# Research Papers — 2025-11 · bundle page 152 of 197

> Full-text markdown of papers #7551–7600 of 9830 published in 2025-11, newest first. AI-readable mirrors of the full 9830-paper 2025-11 archive (50 papers per file).

Canonical page: https://aipod.dev/papers/archive/2025-11/page/152
[← Previous bundle](https://aipod.dev/papers/archive/2025-11/page/151.md)
[Next bundle →](https://aipod.dev/papers/archive/2025-11/page/153.md)

### Explainable AI For Early Detection Of Sepsis

Authors: Atharva Thakur, Shruti Dhumal
Published: 2025-11-09
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2511.06492v1

Sepsis is a life-threatening condition that requires rapid detection and treatment to prevent progression to severe sepsis, septic shock, or multi-organ failure. Despite advances in medical technology, it remains a major challenge for clinicians. While recent machine learning models have shown promise in predicting sepsis onset, their black-box nature limits interpretability and clinical trust. In this study, we present an interpretable AI approach for sepsis analysis that integrates machine learning with clinical knowledge. Our method not only delivers accurate predictions of sepsis onset but also enables clinicians to understand, validate, and align model outputs with established medical expertise.

---

### Zooming into Comics: Region-Aware RL Improves Fine-Grained Comic Understanding in Vision-Language Models

Authors: Yule Chen, Yufan Ren, Sabine Süsstrunk
Published: 2025-11-09
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2511.06490v1

Complex visual narratives, such as comics, present a significant challenge to Vision-Language Models (VLMs). Despite excelling on natural images, VLMs often struggle with stylized line art, onomatopoeia, and densely packed multi-panel layouts. To address this gap, we introduce AI4VA-FG, the first fine-grained and comprehensive benchmark for VLM-based comic understanding. It spans tasks from foundational recognition and detection to high-level character reasoning and narrative construction, supported by dense annotations for characters, poses, and depth. Beyond that, we evaluate state-of-the-art proprietary models, including GPT-4o and Gemini-2.5, and open-source models such as Qwen2.5-VL, revealing substantial performance deficits across core tasks of our benchmarks and underscoring that comic understanding remains an unsolved challenge. To enhance VLMs' capabilities in this domain, we systematically investigate post-training strategies, including supervised fine-tuning on solutions (SFT-S), supervised fine-tuning on reasoning trajectories (SFT-R), and reinforcement learning (RL). Beyond that, inspired by the emerging "Thinking with Images" paradigm, we propose Region-Aware Reinforcement Learning (RARL) for VLMs, which trains models to dynamically attend to relevant regions through zoom-in operations. We observe that when applied to the Qwen2.5-VL model, RL and RARL yield significant gains in low-level entity recognition and high-level storyline ordering, paving the way for more accurate and efficient VLM applications in the comics domain.

---

### Bridging Theory and Practice: A Stochastic Learning-Optimization Model for Resilient Automotive Supply Chains

Authors: Muhammad Shahnawaz, Adeel Safder
Published: 2025-11-09
Categories: stat.ML, cs.LG, math.OC
arXiv: https://arxiv.org/abs/2511.06479v1

Supply chain disruptions and volatile demand pose significant challenges to the UK automotive industry, which relies heavily on Just-In-Time (JIT) manufacturing. While qualitative studies highlight the potential of integrating Artificial Intelligence (AI) with traditional optimization, a formal, quantitative demonstration of this synergy is lacking. This paper introduces a novel stochastic learning-optimization framework that integrates Bayesian inference with inventory optimization for supply chain management (SCM). We model a two-echelon inventory system subject to stochastic demand and supply disruptions, comparing a traditional static optimization policy against an adaptive policy where Bayesian learning continuously updates parameter estimates to inform stochastic optimization. Our simulations over 365 periods across three operational scenarios demonstrate that the integrated approach achieves 7.4\% cost reduction in stable environments and 5.7\% improvement during supply disruptions, while revealing important limitations during sudden demand shocks due to the inherent conservatism of Bayesian updating. This work provides mathematical validation for practitioner observations and establishes a formal framework for understanding AI-driven supply chain resilience, while identifying critical boundary conditions for successful implementation.

---

### DyKAF: Dynamical Kronecker Approximation of the Fisher Information Matrix for Gradient Preconditioning

Authors: Nikolay Yudin, Ekaterina Grishina, Andrey Veprikov, Alexandr Beznosikov, Maxim Rakhuba
Published: 2025-11-09
Categories: cs.LG, math.NA, math.OC
arXiv: https://arxiv.org/abs/2511.06477v1

Recently, optimizers that explicitly treat weights as matrices, rather than flattened vectors, have demonstrated their effectiveness. This perspective naturally leads to structured approximations of the Fisher matrix as preconditioners, where the matrix view induces a Kronecker-factorized form that enables memory-efficient representation. However, constructing such approximations both efficiently and accurately remains an open challenge, since obtaining the optimal factorization is resource-intensive and practical methods therefore rely on heuristic design choices. In this work, we introduce a novel approach that leverages projector-splitting integrators to construct effective preconditioners. Our optimizer, DyKAF (Dynamical Kronecker Approximation of the Fisher Matrix), consistently improves the Fisher matrix approximation quality. Experiments on large language model pre-training and fine-tuning demonstrate that DyKAF outperforms existing optimizers across a range of evaluation metrics.

---

### NOAH: Benchmarking Narrative Prior driven Hallucination and Omission in Video Large Language Models

Authors: Kyuho Lee, Euntae Kim, Jinwoo Choi, Buru Chang
Published: 2025-11-09
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.06475v1

Video large language models (Video LLMs) have recently achieved strong performance on tasks such as captioning, summarization, and question answering. Many models and training methods explicitly encourage continuity across events to enhance narrative coherence. While this improves fluency, it also introduces an inductive bias that prioritizes storyline consistency over strict grounding in visual evidence. We identify this bias, which we call narrative prior, as a key driver of two errors: hallucinations, where non-existent events are introduced or existing ones are misinterpreted, and omissions, where factual events are suppressed because they are misaligned with surrounding context. To systematically evaluate narrative prior-induced errors, we introduce NOAH, a large-scale benchmark that constructs composite videos by inserting clips from other sources into target videos. By varying semantic similarity and insertion position, our benchmark enables controlled and scalable analysis of narrative priors. We design one captioning task with tailored metrics and three QA tasks - Existence, Temporal, and Narrative - yielding more than 60K evaluation samples. Extensive experiments yield three key findings: (i) most Video LLMs exhibit hallucinations and omissions driven by narrative priors, (ii) the patterns of these errors vary across architectures and depend on event similarity and insertion position, and (iii) reliance on narrative priors intensifies under sampling with fewer frames, amplifying errors when event continuity is weak. We establish NOAH as the first standardized evaluation of narrative prior-induced hallucination and omission in Video LLMs, providing a foundation for developing more reliable and trustworthy models. Our benchmark and code are available at https://anonymous550520.github.io/.

---

### GHOST: Solving the Traveling Salesman Problem on Graphs of Convex Sets

Authors: Jingtao Tang, Hang Ma
Published: 2025-11-09
Categories: cs.AI, cs.RO
arXiv: https://arxiv.org/abs/2511.06471v2

We study GCS-TSP, a new variant of the Traveling Salesman Problem (TSP) defined over a Graph of Convex Sets (GCS) -- a powerful representation for trajectory planning that decomposes the configuration space into convex regions connected by a sparse graph. In this setting, edge costs are not fixed but depend on the specific trajectory selected through each convex region, making classical TSP methods inapplicable. We introduce GHOST, a hierarchical framework that optimally solves the GCS-TSP by combining combinatorial tour search with convex trajectory optimization. GHOST systematically explores tours on a complete graph induced by the GCS, using a novel abstract-path-unfolding algorithm to compute admissible lower bounds that guide best-first search at both the high level (over tours) and the low level (over feasible GCS paths realizing the tour). These bounds provide strong pruning power, enabling efficient search while avoiding unnecessary convex optimization calls. We prove that GHOST guarantees optimality and present a bounded-suboptimal variant for time-critical scenarios. Experiments show that GHOST is orders-of-magnitude faster than unified mixed-integer convex programming baselines for simple cases and uniquely handles complex trajectory planning problems involving high-order continuity constraints and an incomplete GCS.

