# Research Papers — 2025-11 · bundle page 102 of 197

> Full-text markdown of papers #5051–5100 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/102
[← Previous bundle](https://aipod.dev/papers/archive/2025-11/page/101.md)
[Next bundle →](https://aipod.dev/papers/archive/2025-11/page/103.md)

### One Request, Multiple Experts: LLM Orchestrates Domain Specific Models via Adaptive Task Routing

Authors: Xu Yang, Chenhui Lin, Haotian Liu, Qi Wang, Yue Yang, Wenchuan Wu
Published: 2025-11-16
Categories: eess.SY, cs.AI
arXiv: https://arxiv.org/abs/2511.12484v2

With the integration of massive distributed energy resources and the widespread participation of novel market entities, the operation of active distribution networks (ADNs) is progressively evolving into a complex, multi-scenario, and multi-objective problem. Although expert engineers have developed numerous domain specific models (DSMs) to address distinct technical problems, mastering, integrating, and orchestrating these heterogeneous DSMs still entail considerable overhead for ADN operators. Therefore, an intelligent approach is urgently required to unify these DSMs and enable efficient coordination. To address this challenge, this paper proposes the ADN-Agent architecture, which leverages a general large language model (LLM) to coordinate multiple DSMs, enabling adaptive intent recognition, task decomposition, and DSM invocation. Within the ADN-Agent, we design a novel communication mechanism that provides a unified and flexible interface for diverse heterogeneous DSMs. Finally, for specific language-intensive subtasks, we propose an automated training pipeline for fine-tuning small language models, thereby effectively enhancing the overall problem-solving capability of the system. Comprehensive comparisons and ablation experiments validate the efficacy of the proposed method and demonstrate that the ADN-Agent architecture outperforms existing LLM application paradigms.

---

### One Request, Multiple Experts: LLM Orchestrates Domain Specific Models via Adaptive Task Routing

Authors: Xu Yang, Chenhui Lin, Haotian Liu, Qi Wang, Yue Yang, Wenchuan Wu
Published: 2025-11-16
Categories: eess.SY, cs.AI
arXiv: https://arxiv.org/abs/2511.12484v1

With the integration of massive distributed energy resources and the widespread participation of novel market entities, the operation of active distribution networks (ADNs) is progressively evolving into a complex multi-scenario, multi-objective problem. Although expert engineers have developed numerous domain specific models (DSMs) to address distinct technical problems, mastering, integrating, and orchestrating these heterogeneous DSMs still entail considerable overhead for ADN operators. Therefore, an intelligent approach is urgently required to unify these DSMs and enable efficient coordination. To address this challenge, this paper proposes the ADN-Agent architecture, which leverages a general large language model (LLM) to coordinate multiple DSMs, enabling adaptive intent recognition, task decomposition, and DSM invocation. Within the ADN-Agent, we design a novel communication mechanism that provides a unified and flexible interface for diverse heterogeneous DSMs. Finally, for some language-intensive subtasks, we propose an automated training pipeline for fine-tuning small language models, thereby effectively enhancing the overall problem-solving capability of the system. Comprehensive comparisons and ablation experiments validate the efficacy of the proposed method and demonstrate that the ADN-Agent architecture outperforms existing LLM application paradigms.

---

### Discovering autonomous quantum error correction via deep reinforcement learning

Authors: Yue Yin, Tailong Xiao, Xiaoyang Deng, Ming He, Jianping Fan, Guihua Zeng
Published: 2025-11-16
Categories: quant-ph, cs.LG
arXiv: https://arxiv.org/abs/2511.12482v2

Quantum error correction is essential for fault-tolerant quantum computing. However, standard methods relying on active measurements may introduce additional errors. Autonomous quantum error correction (AQEC) circumvents this by utilizing engineered dissipation and drives in bosonic systems, but identifying practical encoding remains challenging due to stringent Knill-Laflamme conditions. In this work, we utilize curriculum learning enabled deep reinforcement learning to discover Bosonic codes under approximate AQEC framework to resist both single-photon and double-photon losses. We present an analytical solution of solving the master equation under approximation conditions, which can significantly accelerate the training process of reinforcement learning. The agent first identifies an encoded subspace surpassing the breakeven point through rapid exploration within a constrained evolutionary time-frame, then strategically fine-tunes its policy to sustain this performance advantage over extended temporal horizons. We find that the two-phase trained agent can discover the optimal set of codewords, i.e., the Fock states $\ket{4}$ and $\ket{7}$ considering the effect of both single-photon and double-photon loss. We identify that the discovered code surpasses the breakeven threshold over a longer evolution time and achieve the state-of-art performance. We also analyze the robustness of the code against the phase damping and amplitude damping noise. Our work highlights the potential of curriculum learning enabled deep reinforcement learning in discovering the optimal quantum error correct code especially in early fault-tolerant quantum systems.

