Artificial Intelligence
Knowing When Not to Reuse: Conditional Experience Transfer in Autonomous LLM Post-Training
Tingyun Li, Wenfeng Feng, Weiqing Li et al. (+3 more)
Large
language models offer broad capabilities, but adapting them to evolving domains, tools, and requirements often entails repeated post-training. Autonomous systems automate parts of this process by proposing updates, training candidates, and using evaluation feedback to select subsequent proposals. As evidence accumulates, a central problem emerges: which past update evidence remains actionable after subsequent training has changed the parent model? An update's effect depends on its parent, data, and training stage. Treating past success as context-free permission can waste compute. If the resulting child is promoted, it can also degrade the subsequent training trajectory. We formulate this problem as conditional experience transfer and introduce Boundary-Calibrated Intervention Transfer (BCIT), a method that authorizes experience reuse before weight-changing training. BCIT binds an observed effect to its source context, checks applicability conditions, vetoes candidates with named hard conflicts, and obtains current-state evidence through a bounded training trial when needed. Fully trained candidates still face a shared adoption rule, and only observed events extend
memory. On one 4B model adapted across finance
reasoning, text-to-SQL, and function calling, candidate updates exhibit heterogeneous target and retention effects across the evaluated contexts. Under matched candidates, evidence, and compute, BCIT authorizes fewer harmful updates and attains higher equal-budget final-model quality than the evaluated alternatives. These results support treating experience authorization as a distinct problem in autonomous post-training.
Read the full abstract ▾
All authors Tingyun Li, Wenfeng Feng, Weiqing Li, Abudukelimu Wuerkaixi, Guohua Liu, Yuewei Zhang
Machine Learning
Neural Regression with Embeddings for Numerical Attribute Prediction in Knowledge Graphs
Rupesh Sapkota, Louis Mozart Kamdem Teyou, Moshood Yekini et al. (+2 more)
In recent years, transductive knowledge graph
embedding models have been applied to tasks such as link prediction and query answering. Although knowledge graphs often contain rich numerical attributes, most
embedding models neglect them, limiting their ability to represent real-world knowledge graphs with diverse information. In this work, we propose a neural regression model (LitEm) that enables transductive knowledge graph
embedding models to predict numerical attributes within knowledge graphs. Experimental results demonstrate that LitEm achieves the best or second-best results on most attributes across FB15K-237, YAGO15K, DB15K, and Mutagenesis. Furthermore, we propose a co-training framework that jointly trains state-of-the-art transductive knowledge graph
embedding models with LitEm, which improves link prediction performance mainly for bilinear models and simultaneously enables them to predict numerical attributes. In addition, the literal-awareness evaluation demonstrates that co-training helps models to encode and exploit attribute information in a "literal-aware” manner, suggesting that the observed gains are not merely due to additional parameters. We publicly release our implementation at https://github.com/dice-group/dice-
embeddings.
Read the full abstract ▾
All authors Rupesh Sapkota, Louis Mozart Kamdem Teyou, Moshood Yekini, Caglar Demir, Axel-Cyrille Ngonga Ngomo
Information Retrieval
Beyond a Single Story: Meta-Reviewing Sparse and Incomplete User-generated Contents for Recommendation
Hongren Wang, Tianjun Wei, Yingpeng Du et al. (+2 more)
Data sparsity remains a long-standing challenge in recommender systems, and it becomes more severe for methods relying on user-generated content (UGC) such as textual reviews, which capture fine-grained preferences but require more user efforts to produce. As a result, UGC exhibits (1) missing reviews, where interactions lack any review, and (2) incomplete reviews, where available reviews cover only a subset of relevant attributes. Existing approaches often overlook these UGC-specific issues, leading to degraded accuracy. Motivated by meta-review in academic peer review, we propose MOSAIC (Meta-review On Sparse And Incomplete user-generated Content), which constructs a meta-review for each target user by aggregating attribute-sentiment evidence from neighbor users' reviews. A multi-gate mixture-of-experts (MMoE) architecture jointly optimizes rating prediction and meta-review attribute-sentiment prediction, while an
attention module personalizes the aggregated meta-review signals to each target user, yielding both refined rating predictions and attribute-level explanations. Experiments on four real-world
datasets demonstrate that MOSAIC consistently outperforms state-of-the-art baselines in both recommendation accuracy and explanation quality, mitigating UGC sparsity and incompleteness while delivering consistent gains for users with limited interaction history.
Read the full abstract ▾
All authors Hongren Wang, Tianjun Wei, Yingpeng Du, Jie Zhang, Yin-Leng Theng
Computer Vision
GeoMAD: Geometry-Aware Multi-View Anomaly Detection via Deformable Fusion and Distributional Alignment
Shang-Fu Chen, Jhih-Ciang Wu, Kuan-Chuan Peng et al. (+2 more)
Multi-view anomaly detection (MvAD) detects defects by exploiting complementary observations from multiple camera viewpoints. The central challenge is to fuse views with sufficient
geometric awareness while remaining scalable to multi-class industrial settings. Existing methods typically fall into two extremes: voxel-based fusion provides explicit
geometric alignment but requires costly 3D construction and class-specific assumptions, whereas lightweight patch-based fusion is efficient but relies on discrete candidate matching and lacks continuous cross-view correspondence. In this paper, we propose GeoMAD, a unified multi-view, multi-class AD framework that addresses both
geometric correspondence deficiency and distributional inconsistency. Our Cross-view Deformable Fusion Module (CDFM) learns content-adaptive, view-pair-specific sampling offsets directly on 2D feature maps and arranges them across a multi-scale window pyramid with image-global reference sampling, enabling hierarchical cross-view correspondence without camera calibration, voxel construction, or class-specific 3D supervision. We further introduce Distributional View
Alignment (DVA), a self-supervised cross-view regularization loss that aligns each view's bottleneck distribution against a per-instance view-centric target, enforcing global consistency without pixel-level correspondence. Together, CDFM and DVA bridge local
geometric correspondence and global distributional consistency, providing geometry-aware and distribution-consistent fusion while preserving the efficiency of 2D feature-space learning. Extensive experiments on Real-IAD and MANTA-Tiny show that GeoMAD achieves strong detection and localization performance in unified MvAD.
