Computer Vision
Uicheol Jung, Juyoung Hong, Geuntaek Lim et al. (+1 more)
Text-
video retrieval requires representations that can distinguish
videos with similar scenes, actions, and temporal patterns. Recent
multimodal large
language models have been adapted as
embedding models, but they often represent each input using a single
token from the final layer. This can compress diverse
video-text cues into a single vector and limit fine-grained
retrieval. To address this limitation, we propose MARS, a multi-layer and multi-slot
embedding framework for text-
video retrieval. MARS constructs multiple adaptive representation slots by combining hidden states from different decoder layers, compares corresponding text and
video slots, and aggregates their similarities for
retrieval. To better handle confusing candidates, we further introduce a hard-negative-aware slot specialization objective that encourages the slots to capture discriminative matching cues. Experiments on four text-
video retrieval benchmarks show that MARS achieves state-of-the-art results in both direct similarity-based
retrieval and reranking settings. Ablation studies and analyses demonstrate that multi-layer fusion, multiple slots, and hard-negative-aware slot specialization provide complementary gains. Code is available at https://github.com/sejong-rcv/MARS.
Read the full abstract ▾
All authors Uicheol Jung, Juyoung Hong, Geuntaek Lim, Yukyung Choi
Cryptography and Security
A Finger on the Scale: Covert Policy Steering through Agentic Skills
Jiarui Li, Jiahao Chen, Chunyi Zhou et al. (+5 more)
Reusable
agent skills extend large
language model (LLM)
agents with task procedures, tool-use guidance, and output constraints. Yet these skills also act as externalized behavioral policies, which create a supply-chain risk: a third-party skill may preserve the declared task and valid output interface while covertly redirecting
agent decisions toward an undisclosed objective. We formalize Skill Policy Integrity, which requires a Skill-induced policy to remain aligned with its declared functionality and the user-authorized objective. We further present SkillShift, a constrained black-box framework for covert policy steering without explicit target command injection or task hijacking. It combines semantically plausible policy edits with hierarchical validation, failure-guided optimization, and strategy compression to preserve effectiveness, output validity, transferability, and inconspicuousness. We instantiate this threat in agentic commerce and software dependency use, with SkillShift achieving attacker-favored selection rates of 81.33% and 63.33% while maintaining a 100% utility-preserving rate. The frozen policies also transfer without further optimization across heterogeneous LLM backends and
agent environments. Moreover, the evaluated scanners fail to detect the constructed skills, motivating behavioral
auditing of reusable skills as
agent policy artifacts.
Read the full abstract ▾
All authors Jiarui Li, Jiahao Chen, Chunyi Zhou, Yuwen Pu, Oubo Ma, Zhou Feng, Chunqiang Hu, Shouling Ji
Computer Vision
Stereo 4D Radar for 3D Object Detection: Integrating Geometric Alignment and Absolute Velocity Estimation
Seung-Hyun Song, Dong-Hee Paek, Woong-Chan Byun et al. (+1 more)
Four-dimensional (4D) Radar is a powerful sensing modality capable of detecting surrounding three-dimensional (3D) objects under diverse weather conditions and providing Doppler-based motion information. However, raw 4D Radar signals contain significant clutter from road surfaces, guardrails, and surrounding vehicles, along with multipath-induced ghost reflections and the receiver's inherent noise floor. Consequently, preprocessing
algorithms designed to remove such invalid measurements often make the Radar data excessively sparse. Moreover, the Doppler measurements provided by 4D Radar describe only the radial component of an object's velocity, limiting their ability to recover the full motion state. In this paper, we introduce a stereo 4D Radar-based 3D object detection framework that exploits the
geometric disparity between left and right Radars to estimate the absolute velocity of objects and achieve more robust perception through the fusion of their complementary features. The effectiveness of the proposed framework is validated on our in-house stereo 4D Radar
dataset, demonstrating performance gains of 8.82 points in AP 3D and 9.0 points in AP BEV over state-of-the-art mono 4D Radar baselines. These results demonstrate that absolute velocity estimation combined with stereo geometry-aware feature fusion leads to substantial improvements in 3D object detection.
Read the full abstract ▾
All authors Seung-Hyun Song, Dong-Hee Paek, Woong-Chan Byun, Seung-Hyun Kong
Computer Vision
RGB-to-IR image translation for infrared vehicle detection in unseen UAV domains
Thijs A. Eker, Ella P. Fokkinga, Jan Erik van Woerden et al. (+4 more)
Synthetic training data is crucial for developing
vision AI when real-world data is scarce, as in thermal infrared (IR) aerial vehicle detection. While abundant
UAV RGB imagery motivates RGB-to-IR translation for data augmentation, unobservable thermal traits (e.g., engine heat) make learning transferable mappings challenging. This work investigates whether modern generative translators can overcome this cross-modal gap to improve infrared vehicle detection on unseen
UAV target domains. Translators are trained on paired RGB-IR source
datasets and applied to RGB training images from held-out target
datasets to generate synthetic IR data. Evaluated methods include supervised GANs, ControlNet-based
diffusion models, and foundation-model editing via LoRA. The resulting synthetic IR imagery is used to train RF-DETR vehicle detectors, which are evaluated on unseen IR target test splits across five aerial
datasets, with Kust4K and VTUAV serving as target domains. Synthetic IR consistently outperforms RGB and grayscale baselines. Stable
Diffusion 3.5 with ControlNet yields the best results, improving mAP from 50.8 to 60.1 on Kust4K and from 25.6 to 38.4 on VTUAV compared to models trained only on source-domain IR data. Increasing output diversity via multiple seeds (+1.1 mAP) and
prompt variations (+3.3 mAP) provides additional gains on VTUAV. Although a performance gap to real target IR data remains, generative RGB-to-IR translation effectively mitigates IR data scarcity and improves cross-domain aerial vehicle detection.