---

### Discovering autonomous quantum error correction via deep reinforcement learning

Authors: Yue Yin, Tailong Xiao, Xiaoyang Deng, Ming He, Jianping Fan, Guihua Zeng
Published: 2025-11-16
Categories: quant-ph, cs.LG
arXiv: https://arxiv.org/abs/2511.12482v1

Quantum error correction is essential for fault-tolerant quantum computing. However, standard methods relying on active measurements may introduce additional errors. Autonomous quantum error correction (AQEC) circumvents this by utilizing engineered dissipation and drives in bosonic systems, but identifying practical encoding remains challenging due to stringent Knill-Laflamme conditions. In this work, we utilize curriculum learning enabled deep reinforcement learning to discover Bosonic codes under approximate AQEC framework to resist both single-photon and double-photon losses. We present an analytical solution of solving the master equation under approximation conditions, which can significantly accelerate the training process of reinforcement learning. The agent first identifies an encoded subspace surpassing the breakeven point through rapid exploration within a constrained evolutionary time-frame, then strategically fine-tunes its policy to sustain this performance advantage over extended temporal horizons. We find that the two-phase trained agent can discover the optimal set of codewords, i.e., the Fock states $\ket{4}$ and $\ket{7}$ considering the effect of both single-photon and double-photon loss. We identify that the discovered code surpasses the breakeven threshold over a longer evolution time and achieve the state-of-art performance. We also analyze the robustness of the code against the phase damping and amplitude damping noise. Our work highlights the potential of curriculum learning enabled deep reinforcement learning in discovering the optimal quantum error correct code especially in early fault-tolerant quantum systems.

---

### MaskAnyNet: Rethinking Masked Image Regions as Valuable Information in Supervised Learning

Authors: Jingshan Hong, Haigen Hu, Huihuang Zhang, Qianwei Zhou, Zhao Li
Published: 2025-11-16
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2511.12480v1

In supervised learning, traditional image masking faces two key issues: (i) discarded pixels are underutilized, leading to a loss of valuable contextual information; (ii) masking may remove small or critical features, especially in fine-grained tasks. In contrast, masked image modeling (MIM) has demonstrated that masked regions can be reconstructed from partial input, revealing that even incomplete data can exhibit strong contextual consistency with the original image. This highlights the potential of masked regions as sources of semantic diversity. Motivated by this, we revisit the image masking approach, proposing to treat masked content as auxiliary knowledge rather than ignored. Based on this, we propose MaskAnyNet, which combines masking with a relearning mechanism to exploit both visible and masked information. It can be easily extended to any model with an additional branch to jointly learn from the recomposed masked region. This approach leverages the semantic diversity of the masked regions to enrich features and preserve fine-grained details. Experiments on CNN and Transformer backbones show consistent gains across multiple benchmarks. Further analysis confirms that the proposed method improves semantic diversity through the reuse of masked content.

---

### Co-Layout: LLM-driven Co-optimization for Interior Layout

Authors: Chucheng Xiang, Ruchao Bao, Biyin Feng, Wenzheng Wu, Zhongyuan Liu, Yirui Guan, Ligang Liu
Published: 2025-11-16
Categories: cs.CV, cs.CL, cs.GR
arXiv: https://arxiv.org/abs/2511.12474v2

We present a novel framework for automated interior design that combines large language models (LLMs) with grid-based integer programming to jointly optimize room layout and furniture placement. Given a textual prompt, the LLM-driven agent workflow extracts structured design constraints related to room configurations and furniture arrangements. These constraints are encoded into a unified grid-based representation inspired by ``Modulor". Our formulation accounts for key design requirements, including corridor connectivity, room accessibility, spatial exclusivity, and user-specified preferences. To improve computational efficiency, we adopt a coarse-to-fine optimization strategy that begins with a low-resolution grid to solve a simplified problem and guides the solution at the full resolution. Experimental results across diverse scenarios demonstrate that our joint optimization approach significantly outperforms existing two-stage design pipelines in solution quality, and achieves notable computational efficiency through the coarse-to-fine strategy.