Read the full abstract ▾
All authors Shang-Fu Chen, Jhih-Ciang Wu, Kuan-Chuan Peng, Wen-Huang Cheng, Kai-Lung Hua
Computer Vision
UniGeo: A Multi-modal Large Language Model for Text-Guided Cross-View Geo-Localization
Jiahao Wen, Hang Yu and Zhedong Zheng
Text-guided drone geo-localization aims to identify a target region in a large-scale image gallery from a natural-
language description. Existing methods mainly formulate this task as direct matching between an open-ended text query and candidate images. However, incomplete queries and highly similar candidates often make global cross-modal matching insufficient for reliable fine-grained localization. We propose UniGeo, a unified
multimodal large
language model (MLLM) for text-guided drone geo-localization. Built on a shared
vision-
language framework, UniGeo jointly supports geo-semantic understanding, cross-view semantic generation, and candidate-level verification. Specifically, it establishes stable correspondences among local scene elements, spatial relations, and
language descriptions through geo-semantic learning, and further models semantic mappings between drone and satellite views through cross-view generation. Based on these capabilities, a plug-and-play verification module performs fine-grained discrimination among highly confusable candidates. We further introduce a multi-stage training strategy that progressively learns geo-semantic understanding, cross-view generation, and candidate verification, improving adaptation to text-guided geo-localization. Experiments demonstrate consistent improvements across multiple
retrieval backbones. On GeoText-1652, UniGeo improves R@10 and mAP by 13.59 and 2.83 percentage points, respectively, validating its effectiveness for fine-grained text-guided drone geo-localization.
Read the full abstract ▾
Computer Vision
Parameter Efficient Continual Learning for Sparse Event-Based Transformers
Vaishnavi Nagabhushana, Kartikay Agrawal and Ayon Borthakur
Robotic and edge intelligence systems operate in dynamic environments where data arrives continuously, requiring models to adapt while preserving previously learned knowledge under strict
memory and energy constraints. While parameter-efficient fine-tuning has shown promise for continual learning with
vision transformers, conventional architectures rely on dense computation and remain costly for real-world deployment. Sparse event-based
vision transformers provide energy-efficient event-driven computation, yet their continual learning capabilities remain largely unexplored. We here introduce sLoTh, a parameter-efficient continual learning framework for pretrained sparse event-based (spiking)
vision transformers. sLoTh freezes the backbone and restricts plasticity to scalable-efficient low-rank
attention updates (seLoRA) and shared neuronal threshold modulation, enabling adaptation without replay buffers by updating less than 1% of model parameters. Experiments across CIFAR-100, Tiny-ImageNet, ImageNet-100, and ImageNet-R with up to 100 tasks demonstrate competitive rehearsal-free performance in class-incremental learning and online continual learning, while enabling approximately 6.5x lower energy consumption than conventional dense
vision transformers.
Read the full abstract ▾
Computer Vision
Beyond Atomic Layouts: Compositional Design Understanding with Vision-Language Models
Yiyang Huang, Zhaowen Wang, Simon Jenni et al. (+4 more)
Layout understanding, or the interpretation of element organization, is essential for document analysis, user interface (UI) creation, and graphic design. While recent
vision-
language models (VLMs) excel at interpreting atomic layouts composed of independent elements, they struggle with compositional layouts that require
reasoning over visually entangled elements within hierarchical multi-layer structures. In this paper, we introduce a new task, compositional layout understanding, and present CoDeLayout, a VQA
dataset of ~20K real-world multi-layer layouts annotated with compositional element pairs and design intent. Through empirical analysis on CoDeLayout, we identify two key challenges for existing VLMs: semantic drift between textual metadata and visual content, and structural ambiguity in hierarchical inter-element relationships. To address these challenges, we propose MASON, a post-training paradigm that integrates
multimodal alignment (MA) and structural perception (SP). MA enhances element interpretation by grounding metadata-defined elements to their visual counterparts, mitigating semantic drift, while SP models layer-aware inter-element spatial relationships to improve hierarchical understanding and reduce structural ambiguity. Experiments reveal substantial gaps in existing VLMs: even the strongest baseline, GPT-o3, achieves only 79.68% accuracy, whereas Qwen2.5-VL 7B with MASON reaches 91.66%. Notably, MASON surpasses full-data Direct Finetune using only 30% of the training data and scales better with additional data.
