggregated by an
attention module, MetaAttn. By shifting computation from deep message passing to efficient meta-path aggregation, MetaRTL captures rich relational semantics while maintaining high efficiency. Experiments on 10 real-world
datasets across 24 tasks demonstrate the effectiveness of the proposed method.
Read the full abstract ▾
Information Retrieval
Reproducing Transparent and Scrutable Recommendations: Exploring Open-Weight Models via Natural-Language User Profiles
Noah Mamié and Laurin van den Bergh
In this reproducibility study, we investigate the transparency and scrutability of recommender systems enhanced by incorporating generated natural-
language user profiles that represent user preferences. The original paper explores the synthesis of user profiles from raw user-generated review text across domains such as movies and accommodations (Amazon Movies & TV, TripAdvisor). Crucially, these natural-
language user profiles enable direct user interaction and intervention, allowing users to customize recommendations by correcting misattributed preferences or addressing cold-start settings. We successfully reproduce the core findings of the original study. Additionally, we extend the evaluation by conducting systematic context ablation experiments, multi-seed stability across five distinct random seeds to establish statistical reliability, and a mechanistic interpretability analysis using the nnsight framework to probe internal model representations under counterfactual profile perturbations. Our findings verify the original paper's claim that User Profile Recommendation (UPR) achieves competitive performance under its test-set reranking protocol and makes recommendations more transparent. Perturbing the natural-
language profiles does change predictions, but it shifts predicted ratings uniformly across genres with no detectable genre-selective effect, leaving rankings unchanged even under direct activation steering. We trace this back to the rating-regression objective rather than the profile interface, with ranking-objective models clearly exceeding in this task.
Read the full abstract ▾
Artificial Intelligence
Dual-Axis Policy Optimization for LLM Agents: Bayesian Feedback Attribution and Trajectory Mass Normalization
Yingxuan Zhuang, Binhe Yu, Jingxiao Yang et al. (+6 more)
Reinforcement learning for LLM
agents involves two distinct optimization di- mensions: how environment feedback is exploited within a trajectory, and how complete trajectories are aggregated across a batch. We formulate these dimen- sions as Intra-Trajectory Feedback Attribution and Inter-Trajectory Objec- tive Aggregation, and introduce BATON (
Bayesian Attribution and Trajectory Objective Normalization), a dual-axis policy optimization framework. BATON instantiates the first axis with
Bayesian Feedback Attribution, which constructs a feedback-conditioned posterior over sampled actions, and the second with Trajec- tory Mass Normalization (TMN), which assigns equal optimization mass to com- plete trajectories. Experiments with GRPO and GiGPO on ALFWorld, WebShop, and SearchQA show that both axes provide independent gains and that their combi- nation consistently achieves the strongest overall performance across model scales.
Read the full abstract ▾
All authors Yingxuan Zhuang, Binhe Yu, Jingxiao Yang, Ruopei Sun, Ziting Li, Cheng Tan, Xuhong Zhang, Jianwei Yin, Jintao Chen
Mathematical Software · Cross-listed from physics.flu-dyn
Mixed-precision GPU algorithms for efficient turbulent flow simulations with Raviart-Thomas finite elements
Ivan Prusak, Enes Mustafa Soydan, Ivan Pribec et al. (+1 more)
We propose GPU
algorithms for high-fidelity simulation of incompressible turbulent flows. Discretization in space is performed with H(div)-conforming high-order Raviart-Thomas finite elements for the velocity and an $L^2$-conforming discontinuous Galerkin approximation for the pressure. In time, a consistent splitting scheme based on higher-order BDF time stepping is used, with convection treated explicitly. In this scheme, a pressure Poisson equation and a symmetric reaction-
diffusion-type equation for the velocity need to be solved in each time step. We develop a solution framework with fast
matrix-free operator evaluation for all ingredients, combined with multigrid solvers for the Poisson problem, and propose a robust mixed-precision algorithmic framework. A key to mixed-precision efficiency is a least-squares projection to generate accurate initial guesses for the iterative linear solvers, enabling us to work with relative residual tolerances of $10^{-3}$. In this regime, running the solvers entirely in single precision leads to almost no change in overall iteration counts and maintains the crucial
turbulence statistics, while showing up to $1.7\times$ speedup over pure double-precision simulations.