Read the full abstract ▾
All authors Thijs A. Eker, Ella P. Fokkinga, Jan Erik van Woerden, Elfi I.S. Hofmeijer, Sebastiaan P. Snel, Klamer Schutte, Friso G. Heslinga
Cryptography and Security
The Shape of Ownership: Verifying LLM Provenance through Semantic Structures
Zhongrui Sun, Jiahao Chen, Oubo Ma et al. (+4 more)
As large
language models (LLMs) are increasingly redistributed, adapted, and served behind opaque APIs, model ownership can no longer be established reliably by inspecting model internals or deployment records. This creates a need for behavioral signatures that remain observable through black-box interaction. Yet most existing black-box fingerprints instantiate ownership signals through fixed query-key associations, reducing model identity to sparse memorized associations detached from ordinary behavior and limiting both robustness and stealth (e.g., fine-tuning or quantization) and stealthiness. A stronger fingerprint should instead be distributed, naturally elicited, and expressed at a higher semantic level. To this end, we introduce PROSE (Provenance through Relational Organization of Semantic Expression), replacing fixed query sets with a target semantical domain and brittle response keys with semantic structures internalized as domain-conditioned response behavior. Specifically, the fingerprint is encoded in how the model semantically organizes its in-domain conclusions, rather than in particular
tokens or prescribed outputs. PROSE constructs a private bank of domain-specific semantic templates, internalizes them through mixed fine-tuning on structurally verified and clean responses, and verifies ownership by detecting the designated structures in responses to held-out natural queries. Extensive experiments across multiple model architectures, scales, and target domains show that PROSE achieves a 100% fingerprint detection rate on unmodified models with no observed false positives, preserves model utility, and retains strong detectability under downstream modifications and output transformations.
Read the full abstract ▾
All authors Zhongrui Sun, Jiahao Chen, Oubo Ma, Yuwen Pu, Zhou Feng, Haibo Hu, Shouling Ji
Machine Learning
ProbeMatchDTI: Probe-Driven Multi-Scale Biochemical Pattern Matching for Drug-Target Interaction Prediction
Quan Hao, Mengyue Fan, Zifan Dong et al. (+8 more)
Drug-target interaction (DTI) prediction is an important task in AI-driven drug discovery. Although recent biochemical representation learning methods have improved DTI prediction, their passive feature aggregation tends to favor dominant molecular patterns while suppressing weak yet binding-relevant signals, such as functional groups and residue-context patterns, limiting the modeling of multi-scale biochemical correspondences. To address this issue, we propose ProbeMatchDTI, a pattern-probe-driven framework comprising IterProbe and BindingProbe. IterProbe explicitly retains contextual states across refinement depths and uses learnable probes to select them at each position before cross-entity matching, thereby preserving weak biochemical patterns and strengthening associations among functional groups, local motifs, and molecular scaffolds. BindingProbe then characterizes cross-entity drug-
protein complementarity at local biochemical-unit and whole-pair levels, jointly modeling fine-grained interactions and multi-scale correspondences while preserving weaker binding-relevant associations. Extensive experiments demonstrate the superiority of ProbeMatchDTI, achieving 2.0% and 0.5% higher AUC-ROC on BindingDB and DrugBank, respectively. Feature-level pattern analyses further characterize its probe-driven behavior in cross-scale biochemical pattern matching. We further connect ProbeMatchDTI predictions with an evidence-guided downstream drug-discovery workflow, demonstrating their utility for candidate refinement and validation planning. Our code is available at https://github.com/developer-hq/ProbeMatchDTI
Read the full abstract ▾
All authors Quan Hao, Mengyue Fan, Zifan Dong, Youru Li, Jianduo Zhao, Lechuan Xu, Hao Zhang, Fei Xia, Jigang Wang, Chong Qiu, Liguo Zhang
Machine Learning
Learn from Whoever Is Right: Answer-Verified Multi-Teacher Distillation for Multi-Domain LLMs
Xixiang He, Xingming Li, Baiqi Wu et al. (+4 more)
Modern large
language models (LLMs) rely on reinforcement learning to build strong capabilities in individual domains, but integrating those capabilities into a single deployable model remains challenging. By routing each sample to the teacher whose domain matches it, existing approaches let a domain label decide which teacher provides supervision. However, domain expertise holds only on average: the matched teacher is not always correct on a given sample, while a teacher from another domain sometimes is. The reliable teacher therefore has to be identified per sample, not per domain. In this paper, we introduce Multi-Teacher Self-
Distillation Policy Optimization (MT-SDPO), an on-policy
distillation method that unifies several frozen teachers into one student model. MT-SDPO consists of three components: (1) self-anchors, where a rollout is supervised by a correct rollout from its own group; (2) answer-verified eligibility, where a teacher may supervise a sample only if its own answer passes a verifier; and (3) privileged
distillation, which merges the anchor and all verified feedback into one context that an exponential moving average self-teacher reads and the student does not, thereby keeping one policy at deployment. Across five students from three model families, MT-SDPO lifts the weakest domain of Qwen3-8B by 14.79 points and narrows its domain gap by 74.7%, a better balance than serving one matched teacher per domain. Verified reliability, not domain membership, should decide who teaches. Code is available at https://github.com/hexixiang/MT-SDPO.