---

### Brain-Inspired Planning for Better Generalization in Reinforcement Learning

Authors: Mingde "Harry" Zhao
Published: 2025-11-09
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2511.06470v1

Existing Reinforcement Learning (RL) systems encounter significant challenges when applied to real-world scenarios, primarily due to poor generalization across environments that differ from their training conditions. This thesis explores the direction of enhancing agents' zero-shot systematic generalization abilities by granting RL agents reasoning behaviors that are found to help systematic generalization in the human brain. Inspired by human conscious planning behaviors, we first introduced a top-down attention mechanism, which allows a decision-time planning agent to dynamically focus its reasoning on the most relevant aspects of the environmental state given its instantaneous intentions, a process we call "spatial abstraction". This approach significantly improves systematic generalization outside the training tasks. Subsequently, building on spatial abstraction, we developed the Skipper framework to automatically decompose complex tasks into simpler, more manageable sub-tasks. Skipper provides robustness against distributional shifts and efficacy in long-term, compositional planning by focusing on pertinent spatial and temporal elements of the environment. Finally, we identified a common failure mode and safety risk in planning agents that rely on generative models to generate state targets during planning. It is revealed that most agents blindly trust the targets they hallucinate, resulting in delusional planning behaviors. Inspired by how the human brain rejects delusional intentions, we propose learning a feasibility evaluator to enable rejecting hallucinated infeasible targets, which led to significant performance improvements in various kinds of planning agents. Finally, we suggest directions for future research, aimed at achieving general task abstraction and fully enabling abstract planning.

---

### Error Estimate and Convergence Analysis for Data Valuation

Authors: Zhangyong Liang, Huanhuan Gao, Ji Zhang
Published: 2025-11-09
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.06463v3

Data valuation quantifies data importance, but existing methods cannot ensure validity in a single training process. The neural dynamic data valuation (NDDV) method (3) addresses this limitation. Based on NDDV, we are the first to explore error estimation and convergence analysis in data valuation. Under Lipschitz and smoothness assumptions, we derive quadratic error bounds for loss differences that scale inversely with time steps and quadratically with control variations, ensuring stability. We also prove that the expected squared gradient norm for the training loss vanishes asymptotically, and that the meta loss converges sublinearly over iterations. In particular, NDDV achieves sublinear convergence.

---

### Reconstruction and Secrecy under Approximate Distance Queries

Authors: Shay Moran, Elizaveta Nesterova
Published: 2025-11-09
Categories: cs.LG, cs.IT, math.MG
arXiv: https://arxiv.org/abs/2511.06461v1

Consider the task of locating an unknown target point using approximate distance queries: in each round, a reconstructor selects a query point and receives a noisy version of its distance to the target. This problem arises naturally in various contexts ranging from localization in GPS and sensor networks to privacy-aware data access, and spans a wide variety of metric spaces. It is relevant from the perspective of both the reconstructor (seeking accurate recovery) and the responder (aiming to limit information disclosure, e.g., for privacy or security reasons). We study this reconstruction game through a learning-theoretic lens, focusing on the rate and limits of the best possible reconstruction error. Our first result provides a tight geometric characterization of the optimal error in terms of the Chebyshev radius, a classical concept from geometry. This characterization applies to all compact metric spaces (in fact, even to all totally bounded spaces) and yields explicit formulas for natural metric spaces. Our second result addresses the asymptotic behavior of reconstruction, distinguishing between pseudo-finite spaces -- where the optimal error is attained after finitely many queries -- and spaces where the approximation curve exhibits nontrivial decay. We characterize pseudo-finiteness for convex Euclidean spaces.

---

### Uncertainty-Aware Offline Data-Driven Multi-Objective Optimization

Authors: Huanbo Lyu, Miqing Li, Shiqiao Zhou, Daniel Herring, Jelena Ninic, Zheming Zuo, Lingfeng Wang, James Andrews, Fabian Spill, Shuo Wang
Published: 2025-11-09
Categories: cs.NE
arXiv: https://arxiv.org/abs/2511.06459v2

In offline data-driven multi-objective optimization (MOO), optimization is performed using surrogate models trained only on an offline dataset. These surrogate models contain inherent errors and uncertainty. This epistemic uncertainty can lead to incorrect dominance judgments, thereby misleading the search process. Existing methods mitigate this issue by incorporating uncertainty estimates from Gaussian Process Regression (GPR) to correct dominance judgments; however, they are restricted to GPR, and their optimization strategies cannot be scaled to other uncertainty quantification methods. In addition, GPR-based surrogates suffer from high computational cost. We propose a simple yet effective dual-ranking strategy that flexibly leverages both predictive results and uncertainty estimates from different surrogate models. By performing non-dominated sorting on candidate solutions using both surrogate-based fitness values and uncertainty-aware fitness values, the proposed method prioritizes candidate solutions that are simultaneously high-quality and reliable. Through extensive experimental evaluations, including ablation, sensitivity, and comparative experiments, we demonstrate the effectiveness and robustness of the proposed dual-ranking strategy working with different surrogates. Our dual-ranking framework offers more robust solutions for data-limited, real-world applications.

---

### EchoMark: Perceptual Acoustic Environment Transfer with Watermark-Embedded Room Impulse Response

Authors: Chenpei Huang, Lingfeng Yao, Kyu In Lee, Lan Emily Zhang, Xun Chen, Miao Pan
Published: 2025-11-09
Categories: cs.SD, cs.AI, cs.LG, eess.AS
arXiv: https://arxiv.org/abs/2511.06458v2

Acoustic Environment Matching (AEM) is the task of transferring clean audio into a target acoustic environment, enabling engaging applications such as audio dubbing and auditory immersive virtual reality (VR). Recovering similar room impulse response (RIR) directly from reverberant speech offers more accessible and flexible AEM solution. However, this capability also introduces vulnerabilities of arbitrary ``relocation" if misused by malicious user, such as facilitating advanced voice spoofing attacks or undermining the authenticity of recorded evidence. To address this issue, we propose EchoMark, the first deep learning-based AEM framework that generates perceptually similar RIRs with embedded watermark. Our design tackle the challenges posed by variable RIR characteristics, such as different durations and energy decays, by operating in the latent domain. By jointly optimizing the model with a perceptual loss for RIR reconstruction and a loss for watermark detection, EchoMark achieves both high-quality environment transfer and reliable watermark recovery. Experiments on diverse datasets validate that EchoMark achieves room acoustic parameter matching performance comparable to FiNS, the state-of-the-art RIR estimator. Furthermore, a high Mean Opinion Score (MOS) of 4.22 out of 5, watermark detection accuracy exceeding 99\%, and bit error rates (BER) below 0.3\% collectively demonstrate the effectiveness of EchoMark in preserving perceptual quality while ensuring reliable watermark embedding.

---

### Inpaint360GS: Efficient Object-Aware 3D Inpainting via Gaussian Splatting for 360° Scenes

Authors: Shaoxiang Wang, Shihong Zhang, Christen Millerdurai, Rüdiger Westermann, Didier Stricker, Alain Pagani
Published: 2025-11-09
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.06457v1

Despite recent advances in single-object front-facing inpainting using NeRF and 3D Gaussian Splatting (3DGS), inpainting in complex 360° scenes remains largely underexplored. This is primarily due to three key challenges: (i) identifying target objects in the 3D field of 360° environments, (ii) dealing with severe occlusions in multi-object scenes, which makes it hard to define regions to inpaint, and (iii) maintaining consistent and high-quality appearance across views effectively. To tackle these challenges, we propose Inpaint360GS, a flexible 360° editing framework based on 3DGS that supports multi-object removal and high-fidelity inpainting in 3D space. By distilling 2D segmentation into 3D and leveraging virtual camera views for contextual guidance, our method enables accurate object-level editing and consistent scene completion. We further introduce a new dataset tailored for 360° inpainting, addressing the lack of ground truth object-free scenes. Experiments demonstrate that Inpaint360GS outperforms existing baselines and achieves state-of-the-art performance. Project page: https://dfki-av.github.io/inpaint360gs/