Read the full abstract ▾
All authors Ivan Prusak, Enes Mustafa Soydan, Ivan Pribec, Martin Kronbichler
Computation and Language
F$^{2}$DR: A Fine-Grained Full-Pipeline Reward Framework for DeepSearch Workflows
Bojian Xiong, Wentao Ding, Yujing Lu et al. (+11 more)
With the widespread industrial deployment of Large
Language Models (LLMs), DeepSearch has emerged as the dominant paradigm for resolving complex user queries. It typically operates through an iterative closed-loop workflow consisting of planning and reflection, information
retrieval, and answer generation. However, existing reward models (RMs) and evaluation
benchmarks are primarily designed for static single-turn tasks, failing to capture the full-pipeline complexity of DeepSearch workflows. To address this limitation, we propose F2DR, a fine-grained full-pipeline DeepSearch reward framework. F2DR evaluates DeepSearch workflows across three dimensions: Content, Trajectory, and Answer, enabling comprehensive process-level assessment. We further construct DeepSearch RM-Bench, a dedicated
benchmark for evaluating RMs in DeepSearch scenarios. Extensive experiments demonstrate that F2DR achieves significantly higher evaluation consistency than self-evaluation-based baselines, while DeepSearch RM-Bench exhibits strong discriminative capability across existing open-source RMs. We will publicly release the complete DeepSearch RM-Bench
dataset soon.
Read the full abstract ▾
All authors Bojian Xiong, Wentao Ding, Yujing Lu, Shaowei Zhang, Ling Shi, Jing Liao, Yan Wang, Yueyang Zhang, Long Xia, Zhiyuan Sun, Daiting Shi, Jingzhou He, Yuqi Ren, Deyi Xiong
Software Engineering
EviRCA: Decoupling Evidence Extraction from Reasoning for Microservice Root-Cause Analysis
Yuhao Wang, Zhen Qin, Xingliang Wang et al. (+3 more)
Root-cause analysis (RCA) is a critical yet labor-intensive task for maintaining modern microservice systems, making it an attractive target for large
language models (LLMs). Recent agentic approaches allow an LLM to iteratively explore raw telemetry by generating and executing code, asking a single model to simultaneously retrieve evidence, localize faults, and infer root causes over large volumes of heterogeneous telemetry, which leads to high computational cost, unstable behavior, and limited diagnostic accuracy. However, raw telemetry consists of numeric metrics, structured traces, and machine-generated logs that are not directly suitable for LLM processing. We present EviRCA, a framework for LLM-based RCA that decouples deterministic evidence extraction from LLM
reasoning. A system-agnostic extraction stage converts raw metrics, traces, and logs into a compact set of faithful
multimodal evidence cards, while the LLM reasons only over these structured observations through a small set of predefined read-only tools, without accessing raw telemetry or executing code. We evaluate EviRCA on OpenRCA, a
benchmark built from real, heterogeneous telemetry across three enterprise systems. EviRCA achieves a correct rate of 40.6%-43.9% across two different LLMs, substantially outperforming prior OpenRCA baselines that achieve up to 15.2%, while reducing
token consumption by 15-26x and execution time by 3-20x. Moreover, EviRCA solves hard cases requiring simultaneous
reasoning over time, components, and root causes, a setting where previous approaches reported near-zero performance. Our process-level failure analysis further shows that the bottleneck lies in judging the evidence that the extraction stage has already surfaced, rather than searching for it, suggesting that the effectiveness of LLM-based RCA depends heavily on the quality of evidence extraction.
Read the full abstract ▾
All authors Yuhao Wang, Zhen Qin, Xingliang Wang, Guochang Li, Weize Li, Shuiguang Deng
Robotics
TADreamer: Zero-Shot Language-Guided 3D Navigation for Terrestrial-Aerial Bimodal Robots via Video Imagination
Xiangyu Li, Tiancheng Lai, Xijie Huang et al. (+7 more)
Language-guided
navigation for terrestrial-aerial bimodal
robots requires selecting routes and locomotion modes that match scene context and task intent. Generated
videos can represent such motion sequences, but recovering metrically consistent
navigation references from them is challenging because of scale ambiguity and axis-dependent
geometric distortions. We present TADreamer, a zero-shot framework that grounds
video-imagined
navigation in measured geometry without task-specific training or fine-tuning. A
vision-
language model translates onboard observations and instructions into
navigation prompts, selects valid generated
videos, and provides corrective feedback when regeneration is needed. The selected
video is reconstructed into 3D waypoints annotated with terrestrial or aerial modes. A two-stage calibration procedure uses field-of-view constraints to initialize scale estimation, then refines axis-dependent scales, rotation, and translation by registering the reconstructed point cloud to measured geometry. The calibrated waypoints and mode labels guide a planner that incorporates measured geometry for
robot execution. Real-world experiments demonstrate
navigation across seven indoor and outdoor scenarios. With five candidates per round, usable
videos are obtained within two rounds in all seven scenarios. On the calibration observations, our method reduces mean absolute depth error by 87.7% and mean absolute relative depth error by 86.3% compared with NavDreamer.