---

### Co-Layout: LLM-driven Co-optimization for Interior Layout

Authors: Chucheng Xiang, Ruchao Bao, Biyin Feng, Wenzheng Wu, Zhongyuan Liu, Yirui Guan, Ligang Liu
Published: 2025-11-16
Categories: cs.CV, cs.CL, cs.GR
arXiv: https://arxiv.org/abs/2511.12474v1

We present a novel framework for automated interior design that combines large language models (LLMs) with grid-based integer programming to jointly optimize room layout and furniture placement. Given a textual prompt, the LLM-driven agent workflow extracts structured design constraints related to room configurations and furniture arrangements. These constraints are encoded into a unified grid-based representation inspired by ``Modulor". Our formulation accounts for key design requirements, including corridor connectivity, room accessibility, spatial exclusivity, and user-specified preferences. To improve computational efficiency, we adopt a coarse-to-fine optimization strategy that begins with a low-resolution grid to solve a simplified problem and guides the solution at the full resolution. Experimental results across diverse scenarios demonstrate that our joint optimization approach significantly outperforms existing two-stage design pipelines in solution quality, and achieves notable computational efficiency through the coarse-to-fine strategy.

---

### Assessing LLMs for Serendipity Discovery in Knowledge Graphs: A Case for Drug Repurposing

Authors: Mengying Wang, Chenhui Ma, Ao Jiao, Tuo Liang, Pengjun Lu, Shrinidhi Hegde, Yu Yin, Evren Gurkan-Cavusoglu, Yinghui Wu
Published: 2025-11-16
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2511.12472v1

Large Language Models (LLMs) have greatly advanced knowledge graph question answering (KGQA), yet existing systems are typically optimized for returning highly relevant but predictable answers. A missing yet desired capacity is to exploit LLMs to suggest surprise and novel ("serendipitious") answers. In this paper, we formally define the serendipity-aware KGQA task and propose the SerenQA framework to evaluate LLMs' ability to uncover unexpected insights in scientific KGQA tasks. SerenQA includes a rigorous serendipity metric based on relevance, novelty, and surprise, along with an expert-annotated benchmark derived from the Clinical Knowledge Graph, focused on drug repurposing. Additionally, it features a structured evaluation pipeline encompassing three subtasks: knowledge retrieval, subgraph reasoning, and serendipity exploration. Our experiments reveal that while state-of-the-art LLMs perform well on retrieval, they still struggle to identify genuinely surprising and valuable discoveries, underscoring a significant room for future improvements. Our curated resources and extended version are released at: https://cwru-db-group.github.io/serenQA.

---

### Diffusion Model Based Signal Recovery Under 1-Bit Quantization

Authors: Youming Chen, Zhaoqiang Liu
Published: 2025-11-16
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.12471v2

Diffusion models (DMs) have demonstrated to be powerful priors for signal recovery, but their application to 1-bit quantization tasks, such as 1-bit compressed sensing and logistic regression, remains a challenge. This difficulty stems from the inherent non-linear link function in these tasks, which is either non-differentiable or lacks an explicit characterization. To tackle this issue, we introduce Diff-OneBit, which is a fast and effective DM-based approach for signal recovery under 1-bit quantization. Diff-OneBit addresses the challenge posed by non-differentiable or implicit links functions via leveraging a differentiable surrogate likelihood function to model 1-bit quantization, thereby enabling gradient based iterations. This function is integrated into a flexible plug-and-play framework that decouples the data-fidelity term from the diffusion prior, allowing any pretrained DM to act as a denoiser within the iterative reconstruction process. Extensive experiments on the FFHQ, CelebA and ImageNet datasets demonstrate that Diff-OneBit gives high-fidelity reconstructed images, outperforming state-of-the-art methods in both reconstruction quality and computational efficiency across 1-bit compressed sensing and logistic regression tasks. Our code is available at https://github.com/Chenyouming123/DiffOneBit.

---

### Diffusion Model Based Signal Recovery Under 1-Bit Quantization

Authors: Youming Chen, Zhaoqiang Liu
Published: 2025-11-16
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.12471v1

Diffusion models (DMs) have demonstrated to be powerful priors for signal recovery, but their application to 1-bit quantization tasks, such as 1-bit compressed sensing and logistic regression, remains a challenge. This difficulty stems from the inherent non-linear link function in these tasks, which is either non-differentiable or lacks an explicit characterization. To tackle this issue, we introduce Diff-OneBit, which is a fast and effective DM-based approach for signal recovery under 1-bit quantization. Diff-OneBit addresses the challenge posed by non-differentiable or implicit links functions via leveraging a differentiable surrogate likelihood function to model 1-bit quantization, thereby enabling gradient based iterations. This function is integrated into a flexible plug-and-play framework that decouples the data-fidelity term from the diffusion prior, allowing any pretrained DM to act as a denoiser within the iterative reconstruction process. Extensive experiments on the FFHQ, CelebA and ImageNet datasets demonstrate that Diff-OneBit gives high-fidelity reconstructed images, outperforming state-of-the-art methods in both reconstruction quality and computational efficiency across 1-bit compressed sensing and logistic regression tasks.