Read the full abstract ▾
All authors Xixiang He, Xingming Li, Baiqi Wu, Qiyao Sun, Xuanyu Ji, Ao Cheng, Qingyong Hu
Robotics
ZETA: A Controlled Study of Zero-Shot Cross-Embodiment VLA Transfer for Tabletop Manipulation
Mi Yan, Wenhao Zhang, Zhiqi Zhang et al. (+14 more)
Zero-shot generalization to unseen embodiments is important for generalizable
vision-
language-action (VLA) models as
robot hardware evolves and task-specific data collection remains costly. However, a systematic understanding of this problem remains limited, in part because the literature lacks a unified zero-shot transfer definition and controlled evaluation settings that isolate embodiment changes from differences in tasks, scenes, or protocols. To address this gap, we first distinguish strict zero-shot transfer, where the target embodiment is absent from all training data, from pretrain-exposed zero-shot transfer, where it appears only during pretraining. We then introduce a controlled
benchmark spanning 14 held-out target embodiments across simulation and real-world validation. Within this framework, we conduct a controlled analysis of four factors: state-action representations, pretraining embodiment diversity, auxiliary co-training objectives, and target-embodiment exposure. Experimental results show that local end-effector (EEF) state-action representations, the source embodiment diversity, and auxiliary co-training improve cross-embodiment transfer by around 15, 18, and 7 percentage points, respectively. We further find that adding only 5% target-embodiment data during pretraining improves average target-embodiment progress by 13.4 percentage points, showing that strict and pretrain-exposed zero-shot transfer are distinct and should be reported separately. Together, these findings provide practical guidance for evaluating and improving cross-embodiment VLA transfer in stationary tabletop manipulation with two-finger grippers, while motivating future investigation of broader settings including mobile-base control, dexterous hands, and long-horizon tasks.
Read the full abstract ▾
All authors Mi Yan, Wenhao Zhang, Zhiqi Zhang, Yu Peng, Tangxinyu Wang, Lingfei Zhai, Jiayi Su, Shengliang Deng, Lin Peng, Yaowei Liu, Yuxing Chen, Zhiyuan Wei, Jilong Wang, Jiayi Chen, Jiangran Lyu, Zhizheng Zhang, He Wang
Graphics
LightBridge: Feed-Forward Generative Relighting for 3D Gaussian Splatting
Hezhi Cao, Panhao Cheng, huangsheng du et al. (+3 more)
3D Gaussian Splatting (3DGS) achieves high-quality, real-time novel view synthesis, but the resulting assets have baked-in illumination and cannot be easily relit. Inverse rendering methods optimize simplified reflectance and illumination models for each scene, limiting efficiency and relighting quality. Recent generative approaches leverage large
diffusion models for realistic lighting edits, but applying them to 3DGS typically requires an additional per-scene optimization stage to bake the edited appearance into the representation. We present LightBridge, a feed-forward generative framework for controllable relighting of complete 3DGS assets in a single pass. To enable feed-forward training, we construct a large-scale Multi-Illumination Relighting
Dataset with paired source and target observations of the same scenes. Latent Bridge Relighting
Diffusion models relighting as source-to-target transport in latent space, enabling one-step extraction of 2D visual
tokens without iterative
diffusion sampling. A Gaussian Propagation
Transformer uses a point
transformer with sparse image-to-point self-
attention followed by point-to-image cross-
attention to efficiently propagate these cues across the complete 3DGS, while avoiding full
attention over all image and Gaussian
tokens. Experiments validate these designs, demonstrating competitive relighting quality and efficient single-pass prediction of complete relit 3DGS assets without scene-specific optimization. The code and
dataset will be made publicly available upon acceptance.
Read the full abstract ▾
All authors Hezhi Cao, Panhao Cheng, huangsheng du, Qibiao Li, Youcheng Cai, Ligang Liu
Robotics
World-Model-Augmented Visual Locomotion for Humanoids on Foothold-Constrained Terrain
Yuxi Liu, Lijun Han, Ziming Wang et al. (+3 more)
Foothold-constrained terrain limits feasible footholds to sparse, discontinuous, or narrow support regions, as in gaps, stepping stones, stairs, and balance beams. In such settings, a single misplaced step can cause a fall. Reliable traversal therefore requires precise foot placement and anticipation of upcoming terrain. To address this challenge, we present World-Model-Augmented Visual Locomotion (WM-LOCO), which augments a visual locomotion policy with predictive context from a jointly trained world model. Given onboard depth observations and proprioception, a recurrent state-space model (RSSM) learns action-conditioned latent dynamics that predict future proprioceptive states,
egocentric observations, and task rewards. The resulting recurrent feature is then fed into the proximal policy optimization (PPO) actor-critic, providing predictive context for anticipatory foot placement on foothold-constrained terrain. WM-LOCO achieves average success rates of 96.0% on gaps, 96.9% on stepping stones, 94.0% on stairs, and 92.1% on balance beams, outperforming the evaluated baselines while improving gait efficiency and smoothness. Furthermore, WM-LOCO achieves zero-shot sim-to-real transfer to a Unitree G1, with 92.5% success across these four terrain classes.