Read the full abstract ▾
All authors Xiangyu Li, Tiancheng Lai, Xijie Huang, Ruitian Pang, Siqi Shen, Juncheng Chen, Zaisheng Pan, Chao Xu, Fei Gao, Yanjun Cao
Networking
PyStream: Enhancing Video Streaming Evaluation
Samuel Radler, Leon Prüller, Emanuele Artioli et al. (+2 more)
As streaming services become more commonplace, analyzing their behavior effectively under different network conditions is crucial. This is normally quite expensive, requiring multiple players with different bandwidth configurations to be emulated by a powerful local machine or a cloud environment. Furthermore, emulating a realistic network behavior or guaranteeing adherence to a real network trace is challenging. This paper presents PyStream, a simple yet powerful way to emulate a
video streaming network, allowing multiple simultaneous tests to run locally. By leveraging a network of Docker containers, many of the implementation challenges are abstracted away, keeping the resulting system easily manageable and upgradeable. We demonstrate how PyStream not only reduces the requirements for testing a
video streaming system but also improves the accuracy of the emulations with respect to the current state-of-the-art. On average, PyStream reduces the error between the original network trace and the bandwidth emulated by
video players by a factor of 2-3 compared to Wondershaper, a common network traffic shaper in many
video streaming evaluation environments. Moreover, PyStream decreases the cost of running experiments compared to existing cloud-based
video streaming evaluation environments such as CAdViSE.
Read the full abstract ▾
All authors Samuel Radler, Leon Prüller, Emanuele Artioli, Farzad Tashtarian, Christian Timmerer
Artificial Intelligence
Steering Equilibrium Selection in Regularized Self-Play via the Reference Policy
Luis Leal
Regularized self-play – the family behind DeepNash's Stratego play – drives a two-player zero-sum policy to a Nash
equilibrium by best-responding to a slowly moving,
entropy-regularized reference policy $\rho$. When the game has a polytope of value-equivalent
equilibria, the regularizer silently breaks the tie: with a uniform reference it selects the maximum-
entropy member, the I-projection of $\rho$ onto the Nash set. Can the reference be used to choose the
equilibrium on purpose? On five exactly solvable games plus a 2-D polytope, with exact best responses and equivalence tests over independent seeds, anchoring the reference at a target member and refining steers self-play to that member with mean coordinate error 0.007 at median exploitability $5\times10^{-5}$, TOST-equivalent to the request within $\pm0.05$; the anchoring persists through refinement and follows the reference, not the initialization. Selection follows the reach-weighted I-projection (slope 0.969 [0.950, 0.987]). We report with equal emphasis where the story breaks: fixed off-
manifold references cost 0.08-0.25 exploitability; stiff or flat families require a smaller mirror step, set by a pre-registered rule; boundary targets undershoot;
curvature predicts where boundary saturation bites (rank correlation 0.90, p=0.037) while interior precision is
curvature-independent. Table and MLP steering maps are equivalent within $\pm0.03$ at every target (30 seeds); matched control arms show
attention's robust signature is excess seed variance, any systematic shift bounded at 0.018 and not significant. Against a best response the selection-robustness trade-off is degenerate: steering matters only against fixed, non-
equilibrium opponents. The recipe – anchor the reference at the desired member and refine – reinterprets the KL anchor of RLHF-style RL as a selection knob, not only a stability leash.
Read the full abstract ▾
Information Theory
Online Material-Labeled Environment Reconstruction via Bayesian Multipath Attribution for Low-Altitude ISAC
Meihui Liu, Shu Sun, Ruifeng Gao et al. (+1 more)
Environment reconstruction for low-altitude integrated sensing and communications (
ISAC) has largely focused on geometry-centric maps, overlooking material-dependent propagation effects. Material-labeled reconstruction is therefore a key step toward propagation-aware mapping, enabling more physically grounded channel prediction and uncrewed aerial vehicle (
UAV) networking. However, constructing such maps from wireless multipath observations is challenging in outdoor multi-building scenarios because multipath components (MPCs) from different facades are mixed, path-to-facade attribution is uncertain, and
UAV measurements arrive sequentially under time-varying observation geometries. To address these challenges, we propose a unified online probabilistic framework that represents each reflecting facade as a virtual anchor (VA) and couples
Bayesian VA localization, multipath attribution, and material inference. The
Bayesian front end estimates facade-level geometry and computes soft MPC-to-VA attribution probabilities using a speculardiffuse likelihood model, thereby accounting for both dominant specular paths and diffuse surface-interacted components. These attribution probabilities are used to construct attribution-aware MPC representations, which are aggregated in a VA-centric manner and mapped by a material inference network to facadelevel material evidence. The resulting evidence is recursively fused through an online
Bayesian update to produce stable material posteriors and material-labeled environment maps. Ray-tracing simulations in a representative urban street scenario show that the proposed method substantially outperforms a no-attribution baseline, achieves 93.75% final facade-level material accuracy on a held-out
UAV trajectory, and maintains accurate VA-based facade localization.