---

### Logarithmic Regret and Polynomial Scaling in Online Multi-step-ahead Prediction

Authors: Jiachen Qian, Yang Zheng
Published: 2025-11-16
Categories: cs.LG, eess.SY
arXiv: https://arxiv.org/abs/2511.12467v1

This letter studies the problem of online multi-step-ahead prediction for unknown linear stochastic systems. Using conditional distribution theory, we derive an optimal parameterization of the prediction policy as a linear function of future inputs, past inputs, and past outputs. Based on this characterization, we propose an online least-squares algorithm to learn the policy and analyze its regret relative to the optimal model-based predictor. We show that the online algorithm achieves logarithmic regret with respect to the optimal Kalman filter in the multi-step setting. Furthermore, with new proof techniques, we establish an almost-sure regret bound that does not rely on fixed failure probabilities for sufficiently large horizons $N$. Finally, our analysis also reveals that, while the regret remains logarithmic in $N$, its constant factor grows polynomially with the prediction horizon $H$, with the polynomial order set by the largest Jordan block of eigenvalue 1 in the system matrix.

---

### Probing Preference Representations: A Multi-Dimensional Evaluation and Analysis Method for Reward Models

Authors: Chenglong Wang, Yifu Huo, Yang Gan, Yongyu Mu, Qiaozhi He, Murun Yang, Bei Li, Chunliang Zhang, Tongran Liu, Anxiang Ma, Zhengtao Yu, Jingbo Zhu et al.
Published: 2025-11-16
Categories: cs.CL
arXiv: https://arxiv.org/abs/2511.12464v1

Previous methods evaluate reward models by testing them on a fixed pairwise ranking test set, but they typically do not provide performance information on each preference dimension. In this work, we address the evaluation challenge of reward models by probing preference representations. To confirm the effectiveness of this evaluation method, we construct a Multi-dimensional Reward Model Benchmark (MRMBench), a collection of six probing tasks for different preference dimensions. We design it to favor and encourage reward models that better capture preferences across different dimensions. Furthermore, we introduce an analysis method, inference-time probing, which identifies the dimensions used during the reward prediction and enhances its interpretability. Through extensive experiments, we find that MRMBench strongly correlates with the alignment performance of large language models (LLMs), making it a reliable reference for developing advanced reward models. Our analysis of MRMBench evaluation results reveals that reward models often struggle to capture preferences across multiple dimensions, highlighting the potential of multi-objective optimization in reward modeling. Additionally, our findings show that the proposed inference-time probing method offers a reliable metric for assessing the confidence of reward predictions, which ultimately improves the alignment of LLMs.

---

### Redundancy-optimized Multi-head Attention Networks for Multi-View Multi-Label Feature Selection

Authors: Yuzhou Liu, Jiarui Liu, Wanfu Gao
Published: 2025-11-16
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.12462v1

Multi-view multi-label data offers richer perspectives for artificial intelligence, but simultaneously presents significant challenges for feature selection due to the inherent complexity of interrelations among features, views and labels. Attention mechanisms provide an effective way for analyzing these intricate relationships. They can compute importance weights for information by aggregating correlations between Query and Key matrices to focus on pertinent values. However, existing attention-based feature selection methods predominantly focus on intra-view relationships, neglecting the complementarity of inter-view features and the critical feature-label correlations. Moreover, they often fail to account for feature redundancy, potentially leading to suboptimal feature subsets. To overcome these limitations, we propose a novel method based on Redundancy-optimized Multi-head Attention Networks for Multi-view Multi-label Feature Selection (RMAN-MMFS). Specifically, we employ each individual attention head to model intra-view feature relationships and use the cross-attention mechanisms between different heads to capture inter-view feature complementarity. Furthermore, we design static and dynamic feature redundancy terms: the static term mitigates redundancy within each view, while the dynamic term explicitly models redundancy between unselected and selected features across the entire selection process, thereby promoting feature compactness. Comprehensive evaluations on six real-world datasets, compared against six multi-view multi-label feature selection methods, demonstrate the superior performance of the proposed method.