Read the full abstract ▾
All authors Yiyang Huang, Zhaowen Wang, Simon Jenni, Jing Shi, Yitian Zhang, Yizhou Wang, Yun Fu
Human-Computer Interaction
RegulAR: Graph-Grounded Error Recognition and Assistance for Procedural Tasks in AR
Yi-Lin Ye, Jindu Wang, Hiu Tung Wong et al. (+3 more)
Errors are inevitable in procedural tasks, yet most AR guidance systems focus on step-by-step instruction delivery rather than helping users recognize and recover from mistakes. We present RegulAR, an AR task assistant for procedural error recognition and recovery. RegulAR models task instructions as a hierarchical dependency graph and combines this structure with a
Multimodal Large
Language Model (MLLM) to interpret
egocentric observations during execution. This enables RegulAR to track progress, identify deviations by error type, estimate their impact on later steps, and deliver appropriately salient interventions through an in-situ head-up display that visualizes task state and recovery guidance. By making procedural structure explicit, RegulAR supports not only next-step guidance, but also
reasoning about what went wrong, why it matters, and how users can get back on track. In a within-subject study (N=12), participants reported better task-structure understanding and recovery support with RegulAR than the MLLM-only baseline.
Read the full abstract ▾
All authors Yi-Lin Ye, Jindu Wang, Hiu Tung Wong, Shuchang Xu, Huamin Qu, Wong Kam-Kwai
Computer Vision
LiveVVT: High-Fidelity Video Virtual Try-On in Real Time
Yushe Cao, Shikun Feng, Ruxiang Duan et al. (+4 more)
Diffusion-based
Video Virtual Try-On (VVT) achieves high visual fidelity through bidirectional spatio-temporal modeling, but complete-clip dependence incurs prohibitive latency and computational overhead in practical continuous deployment. Naively enforcing causality disrupts pretrained bidirectional priors and substantially degrades synthesis quality. We introduce LiveVVT, a rolling streaming
diffusion framework that preserves bounded bidirectional modeling within causal recurrent generation. Within a fixed-size window, LiveVVT jointly denoises multiple
video chunks under bounded look-ahead, preserving local bidirectional interactions while emitting one clean chunk per iteration. Beyond the window, two complementary
memories sustain long-term consistency: a bounded temporal
memory propagates recent dynamics and occlusion context, whereas a persistent global appearance
memory, constructed once from the target garment and a frontal try-on keyframe, anchors garment details and dressed appearance throughout the stream. We further introduce a progressive
distillation framework integrating bidirectional VVT learning, teacher-trajectory regression for causal few-step adaptation, and Collaborative Matching
Distillation, which couples teacher-distribution matching with rolling flow matching on real
videos to align optimization with recurrent inference. Experiments on paired and unpaired long-sequence
benchmarks demonstrate superior generation quality over similarly sized models, with $26\times$ lower latency and $11\times$ higher throughput, enabling high-fidelity real-time streaming VVT.
Read the full abstract ▾
All authors Yushe Cao, Shikun Feng, Ruxiang Duan, Liyong Wang, Dianxi Shi, Chun Yu, Junliang Xing
Computer Vision
AesCanvas: A Large-Scale Dataset and Benchmark for Aesthetic Critique and Contextual Suitability
Xuanwei Hu, Haoyu Dong, Kejun Wu et al. (+2 more)
Recent advances in
Multimodal Large
Language Models (MLLMs) have extended Image Aesthetic Assessment (IAA) beyond scalar scores toward interpretable critique and guidance. Yet existing
benchmarks mainly assess intrinsic visual quality or fixed domain criteria, leaving open whether an appealing image is appropriate for a specific purpose, audience, cultural setting, or domain convention. We introduce AesCanvas, a unified suite with two complementary components: CritiqueCanvas with 519,136 instruction-response pairs from 54,300 images supports long-form, multi-dimensional critique across photography, painting, and virtual imagery, whereas ContextCanvas with 301 expert-reviewed use scenarios evaluates contextual aesthetic suitability in realistic use scenarios. Under a unified protocol, we evaluate closed-source frontier, open-weight general, and aesthetic-specific MLLMs. Results reveal a clear separation between critique generation and context-sensitive judgment: reference-based lexical and semantic metrics only partially capture critique quality, while aesthetic specialists remain competitive on selected critique metrics yet substantially lag strong general-purpose MLLMs on ContextCanvas. Further analyses show that aesthetic specialization does not reliably transfer to contextual suitability and that model decisions may fail to track or ground themselves in decisive contextual visual cues. These findings establish culturally situated, evidence-grounded suitability as a distinct objective for aesthetic modeling.
Read the full abstract ▾
All authors Xuanwei Hu, Haoyu Dong, Kejun Wu, Tianyi Liu, Jianjun Gao
Artificial Intelligence
Style as a Confound: False Positives in AI Detection of Non-Native Academic Writing
Hyeonchu Park, Gahye Jeong and Bugeun Kim
AI text detectors are increasingly employed in academic settings, but it remains unclear whether their outputs reflect AI authorship itself or broader linguistic features associated with polished academic English. Previous studies have reported high false-positive rates (FPRs) for non-native English writing, but population-level comparisons confound authorship with differences in topic, domain, and writing style. Professional editing provides a useful setting for examining this issue because it changes the linguistic form of manuscripts while preserving authorship and content. We examined 135,389 document pairs from a professional English editing service (2018-2025), comprising non-native manuscripts and their native-edited versions, to assess how editing affects detector responses controlling for content and authorship. For the 13 AI text detectors, FPRs for human-written texts varied widely, from 0.0% to 100.0%. Responses varied across detectors: the same edits increased AI scores in some detectors but decreased them in others. Notably, score changes correlated with the extent of editing. The findings identify professional editing style as a key confounding variable in AI detector outputs, rather than establishing a full separation of text origin from linguistic style, raising concerns about
fairness and reliability in academic settings.