---

### EIDSeg: A Pixel-Level Semantic Segmentation Dataset for Post-Earthquake Damage Assessment from Social Media Images

Authors: Huili Huang, Chengeng Liu, Danrong Zhang, Shail Patel, Anastasiya Masalava, Sagar Sadak, Parisa Babolhavaeji, WeiHong Low, Max Mahdi Roozbahani, J. David Frost
Published: 2025-11-09
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.06456v2

Rapid post-earthquake damage assessment is crucial for rescue and resource planning. Still, existing remote sensing methods depend on costly aerial images, expert labeling, and produce only binary damage maps for early-stage evaluation. Although ground-level images from social networks provide a valuable source to fill this gap, a large pixel-level annotated dataset for this task is still unavailable. We introduce EIDSeg, the first large-scale semantic segmentation dataset specifically for post-earthquake social media imagery. The dataset comprises 3,266 images from nine major earthquakes (2008-2023), annotated across five classes of infrastructure damage: Undamaged Building, Damaged Building, Destroyed Building, Undamaged Road, and Damaged Road. We propose a practical three-phase cross-disciplinary annotation protocol with labeling guidelines that enables consistent segmentation by non-expert annotators, achieving over 70% inter-annotator agreement. We benchmark several state-of-the-art segmentation models, identifying Encoder-only Mask Transformer (EoMT) as the top-performing method with a Mean Intersection over Union (mIoU) of 80.8%. By unlocking social networks' rich ground-level perspective, our work paves the way for a faster, finer-grained damage assessment in the post-earthquake scenario.

---

### A Multi-Agent System for Semantic Mapping of Relational Data to Knowledge Graphs

Authors: Milena Trajanoska, Riste Stojanov, Dimitar Trajanov
Published: 2025-11-09
Categories: cs.DB, cs.AI
arXiv: https://arxiv.org/abs/2511.06455v1

Enterprises often maintain multiple databases for storing critical business data in siloed systems, resulting in inefficiencies and challenges with data interoperability. A key to overcoming these challenges lies in integrating disparate data sources, enabling businesses to unlock the full potential of their data. Our work presents a novel approach for integrating multiple databases using knowledge graphs, focusing on the application of large language models as semantic agents for mapping and connecting structured data across systems by leveraging existing vocabularies. The proposed methodology introduces a semantic layer above tables in relational databases, utilizing a system comprising multiple LLM agents that map tables and columns to Schema.org terms. Our approach achieves a mapping accuracy of over 90% in multiple domains.

---

### Feature weighting for data analysis via evolutionary simulation

Authors: Aris Daniilidis, Alberto Domínguez Corella, Philipp Wissgott
Published: 2025-11-09
Categories: math.OC, cs.LG
arXiv: https://arxiv.org/abs/2511.06454v3

We analyze an algorithm for assigning weights prior to scalarization in discrete multi-objective problems arising from data analysis. The algorithm evolves weights (interpreted as the relevance of features) by a replicator-type dynamic on the standard simplex, with update indices computed from a normalized data matrix. We prove that the resulting sequence converges globally to a unique interior equilibrium, yielding non-degenerate limiting weights.

---

### MULTIBENCH++: A Unified and Comprehensive Multimodal Fusion Benchmarking Across Specialized Domains

Authors: Leyan Xue, Changqing Zhang, Kecheng Xue, Xiaohong Liu, Guangyu Wang, Zongbo Han
Published: 2025-11-09
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.06452v3

Although multimodal fusion has made significant progress, its advancement is severely hindered by the lack of adequate evaluation benchmarks. Current fusion methods are typically evaluated on a small selection of public datasets, a limited scope that inadequately represents the complexity and diversity of real-world scenarios, potentially leading to biased evaluations. This issue presents a twofold challenge. On one hand, models may overfit to the biases of specific datasets, hindering their generalization to broader practical applications. On the other hand, the absence of a unified evaluation standard makes fair and objective comparisons between different fusion methods difficult. Consequently, a truly universal and high-performance fusion model has yet to emerge. To address these challenges, we have developed a large-scale, domain-adaptive benchmark for multimodal evaluation. This benchmark integrates over 30 datasets, encompassing 15 modalities and 20 predictive tasks across key application domains. To complement this, we have also developed an open-source, unified, and automated evaluation pipeline that includes standardized implementations of state-of-the-art models and diverse fusion paradigms. Leveraging this platform, we have conducted large-scale experiments, successfully establishing new performance baselines across multiple tasks. This work provides the academic community with a crucial platform for rigorous and reproducible assessment of multimodal models, aiming to propel the field of multimodal artificial intelligence to new heights.

---

### A Risk-Neutral Neural Operator for Arbitrage-Free SPX-VIX Term Structures

Authors: Jian'an Zhang
Published: 2025-11-09
Categories: cs.LG, q-fin.CP
arXiv: https://arxiv.org/abs/2511.06451v1

We propose ARBITER, a risk-neutral neural operator for learning joint SPX-VIX term structures under no-arbitrage constraints. ARBITER maps market states to an operator that outputs implied volatility and variance curves while enforcing static arbitrage (calendar, vertical, butterfly), Lipschitz bounds, and monotonicity. The model couples operator learning with constrained decoders and is trained with extragradient-style updates plus projection. We introduce evaluation metrics for derivatives term structures (NAS, CNAS, NI, Dual-Gap, Stability Rate) and show gains over Fourier Neural Operator, DeepONet, and state-space sequence models on historical SPX and VIX data. Ablation studies indicate that tying the SPX and VIX legs reduces Dual-Gap and improves NI, Lipschitz projection stabilizes calibration, and selective state updates improve long-horizon generalization. We provide identifiability and approximation results and describe practical recipes for arbitrage-free interpolation and extrapolation across maturities and strikes.

---

### Countering Multi-modal Representation Collapse through Rank-targeted Fusion

Authors: Seulgi Kim, Kiran Kokilepersaud, Mohit Prabhushankar, Ghassan AlRegib
Published: 2025-11-09
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2511.06450v2

Multi-modal fusion methods often suffer from two types of representation collapse: feature collapse where individual dimensions lose their discriminative power (as measured by eigenspectra), and modality collapse where one dominant modality overwhelms the other. Applications like human action anticipation that require fusing multifarious sensor data are hindered by both feature and modality collapse. However, existing methods attempt to counter feature collapse and modality collapse separately. This is because there is no unifying framework that efficiently addresses feature and modality collapse in conjunction. In this paper, we posit the utility of effective rank as an informative measure that can be utilized to quantify and counter both the representation collapses. We propose \textit{Rank-enhancing Token Fuser}, a theoretically grounded fusion framework that selectively blends less informative features from one modality with complementary features from another modality. We show that our method increases the effective rank of the fused representation. To address modality collapse, we evaluate modality combinations that mutually increase each others' effective rank. We show that depth maintains representational balance when fused with RGB, avoiding modality collapse. We validate our method on action anticipation, where we present \texttt{R3D}, a depth-informed fusion framework. Extensive experiments on NTURGBD, UTKinect, and DARai demonstrate that our approach significantly outperforms prior state-of-the-art methods by up to 3.74\%. Our code is available at: \href{https://github.com/olivesgatech/R3D}{https://github.com/olivesgatech/R3D}.

---

### FLEX: Continuous Agent Evolution via Forward Learning from Experience

Authors: Zhicheng Cai, Xinyuan Guo, Yu Pei, Jiangtao Feng, Jinsong Su, Jiangjie Chen, Ya-Qin Zhang, Wei-Ying Ma, Mingxuan Wang, Hao Zhou
Published: 2025-11-09
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2511.06449v2

Autonomous agents driven by Large Language Models (LLMs) have revolutionized reasoning and problem-solving but remain static after training, unable to grow with experience as intelligent beings do during deployment. We introduce Forward Learning with EXperience (FLEX), a gradient-free learning paradigm that enables LLM agents to continuously evolve through accumulated experience. Specifically, FLEX cultivates scalable and inheritable evolution by constructing a structured experience library through continual reflection on successes and failures during interaction with the environment. FLEX delivers substantial improvements on mathematical reasoning, chemical retrosynthesis, and protein fitness prediction (up to 23% on AIME25, 10% on USPTO50k, and 14% on ProteinGym). We further identify a clear scaling law of experiential growth and the phenomenon of experience inheritance across agents, marking a step toward scalable and inheritable continuous agent evolution. Project Page: https://flex-gensi-thuair.github.io.