Read the full abstract ▾
All authors Yuxi Liu, Lijun Han, Ziming Wang, Ao Zhang, Cong Yang, Wei Sui
Machine Learning
TrajMind: Chaining Role-Specialized LoRAs for Fast-and-Slow Collective Trajectory Anomaly Diagnosis
Jiahao Wu, Zhenqun Yang, Chen Jason Zhang et al. (+1 more)
Diagnosing collective anomalies from urban trajectories is increasingly important for traffic governance, as it reveals what happened, who was involved, and where and when the event occurred. Existing detectors efficiently produce scores or labels, whereas
vision–
language pipelines provide richer semantics; neither couples verifiable diagnosis with low-latency monitoring. The central challenge is to recognize collective patterns and recover exact event details from the source trajectories without running the full diagnostic pipeline for every monitored window. We therefore separate always-on screening from on-demand diagnosis: screening raises alerts, while diagnosis releases only source-verified what–who–where–when records. We present TrajMind, a fast-and-slow framework that switches three role-specialized LoRA adapters over one frozen
vision–
language backbone. Its slow path, \textit{TrajMind$_{\text{slow}}$}, chains canvas-based typing, type-conditioned localization over serialized trajectories, and executable verification, yielding structured, evidence-backed diagnoses. Additionally, the fast path, \textit{TrajMind$_{\text{fast}}$}, screens each window in a single text-only pass, delivering efficient structured alerts. Extensive experiments show that, TrajMind$_{\mathrm{slow}}$ outperforms the strongest baselines by at least $15.3$ percentage points in anomaly typing and $13.8$ percentage points in localization. These gains persist under cross-city transfer, and TrajMind$_{\mathrm{fast}}$ reduces latency by $41.1\%$ and maintains binary balanced accuracy of at least $93.5\%$. Together, TrajMind delivers accurate, evidence-backed diagnoses across cities and efficient front-line monitoring.
Read the full abstract ▾
All authors Jiahao Wu, Zhenqun Yang, Chen Jason Zhang, Qing Li
Machine Learning
A Comparative Study of Graph Representations for GNN-Based Power Grid Control in L2RPN
Adrian Degenkolb, Qiong Huang and Benjamin Schäfer
Graph construction is a critical but underexamined design choice in deep reinforcement learning for power grid control. We present a controlled experimental comparison of different graph representations, including physical
topology, electrical-sensitivity, and hybrid variants for
topology control in the Learning to Run a Power Network (L2RPN) environment. Our findings indicate that matching graph complexity to task granularity is more important than maximizing representational richness, and highlight the importance of controlled representation studies at scale.
Read the full abstract ▾
Networking
Connectivity of HAPS-Based Solutions for Large-Scale Wireless Networks: A Percolation Theory Analysis
Hao Lin, Mustafa A Kishk and Mohamed-Slim Alouini
In the era of sixth-generation (6G) wireless communication, numerous applications are expected to be realized, including environmental monitoring, smart agriculture, remote education, security protection, and intelligent transportation systems. These scenarios require large-scale, continuous Internet services in forests, rivers, oceans, and road networks, to name a few, where optical cables are difficult to deploy. High-altitude platform stations (HAPSs) emerge as a promising solution, offering low-latency, high-capacity services while facilitating the establishment of vertical heterogeneous networks (vHetNets) in fiber-less areas. This article investigates three HAPS-based solutions, where HAPSs can serve wireless devices directly or via gateway (GW) networks: the HAPS-to-device (H2D) scheme, the HAPS-to-GW-to-device (H2G2D) scheme, and the hybrid scheme. Leveraging percolation theory, we study the feasibility of large-scale continuous Internet coverage, where the key performance indicator (KPI) is the percolation probability. We discuss the subcritical and supercritical cases in different coverage schemes, and prove that the phase transition from zero to nonzero percolation probability appears when increasing the HAPS density or GW density. Numerical results verify that the curve of the critical condition of the phase transition exists between the derived lower bound and upper bound, which can help reduce the upfront cost of HAPS-based vHetNet solutions.
Read the full abstract ▾
Systems and Control
Physics-based Online Adaptive Koopman Model Predictive Attitude Control for Combined Spacecraft with Dynamic Uncertainties
Yicheng Sun, Yueyong Lyu, Yuhan Liu et al. (+2 more)
This paper proposes a physics-based adaptive Koopman Model Predictive Control (MPC) strategy for combined spacecraft attitude stabilization under inertia uncertainties and active target maneuverability. A novel, quaternion-based Koopman model is constructed from a set of analytical lifting functions derived from the quaternion kinematics, which provides a more compact and physically interpretable linear representation of the nonlinear dynamics compared with the conventional black-box EDMD and higher-dimensional DCM-based model. Leveraging the linear structure of this nominal model, a gradient descent-based update law is employed to efficiently identify time-varying inertial uncertainties from real-time input/output data. By integrating this adaptive linear model into the MPC framework, the optimal control problem reduces to a computationally efficient Quadratic Program (QP), thereby significantly lowering the online computational burden compared to nonlinear adaptive MPC. Recursive feasibility and regional input-to-state stability are formally established through the design of terminal ingredients for the MPC. The effectiveness and superiority of the proposed strategy are validated through comparative simulations of an attitude stabilization task for combined spacecraft in a high-fidelity 3D simulator.