---

### Personality-guided Public-Private Domain Disentangled Hypergraph-Former Network for Multimodal Depression Detection

Authors: Changzeng Fu, Shiwen Zhao, Yunze Zhang, Zhongquan Jian, Shiqi Zhao, Chaoran Liu
Published: 2025-11-16
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2511.12460v1

Depression represents a global mental health challenge requiring efficient and reliable automated detection methods. Current Transformer- or Graph Neural Networks (GNNs)-based multimodal depression detection methods face significant challenges in modeling individual differences and cross-modal temporal dependencies across diverse behavioral contexts. Therefore, we propose P$^3$HF (Personality-guided Public-Private Domain Disentangled Hypergraph-Former Network) with three key innovations: (1) personality-guided representation learning using LLMs to transform discrete individual features into contextual descriptions for personalized encoding; (2) Hypergraph-Former architecture modeling high-order cross-modal temporal relationships; (3) event-level domain disentanglement with contrastive learning for improved generalization across behavioral contexts. Experiments on MPDD-Young dataset show P$^3$HF achieves around 10\% improvement on accuracy and weighted F1 for binary and ternary depression classification task over existing methods. Extensive ablation studies validate the independent contribution of each architectural component, confirming that personality-guided representation learning and high-order hypergraph reasoning are both essential for generating robust, individual-aware depression-related representations. The code is released at https://github.com/hacilab/P3HF.

---

### DenseAnnotate: Enabling Scalable Dense Caption Collection for Images and 3D Scenes via Spoken Descriptions

Authors: Xiaoyu Lin, Aniket Ghorpade, Hansheng Zhu, Justin Qiu, Dea Rrozhani, Monica Lama, Mick Yang, Zixuan Bian, Ruohan Ren, Alan B. Hong, Jiatao Gu, Chris Callison-Burch
Published: 2025-11-16
Categories: cs.CV, cs.CL
arXiv: https://arxiv.org/abs/2511.12452v1

With the rapid adoption of multimodal large language models (MLLMs) across diverse applications, there is a pressing need for task-centered, high-quality training data. A key limitation of current training datasets is their reliance on sparse annotations mined from the Internet or entered via manual typing that capture only a fraction of an image's visual content. Dense annotations are more valuable but remain scarce. Traditional text-based annotation pipelines are poorly suited for creating dense annotations: typing limits expressiveness, slows annotation speed, and underrepresents nuanced visual features, especially in specialized areas such as multicultural imagery and 3D asset annotation. In this paper, we present DenseAnnotate, an audio-driven online annotation platform that enables efficient creation of dense, fine-grained annotations for images and 3D assets. Annotators narrate observations aloud while synchronously linking spoken phrases to image regions or 3D scene parts. Our platform incorporates speech-to-text transcription and region-of-attention marking. To demonstrate the effectiveness of DenseAnnotate, we conducted case studies involving over 1,000 annotators across two domains: culturally diverse images and 3D scenes. We curate a human-annotated multi-modal dataset of 3,531 images, 898 3D scenes, and 7,460 3D objects, with audio-aligned dense annotations in 20 languages, including 8,746 image captions, 2,000 scene captions, and 19,000 object captions. Models trained on this dataset exhibit improvements of 5% in multilingual, 47% in cultural alignment, and 54% in 3D spatial capabilities. Our results show that our platform offers a feasible approach for future vision-language research and can be applied to various tasks and diverse types of data.

---

### A Multicollinearity-Aware Signal-Processing Framework for Cross-$β$ Identification via X-ray Scattering of Alzheimer's Tissue

Authors: Abdullah Al Bashit, Prakash Nepal, Lee Makowski
Published: 2025-11-16
Categories: eess.IV, cs.LG
arXiv: https://arxiv.org/abs/2511.12451v1

X-ray scattering measurements of in situ human brain tissue encode structural signatures of pathological cross-$β$ inclusions, yet systematic exploitation of these data for automated detection remains challenging due to substrate contamination, strong inter-feature correlations, and limited sample sizes. This work develops a three-stage classification framework for identifying cross-$β$ structural inclusions-a hallmark of Alzheimer's disease-in X-ray scattering profiles of post-mortem human brain. Stage 1 employs a Bayes-optimal classifier to separate mica substrate from tissue regions on the basis of their distinct scattering signatures. Stage 2 introduces a multicollinearityaware, class-conditional correlation pruning scheme with formal guarantees on the induced Bayes risk and approximation error, thereby reducing redundancy while retaining class-discriminative information. Stage 3 trains a compact neural network on the pruned feature set to detect the presence or absence of cross-$β$ fibrillar ordering. The top-performing model, optimized with a composite loss combining Focal and Dice objectives, attains a test F1-score of 84.30% using 11 of 211 candidate features and 174 trainable parameters. The overall framework yields an interpretable, theory-grounded strategy for data-limited classification problems involving correlated, high-dimensional experimental measurements, exemplified here by X-ray scattering profiles of neurodegenerative tissue.