---

### When AI Agents Collude Online: Financial Fraud Risks by Collaborative LLM Agents on Social Platforms

Authors: Qibing Ren, Zhijie Zheng, Jiaxuan Guo, Junchi Yan, Lizhuang Ma, Jing Shao
Published: 2025-11-09
Categories: cs.MA, cs.AI, cs.CL, cs.SI
arXiv: https://arxiv.org/abs/2511.06448v2

In this work, we study the risks of collective financial fraud in large-scale multi-agent systems powered by large language model (LLM) agents. We investigate whether agents can collaborate in fraudulent behaviors, how such collaboration amplifies risks, and what factors influence fraud success. To support this research, we present MultiAgentFraudBench, a large-scale benchmark for simulating financial fraud scenarios based on realistic online interactions. The benchmark covers 28 typical online fraud scenarios, spanning the full fraud lifecycle across both public and private domains. We further analyze key factors affecting fraud success, including interaction depth, activity level, and fine-grained collaboration failure modes. Finally, we propose a series of mitigation strategies, including adding content-level warnings to fraudulent posts and dialogues, using LLMs as monitors to block potentially malicious agents, and fostering group resilience through information sharing at the societal level. Notably, we observe that malicious agents can adapt to environmental interventions. Our findings highlight the real-world risks of multi-agent financial fraud and suggest practical measures for mitigating them. Code is available at https://github.com/zheng977/MutiAgent4Fraud.

---

### Personality over Precision: Exploring the Influence of Human-Likeness on ChatGPT Use for Search

Authors: Mert Yazan, Frederik Bungaran Ishak Situmeang, Suzan Verberne
Published: 2025-11-09
Categories: cs.HC, cs.AI
arXiv: https://arxiv.org/abs/2511.06447v1

Conversational search interfaces, like ChatGPT, offer an interactive, personalized, and engaging user experience compared to traditional search. On the downside, they are prone to cause overtrust issues where users rely on their responses even when they are incorrect. What aspects of the conversational interaction paradigm drive people to adopt it, and how it creates personalized experiences that lead to overtrust, is not clear. To understand the factors influencing the adoption of conversational interfaces, we conducted a survey with 173 participants. We examined user perceptions regarding trust, human-likeness (anthropomorphism), and design preferences between ChatGPT and Google. To better understand the overtrust phenomenon, we asked users about their willingness to trade off factuality for constructs like ease of use or human-likeness. Our analysis identified two distinct user groups: those who use both ChatGPT and Google daily (DUB), and those who primarily rely on Google (DUG). The DUB group exhibited higher trust in ChatGPT, perceiving it as more human-like, and expressed greater willingness to trade factual accuracy for enhanced personalization and conversational flow. Conversely, the DUG group showed lower trust toward ChatGPT but still appreciated aspects like ad-free experiences and responsive interactions. Demographic analysis further revealed nuanced patterns, with middle-aged adults using ChatGPT less frequently yet trusting it more, suggesting potential vulnerability to misinformation. Our findings contribute to understanding user segmentation, emphasizing the critical roles of personalization and human-likeness in conversational IR systems, and reveal important implications regarding users' willingness to compromise factual accuracy for more engaging interactions.

---

### SR-KI: Scalable and Real-Time Knowledge Integration into LLMs via Supervised Attention

Authors: Bohan Yu, Wei Huang, Kang Liu
Published: 2025-11-09
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2511.06446v1

This paper proposes SR-KI, a novel approach for integrating real-time and large-scale structured knowledge bases (KBs) into large language models (LLMs). SR-KI begins by encoding KBs into key-value pairs using a pretrained encoder, and injects them into LLMs' KV cache. Building on this representation, we employ a two-stage training paradigm: first locating a dedicated retrieval layer within the LLM, and then applying an attention-based loss at this layer to explicitly supervise attention toward relevant KB entries. Unlike traditional retrieval-augmented generation methods that rely heavily on the performance of external retrievers and multi-stage pipelines, SR-KI supports end-to-end inference by performing retrieval entirely within the models latent space. This design enables efficient compression of injected knowledge and facilitates dynamic knowledge updates. Comprehensive experiments demonstrate that SR-KI enables the integration of up to 40K KBs into a 7B LLM on a single A100 40GB GPU, and achieves strong retrieval performance, maintaining over 98% Recall@10 on the best-performing task and exceeding 88% on average across all tasks. Task performance on question answering and KB ID generation also demonstrates that SR-KI maintains strong performance while achieving up to 99.75% compression of the injected KBs.

---

### How Wide and How Deep? Mitigating Over-Squashing of GNNs via Channel Capacity Constrained Estimation

Authors: Zinuo You, Jin Zheng, John Cartlidge
Published: 2025-11-09
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.06443v1

Existing graph neural networks typically rely on heuristic choices for hidden dimensions and propagation depths, which often lead to severe information loss during propagation, known as over-squashing. To address this issue, we propose Channel Capacity Constrained Estimation (C3E), a novel framework that formulates the selection of hidden dimensions and depth as a nonlinear programming problem grounded in information theory. Through modeling spectral graph neural networks as communication channels, our approach directly connects channel capacity to hidden dimensions, propagation depth, propagation mechanism, and graph structure. Extensive experiments on nine public datasets demonstrate that hidden dimensions and depths estimated by C3E can mitigate over-squashing and consistently improve representation learning. Experimental results show that over-squashing occurs due to the cumulative compression of information in representation matrices. Furthermore, our findings show that increasing hidden dimensions indeed mitigate information compression, while the role of propagation depth is more nuanced, uncovering a fundamental balance between information compression and representation complexity.

---

### Towards Resource-Efficient Multimodal Intelligence: Learned Routing among Specialized Expert Models

Authors: Mayank Saini, Arit Kumar Bishwas
Published: 2025-11-09
Categories: cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2511.06441v1

As AI moves beyond text, large language models (LLMs) increasingly power vision, audio, and document understanding; however, their high inference costs hinder real-time, scalable deployment. Conversely, smaller open-source models offer cost advantages but struggle with complex or multimodal queries. We introduce a unified, modular framework that intelligently routes each query - textual, multimodal, or complex - to the most fitting expert model, using a learned routing network that balances cost and quality. For vision tasks, we employ a two-stage open-source pipeline optimized for efficiency and reviving efficient classical vision components where they remain SOTA for sub-tasks. On benchmarks such as Massive Multitask Language Understanding (MMLU) and Visual Question Answering (VQA), we match or exceed the performance of always-premium LLM (monolithic systems with one model serving all query types) performance, yet reduce the reliance on costly models by over 67%. With its extensible, multi-agent orchestration, we deliver high-quality, resource-efficient AI at scale.

---

### Optimizing Chain-of-Thought Confidence via Topological and Dirichlet Risk Analysis

Authors: Abhishek More, Anthony Zhang, Nicole Bonilla, Ashvik Vivekan, Kevin Zhu, Parham Sharafoleslami, Maheep Chaudhary
Published: 2025-11-09
Categories: cs.AI, cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2511.06437v1

Chain-of-thought (CoT) prompting enables Large Language Models to solve complex problems, but deploying these models safely requires reliable confidence estimates, a capability where existing methods suffer from poor calibration and severe overconfidence on incorrect predictions. We propose Enhanced Dirichlet and Topology Risk (EDTR), a novel decoding strategy that combines topological analysis with Dirichlet-based uncertainty quantification to measure LLM confidence across multiple reasoning paths. EDTR treats each CoT as a vector in high-dimensional space and extracts eight topological risk features capturing the geometric structure of reasoning distributions: tighter, more coherent clusters indicate higher confidence while dispersed, inconsistent paths signal uncertainty. We evaluate EDTR against three state-of-the-art calibration methods across four diverse reasoning benchmarks spanning olympiad-level mathematics (AIME), grade school math (GSM8K), commonsense reasoning, and stock price prediction \cite{zhang2025aime, cobbe2021training, talmor-etal-2019-commonsenseqa, yahoo_finance}. EDTR achieves 41\% better calibration than competing methods with an average ECE of 0.287 and the best overall composite score of 0.672, while notably achieving perfect accuracy on AIME and exceptional calibration on GSM8K with an ECE of 0.107, domains where baselines exhibit severe overconfidence. Our work provides a geometric framework for understanding and quantifying uncertainty in multi-step LLM reasoning, enabling more reliable deployment where calibrated confidence estimates are essential.