Read the full abstract ▾
Computation and Language
Towards Expert Financial QA via Self-Improving RAG
Junjie Xiong, Shawheen Ghezavat and Aum Hirpara
Expert-level financial question answering requires both grounded verification to catch numeric
hallucinations and audit trails for regulatory compliance, attributes that standard single-pass RAG systems lack. We take a step toward this goal with Self-Improving RAG, a framework that decomposes document QA into three specialized
agents (
Retrieval,
Reasoning, and Judge) coordinated by an orchestrator with feedback-driven self-correction. When the Judge
Agent scores an answer below a dynamic threshold, the system triggers retry with escalated strategies: broader
retrieval, more careful prompting, and relaxed acceptance criteria. We evaluate on FinanceBench (SEC filing QA), where Self-Improving RAG achieves 86% oracle-guided accuracy (measuring agreement with gold answers) with a 36.4% Lazarus Rate, recovering nearly 4 in 10 initially incorrect answers through targeted retry. A key finding is that a fixed
retrieval pipeline with judge-driven retry achieves strong results without dynamic routing, providing full interpretability. Every decision is logged with confidence scores, enabling the audit trails required for regulated financial applications.
Read the full abstract ▾
Artificial Intelligence
Accelerating Scientific Research with Gemini in the Real-World
Samuel Schmidgall, Xiaokai Zhu, Marian Shaw et al. (+32 more)
We present an extension and comprehensive real-world validation of Co-Scientist, a Gemini-based multi-
agent system designed to accelerate end-to-end scientific research across hypothesis generation, experimentation, and manuscript generation. Moving beyond in silico hypothesis generation, this specialized configuration transitions Co-Scientist into an execution-grounded research partner advancing closed-loop scientific workflows across materials science, biology, and computer science. In materials science, Co-Scientist interfaced with a semi-automated chemical vapor deposition reactor to design a safe precursor route for MXenes; experimental execution produced a lamellar 2D material sharing key structural similarities with the Ti3C2Tx MXene
lattice, although further experiments are needed to confirm the atomic structure. Leveraging Gemini 3 Deep Think for rapid, lab-in-the-loop execution, it also tailored growth recipes to laboratory constraints in minutes, enabling single-attempt growth of monolayer MoS2, MoSe2, and WS2
semiconductors. In biology, Co-Scientist predicted emergent swarming phenotypes of engineered E. coli across inducer (IPTG) gradients from sparse imaging data, quantitatively matching unpublished wet-lab morphological measurements. In computer science, Co-Scientist autonomously discovered an inference-time scaling architecture that outperformed six frontier models on HealthBench (Hard and Professional) while reducing potential clinical harm under blinded physician evaluation. Finally, a double-blind study of end-to-end generated papers with 30 domain experts across 450 reviews demonstrates that Co-Scientist's reliability modules reduce
hallucination and plagiarism while improving research safety. Together, these results demonstrate progress toward closed-loop multi-
agent scientific AI systems capable of accelerating real-world scientific discovery.
Read the full abstract ▾
All authors Samuel Schmidgall, Xiaokai Zhu, Marian Shaw, Lin Yang, Valentin Liévin, Jingyun Yang, Yuchen Zhuang, Tim Strother, Alex Bijamov, Min Woo Sun, Anil Palepu, Justin Chen, David Steiner, Jacqueline Shreibati, Wei-Hung Weng, Yilin Zhao, Xingjian Hu, Nicholas Zahn, Sadhya Garg, Julia Kirby, Yuxiang Gan, Jiaoli Li, Divy Thakkar, Shekoofeh Azizi, David Racz, Juraj Gottweis, Vivek Natarajan, Chenglin Wu, Tal Danino, Keran Rong, Haozhe Wang, Benoit Schillings, Yong Cheng, Quoc V. Le, Tao Tu
Computation and Language
PragAlign: Evidence-Sensitive Reply Assistance Across Chinese and Japanese Appropriateness Judgments
Xin Zhong and Satori Hachisuka
Reply assistance in
multilingual settings requires linguistic competence and culturally situated judgments of appropriateness. We present PragAlign, which separates context reading from selective clarification, and evaluate it alongside Direct and Rule. Nine native Chinese speakers judged Chinese materials, while three native Japanese speakers judged matched Japanese versions. In the Chinese evaluation, PragAlign received significantly better ranks than both baselines. In the Japanese evaluation, Direct had the lowest mean rank, PragAlign had the highest top-rank rate, and the omnibus difference was not significant. The groups selected the same top condition in 5 of 10 scenarios, including four shared PragAlign selections. The results identify shared and
language-specific judgment patterns and inform reply assistance designed to support linguistic and cultural understanding.
Read the full abstract ▾
Cryptography and Security
KubeCap: A Framework for Capability Minimization in Kubernetes via Static Analysis and LLM-Assisted Rule Inference
Yuhao Liu, Yingnan Zhou, Weijie Liu et al. (+2 more)
As the most widely used container orchestration platform, Kubernetes provides flexible privilege configuration by allowing developers to manage Linux capabilities via manifest files. However, developers rely on default settings or coarse-grained security contexts in practice, violating the principle of least privilege and enlarging the attack surface of containerized workloads. Existing studies either detect vulnerable patterns in Kubernetes manifests or infer required capabilities for standalone Linux programs, but they do not directly address capability minimization in Kubernetes. To bridge this gap, we first conduct an empirical study on three open-source
datasets, revealing that 74.67% of projects lack capability configurations. Motivated by our observations, we propose KubeCap, a framework for Kubernetes capability minimization. KubeCap translates deployment specifications into deterministic manifests, locates container entrypoints, performs reachability-guided system call analysis, and leverages LLM-assisted rule specification to derive syscall–parameter–capability relations from Linux kernel code. Based on these results, KubeCap infers the minimal capability set required by each workload and automatically generates repaired manifests. Evaluation on 10 representative Go-based Kubernetes projects shows an average capability reduction rate of 54.97%, outperforming rapid type analysis and class hierarchy analysis baselines while maintaining practical analysis cost. These results demonstrate KubeCap's effectiveness in enforcing least privilege in Kubernetes.