Read the full abstract ▾
All authors Meihui Liu, Shu Sun, Ruifeng Gao, Qiuming Zhu
Sound
CoReLoop: Parameter-Efficient Controlled Recurrent Refinement for Audio Deepfake Detection
Kunyu Feng, Yuxiang Wang, Li Wang et al. (+2 more)
Audio deepfake detectors are expected to remain robust to diverse attacks,
datasets, and recording conditions, yet collecting training data that cover every future condition is impractical. We investigate whether an already-trained SSL-based detector can improve its generalization through additional recurrent computation, without introducing new training data or updating its original parameters. Directly feeding the encoder output back as its next input, however, severely degrades detection, revealing a mismatch between the representations produced and consumed by a model trained for single-pass inference. We therefore propose CoReLoop, which enables controlled recurrent refinement through loop-specific LoRA and lightweight modules that adapt recurrent inputs, regulate state updates, and align refined representations with the frozen classifier. Across 14 diverse test sets, CoReLoop improves pooled EER across 3-, 6-, 12-, and 24-layer encoders; on the 24-layer model, two-pass refinement reduces EER from 4.85% to 3.74% while training only approximately 11M of 598M parameters. An optional halting head further selects refinement depth per utterance, achieving 3.73% EER with an average of 1.18 passes. Analysis shows that later-pass saturation coincides with smaller applied updates and nearly balanced corrections and regressions, while the recurrent state continues to change.
Read the full abstract ▾
All authors Kunyu Feng, Yuxiang Wang, Li Wang, Wan Lin, Zhizheng Wu
Robotics
RotateIt! Fast and Reliable Single-Arm Garment Unfolding via Online-Adaptive Dynamic Rotation
Zeqing Zhang, Zuokun Xie, Ao Fang et al. (+4 more)
Robotic garment unfolding is essential for downstream tasks, yet quasi-static methods require repeated actions, while existing dynamic approaches predominantly rely on bimanual flinging. We present RotateIt!, a single-arm framework that uses adaptive axial rotation for dynamic garment unfolding. To the best of our knowledge, it is the first unfolding framework to employ dynamic axial rotation as its primary manipulation primitive. From a randomly initialized tabletop configuration, the
robot selects a rotation-effective grasp and rotates the lifted garment about an approximately fixed anchor, generating inertial tension that separates overlapping layers within a compact workspace. A grasp ranker selects the anchor, while an online residual policy adapts the rotation extent and speed, thereby determining the release timing. Across seen and unseen simulated garments and eight unseen real garments, RotateIt! improves success within three attempts by 44.0-61.0 percentage points over quasi-static pick-and-place. The simulation-trained policies transfer zero-shot to the real world, achieving 75.6% success, 41% higher first-attempt coverage, and 26% higher final coverage. The resulting states further enable autonomous robotic folding without manual rearrangement.
Read the full abstract ▾
All authors Zeqing Zhang, Zuokun Xie, Ao Fang, Bin Dai, Zhengjie Shu, Yifeng Tang, Ziwei Wang
Computer Vision
SnapPhysics: A Physics-Aware Scene Graph from a Single View for Interactive Mixed Reality Scenes
Suji Kang, Seok-Young Kim, Young Bin Kim et al. (+4 more)
We propose SnapPhysics, a training-free framework that reconstructs 3D objects and estimates their physical properties such as mass, friction, and center of
gravity from a single image. For physically coherent interactions in mixed reality (MR), such properties are as important as geometry. Prior approaches infer them by analyzing object dynamics in
video, which is computationally costly, or by querying
vision-
language models (VLMs) on single images, which lacks
geometric grounding and inter-object relationships. We address these limitations by combining instance-level 3D reconstruction and spatial
alignment with a physics-aware scene graph that encodes these relationships and per-object metric geometry as structured context for VLM-based property
reasoning. Experiments on 3D-FRONT show that SnapPhysics improves scene-level F-Score by 18.6% over the best learning-based method, and on real captured scenes with ground-truth mass, it reduces the mean absolute log difference error (mALDE) by up to 20.5% and improves log-scale correlation ($r^2_{\mathrm{ls}}$) by up to 19.6% over VLM-only estimation. SnapPhysics enables physically interactive MR experiences without manual parameter tuning. Project page: https://snapphysics-ismar2026.github.io/.
Read the full abstract ▾
All authors Suji Kang, Seok-Young Kim, Young Bin Kim, Taewook Ha, Dieter Schmalstieg, Shohei Mori, Woontack Woo
Artificial Intelligence · Cross-listed from quant-ph
Long-horizon autoformalization of a core theorem underlying MIP* = RE
Sirui Lu, Ruixuan Deng, Yanqiao Zhu et al. (+1 more)
Landmark mathematical formalizations have taken specialist teams years to complete. We present FormalFlow, a system that coordinates AI proving
agents under human supervision to address statement drift and proof composition in long-horizon formalization. Drawing on software-engineering principles and practices, it uses a shared blueprint to guide nested planning, proving, and review loops. Using FormalFlow, we completed a machine-checked Lean 4 proof of the
quantum soundness of the classical low individual-degree test, a core
theorem underlying MIP* = RE, in 63 days. The final library contains 126,367 lines of Lean code, all generated by
agents. Beyond providing a verified foundation for
quantum complexity, the formalization corrects side conditions and intermediate error bounds in the published proof and improves the error exponent of the main
theorem. The development record shows what it takes to trust proofs written by AI
agents and provides reusable tools for verifying research mathematics at scale.