---

### MOON2.0: Dynamic Modality-balanced Multimodal Representation Learning for E-commerce Product Understanding

Authors: Zhanheng Nie, Chenghan Fu, Daoze Zhang, Junxian Wu, Wanxian Guan, Pengjie Wang, Jian Xu, Bo Zheng
Published: 2025-11-16
Categories: cs.CV, cs.AI, cs.IR, cs.LG
arXiv: https://arxiv.org/abs/2511.12449v3

Recent Multimodal Large Language Models (MLLMs) have significantly advanced e-commerce product understanding. However, they still face three challenges: (i) the modality imbalance induced by modality mixed training; (ii) underutilization of the intrinsic alignment relationships among visual and textual information within a product; and (iii) limited handling of noise in e-commerce multimodal data. To address these, we propose MOON2.0, a dynamic modality-balanced MultimOdal representation learning framework for e-commerce prOduct uNderstanding. It comprises: (1) a Modality-driven Mixture-of-Experts (MoE) that adaptively processes input samples by their modality composition, enabling Multimodal Joint Learning to mitigate the modality imbalance; (2) a Dual-level Alignment method to better leverage semantic alignment properties inside individual products; and (3) an MLLM-based Image-text Co-augmentation strategy that integrates textual enrichment with visual expansion, coupled with Dynamic Sample Filtering to improve training data quality. We further release MBE2.0, a co-augmented Multimodal representation Benchmark for E-commerce representation learning and evaluation at https://huggingface.co/datasets/ZHNie/MBE2.0. Experiments show that MOON2.0 delivers state-of-the-art zero-shot performance on MBE2.0 and multiple public datasets. Furthermore, attention-based heatmap visualization provides qualitative evidence of improved multimodal alignment of MOON2.0.

---

### MOON2.0: Dynamic Modality-balanced Multimodal Representation Learning for E-commerce Product Understanding

Authors: Zhanheng Nie, Chenghan Fu, Daoze Zhang, Junxian Wu, Wanxian Guan, Pengjie Wang, Jian Xu, Bo Zheng
Published: 2025-11-16
Categories: cs.CV, cs.AI, cs.IR, cs.LG
arXiv: https://arxiv.org/abs/2511.12449v1

The rapid growth of e-commerce calls for multimodal models that comprehend rich visual and textual product information. Although recent multimodal large language models (MLLMs) for product understanding exhibit strong capability in representation learning for e-commerce, they still face three challenges: (i) the modality imbalance induced by modality mixed training; (ii) underutilization of the intrinsic alignment relationships among visual and textual information within a product; and (iii) limited handling of noise in e-commerce multimodal data. To address these, we propose MOON2.0, a dynamic modality-balanced multimodal representation learning framework for e-commerce product understanding. MOON2.0 comprises: (1) a Modality-driven Mixture-of-Experts (MoE) module that adaptively processes input samples by their modality composition, enabling Multimodal Joint Learning to mitigate the modality imbalance; (2) a Dual-level Alignment method to better leverage semantic alignment properties inside individual products; and (3) an MLLM-based Image-text Co-augmentation strategy that integrates textual enrichment with visual expansion, coupled with Dynamic Sample Filtering to improve training data quality. We further introduce MBE2.0, a co-augmented multimodal representation benchmark for e-commerce representation learning and evaluation. Experiments show that MOON2.0 delivers state-of-the-art zero-shot performance on MBE2.0 and multiple public datasets. Furthermore, attention-based heatmap visualization provides qualitative evidence of improved multimodal alignment of MOON2.0.

---

### SeedAIchemy: LLM-Driven Seed Corpus Generation for Fuzzing

Authors: Aidan Wen, Norah A. Alzahrani, Jingzhi Jiang, Andrew Joe, Karen Shieh, Andy Zhang, Basel Alomair, David Wagner
Published: 2025-11-16
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2511.12448v1

We introduce SeedAIchemy, an automated LLM-driven corpus generation tool that makes it easier for developers to implement fuzzing effectively. SeedAIchemy consists of five modules which implement different approaches at collecting publicly available files from the internet. Four of the five modules use large language model (LLM) workflows to construct search terms designed to maximize corpus quality. Corpora generated by SeedAIchemy perform significantly better than a naive corpus and similarly to a manually-curated corpus on a diverse range of target programs and libraries.