Read the full abstract ▾
All authors Yicheng Sun, Yueyong Lyu, Yuhan Liu, Yanning Guo, Wei Pan
Cryptography and Security
SpiderSapien: Client-Centric Web Crawler and Security Scanner
Eric Olsson, Benjamin Eriksson, Adam Doupé et al. (+1 more)
Black-box web application crawling and scanning play an important role for security testing of web applications. Yet state-of-the-art scanners fall short of addressing key characteristics of a modern web application: its extreme dynamism and interactivity on the client side. This paper identifies immersive interaction as a key ingredient for scanners to deeply explore modern web applications. We propose SpiderSapien, a client-centric crawler and security scanner. SpiderSapien incorporates a unique combination of high-level, user-facing feedback channels from the web application to achieve immersive interaction in a black-box crawling loop. These feedback channels include both novel methods to detect interactable elements and sensibly order UI interactions, and orthogonally using an LLM to solve forms. In doing so, we demonstrate how to reliably discover and test deep states of modern web applications. Furthermore, our modular approach and useful abstraction layer can serve as a building block for future scanners. The evaluation of our approach shows substantial improvements in both code coverage and vulnerability detection over previous work. Our approach increased average code coverage across applications by at least 46% over any other scanner, or 16% when compared to the union of all other scanners. We find XSS vulnerabilities in 7 web applications, while any other scanner finds XSS in up to 2 applications.
Read the full abstract ▾
All authors Eric Olsson, Benjamin Eriksson, Adam Doupé, Andrei Sabelfeld
Computer Vision
Spatially Aware World Action Model via Geometric Latent Diffusion
Javier Alejandro Lopetegui Gonzalez, Paul Pacaud and Cordelia Schmid
World Action Models (WAMs) leverage the capabilities of large-scale pretrained
video diffusion models to jointly predict future observations and actions, inheriting rich visual and physical priors from internet-scale
video. This has made them a promising paradigm for
robot policy learning, yet the prevailing models operate exclusively on RGB observations and do not leverage 3D information. To bridge this gap, we introduce a Spatially Aware World Action Model (SA-WAM), which repurposes a pretrained
video model for joint action, RGB, and depth prediction, enabling 3D-aware world modeling and action prediction within a single
diffusion backbone. We use a nonlinear encoding that maps the unbounded depth signal into the bounded input domain expected by the frozen VAE tokenizer. This allows us to reuse the tokenizer without 3D-specific fine-tuning, incorporating
geometric information without sacrificing the pretrained priors. SA-WAM achieves state-of-the-art results on the RoboCasa and LIBERO-Plus
benchmarks, while simultaneously improving future-state predictions. Furthermore, SA-WAM outperforms strong baselines in real-world evaluation using a UR5 robotic arm, with strong gains in randomized environments. We analyze the correlation between world model prediction quality and rollout success, providing insights into WAM performance and avenues for its improvement.
Read the full abstract ▾
Computer Vision
Fine-Grained Anomaly Perception in Wild UGC-Enhanced Images: A Comprehensive Dataset and Difference-Fusion Framework
Yan Zhong, Gefei Chen, Qiufang Ma et al. (+4 more)
Image enhancement and restoration have become standard back-end operations on short-
video and social media platforms to boost UGC visual experience. Yet these processes inevitably introduce visual anomalies–especially in faces, texts, and textures–that directly undermine perceptual fidelity and viewer trust. While existing IQA methods perform well on classic distortions, they target holistic quality assessment and fail to capture the specific, localized anomalies caused by enhancement
algorithms in real-world UGC. To bridge this gap, we formally define a new task-quality Anomaly Perception for UGC image Enhancement (UEAP), and contribute the first UEAP
benchmark dataset, named UEAP-4k, curated from the real business scenarios. It provides fine-grained annotations for anomaly categories, localization and severity levels. Furthermore, we propose a Difference-Fusion Anomaly Perception Method (DFAP-UGC) for wild UGC-enhanced images, which leverages explicit problem-reference difference fusion with dense spatial querying, regional verification, and quality-aware ranking, enabling robust anomaly identification in challenging scenarios. To handle the inherent coupling of subtasks in this new task, we propose a Locality-Aware Dynamic Task Prioritization (LADTP) training strategy that enables effective end-to-end learning and eliminates multi-stage overhead. Extensive experiments show that our method outperforms baselines adapted from classical approaches for this task, validating the value of this
dataset and the superior of DFAP-UGC for robust UGC-enhanced image anomaly perception. Code and data will be public.
Read the full abstract ▾
All authors Yan Zhong, Gefei Chen, Qiufang Ma, Zhen Wang, Zhiwei Fan, Lei Shi, Tingting Jiang
Computer Vision
Doppio: A Dataset for Contactless Weight Estimation of Falling Particles
Simon Kiefhaber, Jan-Martin O. Steitz, Julia Grabinski et al. (+5 more)
Measuring the mass of powder, including falling particles, is a common task in industrial applications. While scales are effective for static measurements, many applications require contactless sensing, where existing solutions are often costly, application-specific, and technically complex. In this work, we investigate computer
vision as a practical alternative for contactless mass estimation. As an accessible real-world case study, we focus on coffee grinding and introduce Doppio, a novel
video dataset capturing
videos of falling ground coffee, paired with precise, per-frame ground-truth weight measurements. To demonstrate contactless measuring, we evaluate deep learning-based approaches ranging from purely spatial feed-forward networks to recurrent spatio-temporal models. These models are analyzed with respect to their predictive accuracy and computational trade-offs. We demonstrate that deep learning-based computer
vision models accurately estimate the cumulative weight of falling particles, establishing a solid foundation for future
vision-based contactless measurement solutions.