Read the full abstract ▾
All authors Yuhao Liu, Yingnan Zhou, Weijie Liu, Yan Jia, Zheli Liu
Computation and Language
Phoneme-guided TTS augmentation for ASR: A unified pipeline and multilingual evaluation
Zhen Wang, TianRui Wu, RongQi Han et al. (+3 more)
Synthetic
speech can provide additional supervision for automatic
speech recognition (ASR), but constructing useful synthetic training data requires choosing both what to synthesize and how to synthesize it. We present a phoneme-guided text-to-
speech (TTS) augmentation pipeline for ASR that connects
multilingual speech generation with candidate-text selection and reference-
speech quality control. Within this pipeline, we propose phoneme-frequency-guided selection (PFGS), which uses phoneme frequencies from real ASR training transcripts to prioritize candidate texts containing common phonetic content. Experiments with separate monolingual ASR systems cover four
languages and 13 test sets. With random text selection, the pipeline improves recognition on 11 test sets at one or more synthesis ratios. PFGS further outperforms random selection on nine test sets, with relative word error rate (WER) reductions of up to 19.3%. An ablation with fixed target texts and synthesis counts further shows the benefit of reference-
speech filtering. These results support using real-data phoneme statistics to guide the construction of effective synthetic supervision for ASR.
Read the full abstract ▾
All authors Zhen Wang, TianRui Wu, RongQi Han, Hao Wu, Wei Liang, Wei Xu
Artificial Intelligence
Five Primitives for Governing Autonomous AI Agents at Runtime
Jiten Oswal and John Cadeddu
Enterprise deployments of autonomous AI
agents inherit a control model built for human users and long-lived services, and the fit fails in three specific ways:
agent principals are ephemeral, appearing and vanishing faster than provisioning; their actions are selected by a model rather than programmed, so the set of things they may attempt is not known in advance; and the population is discovered rather than provisioned, because anyone who can call an API can create one. We argue that governing such
agents is a runtime problem – not a model-
alignment problem and not a build-time problem – and we derive five primitives from the questions that must be answered before an action takes effect and after it has: discovery, identity, governance, attestation, and supply chain. For each we state what fails if it is absent and why the others cannot structurally supply it. We describe an implementation in which an
agent's action is mediated against policy before it takes effect, authorised against a per-tenant action vocabulary, and recorded in a hash-linked signed ledger a third party can verify with the vendor out of the loop. We report what the architecture costs: the enforcement point sits on the request's critical path, identity requires a sidecar per workload, and fail-closed mediation converts availability incidents into denial. We are explicit about implementation status: four primitives are built and running in private pilots, and the fifth is built as separate tooling and not yet integrated into the request path. We keep it in the set deliberately: a five-part decomposition that exactly matches what its authors happened to build is not a taxonomy but a description of a codebase.
Read the full abstract ▾
Artificial Intelligence
Relational Over-Regularization: Graph-Based AI-Generated Text Detection via Sentence Transition Deviation
Hyeonchu Park and Bugeun Kim
Detecting AI-generated text (AIGT) remains challenging because existing approaches rely on
token-level statistical signals or independent stylometric features, causing them to overfit to specific generators and fail under distribution shift. We identify a structural signal at the sentence-pair level: LLMs produce inter-sentence transition variance that deviates from human writing through inflated variance driven by recurring similarity bursts at paragraph boundaries and templated transitions. We formalize this as Relational Over-Regularization (ROR) and validate it across four
benchmarks (p < 0.001). The central contribution is this relational problem formulation, not a novel GNN architecture; CSFG is one concrete instantiation for operationalizing ROR. To exploit this signal, we propose the Cross-Source Stylometric Fingerprint Graph (CSFG), a graph-based framework that encodes positional, sequential, semantic, and transition deviation signals as learnable GNN edge features. The per-edge signed deviation {\delta}_ij operationalizes ROR without hand-crafted thresholds and acts as a false-positive calibrator. CSFG achieves 97.14% accuracy under binary detection, outperforming the strongest graph-based baseline by 11.14 pp, with a false-positive rate of 1.57% and robust generalization to unseen LLMs in the inflated-variance regime; detection degrades for generators whose transition variance falls at or below the human baseline.
Read the full abstract ▾
Computation and Language
Beyond Reflection: Affirmation as a Promising Behavioral Marker Associated with Quality in Text-Based Counseling
Michimasa Inaba
While AI-assisted text-based counseling is gaining
attention, it remains empirically unclear which counselor behaviors are associated with higher dialogue quality. Existing research often focuses heavily on Reflection, borrowing frameworks from Motivational Interviewing. To address this gap, we conduct a multi-layered analysis using KokoroChat, a large-scale Japanese text counseling
dataset conducted by professional counselors and trainees, newly annotated with counselor strategy tags and client distress levels. Our results show that, under the quality indicators used in this study, Affirmation is more consistently associated with session quality than Reflection among the analyzed strategies. Cross-
dataset transfer experiments further suggest that this quality signal can be observed to some extent on ESConv, an English
dataset with non-expert supporters. These findings provide empirical implications for counselor training and emotional support system design. We release the additional KokoroChat annotations and experimental source code at https://github.com/UEC-InabaLab/BeyondReflection.
