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
Complex Variables
On $\varphi$-Normality of Harmonic Mappings and Their Families
Gopal Datt and Ritesh Pal
In this paper, we present Lappan's five-point type criteria for $\varphi$-normality of sense-preserving harmonic mappings and families of harmonic mappings in the unit disc $\mathbb{D}$. We establish a normality criterion involving the higher-order spherical derivative of order $k$, and $k+2$ distinct test values under suitable conditions. We further reduce the number of test values to $\left[\frac{k}{2}\right]+2$ under an additional differential condition involving the analytic and co-analytic parts. We also prove a generalization in which the spherical derivative is replaced by a
polynomial with non-negative real coefficients.
Read the full abstract ▾
Fluid Dynamics
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
Audio and Speech Processing
Consensus-Guided Shared-Specific Tri-View Learning for Speech Emotion Recognition
Bing Huang, Yujian Ma, Xikun Lu et al. (+2 more)
Speech emotion recognition (SER) benefits from heterogeneous acoustic representations, but views derived from the same utterance contain both overlapping emotional evidence and representation-dependent cues. Direct fusion may therefore propagate redundant information or obscure complementary details. To address this issue, we propose Tri-view Consensus-Guided Fusion (TriCGF) for jointly modeling spectrogram, Mel-frequency cepstral coefficients, and HuBERT representations. TriCGF organizes each view into common and view-specific components before fusion. Cross-view Consensus Learning aggregates the common components into a global reference, while View-wise Gated Integration adaptively combines this reference with each view-specific component. A soft difference regularizer further discourages excessive information overlap. Under speaker-independent evaluation, TriCGF achieves 74.19% weighted accuracy (WA) and 75.17% unweighted accuracy (UA) on IEMOCAP, and 94.36% WA and 94.28% UA on EmoDB, outperforming representative SER methods on both
datasets.
Read the full abstract ▾
All authors Bing Huang, Yujian Ma, Xikun Lu, Xianquan Jiang, Jinqiu Sang
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
Statistics Applications
Identifying Damage Pathways Linking Sequence Composition to Storage Failure in DNA Data Storage via High-Dimensional Mediation Analysis
Jingyi Li, Huaming Wu and Haixiang Zhang
DNA data storage offers extraordinary information density and long-term durability, but its reliability is limited by sequence-dependent errors introduced during synthesis and accumulated during storage. It remains unclear how sequence composition is associated with storage failure through specific molecular damage components. We develop a high-dimensional semiparametric mediation framework for survival outcomes. GC content is treated as the exposure, a high-dimensional baseline damage spectrum (a vector of per-read damage counts stratified by trinucleotide context and error type) as the mediator, and storage-quality failure as the outcome. Nonlinear
covariate effects in both the mediator and survival models are approximated using deep neural networks. A three-step procedure combining product-of-coefficients screening, Smoothly Clipped Absolute Deviation (SCAD) penalized estimation, and joint significance testing is developed for mediator selection and inference. Applied to an aging experiment on electrochemically synthesized DNA, the method identifies 14 significant mediators, all corresponding to single-base deletions, with estimated mediated effects concentrated in trinucleotide contexts ending in C. These results reveal deletion-type damage as a major pathway linking sequence composition to reduced archival reliability and suggest candidate sequence features for future optimization and error-control strategies. The proposed framework thus offers a mechanism-oriented statistical approach for understanding and improving the reliability of DNA data storage.
Read the full abstract ▾
Analysis of PDEs
Contact discontinuities for 3-D axisymmetric flows with nonzero swirl
Myoungjean Bae and Jong-Seo Yoon
In this paper, we prove the existence and far-field behavior of an axisymmetric solution $(\rho,\mathbf{u},p)$ to the steady Euler system in an infinitely long cylindrical nozzle with a perturbed wall $r=R(x_1)$, containing a contact discontinuity $r=g_D(x_1)$. The background flow carries a nonzero swirl component $\beta_0\mathbf{e}_\theta$, where $\beta_0$ is not necessarily small. Consequently, the background
entropy, Bernoulli function, and angular momentum density depend on the radial variable, and their radial derivatives are not necessarily small.