Read the full abstract ▾
All authors Simon Kiefhaber, Jan-Martin O. Steitz, Julia Grabinski, Christoph Reich, Paul Wagner, Max Zimmermann, Simone Schaub-Meyer, Stefan Roth
Computation and Language
When Persona Attributes Improve Population Alignment in Large Language Models
Leon Fröhling, Jens Rupprecht, Markus Strohmaier et al. (+1 more)
Large
Language Models (LLMs) are increasingly used to predict the responses of human participants in survey panels. Towards that goal, persona prompting has recently emerged as a technique to inform and align large pretrained
language models. Persona prompting refers to the practice of using short textual descriptions of 'personas' in
prompts to steer the LLM's generations. Personas describe individuals through different attributes such as their socio-demographics, attitudes, or behaviors, with the aim of aligning LLMs to produce responses that correlate with the corresponding human responses. Yet, recent work has produced mixed and partly conflicting results of persona prompting without clear patterns of success and failure. Among the few consistent findings is that the selection of persona attributes matters, and that using more attributes does not necessarily lead to better performance. It remains unclear how different attribute selection methods perform and how to choose among them. In this paper, we propose that observed human response variation of a survey question is a potential explanation for the mixed performance observed so far. In addition, we compare the performance of persona prompting associated with different methods for selecting persona attributes. We evaluate these methods on four different (general) social surveys across two countries, six LLMs, and twenty prediction tasks per survey. Our work helps to identify when persona prompting can be expected to be useful in survey prediction tasks, and provides new insights on the effectiveness of different attribute selection methods for LLM-based survey prediction using persona prompting.
Read the full abstract ▾
All authors Leon Fröhling, Jens Rupprecht, Markus Strohmaier, Claudia Wagner
Machine Learning
Spectral Initialization and Scheduled Graph Smoothness for Uncertain Knowledge Graph Completion
Md Abrar Jahin, Taufikur Rahman Fuad, Jay Pujara et al. (+1 more)
Uncertain knowledge graphs (UKGs) extend knowledge graphs by assigning each triple a continuous confidence score. Since most possible triples lack observed confidences, recent methods rely on semi-supervised learning to generate pseudo-labels. These methods initialize entity
embeddings without using the confidence-weighted graph, discarding its global community and hub structure. We introduce QUEST, which adds no trainable parameters to the standard confidence-distribution learning pipeline. First, QUEST initializes entity
embeddings using the smallest non-trivial eigenvectors of the confidence-weighted graph
Laplacian, incorporating community and hub structure before training. Second, QUEST applies an unbiased mini-batch Dirichlet energy regularizer to enforce early-stage structural consistency. On two UKG
datasets, QUEST improves confidence prediction and link prediction on six of eight metric-
dataset pairs over prior methods and matches the previous best on the remaining two, while removing the instability spike observed on dense graphs. These results indicate that spectral structural priors combined with a graph Dirichlet energy regularizer improve accuracy, training stability, and checkpoint reliability in UKG completion.
Read the full abstract ▾
All authors Md Abrar Jahin, Taufikur Rahman Fuad, Jay Pujara, Craig A. Knoblock
Distributed Computing
AceSpec: An Asymmetric Edge-Cloud Collaborative Framework for Communication-Efficient LLM Inference
Yida Zhang, Zhiyong Gao, Shuaibing Yue et al. (+2 more)
Deploying Large
Language Models (LLMs) on edge devices typically relies on model compression or split inference. However, compression degrades
reasoning capabilities, while split inference suffers from severe Wide Area Network (WAN) communication bottlenecks. Edge-cloud speculative decoding emerges as a promising alternative, leveraging an edge small model to draft
tokens for cloud verification. Yet, over volatile WANs, inevitable prediction rejections trigger catastrophic pipeline stalls and network-wide rollbacks, neutralizing collaborative gains. To overcome this, we propose AceSpec, an asymmetric edge-cloud collaborative framework. AceSpec utilizes un-saturated edge compute to proactively construct a probabilistic state cache, effectively transforming network-wide pipeline flushes into $\mathcal{O}(1)$ local
memory lookups. To preserve bandwidth, it employs an asymmetric communication protocol that transmits minimal main-chain indices uplink and compact sparse distributions downlink. Furthermore, we introduce a network-aware, Lagrangian-optimized resource allocation strategy that dynamically maximizes the local cache hit rate. Evaluations demonstrate that AceSpec achieves up to a 3.52$\times$ throughput speedup and exhibits exceptional bandwidth immunity, sustaining near-peak inference performance even under severely constrained 50 Kbps WAN conditions.
Read the full abstract ▾
All authors Yida Zhang, Zhiyong Gao, Shuaibing Yue, Jie Li, Rui Wang
Computer Vision
Beauty is in the AI of the beholder: MLLMs systematically overrate facial attractiveness
Santiago Grandas, Juan Sebastian Cely-Acosta, Mohit Mendiratta et al. (+2 more)
Beauty assessments from
Multimodal Large
Language Models (MLLMs) are increasingly popular amongst users, companies, and aestheticians. This raises the question of whether these AI models can accurately reflect human judgments of attractiveness. In a pre- registered exploratory study, we compared the attractiveness ratings of 2,513 human participants to four widely used commercial AI models: Claude, Gemini, GPT, and Grok. Results showed that MLLMs systematically rate faces more favourably and within a narrower range than humans and, at the time of study, do not reproduce human ratings in absolute terms. However, MLLMs exhibit strong correlations with human attractiveness judgments, accurately tracking the rank-ordering of faces. MLLMs may judge faces by different cues than humans; only face age was a predictor of facial attractiveness in both humans and MLLMs, with inconsistent patterns across models for ethnicity and gender. AI models strongly agree with one another, except for Grok, which also showed the lowest agreement with humans. Our findings suggest that while they may be able to approximate rank-orderings of human attractiveness, current off-the-shelf commercial MLLMs systematically overrate the beauty of human faces.