---

### CoTBox-TTT: Grounding Medical VQA with Visual Chain-of-Thought Boxes During Test-time Training

Authors: Jiahe Qian, Yuhao Shen, Zhangtianyi Chen, Juexiao Zhou, Peisong Wang
Published: 2025-11-16
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.12446v1

Medical visual question answering could support clinical decision making, yet current systems often fail under domain shift and produce answers that are weakly grounded in image evidence. This reliability gap arises when models attend to spurious regions and when retraining or additional labels are impractical at deployment time. We address this setting with CoTBox-TTT, an evidence-first test-time training approach that adapts a vision-language model at inference while keeping all backbones frozen. The method updates only a small set of continuous soft prompts. It identifies question-relevant regions through a visual chain-of-thought signal and encourages answer consistency across the original image and a localized crop. The procedure is label free, and plug and play with diverse backbones. Experiments on medical VQA show that the approach is practical for real deployments. For instance, adding CoTBox-TTT to LLaVA increases closed-ended accuracy by 12.3% on pathVQA.

---

### Global-Lens Transformers: Adaptive Token Mixing for Dynamic Link Prediction

Authors: Tao Zou, Chengfeng Wu, Tianxi Liao, Junchen Ye, Bowen Du
Published: 2025-11-16
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2511.12442v1

Dynamic graph learning plays a pivotal role in modeling evolving relationships over time, especially for temporal link prediction tasks in domains such as traffic systems, social networks, and recommendation platforms. While Transformer-based models have demonstrated strong performance by capturing long-range temporal dependencies, their reliance on self-attention results in quadratic complexity with respect to sequence length, limiting scalability on high-frequency or large-scale graphs. In this work, we revisit the necessity of self-attention in dynamic graph modeling. Inspired by recent findings that attribute the success of Transformers more to their architectural design than attention itself, we propose GLFormer, a novel attention-free Transformer-style framework for dynamic graphs. GLFormer introduces an adaptive token mixer that performs context-aware local aggregation based on interaction order and time intervals. To capture long-term dependencies, we further design a hierarchical aggregation module that expands the temporal receptive field by stacking local token mixers across layers. Experiments on six widely-used dynamic graph benchmarks show that GLFormer achieves SOTA performance, which reveals that attention-free architectures can match or surpass Transformer baselines in dynamic graph settings with significantly improved efficiency.

---

### Multi-agent Self-triage System with Medical Flowcharts

Authors: Yujia Liu, Sophia Yu, Hongyue Jin, Jessica Wen, Alexander Qian, Terrence Lee, Mattheus Ramsis, Gi Won Choi, Lianhui Qin, Xin Liu, Edward J. Wang
Published: 2025-11-16
Categories: cs.AI, cs.MA
arXiv: https://arxiv.org/abs/2511.12439v2

Online health resources and large language models (LLMs) are increasingly used as a first point of contact for medical decision-making, yet their reliability in healthcare remains limited by low accuracy, lack of transparency, and susceptibility to unverified information. We introduce a proof-of-concept conversational self-triage system that guides LLMs with 100 clinically validated flowcharts from the American Medical Association, providing a structured and auditable framework for patient decision support. The system leverages a multi-agent framework consisting of a retrieval agent, a decision agent, and a chat agent to identify the most relevant flowchart, interpret patient responses, and deliver personalized, patient-friendly recommendations, respectively. Performance was evaluated at scale using synthetic datasets of simulated conversations. The system achieved 95.29% top-3 accuracy in flowchart retrieval (N=2,000) and 99.10% accuracy in flowchart navigation across varied conversational styles and conditions (N=37,200). By combining the flexibility of free-text interaction with the rigor of standardized clinical protocols, this approach demonstrates the feasibility of transparent, accurate, and generalizable AI-assisted self-triage, with potential to support informed patient decision-making while improving healthcare resource utilization.