Read the full abstract ▾
All authors Sirui Lu, Ruixuan Deng, Yanqiao Zhu, Zhengfeng Ji
Robotics
Vehicle Trajectory Prediction via Neural Fusion of Multiple EKF-Based Trajectory Candidates
Seong-Jun Kim and Seung-Hyun Kong
Predicting the future trajectories of surrounding vehicles in autonomous driving is important for collision risk assessment and safe ego-vehicle path planning. Conventional neural network-based trajectory predictors typically achieve strong prediction performance by exploiting
agent history, dynamic scene graphs, and semantic maps. However, in specific motion regimes such as acceleration, deceleration, and turning, these predictors may fail to reflect physically feasible trajectories. To address this issue, this study proposes a framework that fuses the output of Trajectron++, a neural network-based trajectory predictor, with extended Kalman filter (EKF)-based multiple trajectory candidates at a late stage. On the nuScenes
dataset, the proposed method reduces the average displacement error and final displacement error of the Trajectron++
robot baseline by 13.7% and 14.6%, respectively, without modifying the baseline architecture. These results indicate that EKF-based trajectory candidates can effectively complement neural trajectory prediction through learned fusion.
Read the full abstract ▾
Computer Vision
Absence is Presence: Understanding Visual Scene Negative Events Under Safety Cognitive Constraint
Zhiyun Jiang, Hanyong Wang, Binbin Liang et al. (+3 more)
Traditional scene understanding focuses on affirmative information objectively present in images. However, in safety-critical domains, comprehending key information that should exist but is actually absent is vital for risk mitigation. To bridge this gap, we focus on visual scene negative captioning with safety as the cognitive constraint. The core challenge is to convert physical absence into semantic negative events. Existing
vision-
language models (VLMs) struggle with this process because affirmation bias suppresses negative
reasoning, while limited mental filling capability and representation bias further hinder the inference of absent information. To address these challenges, we propose a negative captioning framework based on counterfactual reconstruction and contrastive decoding (CRCD). Inspired by human cognition, CRCD reformulates the task as counterfactual latent change captioning to bypass affirmation bias. It contrasts a synthesized safe expectation with reality to identify semantic omissions. To address limited mental filling, we design a dual-branch counterfactual reconstruction architecture. The amodal completion branch restores defective objects, while the functional association branch infers completely absent safety objects. Concurrently, a multi-condition representation learning mechanism is integrated to mitigate representation bias by projecting universal features onto predefined safety criteria subspaces, thereby capturing information across more dimensions. By decoding feature-level semantic residuals between the reconstructed scene prototype and raw input, CRCD bounds the non-existence search space and activates the decoder's negative logic. Extensive experiments validate the effectiveness of CRCD, establishing a high-performance baseline for this pioneering task.
Read the full abstract ▾
All authors Zhiyun Jiang, Hanyong Wang, Binbin Liang, Yu Xie, Menglong Yang, Wei Li
Computation and Language
Dictionary-Constrained Grapheme-to-Phoneme for Unsegmented Languages from LLM-Annotated Data
Rui Hu, Zhenpeng Zhan and Xiaolong Lin
Grapheme-to-phoneme (G2P) conversion turns raw text into its phonemic form and is an essential part of both text-to-
speech (TTS) and automatic
speech recognition (ASR) systems. It is required to be fast, stable and context-aware. For unsegmented
languages such as Japanese, G2P additionally couples word
segmentation with highly context-dependent polyphone disambiguation, and the scarcity of accurately annotated data remains a bottleneck. In this paper, we present a context-aware,
segmentation-agnostic neural G2P framework that models the joint
segmentation-and-reading hypothesis space, scoring paths of a discriminative conditional random field (CRF) over a dictionary-derived word
lattice. To tackle data scarcity, we utilize large
language models (LLMs) to generate more than 2 million sentences. Experimental results demonstrate that our method substantially outperforms conventional morphological analyzer-based methods and neural sequence models. On the Joyo-Kanji-Yomi
benchmark, our method reaches 99.62% target word reading accuracy, 0.32% target word phoneme error rate (PER) and 0.14% sentence PER.