---

### Diagnose Like A REAL Pathologist: An Uncertainty-Focused Approach for Trustworthy Multi-Resolution Multiple Instance Learning

Authors: Sungrae Hong, Sol Lee, Jisu Shin, Jiwon Jeong, Mun Yong Yi
Published: 2025-11-09
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.06433v2

With the increasing demand for histopathological specimen examination and diagnostic reporting, Multiple Instance Learning (MIL) has received heightened research focus as a viable solution for AI-centric diagnostic aid. Recently, to improve its performance and make it work more like a pathologist, several MIL approaches based on the use of multiple-resolution images have been proposed, delivering often higher performance than those that use single-resolution images. Despite impressive recent developments of multiple-resolution MIL, previous approaches only focus on improving performance, thereby lacking research on well-calibrated MIL that clinical experts can rely on for trustworthy diagnostic results. In this study, we propose Uncertainty-Focused Calibrated MIL (UFC-MIL), which more closely mimics the pathologists' examination behaviors while providing calibrated diagnostic predictions, using multiple images with different resolutions. UFC-MIL includes a novel patch-wise loss that learns the latent patterns of instances and expresses their uncertainty for classification. Also, the attention-based architecture with a neighbor patch aggregation module collects features for the classifier. In addition, aggregated predictions are calibrated through patch-level uncertainty without requiring multiple iterative inferences, which is a key practical advantage. Against challenging public datasets, UFC-MIL shows superior performance in model calibration while achieving classification accuracy comparable to that of state-of-the-art methods.

---

### CG-TTRL: Context-Guided Test-Time Reinforcement Learning for On-Device Large Language Models

Authors: Peyman Hosseini, Ondrej Bohdal, Taha Ceritli, Ignacio Castro, Matthew Purver, Mete Ozay, Umberto Michieli
Published: 2025-11-09
Categories: cs.LG, cs.CL
arXiv: https://arxiv.org/abs/2511.06430v1

Test-time Reinforcement Learning (TTRL) has shown promise in adapting foundation models for complex tasks at test-time, resulting in large performance improvements. TTRL leverages an elegant two-phase sampling strategy: first, multi-sampling derives a pseudo-label via majority voting, while subsequent downsampling and reward-based fine-tuning encourages the model to explore and learn diverse valid solutions, with the pseudo-label modulating the reward signal. Meanwhile, in-context learning has been widely explored at inference time and demonstrated the ability to enhance model performance without weight updates. However, TTRL's two-phase sampling strategy under-utilizes contextual guidance, which can potentially improve pseudo-label accuracy in the initial exploitation phase while regulating exploration in the second. To address this, we propose context-guided TTRL (CG-TTRL), integrating context dynamically into both sampling phases and propose a method for efficient context selection for on-device applications. Our evaluations on mathematical and scientific QA benchmarks show CG-TTRL outperforms TTRL (e.g. additional 7% relative accuracy improvement over TTRL), while boosting efficiency by obtaining strong performance after only a few steps of test-time training (e.g. 8% relative improvement rather than 1% over TTRL after 3 steps).

---

### Walking the Tightrope of LLMs for Software Development: A Practitioners' Perspective

Authors: Samuel Ferino, Rashina Hoda, John Grundy, Christoph Treude
Published: 2025-11-09
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2511.06428v2

Background: Large Language Models emerged with the potential of provoking a revolution in software development (e.g., automating processes, workforce transformation). Although studies have started to investigate the perceived impact of LLMs for software development, there is a need for empirical studies to comprehend how to balance forward and backward effects of using LLMs. Objective: We investigated how LLMs impact software development and how to manage the impact from a software developer's perspective. Method: We conducted 22 interviews with software practitioners across 3 rounds of data collection and analysis, between October (2024) and September (2025). We employed Socio-Technical Grounded Theory for Data Analysis (STGT4DA) to rigorously analyse interview participants' responses. Results: We identified the benefits (e.g., maintain developer flow, improve developer mental models, and foster entrepreneurship) and challenges (e.g., damage to developers' reputation) of using LLMs at individual, team, organisation, and society levels; as well as actionable guidances into how mitigate these challenges. Conclusion: Critically, we present the trade-offs that software practitioners, teams, and organisations face in working with LLMs. Our findings are particularly useful for software team leaders and IT managers to assess the viability of LLMs within their specific context.

---

### Dutch Metaphor Extraction from Cancer Patients' Interviews and Forum Data using LLMs and Human in the Loop

Authors: Lifeng Han, David Lindevelt, Sander Puts, Erik van Mulligen, Suzan Verberne
Published: 2025-11-09
Categories: cs.CL, cs.CY
arXiv: https://arxiv.org/abs/2511.06427v2

Metaphors and metaphorical language (MLs) play an important role in healthcare communication between clinicians, patients, and patients' family members. In this work, we focus on Dutch language data from cancer patients. We extract metaphors used by patients using two data sources: (1) cancer patient storytelling interview data and (2) online forum data, including patients' posts, comments, and questions to professionals. We investigate how current state-of-the-art large language models (LLMs) perform on this task by exploring different prompting strategies such as chain of thought reasoning, few-shot learning, and self-prompting. With a human-in-the-loop setup, we verify the extracted metaphors and compile the outputs into a corpus named HealthQuote.NL. We believe the extracted metaphors can support better patient care, for example shared decision making, improved communication between patients and clinicians, and enhanced patient health literacy. They can also inform the design of personalized care pathways. We share prompts and related resources at https://github.com/4dpicture/HealthQuote.NL

---

### Non-Negative Stiefel Approximating Flow: Orthogonalish Matrix Optimization for Interpretable Embeddings

Authors: Brian B. Avants, Nicholas J. Tustison, James R Stone
Published: 2025-11-09
Categories: stat.ML, cs.CV, cs.LG, stat.ME
arXiv: https://arxiv.org/abs/2511.06425v1

Interpretable representation learning is a central challenge in modern machine learning, particularly in high-dimensional settings such as neuroimaging, genomics, and text analysis. Current methods often struggle to balance the competing demands of interpretability and model flexibility, limiting their effectiveness in extracting meaningful insights from complex data. We introduce Non-negative Stiefel Approximating Flow (NSA-Flow), a general-purpose matrix estimation framework that unifies ideas from sparse matrix factorization, orthogonalization, and constrained manifold learning. NSA-Flow enforces structured sparsity through a continuous balance between reconstruction fidelity and column-wise decorrelation, parameterized by a single tunable weight. The method operates as a smooth flow near the Stiefel manifold with proximal updates for non-negativity and adaptive gradient control, yielding representations that are simultaneously sparse, stable, and interpretable. Unlike classical regularization schemes, NSA-Flow provides an intuitive geometric mechanism for manipulating sparsity at the level of global structure while simplifying latent features. We demonstrate that the NSA-Flow objective can be optimized smoothly and integrates seamlessly with existing pipelines for dimensionality reduction while improving interpretability and generalization in both simulated and real biomedical data. Empirical validation on the Golub leukemia dataset and in Alzheimer's disease demonstrate that the NSA-Flow constraints can maintain or improve performance over related methods with little additional methodological effort. NSA-Flow offers a scalable, general-purpose tool for interpretable ML, applicable across data science domains.

---

### Turbo-DDCM: Fast and Flexible Zero-Shot Diffusion-Based Image Compression

Authors: Amit Vaisman, Guy Ohayon, Hila Manor, Michael Elad, Tomer Michaeli
Published: 2025-11-09
Categories: eess.IV, cs.AI, cs.CV, eess.SP, stat.ML
arXiv: https://arxiv.org/abs/2511.06424v2

While zero-shot diffusion-based compression methods have seen significant progress in recent years, they remain notoriously slow and computationally demanding. This paper presents an efficient zero-shot diffusion-based compression method that runs substantially faster than existing methods, while maintaining performance that is on par with the state-of-the-art techniques. Our method builds upon the recently proposed Denoising Diffusion Codebook Models (DDCMs) compression scheme. Specifically, DDCM compresses an image by sequentially choosing the diffusion noise vectors from reproducible random codebooks, guiding the denoiser's output to reconstruct the target image. We modify this framework with Turbo-DDCM, which efficiently combines a large number of noise vectors at each denoising step, thereby significantly reducing the number of required denoising operations. This modification is also coupled with an improved encoding protocol. Furthermore, we introduce two flexible variants of Turbo-DDCM, a priority-aware variant that prioritizes user-specified regions and a distortion-controlled variant that compresses an image based on a target PSNR rather than a target BPP. Comprehensive experiments position Turbo-DDCM as a compelling, practical, and flexible image compression scheme.