Read the full abstract ▾
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
Computational Physics
Exergy-Anergy Representation of Turbomachine Performance Characteristics
Tihomir Varchev, Yiwen Yuan, Tobias Schateikis et al. (+1 more)
The performance synthesis calculation of aircraft engines relies on tabulated
datasets for the simulation of the complex turbomachinery components at acceptable runtimes. Typically, these so-called performance maps express the change of the fluid's energetic state over the component in terms of the total pressure ratio and the isentropic efficiency of the process. However, the definitions of both parameters are different for compressors and turbines and the isentropic efficiency is in both cases not defined for a unity pressure ratio. Moreover, this parameter combination is not directly applicable when modelling the engine at the aircraft level, which is required for modern highly integrated aircraft design. As exergy analysis is an established tool for aircraft design asessment, novel performance maps are proposed that describe the change in exergy and anergy over a given turbomachine component. Both changes are expressed as non-dimensional parameters whose definition is consistent for compressors and turbines, and is compatible with a unity pressure ratio. It is shown that the presented exergy-anergy maps are obtainable on a standard turbomachine test bed or through transformation of existing maps. It is highlighted using examples, that the conversion between existing maps and exergy-anergy maps is completely lossless. The different operating regimes of the turbomachines are clearly distinguishable in the novel map representation, which allows an assessment of the map's physical consistency. It is therefore concluded, that the exergy-anergy maps are an important alternative to the performance map variants established today.
Read the full abstract ▾
All authors Tihomir Varchev, Yiwen Yuan, Tobias Schateikis, Stephan Staudacher
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
Quantum Physics
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
Quantum Physics
Local unitary equivalence of orthogonal arrays and related linear codes
Miaomiao Zheng, Yajuan Zang, Xiuling Shan et al. (+1 more)
Orthogonal arrays (OAs) are combinatorial configurations with applications in experimental design, error-correcting codes, and
quantum information. Local
unitary (LU) equivalence provides a natural framework for classifying multipartite entangled states. Using the correspondence between OAs and
quantum states, Goyeneche and Życzkowski [Phys. Rev. A, 2014, 90: 022316] posed the problem of determining when OAs are $LU$ equivalent. In this paper, we construct OAs from generator
matrices and establish conditions for
Fourier-based $LU$ equivalence of OAs and irredundant orthogonal arrays (IrOAs). For
prime alphabets, we identify the
Fourier partners of the linear OAs considered here with the arrays of their corresponding dual codes. This gives an explicit connection between $LU$ equivalence and coding theory. We also identify families of $LU$ equivalent OAs arising from specific classes of linear codes.
Read the full abstract ▾
All authors Miaomiao Zheng, Yajuan Zang, Xiuling Shan, Zihong Tian
Combinatorics
The small Davenport constant of $H_{27}\times C_3^r$
Andreas Volkmann
Let $H_{27}=\mathrm{UT}_3(\mathbb{F}_3)$ be the nonabelian group of order $27$ and exponent $3$. We prove that $\mathsf{d}(H_{27}\times C_3^r)=2r+6$ for every integer $r\geq0$. The proof combines an affine coefficient identity in the group
algebra of an elementary abelian group with a decomposition of the nonorthogonality graph of $\mathbb{F}_3^2$ into eight edge-disjoint zero-sum triangles. It is uniform in $r$, does not use the value of the small Davenport constant for a smaller nonabelian group, and requires no computational enumeration.
Read the full abstract ▾
High Energy Physics (Phenomenology)
FLARE: an open-source data workflow orchestration tool
Cameron Cooper Harris, Aman Desai and Paul Jackson
Flare is an open-source Python-based data workflow orchestration tool powered by b2luigi. It automates the workflow of Monte Carlo (MC) generators inside the Key4HEP stack, such as Whizard, MadGraph5 and Pythia8, together with fast detector simulation using Delphes. It also automates the Future Circular
Collider (FCC) physics analysis software workflow. These workflows are combined, giving a user an automated pipeline from MC production to final FCCAnalyses histograms. With its customisation options and Python API,
Flare simplifies executing FCC-ee analyses, especially when custom MC events are required.