Read the full abstract ▾
Systems and Control
Design of Economic Dispatch Schemes of An Isolated BESS Network Based on Distributed Discrete-time PI+Rest Consensus
Yalin Zhang, Zhongxin Liu and Zengqiang Chen
Battery energy storage systems (BESSs) are widely integrated into smart grids. For an isolated BESS network, however, capacity degradation and power loss of battery units increase operating costs. To alleviate this problem, two distributed economic dispatch (ED) schemes with discrete-time dynamics are developed in this paper, thus obtaining the optimal output power vector and ensuring supply-demand balance while considering dynamic line loss and capacity constraints. It is worth mentioning that proportional-integral protocols with reset mechanisms (PI+R protocols) are introduced into these schemes which can greatly improve the consensus rate and control accuracy. Specifically, a marginal cost (MC) consensus controller and an average power mismatch
estimator are the core components of each scheme, where these two are coupled to each other. In this regard, the difference between the two schemes is that for the MC consensus controllers, one involves incorporating the estimated average power mismatch feedback term into the closed-loop system error to design the PI+R protocol, while the other does not. In addition, regarding to each PI+R protocol, the integral term is reset to 0 when the proportional term experiences zero crossing, in order to accelerate the convergence rate and reduce overshoot. The effectiveness, conditions under which the reset mechanism works, and stability of these schemes are all well analyzed. Finally, some simulation cases are designed and compared with an existing solution. From the simulation results, it can be seen that the designed second scheme greatly improves the performance of the previous scheme in consensus rate, convergence rate, BESS/
agent plug and play, load switching, and wide area system application.
Read the full abstract ▾
Robotics
HEROIC: Heterogeneous Evidential Reasoning for Open-Vocabulary Identification and Cross-Robot Collaboration
Mihir Chauhan, Aarav Jain, Addison Zucek et al. (+3 more)
Multi-
agent heterogeneous air-ground
robot teams are attractive for open world search, with applications for reconnaissance, urban search and rescue missions (USAR), disaster response and recovery, and hazardous environments. These two platforms have different failure modes: aerial
robots cover ground quickly but cannot resolve small or occluded targets from altitude, while ground
robots can identify objects-of-interest, such as people or hazardous objects, at close range but cover less area. Existing
language-tasked teams either have roles fixed prior, or have a
language model assign them from hand-written capability tags, so the team is unable to know when within a mission an asset is no longer useful. We present HEROIC, a decentralized heterogeneous multi-
agent open-vocabulary search coordination framework that requires
agents to communicate in natural
language only. HEROIC's initial
agent role assignment is derived from sensor properties and a scale law to determine whether targets can be detected with a high confidence. From the mission's natural
language prompt alone, this law assigns aerial flight altitudes and sweep spacing. When this calculated height falls below the altitude for safe flight, aerial
agents re-task themselves from searcher to aerial triage, escort, and route guide for ground
agents. Both
robots maintain an evidential belief over the search area (bearing rays for positive evidence, a log-odds posterior for negative evidence) and gate any arrival on close-range verification. In full-stack experiments, HEROIC reaches the target 84% of the time across all 6 scenes, compares to 35-54% for
vision-
language frontier baselines, frontier-based search, lawnmower, and random-walk running the same perception, all while being 2-4x sooner to arrive at the target.
Read the full abstract ▾
All authors Mihir Chauhan, Aarav Jain, Addison Zucek, Manmeet Dang, Damon Conover, Aniket Bera
Robotics
Affective Shared Autonomy: Temporal Affect Dynamics and Subjective Evaluation in Bimanual Teleoperation Tasks
Zhengji Liang, Guiyin Tian, Sijin Qu et al. (+2 more)
Physical teleoperation integrates human cognitive flexibility with robotic precision, yet demanding manipulation tasks frequently induce severe cognitive workload, acute frustration, and execution breakdown. Conventional shared autonomy paradigms rely primarily on task-based rules, such as spatial error boundaries, which disregard the operator's transient affective state and risk misaligned control interventions. To address this limitation, we propose an affect-aware shared autonomy teleoperation framework that dynamically modulates robotic assistance based on real-time operator state estimation. The system estimates operator affective states from synchronized facial
video, cardiac signals, and bilateral arm kinematics, outputting a seven-state affective distribution and a three-category operational abstraction (neutral, productive, adverse). Affect-aware assistance is selectively triggered when the user is detected in a continuous adverse state, preserving task-positive engagement without unnecessary disruption. The empirical user study ($N = 30$) confirms that the proposed affective assistance increases the productive states by up to 39.7% without compromising user agency. The collected
dataset represents the first
multimodal dataset that provides continuous visual, physiological, and operator's bilateral motion tracking of temporal affective state shifts during bimanual teleoperation. Our
multimodal fusion model outperforms zero-shot baselines (Qwen, MiniCPM-V) in tracking temporal state dynamics. This real-world deployment offers a new human-centric framework that integrates visual, physiological, and motion tracking for physical human-
robot interaction.