---

### DiffusionUavLoc: Visually Prompted Diffusion for Cross-View UAV Localization

Authors: Tao Liu, Kan Ren, Qian Chen
Published: 2025-11-09
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.06422v1

With the rapid growth of the low-altitude economy, unmanned aerial vehicles (UAVs) have become key platforms for measurement and tracking in intelligent patrol systems. However, in GNSS-denied environments, localization schemes that rely solely on satellite signals are prone to failure. Cross-view image retrieval-based localization is a promising alternative, yet substantial geometric and appearance domain gaps exist between oblique UAV views and nadir satellite orthophotos. Moreover, conventional approaches often depend on complex network architectures, text prompts, or large amounts of annotation, which hinders generalization. To address these issues, we propose DiffusionUavLoc, a cross-view localization framework that is image-prompted, text-free, diffusion-centric, and employs a VAE for unified representation. We first use training-free geometric rendering to synthesize pseudo-satellite images from UAV imagery as structural prompts. We then design a text-free conditional diffusion model that fuses multimodal structural cues to learn features robust to viewpoint changes. At inference, descriptors are computed at a fixed time step t and compared using cosine similarity. On University-1652 and SUES-200, the method performs competitively for cross-view localization, especially for satellite-to-drone in University-1652.Our data and code will be published at the following URL: https://github.com/liutao23/DiffusionUavLoc.git.

---

### MONICA: Real-Time Monitoring and Calibration of Chain-of-Thought Sycophancy in Large Reasoning Models

Authors: Jingyu Hu, Shu Yang, Xilin Gong, Hongming Wang, Weiru Liu, Di Wang
Published: 2025-11-09
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2511.06419v1

Large Reasoning Models (LRMs) suffer from sycophantic behavior, where models tend to agree with users' incorrect beliefs and follow misinformation rather than maintain independent reasoning. This behavior undermines model reliability and poses societal risks. Mitigating LRM sycophancy requires monitoring how this sycophancy emerges during the reasoning trajectory; however, current methods mainly focus on judging based on final answers and correcting them, without understanding how sycophancy develops during reasoning processes. To address this limitation, we propose MONICA, a novel Monitor-guided Calibration framework that monitors and mitigates sycophancy during model inference at the level of reasoning steps, without requiring the model to finish generating its complete answer. MONICA integrates a sycophantic monitor that provides real-time monitoring of sycophantic drift scores during response generation with a calibrator that dynamically suppresses sycophantic behavior when scores exceed predefined thresholds. Extensive experiments across 12 datasets and 3 LRMs demonstrate that our method effectively reduces sycophantic behavior in both intermediate reasoning steps and final answers, yielding robust performance improvements.

---

### How Well Do LLMs Understand Drug Mechanisms? A Knowledge + Reasoning Evaluation Dataset

Authors: Sunil Mohan, Theofanis Karaletsos
Published: 2025-11-09
Categories: cs.CL
arXiv: https://arxiv.org/abs/2511.06418v1

Two scientific fields showing increasing interest in pre-trained large language models (LLMs) are drug development / repurposing, and personalized medicine. For both, LLMs have to demonstrate factual knowledge as well as a deep understanding of drug mechanisms, so they can recall and reason about relevant knowledge in novel situations. Drug mechanisms of action are described as a series of interactions between biomedical entities, which interlink into one or more chains directed from the drug to the targeted disease. Composing the effects of the interactions in a candidate chain leads to an inference about whether the drug might be useful or not for that disease. We introduce a dataset that evaluates LLMs on both factual knowledge of known mechanisms, and their ability to reason about them under novel situations, presented as counterfactuals that the models are unlikely to have seen during training. Using this dataset, we show that o4-mini outperforms the 4o, o3, and o3-mini models from OpenAI, and the recent small Qwen3-4B-thinking model closely matches o4-mini's performance, even outperforming it in some cases. We demonstrate that the open world setting for reasoning tasks, which requires the model to recall relevant knowledge, is more challenging than the closed world setting where the needed factual knowledge is provided. We also show that counterfactuals affecting internal links in the reasoning chain present a much harder task than those affecting a link from the drug mentioned in the prompt.

---

### AUTO-Explorer: Automated Data Collection for GUI Agent

Authors: Xiangwu Guo, Difei Gao, Mike Zheng Shou
Published: 2025-11-09
Categories: cs.AI
arXiv: https://arxiv.org/abs/2511.06417v1

Recent advancements in GUI agents have significantly expanded their ability to interpret natural language commands to manage software interfaces. However, acquiring GUI data remains a significant challenge. Existing methods often involve designing automated agents that browse URLs from the Common Crawl, using webpage HTML to collect screenshots and corresponding annotations, including the names and bounding boxes of UI elements. However, this method is difficult to apply to desktop software or some newly launched websites not included in the Common Crawl. While we expect the model to possess strong generalization capabilities to handle this, it is still crucial for personalized scenarios that require rapid and perfect adaptation to new software or websites. To address this, we propose an automated data collection method with minimal annotation costs, named Auto-Explorer. It incorporates a simple yet effective exploration mechanism that autonomously parses and explores GUI environments, gathering data efficiently. Additionally, to assess the quality of exploration, we have developed the UIXplore benchmark. This benchmark creates environments for explorer agents to discover and save software states. Using the data gathered, we fine-tune a multimodal large language model (MLLM) and establish a GUI element grounding testing set to evaluate the effectiveness of the exploration strategies. Our experiments demonstrate the superior performance of Auto-Explorer, showing that our method can quickly enhance the capabilities of an MLLM in explored software.

---

### SofT-GRPO: Surpassing Discrete-Token LLM Reinforcement Learning via Gumbel-Reparameterized Soft-Thinking Policy Optimization

Authors: Zhi Zheng, Yu Gu, Wei Liu, Yee Whye Teh, Wee Sun Lee
Published: 2025-11-09
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2511.06411v2

The soft-thinking paradigm for Large Language Model (LLM) reasoning can outperform the conventional discrete-token Chain-of-Thought (CoT) reasoning in some scenarios, underscoring its research and application value. However, while the discrete-token CoT reasoning pattern can be reinforced through policy optimization algorithms such as group relative policy optimization (GRPO), extending the soft-thinking pattern with Reinforcement Learning (RL) remains challenging. This difficulty stems from the complexities of injecting stochasticity into soft-thinking tokens and updating soft-thinking policies accordingly. As a result, previous attempts to combine soft-thinking with GRPO typically underperform their discrete-token GRPO counterparts. To fully unlock the potential of soft-thinking, this paper presents a novel policy optimization algorithm, SofT-GRPO, to reinforce LLMs under the soft-thinking reasoning pattern. SofT-GRPO injects the Gumbel noise into logits, employs the Gumbel-Softmax technique to avoid soft-thinking tokens outside the pre-trained embedding space, and leverages the reparameterization trick in policy gradient. We conduct experiments across base LLMs ranging from 1.5B to 7B parameters, and results demonstrate that SofT-GRPO enables soft-thinking LLMs to slightly outperform discrete-token GRPO on Pass@1 (+0.13% on average accuracy), while exhibiting a substantial uplift on Pass@32 (+2.19% on average accuracy). Codes and weights are available on https://github.com/zz1358m/SofT-GRPO-master

---

### VDNeRF: Vision-only Dynamic Neural Radiance Field for Urban Scenes

Authors: Zhengyu Zou, Jingfeng Li, Hao Li, Xiaolei Hou, Jinwen Hu, Jingkun Chen, Lechao Cheng, Dingwen Zhang
Published: 2025-11-09
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.06408v1

Neural Radiance Fields (NeRFs) implicitly model continuous three-dimensional scenes using a set of images with known camera poses, enabling the rendering of photorealistic novel views. However, existing NeRF-based methods encounter challenges in applications such as autonomous driving and robotic perception, primarily due to the difficulty of capturing accurate camera poses and limitations in handling large-scale dynamic environments. To address these issues, we propose Vision-only Dynamic NeRF (VDNeRF), a method that accurately recovers camera trajectories and learns spatiotemporal representations for dynamic urban scenes without requiring additional camera pose information or expensive sensor data. VDNeRF employs two separate NeRF models to jointly reconstruct the scene. The static NeRF model optimizes camera poses and static background, while the dynamic NeRF model incorporates the 3D scene flow to ensure accurate and consistent reconstruction of dynamic objects. To address the ambiguity between camera motion and independent object motion, we design an effective and powerful training framework to achieve robust camera pose estimation and self-supervised decomposition of static and dynamic elements in a scene. Extensive evaluations on mainstream urban driving datasets demonstrate that VDNeRF surpasses state-of-the-art NeRF-based pose-free methods in both camera pose estimation and dynamic novel view synthesis.