Read the full abstract ▾
Atomic Physics
Observation of multiphoton entanglement in resonance fluoresce
Xiao-Long Zhou, Jian Wang, Ze-Min Shen et al. (+8 more)
Resonance fluorescence, the process in which a single two-level
quantum emitter interacts with a near-resonant coherent light, is a cornerstone of
quantum optics as a paradigmatic light-matter interaction.
Quantum phenomena in resonance fluorescence have been accounted for in terms of one- and two-
photon processes; however, the physical processes arising from the interaction of a single two-level atom with higher
photon numbers remain unexplored experimentally. Here we experimentally reveal the multiphoton scattering nature of resonance fluorescence, which intrinsically gives rise to multiphoton
entanglement. By accessing
quantum fluctuations in the field emitted from a cavity-
quantum electrodynamics system, we resolve third- and fourth-order
photon scattering events from a single two-level atom. In the three-
photon component, the scattered
photons are shown to be genuinely energy-time entangled, as verified by a violation of Svetlichny's inequality. As a demonstration of an application, a
quantum secret sharing protocol (QSS) is implemented using this entangled
photon source. Our study refines the descriptive framework of resonance fluorescence and broadens the scope of its investigation. It also establishes a fundamentally simple route for generating multiphoton entangled states for
quantum information processing and
quantum metrology.
Read the full abstract ▾
All authors Xiao-Long Zhou, Jian Wang, Ze-Min Shen, Dong-Yu Huang, Si-Jian He, Qi-Yang Huang, Yi-Jia Liu, Yu-Shu Chen, Quan Jiang, Chuan-Feng Li, Guang-Can Guo
Quantum Physics
90%-Efficient Optical Storage in a Rare-Earth Crystal with a Low-Loss Impedance-Matched Cavity
Weiye Sun, Fudong Wang, Mucheng Guo et al. (+7 more)
High-efficiency optical storage in rare-earth-ion-doped
crystals is challenging because of their typically weak optical absorption,which makes cavity-enhanced
memories highly sensitive to parasitic intracavity loss. Here we demonstrate a 90.1(5)% storage efficiency for coherent optical pulses in an impedance-matched cavity atomic-frequency-comb
memory based on Eu3+:Y2SiO5. The Brewster-angle configuration of the
crystal and fully cryogenic Fabry-Pérot cavity reduce the round-trip intracavity loss to 0.37%. Quantitative modeling shows that further improvement is limited primarily by AFC preparation and its associated dispersive response rather than by residual cavity loss,identifying the principal requirements for further approaching unity efficiency.
Read the full abstract ▾
All authors Weiye Sun, Fudong Wang, Mucheng Guo, Xiantong An, Zhenqi Xu, Zhehao Xu, Xingmin He, Matthew J.Sellars, Shuping Liu, and Manjin Zhong
Optics
Aberration sensing in fluorescence microscopy using quantum correlations
Shay Elmalem, Shaurya Aarav, Allard K. F. Hübler et al. (+2 more)
Widefield fluorescence microscopy is an essential biological imaging tool, yet its penetration depth is fundamentally restricted by tissue-induced aberrations. Correcting these requires precise characterization of the point spread function (PSF), but existing wavefront sensing techniques rely either on often-unavailable guide
stars, or on computationally heavy indirect phase
retrieval methods, that could struggle in low-contrast regions. Here, we show that the PSF can be mapped directly and non-invasively by exploiting
quantum correlations between
photons. Standard fluorophores inherently exhibit
photon antibunching, effectively acting as sources of “missing”
photon pairs. By capturing these correlation statistics across a wide field of view using a single-
photon avalanche diode (SPAD) array imager, we extract the local PSF autocorrelation directly from the fluorescence emission itself. This approach bypasses the limitations of classical intensity measurements, requiring no iterative or complex numerical optimization. We demonstrate widefield direct PSF
retrieval in a second or less, paving the way for real-time operation. By translating
quantum optical concepts to conventional fluorescent probes, this technique provides a robust, direct pathway to deep-tissue adaptive optics in life sciences.
Read the full abstract ▾
All authors Shay Elmalem, Shaurya Aarav, Allard K. F. Hübler, Hugo Defienne, Dan Oron
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