Read the full abstract ▾
All authors Zhengji Liang, Guiyin Tian, Sijin Qu, Hainan Liu, Shiyan Hu
Machine Learning
DeliveryGym: An RL Environment for Long-Horizon Embodied Agent Planning with Adaptive Curriculum
Haoqiang Kang, Yiming Zhang, Yiyang Guo et al. (+5 more)
Executable environments enable LLM
agents to learn from the consequences of their actions. For
embodied agents, those consequences extend beyond whether the current task succeeds: completing a delivery can consume the time, energy, or money needed for later work. Learning to plan therefore requires environments that preserve these dependencies and turn them into feedback across a complete trajectory. We introduce DeliveryGym, a 3D environment for evaluating and training
agents on continuous courier shifts. It couples
multimodal tool interaction with persistent world dynamics and computes trajectory rewards from simulator events, making the costs of an
agent's decisions available for reinforcement learning (RL). The environment also adapts future training shifts to the policy's observed weaknesses while keeping evaluation fixed. Across six models and 13 city maps, evaluation exposes a gap between reliably executing assigned deliveries and choosing and sequencing work over a shift. On the unseen-city test set, RL improves Qwen3-VL-4B's net income by 54.3%, showing that learning from complete shifts improves performance under these coupled constraints. Adapting the training environment improves evaluation income by 18% over uniform sampling at 100 updates, indicating that which situations an
agent practices also matters. DeliveryGym provides an executable setting for studying how
agents learn to coordinate deliveries and preserve resources for later orders within an episode.
Read the full abstract ▾
All authors Haoqiang Kang, Yiming Zhang, Yiyang Guo, Chuying Li, Jianzhi Shen, Tianruo Rose Xu, Xiaokang Ye, Lianhui Qin
Computation and Language
Evolution or Illusion? Rethinking Evaluation in LLM Evolutionary Search
Tal Oved, Roi Pony, Oshri Naparstek et al. (+1 more)
LLM-driven evolutionary search finds programs by launching seeds and iterating each one. Papers report a single budget setting, usually one seed run for a fixed number of iterations, and rank methods from that one point. We show this is not enough. We evaluate three evolutionary search strategies on five optimization tasks, commonly used by papers in the genre to report results. We run the analysis over a full grid of seeds and iterations. Our findings suggest that the best way to split a fixed budget between more seeds (width) and more iterations (depth) changes with the strategy, the task, and the total budget. Furthermore, we observe that the ranking of strategies also changes with the budget. On one task the strategy that looks worst at one seed is best at forty seeds. On another the best number of iterations is well below the value common in practice, so extra depth wastes budget that more seeds would turn into score. We provide a measurement protocol that reports the seeds-by-iterations frontier and practical guidance for using it.
Read the full abstract ▾
All authors Tal Oved, Roi Pony, Oshri Naparstek, Udi Barzelay
Robotics
LIFD: Anchored Diffusion for 3D-Aware Scene Memory in Robotic Manipulation
Wenbo Li, Yiteng Chen, Wenhao Li et al. (+1 more)
During manipulation,
robot and scene motion can move previously observed regions outside the camera's field of view. Geometry-aware RGB features encode visible structure, while control under partial observability requires scene
memory that integrates observation history and grounds inferred content in current evidence. We introduce \lifd{} (Look, Imagine, Focus, and Do), a framework for persistent, 3D-aware scene
memory. LIFD learns scene
tokens through multi-view agreement, then completes them from a single RGB view and recurrent
memory using rectified flow. Anchor-Guided Cross-
Attention anchors generation to current geometry-aware features, and compact slot features condition a visuomotor policy. Multi-view and
geometric supervision are used during representation learning; deployment requires one RGB camera, proprioception, and a task instruction. LIFD (Staged) reaches 91.6% average success on LIBERO and 79.8% on MetaWorld, improving LIBERO average success by 11.1 percentage points over Joint training. After policy-head adaptation with ten demonstrations per family, LIFD achieves 56.0% mean success across four UR5e task families, compared with 40.5% for OpenVLA-7B.
Read the full abstract ▾
All authors Wenbo Li, Yiteng Chen, Wenhao Li, Qingyao Wu
Data Structures and Algorithms
Zhao Song and Song Yue
Marcus, Spielman, and Srivastava [MSS15] established the existence of Kadison–Singer partitions. We provide
polynomial-time
algorithms for the Kadison–Singer problem. For Hermitian
matrices $A_1,\ldots,A_m\in\mathbb C^{n\times n}$ of rank at most one, we give two
algorithms that find signs $\sigma\in\{\pm1\}^m$ satisfying $\|\sum_i \sigma_iA_i\|\le C\|\sum_i A_i^2\|^{1/2}$. The deterministic
algorithm achieves $C=3.3443$ using $\widetilde O(mn^2+n^{4.75})$ arithmetic operations. The randomized
algorithm achieves $C=4.8628$ using $\widetilde O(mn^2+n^{3.58})$ arithmetic operations in expectation. For vectors satisfying $\sum_i a_ia_i^*=I$ and $\|a_i\|^2\le\alpha$, the
algorithms yield partitions $[m]=I_1\cup I_2$ satisfying $\|\sum_{i\in I_j}a_ia_i^*-I/2\|\le (C/2)\sqrt\alpha$ for $j=1,2$.