---

### Fast Riemannian-manifold Hamiltonian Monte Carlo for hierarchical Gaussian-process models

Authors: Takashi Hayakawa, Satoshi Asai
Published: 2025-11-09
Categories: stat.ML, cs.LG, stat.CO
arXiv: https://arxiv.org/abs/2511.06407v1

Hierarchical Bayesian models based on Gaussian processes are considered useful for describing complex nonlinear statistical dependencies among variables in real-world data. However, effective Monte Carlo algorithms for inference with these models have not yet been established, except for several simple cases. In this study, we show that, compared with the slow inference achieved with existing program libraries, the performance of Riemannian-manifold Hamiltonian Monte Carlo (RMHMC) can be drastically improved by optimising the computation order according to the model structure and dynamically programming the eigendecomposition. This improvement cannot be achieved when using an existing library based on a naive automatic differentiator. We numerically demonstrate that RMHMC effectively samples from the posterior, allowing the calculation of model evidence, in a Bayesian logistic regression on simulated data and in the estimation of propensity functions for the American national medical expenditure data using several Bayesian multiple-kernel models. These results lay a foundation for implementing effective Monte Carlo algorithms for analysing real-world data with Gaussian processes, and highlight the need to develop a customisable library set that allows users to incorporate dynamically programmed objects and finely optimises the mode of automatic differentiation depending on the model structure.

---

### On Modality Incomplete Infrared-Visible Object Detection: An Architecture Compatibility Perspective

Authors: Shuo Yang, Yinghui Xing, Shizhou Zhang, Zhilong Niu
Published: 2025-11-09
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2511.06406v1

Infrared and visible object detection (IVOD) is essential for numerous around-the-clock applications. Despite notable advancements, current IVOD models exhibit notable performance declines when confronted with incomplete modality data, particularly if the dominant modality is missing. In this paper, we take a thorough investigation on modality incomplete IVOD problem from an architecture compatibility perspective. Specifically, we propose a plug-and-play Scarf Neck module for DETR variants, which introduces a modality-agnostic deformable attention mechanism to enable the IVOD detector to flexibly adapt to any single or double modalities during training and inference. When training Scarf-DETR, we design a pseudo modality dropout strategy to fully utilize the multi-modality information, making the detector compatible and robust to both working modes of single and double modalities. Moreover, we introduce a comprehensive benchmark for the modality-incomplete IVOD task aimed at thoroughly assessing situations where the absent modality is either dominant or secondary. Our proposed Scarf-DETR not only performs excellently in missing modality scenarios but also achieves superior performances on the standard IVOD modality complete benchmarks. Our code will be available at https://github.com/YinghuiXing/Scarf-DETR.

---

### InfoAffect: Affective Annotations of Infographics in Information Spread

Authors: Zihang Fu, Yunchao Wang, Chenyu Huang, Guodao Sun, Ronghua Liang
Published: 2025-11-09
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.06404v2

Infographics are widely used in social media to convey complex information, yet how they influence users' affects remains underexplored due to the scarcity of relevant datasets. To address this gap, we introduce a 3.5k-sample affect-annotated InfoAffect dataset, which combines textual content with real-world infographics. We first collected the raw data from six fields and aligned it via preprocessing, the accompanied-text-priority method, and three strategies to guarantee quality and compliance. After that, we constructed an Affect Table to constrain annotation. We used five state-of-the-art multimodal large language models (MLLMs) to analyze both modalities, and their outputs were fused with the Reciprocal Rank Fusion (RRF) algorithm to yield robust affects and confidences. We conducted a user study with two experiments to validate usability and assess the InfoAffect dataset using the Composite Affect Consistency Index (CACI), achieving an overall score of 0.608, which indicates high accuracy. The InfoAffect dataset is available in a public repository at https://github.com/bulichuchu/InfoAffect-dataset.

---

### SugarTextNet: A Transformer-Based Framework for Detecting Sugar Dating-Related Content on Social Media with Context-Aware Focal Loss

Authors: Lionel Z. Wang, Shihan Ben, Yulu Huang, Simeng Qin
Published: 2025-11-09
Categories: cs.CL, cs.CY, cs.SI
arXiv: https://arxiv.org/abs/2511.06402v2

Sugar dating-related content has rapidly proliferated on mainstream social media platforms, giving rise to serious societal and regulatory concerns, including commercialization of intimate relationships and the normalization of transactional relationships.~Detecting such content is highly challenging due to the prevalence of subtle euphemisms, ambiguous linguistic cues, and extreme class imbalance in real-world data.~In this work, we present SugarTextNet, a novel transformer-based framework specifically designed to identify sugar dating-related posts on social media.~SugarTextNet integrates a pretrained transformer encoder, an attention-based cue extractor, and a contextual phrase encoder to capture both salient and nuanced features in user-generated text.~To address class imbalance and enhance minority-class detection, we introduce Context-Aware Focal Loss, a tailored loss function that combines focal loss scaling with contextual weighting.~We evaluate SugarTextNet on a newly curated, manually annotated dataset of 3,067 Chinese social media posts from Sina Weibo, demonstrating that our approach substantially outperforms traditional machine learning models, deep learning baselines, and large language models across multiple metrics.~Comprehensive ablation studies confirm the indispensable role of each component.~Our findings highlight the importance of domain-specific, context-aware modeling for sensitive content detection, and provide a robust solution for content moderation in complex, real-world scenarios.

---

### Efficient LLM Safety Evaluation through Multi-Agent Debate

Authors: Dachuan Lin, Guobin Shen, Zihao Yang, Tianrong Liu, Dongcheng Zhao, Yi Zeng
Published: 2025-11-09
Categories: cs.AI, cs.CR
arXiv: https://arxiv.org/abs/2511.06396v3

Safety evaluation of large language models (LLMs) increasingly relies on LLM-as-a-judge pipelines, but strong judges can still be expensive to use at scale. We study whether structured multi-agent debate can improve judge reliability while keeping backbone size and cost modest. To do so, we introduce HAJailBench, a human-annotated jailbreak benchmark with 11,100 labeled interactions spanning diverse attack methods and target models, and we pair it with a Multi-Agent Judge framework in which critic, defender, and judge agents debate under a shared safety rubric. On HAJailBench, the framework improves over matched small-model prompt baselines and prior multi-agent judges, while remaining more economical than GPT-4o under the evaluated pricing snapshot. Ablation results further show that a small number of debate rounds is sufficient to capture most of the gain. Together, these results support structured, value-aligned debate as a practical design for scalable LLM safety evaluation.

---

### HatePrototypes: Interpretable and Transferable Representations for Implicit and Explicit Hate Speech Detection

Authors: Irina Proskurina, Marc-Antoine Carpentier, Julien Velcin
Published: 2025-11-09
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2511.06391v3

Optimization of offensive content moderation models for different types of hateful messages is typically achieved through continued pre-training or fine-tuning on new hate speech benchmarks. However, existing benchmarks mainly address explicit hate toward protected groups and often overlook implicit or indirect hate, such as demeaning comparisons, calls for exclusion or violence, and subtle discriminatory language that still causes harm. While explicit hate can often be captured through surface features, implicit hate requires deeper, full-model semantic processing. In this work, we question the need for repeated fine-tuning and analyze the role of HatePrototypes, class-level vector representations derived from language models optimized for hate speech detection and safety moderation. We find that these prototypes, built from as few as 50 examples per class, enable cross-task transfer between explicit and implicit hate, with interchangeable prototypes across benchmarks. Moreover, we show that parameter-free early exiting with prototypes is effective for both hate types. We release the code, prototype resources, and evaluation scripts to support future research on efficient and transferable hate speech detection.