Read the full abstract ▾
Numerical Analysis
A linear mass-lumped finite element method for the Landau-Lifshitz-Gilbert equation: unconditional energy dissipation and length preservation
Qiumei Huang, Binghong Li, Xiaoli Li et al. (+2 more)
We develop a linear, unconditionally energy-dissipative, mass-lumped finite element method for the highly nonlinear Landau–Lifshitz–Gilbert (LLG) equation on quasi-uniform triangular meshes. The method is built on a projection strategy for enforcing the nonconvex pointwise constraint $|\mathbf{m}| = 1$, whose simultaneous preservation with unconditional energy stability remains challenging for standard finite element discretizations. The key innovation is a unified hybrid finite element-finite difference framework that underlies both the design and the analysis of the proposed method. In the scheme construction, we exploit the weak formulation and nodal structure of mass-lumped finite element method, while incorporating suitable interpolation operators and a node-wise length-preserving mechanism inspired by finite difference discretizations. This combination yields a linear scheme that preserves the node-wise unit-length constraint and satisfies a discrete energy dissipation law. The same hybrid framework also plays a central role in the error analysis, where the weak formulation and quasi-uniform mesh structure of finite elements are combined with interpolation-based and nodewise finite difference method to control the strongly nonlinear damping term and to establish an optimal-order error estimate. More importantly, the proposed method provides a unified framework that systematically integrates the
geometric flexibility of finite element method with the pointwise constraint-preserving property of finite difference method, and thus offers a general strategy for designing and analyzing structure-preserving discretizations of constrained dissipative systems. Numerical experiments, including a classical blow-up simulation, confirm the predicted accuracy, energy dissipation, and robustness of the method.
Read the full abstract ▾
All authors Qiumei Huang, Binghong Li, Xiaoli Li, Cheng Wang, Jiang Yang
Computer Vision
Domain-Specific Self-Supervised Representation Learning for Retinal Fundus Classification
Bekzat Nurlanbekova and Fung Fung Ting
Annotated medical images remain scarce and costly to obtain, which motivates self-supervised learning (SSL). We present a controlled empirical study of two SSL frameworks, SimSiam and SimCLR, for retinal fundus classification, asking whether retina-specific augmentations (Graham's local-mean subtraction and CLAHE) improve representations beyond standard augmentation and grayscale conversion. ResNet-18 backbones are pretrained on 48K unlabeled fundus images and evaluated by linear probing and fine-tuning on EDID (multi-disease) and RetinaMNIST (DR grading). On EDID, grayscale conversion accounts for most of SimSiam's linear-probe gain, and Graham or CLAHE add little on top of it. After fine-tuning, SimSiam with Graham+Gray exceeds an ImageNet-supervised baseline on RetinaMNIST (+3.0 accuracy points) but only matches it on EDID. Retina-specific augmentation therefore helps inconsistently and should be validated per SSL method and task.
Read the full abstract ▾
Information Retrieval
BLANC: Discovering Patent White Space via Changes in Normalized Pointwise Mutual Information Between Multi-View Clusters
Shuichi Miyazawa and Kensuke Fujii
Identifying white space — the unexplored but potentially valuable regions of a patent landscape — is essential for strategic R&D planning, yet existing methods rely on manual patent mapping or apply single-view clustering without quantitative gap detection. We propose BLANC (Blank Landscape Analysis through NPMI Conditioning), a three-phase pipeline combining (1) multi-view neural topic modeling along three semantic dimensions (application/use, novelty, inventive step); (2) Normalized Pointwise Mutual Information (NPMI) to quantify cross-dimensional cluster association; and (3) conditional detection that flags combinations whose NPMI drops when the corpus is filtered by a user-specified keyword. The drop is captured by a new metric, $\Delta$NPMI, which identifies combinations "established globally, unexplored locally." Because white space has no ground truth, we evaluate BLANC on two public USPTO corpora — machine learning/AI (5,417 patents, CPC G06N) and glass compositions (1,982 patents, CPC C03C) — by artificially depleting known technology combinations and testing recovery. When three-quarters of a target pair's documents are removed, BLANC recovers 34.1% (ML/AI) and 27.3% (glass) of the depleted combinations, whereas size-matched removals not aimed at them (random documents, or those of a different established combination) essentially never do: the target is never recovered in 191 decoy trials. Collapsing the three semantic views into one recovers nothing, while prior co-occurrence measures also flag the target under random removal, offering no specificity. In a proprietary case (302 float glass / glass-ceramics patents), the keyword "fluorine" reveals a fluorine surface treatment $\times$ warpage suppression candidate ($\Delta$NPMI up to 0.48) that experts had independently identified.
Read the full abstract ▾
Computer Vision
Reason in the Words You Speak: Idiolectal Paraphrasing Off-Policy Traces for Reasoning Distillation in VideoLLMs
Ji Soo Lee, Jinyoung Park, Seohyun Lee et al. (+4 more)
Recent large
language models achieve strong performance on complex
reasoning tasks, where reinforcement learning with Group Relative Policy Optimization (GRPO) has emerged as a leading paradigm for optimizing models on self-generated trajectories. However, the on-policy nature of GRPO bounds the model to the
reasoning skills it can already produce, restricting to learn more advanced capabilities. Prior works inject privileged
reasoning traces from a stronger teacher policy to guide training, yet these traces are inherently out of distribution with respect to the student policy. We observe that this mismatch between on-policy and off-policy causes gradient clipping on semantically critical
reasoning tokens, ultimately rewarding correct answers while leaving the
reasoning that justifies them unlearned. Hence, we propose Echo-GRPO, a framework that lets the model reason in the words it speaks. Rather than imitating low-probability privileged traces from the teacher model, Echo-GRPO rewrites them into the student policy's own idiolect, that is, its own characteristic vocabulary and expression patterns, while preserving their semantics via Dual-Reference Decoding. We instantiate this framework as VideoEcho-R1 for
video reasoning distillation, achieving consistent improvements across three
multimodal LLM backbones and five
benchmarks. Finally, we show that our idiolectal paraphrasing is a plug-in module that consistently improves both RL and supervised fine-tuning frameworks for
reasoning distillation, demonstrating that policy-aligned supervision extends beyond GRPO.