Read the full abstract ▾
Computer Vision
AI Smart Glasses for Wearable Intelligence: From Egocentric Sensing to Agentic Personalization
Xu Yuan, Yi Wang, Zhuohang Jiang et al. (+8 more)
Recent advances in artificial intelligence (AI) are reshaping smart glasses from
egocentric capture and display devices into platforms for wearable intelligence. Smart glasses increasingly serve as wearable AI systems that connect first-person observation with real-time assistance under strict form-factor constraints. We frame this transition through the lens of AI smart glasses and define them as a system-level concept in which
egocentric sensing, resource-aware computing, intelligent
reasoning,
multimodal interaction, and real-world application constraints are co-designed for personalized assistance in the physical world. To systematically study this perspective, we organize the survey around four connected dimensions. First, we examine the hardware foundation that bounds sensing, computation, feedback delivery, and sustained deployment. Second, we study wearable intelligence, where
egocentric signals are transformed into perceptual, contextual, and agentic capabilities. Third, we discuss interaction design, through which users request, receive, correct, and regulate assistance during ongoing activity. Fourth, we analyze application scenarios across healthcare, accessibility, situated learning, daily life assistance, cultural tourism, and industrial support, showing how domain requirements reshape system design and evaluation. We further identify five cross-cutting research challenges for future AI smart glasses: next-generation hardware, trustworthy
egocentric intelligence, lifelong personalized
memory, proactive intelligence, and
embodied foundation models. By centering smart glasses as wearable-intelligence platforms, this survey provides a unified framework for organizing technologies, applications, and open challenges in this emerging area.
Read the full abstract ▾
All authors Xu Yuan, Yi Wang, Zhuohang Jiang, Haohao Qu, Yujuan Ding, Shanru Lin, Guoliang Xing, Hongxia Yang, Jiannong Cao, Qing Li, Wenqi Fan
Performance
Whittle index approach to multi-server scheduling with convex delay costs and impatient customers
Samuli Aalto
We consider the dynamic scheduling problem in a multi-class M/G/N + M queue with convex delay costs and impatient customers that have exponential abandonment times. We apply the Whittle index approach to find a reasonable heuristic solution for this tricky problem. By assuming exponential abandonment times, we are able to make a very straightforward use of the results of the corresponding problem with patient customers presented in Queueing Systems, Vol. 110, Article no. 2, 2026. Our main theoretical achievements are proving that the closed version of the corresponding discrete-time problem is indexable and deriving an explicit expression for the Whittle index. The discrete-time results are utilized to develop the Whittle index policy for the original continuous-time scheduling problem.
Read the full abstract ▾
Cryptography and Security
Sybil-TraceGuard: Traceability-enhanced Sybil Guardian for Connected and Autonomous Vehicles Using Dynamic Semi-supervised GNN
Qian Xu, Jiaxun Zhang, Chengyue Wang et al. (+1 more)
Connected and autonomous vehicles (CAVs) face severe Sybil attacks, where attackers exploit
privacy-preserving pseudonym-switching mechanisms to anomaly alternate identities while forging Basic Safety Messages (BSMs). Although existing schemes can flag suspicious behaviors, these temporally fragmented Sybil identities render traditional single-point and sequence-based deep learning methods ineffective. Linking these fragmented identities back to the source attacker is essential for root-cause elimination, particularly under extreme label scarcity. Therefore, the Sybil-TraceGuard is proposed as a dynamic semi-supervised spatio-temporal GNN framework for Sybil Guardian, prioritizing "who is responsible" over "whether an attack is happening". It comprises four tightly coupled modules: Incremental Stream Attack Detection (ISAD) for efficient Sybil attack pre-screening; the Dynamic
Topology-aware Constructor (DTC) for constructing spatio-temporal dynamic graphs; the Spatial GAT-Encoder with Multi-head
Attention (SGEM) to capture multi-identity logical conflicts in spatial interactions; and the Multi-scale Spatio-Temporal Audit (MSTA) to audit short-term and long-term temporal inconsistencies. These modules are optimized within a semi-supervised Mean-Teacher framework via feature-edge shuffling perturbations, regularizing the latent feature space using minimal labels. Experiments across four Sybil attack scenarios demonstrate that Sybil-TraceGuard effectively links fragmented pseudonyms to source attackers. It outperforms state-of-the-art baselines across unlabeled ratios of 0.70-0.95, maintaining high stability and sensitivity despite extreme class imbalance and varying hyperparameter settings.
Read the full abstract ▾
All authors Qian Xu, Jiaxun Zhang, Chengyue Wang, Zhenning Li