---

### Ghost in the Transformer: Detecting Model Reuse with Invariant Spectral Signatures

Authors: Suqing Wang, Ziyang Ma, Li Xinyi, Zuchao Li
Published: 2025-11-09
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2511.06390v3

Large Language Models (LLMs) are widely adopted, but their high training cost leads many developers to fine-tune existing open-source models. While most adhere to open-source licenses, some falsely claim original training despite clear derivation from public models, raising pressing concerns about intellectual property protection and the need to verify model provenance. In this paper, we propose GhostSpec, a lightweight yet effective method for verifying LLM lineage without access to training data or modification of model behavior. Our approach constructs compact and robust fingerprints by applying singular value decomposition (SVD) to invariant products of internal attention weight matrices. Unlike watermarking or output-based methods, GhostSpec is fully data-free, non-invasive, and computationally efficient. Extensive experiments show it is robust to fine-tuning, pruning, expansion, and adversarial transformations, reliably tracing lineage with minimal overhead. By offering a practical solution for model verification, our method contributes to intellectual property protection and fosters a transparent, trustworthy LLM ecosystem. Our code is available at https://github.com/DX0369/GhostSpec.

---

### HyMoERec: Hybrid Mixture-of-Experts for Sequential Recommendation

Authors: Kunrong Li, Zhu Sun, Kwan Hui Lim
Published: 2025-11-09
Categories: cs.IR, cs.AI
arXiv: https://arxiv.org/abs/2511.06388v1

We propose HyMoERec, a novel sequential recommendation framework that addresses the limitations of uniform Position-wise Feed-Forward Networks in existing models. Current approaches treat all user interactions and items equally, overlooking the heterogeneity in user behavior patterns and diversity in item complexity. HyMoERec initially introduces a hybrid mixture-of-experts architecture that combines shared and specialized expert branches with an adaptive expert fusion mechanism for the sequential recommendation task. This design captures diverse reasoning for varied users and items while ensuring stable training. Experiments on MovieLens-1M and Beauty datasets demonstrate that HyMoERec consistently outperforms state-of-the-art baselines.

---

### Learning the Inverse Ryu--Takayanagi Formula with Transformers

Authors: Sejin Kim
Published: 2025-11-09
Categories: hep-th, cs.LG
arXiv: https://arxiv.org/abs/2511.06387v2

We study the inverse problem of holographic entanglement entropy in AdS$_3$ using a data-driven generative model. Training data consist of randomly generated geometries and their holographic entanglement entropies using the Ryu--Takayanagi formula. After training, the Transformer reconstructs the blackening function within our metric ansatz from previously unseen inputs. The Transformer achieves accurate reconstructions on smooth black hole geometries and extrapolates to horizonless backgrounds. We describe the architecture and data generation process, and we quantify accuracy on both $f(z)$ and the reconstructed $S(\ell)$. Code and evaluation scripts are available at the provided repository.

---

### What Makes Reasoning Invalid: Echo Reflection Mitigation for Large Language Models

Authors: Chen He, Xun Jiang, Lei Wang, Hao Yang, Chong Peng, Peng Yan, Fumin Shen, Xing Xu
Published: 2025-11-09
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2511.06380v1

Large Language Models (LLMs) have demonstrated remarkable performance across a wide range of reasoning tasks. Recent methods have further improved LLM performance in complex mathematical reasoning. However, when extending these methods beyond the domain of mathematical reasoning to tasks involving complex domain-specific knowledge, we observe a consistent failure of LLMs to generate novel insights during the reflection stage. Instead of conducting genuine cognitive refinement, the model tends to mechanically reiterate earlier reasoning steps without introducing new information or perspectives, a phenomenon referred to as "Echo Reflection". We attribute this behavior to two key defects: (1) Uncontrollable information flow during response generation, which allows premature intermediate thoughts to propagate unchecked and distort final decisions; (2) Insufficient exploration of internal knowledge during reflection, leading to repeating earlier findings rather than generating new cognitive insights. Building on these findings, we proposed a novel reinforcement learning method termed Adaptive Entropy Policy Optimization (AEPO). Specifically, the AEPO framework consists of two major components: (1) Reflection-aware Information Filtration, which quantifies the cognitive information flow and prevents the final answer from being affected by earlier bad cognitive information; (2) Adaptive-Entropy Optimization, which dynamically balances exploration and exploitation across different reasoning stages, promoting both reflective diversity and answer correctness. Extensive experiments demonstrate that AEPO consistently achieves state-of-the-art performance over mainstream reinforcement learning baselines across diverse benchmarks.

---

### ArtReg: Visuo-Tactile based Pose Tracking and Manipulation of Unseen Articulated Objects

Authors: Prajval Kumar Murali, Mohsen Kaboli
Published: 2025-11-09
Categories: cs.RO, cs.CV
arXiv: https://arxiv.org/abs/2511.06378v1

Robots operating in real-world environments frequently encounter unknown objects with complex structures and articulated components, such as doors, drawers, cabinets, and tools. The ability to perceive, track, and manipulate these objects without prior knowledge of their geometry or kinematic properties remains a fundamental challenge in robotics. In this work, we present a novel method for visuo-tactile-based tracking of unseen objects (single, multiple, or articulated) during robotic interaction without assuming any prior knowledge regarding object shape or dynamics. Our novel pose tracking approach termed ArtReg (stands for Articulated Registration) integrates visuo-tactile point clouds in an unscented Kalman Filter formulation in the SE(3) Lie Group for point cloud registration. ArtReg is used to detect possible articulated joints in objects using purposeful manipulation maneuvers such as pushing or hold-pulling with a two-robot team. Furthermore, we leverage ArtReg to develop a closed-loop controller for goal-driven manipulation of articulated objects to move the object into the desired pose configuration. We have extensively evaluated our approach on various types of unknown objects through real robot experiments. We also demonstrate the robustness of our method by evaluating objects with varying center of mass, low-light conditions, and with challenging visual backgrounds. Furthermore, we benchmarked our approach on a standard dataset of articulated objects and demonstrated improved performance in terms of pose accuracy compared to state-of-the-art methods. Our experiments indicate that robust and accurate pose tracking leveraging visuo-tactile information enables robots to perceive and interact with unseen complex articulated objects (with revolute or prismatic joints).

---

### Vocabulary In-Context Learning in Transformers: Benefits of Positional Encoding

Authors: Qian Ma, Ruoxiang Xu, Yongqiang Cai
Published: 2025-11-09
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.06376v1

Numerous studies have demonstrated that the Transformer architecture possesses the capability for in-context learning (ICL). In scenarios involving function approximation, context can serve as a control parameter for the model, endowing it with the universal approximation property (UAP). In practice, context is represented by tokens from a finite set, referred to as a vocabulary, which is the case considered in this paper, \emph{i.e.}, vocabulary in-context learning (VICL). We demonstrate that VICL in single-layer Transformers, without positional encoding, does not possess the UAP; however, it is possible to achieve the UAP when positional encoding is included. Several sufficient conditions for the positional encoding are provided. Our findings reveal the benefits of positional encoding from an approximation theory perspective in the context of ICL.

---

### Adaptive Regularization for Large-Scale Sparse Feature Embedding Models

Authors: Mang Li, Wei Lyu
Published: 2025-11-09
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2511.06374v2

The one-epoch overfitting problem has drawn widespread attention, especially in CTR and CVR estimation models in search, advertising, and recommendation domains. These models which rely heavily on large-scale sparse categorical features, often suffer a significant decline in performance when trained for multiple epochs. Although recent studies have proposed heuristic solutions, the fundamental cause of this phenomenon remains unclear. In this work, we present a theoretical explanation grounded in Rademacher complexity, supported by empirical experiments, to explain why overfitting occurs in models with large-scale sparse categorical features. Based on this analysis, we propose a regularization method that constrains the norm budget of embedding layers adaptively. Our approach not only prevents the severe performance degradation observed during multi-epoch training, but also improves model performance within a single epoch. This method has already been deployed in online production systems.

---