Read the full abstract ▾
All authors Santiago Grandas, Juan Sebastian Cely-Acosta, Mohit Mendiratta, Shafee Hassan, Macken Murphy
Graphics
Telligram: Text-Driven Calligram Generation via Diffusion-Guided Skeleton Optimization
Tianci Shi and Pengfei Xu
Compact calligram generation aims to form a semantic shape while keeping letters recognizable. Most existing methods are shape-conditioned and mainly solve downstream letter layout inside a given contour. We study text-only calligram generation without an input contour. This setting is difficult because semantic shape formation and letter readability strongly interfere with each other when optimized in a single stage. Pushing the word toward a clear figure can easily damage glyph structure, while preserving readable letters can weaken the target shape. To address this difficulty, we present Telligram, a training-free, low-tuning, two-stage framework composed of Semantic Occupancy Prior Formation and Readability-Constrained Glyph Realization. The first stage uses Variational Score
Distillation (VSD) with structured skeleton optimization and hierarchical gradient projection to produce a semantic occupancy prior. The second stage converts this occupancy prior into per-letter regions and reconstructs readable glyph layouts through lightweight
geometric processing. The framework generates coherent and creative word-level semantic calligrams directly from text
prompts.
Read the full abstract ▾
Computer Vision
Orthogonal Ensembles and Tested Explanations for Performer-Independent Body-Motion Emotion Recognition
Naoto Nishida and Yoshio Ishiguro
We study body-only, 12-class acted-
emotion classification from skeleton motion under leave-performer-out (LPO) evaluation, a hard, underdetermined setting: chance is 8.3%, and a protocol-matched reproduced STGCN++ baseline reaches only 25.73 +/- 4.03% Macro-F1. We show that reliable gains come not from a new architecture but from combining eleven models with orthogonal error modes: under 10-fold LPO cross-validation on the labeled training performers, an equal-weight logit-mean ensemble reaches 36.80 +/- 4.00% per-fold Macro-F1, a protocol-matched +11.07 pp (+43% relative) over the same-split reproduced baseline. Our central contribution is a tested explanation suite: for a strong ensemble member, part-masking and counterfactual edits show (rather than assert) that its decisions depend on motion-grounded body-region evidence, and this region saliency aligns with rule-based Laban Movement Analysis (LMA) attributes far more than with classical kinematics: region-level saliency-LMA Spearman rho = +0.500 versus +0.033, roughly 15x, and the
alignment holds for the submitted 11-way ensemble itself at rho = +0.517; the audit is post hoc and needs no retraining. The same suite faithfully reports a negative: within-window temporal saliency is diffuse rather than localized. On the hidden challenge test set the submitted ensemble scored 37.23 % Macro-F1 and received the Best Performance Award of the MMAC Challenge 2026 (Human score is 39 %). Code is available at https://github.com/nawta/diema-challenge and the presentation at https://nawta.github.io/mmac2026/.
Read the full abstract ▾
Machine Learning
Rethinking the Teacher-Student Framework for Test-Time Adaptation
Damian Sójka, Marc Masana, Bartłomiej Twardowski et al. (+1 more)
Test-Time Adaptation (TTA) has recently emerged as a promising strategy that allows the adaptation of pre-trained models to changing data distributions at deployment time, without access to any labels. To mitigate error accumulation, researchers have widely adopted the teacher-student framework, though its long-term stability is often taken for granted. In this work, we challenge the common strategy of setting the teacher weights to an exponential moving average of the student by showing that error accumulation still occurs, although it is mostly apparent on longer sequences compared to those commonly utilized. We analyze the stability-plasticity trade-off within the teacher-student framework and propose to use an intransigent teacher that does not update its weights. Surprisingly, we show that this simple change allows TTA methods to significantly improve their performance on multiple
datasets with longer scenarios and result in increased robustness to changes in hyperparameters. Finally, we show that those changes can be seamlessly and effectively applied to various architectures and experimental setups, including semantic
segmentation. The code is available at https://github.com/dmn-sjk/intransigent_teacher.
Read the full abstract ▾
All authors Damian Sójka, Marc Masana, Bartłomiej Twardowski, Sebastian Cygert
Computer Vision
SR-Edit: Region-Aware Image Editing via Self-Refinement
Andong Wang, Zehua Chen, Yuxuan Jiang et al. (+1 more)
With the recent rapid progress in generative models, image editing has made remarkable advances, yet achieving faithful edits that precisely modify only the target regions while strictly preserving all other regions remains challenging. Since externally provided region annotations are often difficult to obtain in practice, a growing body of work seeks to improve preservation by automatically inferring edit and non-edit regions, and then enforcing consistency on the latter. However, these approaches still suffer from inaccurate region estimation and heuristic correction strategies that distort the native inference process, making methods designed for fidelity themselves a new source of artifacts. We propose SR-Edit, an image editing framework that overcomes these issues via iterative self-refinement. Specifically, at each iteration, SR-Edit first (i) extracts progressively precise and self-consistent region separation from the model's own predictions by lightweight post-processing, and then (ii) enforces preservation in non-edit areas through correction updates that remain aligned with the original sampling dynamics. Extensive experiments demonstrate that SR-Edit achieves superior preservation and overall image quality compared to existing editing techniques.