Read the full abstract ▾
All authors Ji Soo Lee, Jinyoung Park, Seohyun Lee, Jongha Kim, Joonmyung Choi, Jinsung Yoon, Hyunwoo J. Kim
Artificial Intelligence
SIGMA: Structured Noise-Effect-Aware Grouped Multi-Agent Aggregation
Li Mingqian
Cooperative multi-
agent reinforcement learning (MARL) faces significant challenges in maintaining robust coordination under noisy observations. Although observation disturbances are often introduced independently across
agents, their downstream effects on cooperative decision-making can become structured through underlying cooperation structures. We characterize this phenomenon as structured noise effects, where noise-induced decision effects exhibit local correlation among
agents with stronger task-related dependencies while remaining globally heterogeneous across different
agents and local structures. Existing robust MARL methods, however, rarely explicitly characterize or exploit such structure-dependent noise effects. To address this limitation, we propose SIGMA, a hierarchical collaboration framework that exploits cooperation structures to learn robust representations under noisy observations. SIGMA first organizes
agents into adaptive local structures through density-based grouping and performs intra-group consensus aggregation to preserve shared task-relevant information while smoothing
agent-specific representation deviations. Inter-group
attention then adaptively integrates information across different groups to preserve global coordination while accommodating their heterogeneous contributions. Experiments on noisy-observation tasks in StarCraft II empirically validate the structured noise effects and demonstrate that SIGMA consistently improves robustness under observation noise while maintaining competitive performance in noise-free environments.
Read the full abstract ▾
Computation and Language
FOCUS & RePAIR: Mitigating Text Degeneration via Token-Level Guidance for Pruned Large Language Models
Junyoung Lee, Sehyeon Park, Shinhyoung Jang et al. (+5 more)
Pruning is a practical approach to compress large
language models (LLMs), but it can amplify text degeneration, especially repetition loops, even when perplexity and task accuracy remain largely unchanged. In this work, we present a
token-level analysis of this failure mode by viewing decoding as a dynamical process that enters and persists in a small set of recurrent contexts. Our analysis decomposes degeneration into loop entry risk and loop persistence, and shows that persistence is controlled by the escape mass assigned to plausible alternatives within the
token sampling set. Motivated by these findings, we propose two
token-level guidance objectives for post-
pruning fine-tuning. FOCUS reweights
distillation toward high-confidence teacher regions to suppress leakage, while RePAIR uses onset-centered positive/negative continuation pairs with a margin loss to promote plausible alternatives and prevent early commitment to repetition loops. Experiments on open-ended continuation and instruction-based generation show that both methods consistently reduce repetition and improve generation quality.
Read the full abstract ▾
All authors Junyoung Lee, Sehyeon Park, Shinhyoung Jang, Seonha Ryu, Hojeong Kim, Hyunsei Lee, Il Hong Suh, Yeseong Kim
Computers and Society
How Does Science Education Research Respond to Sociopolitical Change? A BERTopic Analysis of Korean Research
Jibeom Seo, Junghyo Jo, Sonya N. Martin et al. (+1 more)
Research fields do not evolve in isolation: their questions and priorities shift with policy, curriculum reform, and broader social change. Analyzing published literature can reveal not only how a field matures but also how it responds to these conditions. Prior work in science education has focused on identifying research topics and their trends, but paid less
attention to the external conditions in which research is produced. We examine Korean science education research from 2008 to 2025, a case in which centralized curriculum revision, government education initiatives, and demographic decline are prominent. Using BERTopic, an
embedding-based topic modeling technique, we identify major topics and temporal trends, and analyze their associations with selected sociopolitical factors. We interpret each topic and distinguish three groups: sociopolitical, subject-specific, and student-related topics. Within the first group, science teacher professionalism and curriculum implementation, science education for gifted students, and STEAM education show the strongest associations with sociopolitical conditions, such as government policy initiatives and declining enrollment in science-gifted education, whereas digital-based science education does not. The subject-specific and student-related groups, by contrast, show no comparable movement and are not linked to the external indicators we examine; this pattern is interpreted as reflecting stronger disciplinary grounding. Taken together, these patterns suggest that a topic's anchoring to policy and practice or to academic disciplines shapes how closely it tracks external change. This helps explain why some research agendas move with their national context while others hold steady, and why the same topic may develop differently across countries.