Read the full abstract ▾
All authors Andong Wang, Zehua Chen, Yuxuan Jiang, Jun Zhu
Computer Vision
Blending Concepts: Benchmarking Visual Metaphor Generation in Text-to-Image Models
Chuer Chen, Zichen Wang, Yi He et al. (+2 more)
Text-to-image (T2I) models have achieved remarkable success at faithfully rendering specified objects and attributes, yet their ability to produce visual metaphors, images that convey abstract ideas by combining elements from two distinct domains, remains largely unexamined. To bridge this gap, we introduce VMetaphor-Bench, the first
benchmark for evaluating visual metaphor generation in T2I models. It comprises 1,500 visual metaphors curated from real-world creative imagery, organized into three levels and ten categories, with each sample paired with two
prompts of differing specificity. For evaluation, we develop a hybrid framework within an MLLM-as-judge paradigm, combining a multiple-choice question (MCQ) based protocol of 9,594 questions across four levels of metaphorical fidelity with a dimension-based scoring protocol along three perceptual dimensions. Extensive evaluation of 11 representative T2I models reveals that even the strongest proprietary models struggle with compositional structuring and cross-domain mapping, key aspects of metaphorical expression, highlighting visual metaphor generation as an important frontier for future T2I research.
Read the full abstract ▾
All authors Chuer Chen, Zichen Wang, Yi He, Zhengxi Yu, Nan Cao
Information Retrieval
Training seeds and model-selection stability in recommender-system evaluation
Juan Manuel Rodriguez, Oleg Lesota and Antonela Tommasel
Recommender-system experiments often rely on a single random training seed, assuming that run-to-run stochasticity has limited impact on evaluation conclusions. This assumption is risky, as a training seed may influence several
algorithm-dependent mechanisms, including parameter initialization, mini-batch ordering, dropout, masking, latent sampling, and training-time negative sampling. We examine this assumption by fixing the data partition and varying the training seed across hyperparameter configurations. We analyze seed effects at three levels: user-level metric sensitivity, validation-based model selection and recommendation-list agreement. Results show that seed variation is often detectable. Its impact depends on whether configurations are clearly separated, whether validation results transfer to test, and whether similar scores lead to similar top-$k$ lists. Findings suggest that reporting single-seed results can overstate the stability of recommender system evaluation, and that training seeds should be treated as part of the evaluation protocol rather than as incidental implementation noise.
Read the full abstract ▾
Data Structures and Algorithms
The Price of Almost Navigability
Tomer Waizer and Yoav Danieli
Navigability is a fundamental property of graph-based search structures and plays an important role in the analysis of nearest-neighbor
algorithms. Informally, a graph is navigable if, from any current point and toward any desired target, there is always an outgoing edge that moves strictly closer to that target. While this property provides a strong guarantee for greedy search, it can be inherently expensive: in the worst case, navigable graphs require $\Omega(n^{3/2})$ edges, where $n$ is the size of the
dataset. Recently, Avi and Musco introduced $(1-\epsilon)$-almost navigability, a natural relaxation in which, from every current point, such a progress-making edge is required for almost all targets, while an $\epsilon$ fraction of targets may fail this condition \cite{avimusco2026almost}. They showed that every
dataset admits such a graph with $O(n/\epsilon)$ edges. In this work, we prove a matching lower bound, establishing the optimality of their construction and giving a complete characterization of the sparsity achievable by almost-navigable graphs. For most values of $\epsilon$, our hard instances lie in Euclidean spaces of polylogarithmic dimension, across the full worst-case range of $\epsilon $, dimension $d=O(\sqrt{n}\log^{3/2} n)$ suffices. The same construction also sharpens our understanding of ordinary navigability: in the latter dimension, we exhibit
datasets for which every navigable graph has $\Omega(n^{3/2})$ edges. Our proof reveals a surprising connection between almost navigability and the classical Zarankiewicz problem of constructing dense graphs with limited pairwise neighborhood overlap. This connection lets us translate extremal graph constructions into hard
geometric instances for
navigation, linking two seemingly different notions of graph sparsity.
Read the full abstract ▾
Machine Learning
RINSE: Robust Target-Time Normality Estimation for Zero-Shot Graph Anomaly Detection
Taufikur Rahman Fuad, Md Abrar Jahin and Amir Hussain
Zero-shot graph anomaly detection seeks to deploy a detector trained on source graphs to unseen, unlabeled targets, yet domain shift can make source-derived notions of normality unreliable. We introduce RINSE (Robust Iterative Normality Self-Estimation), a gradient-free target-time framework that keeps the source-trained detector fixed while sequentially estimating target normality, representation calibration, and evidence reliability from the target graph. Its core idea is to identify a reliable subset of low-residual target nodes, use them to construct a trimmed target-aware normality model, and combine complementary anomaly evidence through reliability-gated rank fusion and encoder ensembling. Across eight unseen target graphs, RINSE achieves the highest average AUPRC among the evaluated methods under two separate preprocessing protocols, while block ablations and sensitivity analyses support the combined design. These results support robust target-time estimation as a practical approach to generalist graph anomaly detection without target labels, gradients, or per-target tuning.
Read the full abstract ▾