Read the full abstract ▾
All authors Jibeom Seo, Junghyo Jo, Sonya N. Martin, Taejin Byun
Computation and Language
Do LLMs Understand Personality? Rethinking Persona Fidelity Evaluation through Structured Behavioral Inference
Mengfan Li, Zesheng Wei, Xuanhua Shi et al. (+1 more)
As large
language models are increasingly deployed to simulate diverse human characters, ensuring persona fidelity, defined as the extent to which an
agent's behavior consistently reflects the psychological and stylistic characteristics of a target persona, has become a critical requirement. However, existing evaluation paradigms primarily rely on either holistic LLM-based judges, which are prone to "holistic appraisal
hallucination”, or static psychometric inventories, which fail to capture the context-dependent fidelity required in dynamic dialogue. To address these limitations, we propose PRISM (Persona
Reasoning with Inverse SFL-based Modeling), a psycholinguistically grounded framework that reformulates persona fidelity evaluation as a structured inverse inference task. Inspired by Systemic Functional Linguistics (SFL), PRISM decomposes persona fidelity into three functional dimensions: Task Framing, Interpersonal Stance, and Linguistic Style. It estimates dimension-specific evidence over a persona-conditioned label space and aggregates these signals into an interpretable and auditable evaluation process. Experiments show that PRISM yields more accurate and stable judgements than traditional holistic judging, providing a more reliable framework for persona fidelity evaluation.
Read the full abstract ▾
All authors Mengfan Li, Zesheng Wei, Xuanhua Shi, Yang Deng
Robotics
PredVLA: Predictive Sensorimotor Modeling for Sub-Million-Parameter Robot Manipulation
Hiroki Sawada and Shunichi Kasahara
Large pretrained
vision-
language-action models achieve strong
robot-manipulation performance, while compact alternatives have largely pursued efficiency by compressing the prevailing observation-to-action paradigm. We investigate whether predictive sensorimotor modeling can make more effective use of a limited parameter budget than direct observation-to-action mapping. We present PredVLA, a
language-conditioned predictive-coding policy with only 0.68 million trainable network parameters and no
robot-data pretraining. Its hierarchical recurrent dynamics predict visual features and proprioception, while observations influence latent state only through prediction-error-driven online inference. On LIBERO, PredVLA achieves an 86.9% mean success rate across the three short-horizon suites and 75.4% across all four suites. Under a controlled comparison using the same frozen front end, demonstrations, action decoder, and evaluation protocol, PredVLA achieves 3.7x and 7.4x the three-suite mean success rates of parameter-matched
Transformer and LSTM behavior-cloning policies, respectively. A mechanism-by-mechanism transition to the recurrent behavior-cloning baseline shows that replacing the predictive pathway with direct observation input produces the largest single performance drop, accounting for approximately $70\%$ of the endpoint gap. Further ablations identify distinct contributions from training-time latent inference, test-time error regression, hierarchical timescales, and sensory prediction-error channels. Together, these results support predictive sensorimotor modeling as a strong inductive bias for compact
language-conditioned
robot control.
Read the full abstract ▾
Computer Vision
RECAP-Forcing: Retaining Content Appearances for Long Video Generation
Haiyang Xu, Zheng Ding and Zhuowen Tu
Long autoregressive
video generation faces a fundamental
memory challenge: with a finite
attention window, a model must decide which information from an ever-expanding history to retain. Existing methods organize
memory temporally, preserving recent frames while compressing or discarding older ones. We instead propose RECAP-Forcing, organizing
memory by appearance novelty. A long
video is not merely a sequence of frames, but an evolving cast of subjects, objects, and scenes whose identities must remain consistent over time. We organize
memory by retaining the KV cache associated with newly appearing content–such as entering subjects, disoccluded regions, and newly introduced scenes–at the moment it first becomes visible, prioritizing novelty over recency.
Memory should scale with the amount of newly introduced content, rather than with
video length. This appearance-indexed
memory makes long-range consistency an explicit property of the
memory structure. Our framework unifies two mechanisms under this single principle. At the beginning of a
video, when all visible content is novel, an
attention sink preserves the initial scene. As the
video evolves, an optical-flow-based novelty bank extends the same principle by selectively retaining newly revealed content. As a training-free inference method with no additional learnable parameters, RECAP-Forcing consistently improves visual quality and semantic fidelity across multiple strong baselines and outperforms existing
memory methods.
Read the full abstract ▾
Robotics
Beyond the Proving Ground: Independent Public-Road Testing of Assisted Lane Change Systems using LiDAR
Marcello Cellina, Akos Kriston, Antonio Migneco et al. (+7 more)
Testing of commercial Advanced Driver Assistance Systems is essential to ensure safety and compliance during type approval and in service operation. However, proving ground scenarios may not reflect real world driving complexity, while geo fencing can require manufacturer collaboration and limit assessment independence. This work presents a methodology for independently testing Assisted Lane Change systems on public roads. A campaign on the A31 French motorway used a test vehicle equipped with a
LiDAR based vehicle detection and tracking system. Tests covered combinations of inter vehicle distance and speed between the test vehicle and the take over vehicle. Real time kinematic global
navigation satellite system receivers assessed detection and tracking performance. Recorded lane change trajectories were compared with the lane change suppression requirements of UNECE Regulation Number 79. Of 27 predefined lane change manoeuvres, 18 were completed and 9 suppressed. In 6 cases, the system allowed manoeuvres that did not meet regulatory minimum distance requirements. In 3 cases, the deviation remained statistically significant after accounting for measurement uncertainty. To the authors knowledge, this is the first public road campaign designed to assess Assisted Lane Change compliance with Regulation Number 79 safety distance requirements. The results demonstrate the suitability of
LiDAR based sensing for this purpose. The methodology can support
market surveillance and future regulatory revisions by revealing real world behaviours not covered by approval procedures.
Read the full abstract ▾
All authors Marcello Cellina, Akos Kriston, Antonio Migneco, Davide Maggi, Stefano Favelli, Fabrizio Re, Fabrizio Minarini, Andrea Nuovo, Riccardo Dona, Biagio Ciuffo