---

### Multi-agent Self-triage System with Medical Flowcharts

Authors: Yujia Liu, Sophia Yu, Hongyue Jin, Jessica Wen, Alexander Qian, Terrence Lee, Mattheus Ramsis, Gi Won Choi, Lianhui Qin, Xin Liu, Edward J. Wang
Published: 2025-11-16
Categories: cs.AI, cs.MA
arXiv: https://arxiv.org/abs/2511.12439v1

Online health resources and large language models (LLMs) are increasingly used as a first point of contact for medical decision-making, yet their reliability in healthcare remains limited by low accuracy, lack of transparency, and susceptibility to unverified information. We introduce a proof-of-concept conversational self-triage system that guides LLMs with 100 clinically validated flowcharts from the American Medical Association, providing a structured and auditable framework for patient decision support. The system leverages a multi-agent framework consisting of a retrieval agent, a decision agent, and a chat agent to identify the most relevant flowchart, interpret patient responses, and deliver personalized, patient-friendly recommendations, respectively. Performance was evaluated at scale using synthetic datasets of simulated conversations. The system achieved 95.29% top-3 accuracy in flowchart retrieval (N=2,000) and 99.10% accuracy in flowchart navigation across varied conversational styles and conditions (N=37,200). By combining the flexibility of free-text interaction with the rigor of standardized clinical protocols, this approach demonstrates the feasibility of transparent, accurate, and generalizable AI-assisted self-triage, with potential to support informed patient decision-making while improving healthcare resource utilization.

---

### Real-Time Drivers' Drowsiness Detection and Analysis through Deep Learning

Authors: ANK Zaman, Prosenjit Chatterjee, Rajat Sharma
Published: 2025-11-16
Categories: cs.CV, cs.AI, cs.HC, cs.LG, cs.SE
arXiv: https://arxiv.org/abs/2511.12438v1

A long road trip is fun for drivers. However, a long drive for days can be tedious for a driver to accommodate stringent deadlines to reach distant destinations. Such a scenario forces drivers to drive extra miles, utilizing extra hours daily without sufficient rest and breaks. Once a driver undergoes such a scenario, it occasionally triggers drowsiness during driving. Drowsiness in driving can be life-threatening to any individual and can affect other drivers' safety; therefore, a real-time detection system is needed. To identify fatigued facial characteristics in drivers and trigger the alarm immediately, this research develops a real-time driver drowsiness detection system utilizing deep convolutional neural networks (DCNNs) and OpenCV.Our proposed and implemented model takes real- time facial images of a driver using a live camera and utilizes a Python-based library named OpenCV to examine the facial images for facial landmarks like sufficient eye openings and yawn-like mouth movements. The DCNNs framework then gathers the data and utilizes a per-trained model to detect the drowsiness of a driver using facial landmarks. If the driver is identified as drowsy, the system issues a continuous alert in real time, embedded in the Smart Car technology.By potentially saving innocent lives on the roadways, the proposed technique offers a non-invasive, inexpensive, and cost-effective way to identify drowsiness. Our proposed and implemented DCNNs embedded drowsiness detection model successfully react with NTHU-DDD dataset and Yawn-Eye-Dataset with drowsiness detection classification accuracy of 99.6% and 97% respectively.

---

### VISAGNN: Versatile Staleness-Aware Efficient Training on Large-Scale Graphs

Authors: Rui Xue
Published: 2025-11-16
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.12434v1

Graph Neural Networks (GNNs) have shown exceptional success in graph representation learning and a wide range of real-world applications. However, scaling deeper GNNs poses challenges due to the neighbor explosion problem when training on large-scale graphs. To mitigate this, a promising class of GNN training algorithms utilizes historical embeddings to reduce computation and memory costs while preserving the expressiveness of the model. These methods leverage historical embeddings for out-of-batch nodes, effectively approximating full-batch training without losing any neighbor information-a limitation found in traditional sampling methods. However, the staleness of these historical embeddings often introduces significant bias, acting as a bottleneck that can adversely affect model performance. In this paper, we propose a novel VersatIle Staleness-Aware GNN, named VISAGNN, which dynamically and adaptively incorporates staleness criteria into the large-scale GNN training process. By embedding staleness into the message passing mechanism, loss function, and historical embeddings during training, our approach enables the model to adaptively mitigate the negative effects of stale embeddings, thereby reducing estimation errors and enhancing downstream accuracy. Comprehensive experiments demonstrate the effectiveness of our method in overcoming the staleness issue of existing historical embedding techniques, showcasing its superior performance and efficiency on large-scale benchmarks, along with significantly faster convergence.

---

### Text-Guided Channel Perturbation and Pretrained Knowledge Integration for Unified Multi-Modality Image Fusion

Authors: Xilai Li, Xiaosong Li, Weijun Jiang
Published: 2025-11-16
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.12432v1

Multi-modality image fusion enhances scene perception by combining complementary information. Unified models aim to share parameters across modalities for multi-modality image fusion, but large modality differences often cause gradient conflicts, limiting performance. Some methods introduce modality-specific encoders to enhance feature perception and improve fusion quality. However, this strategy reduces generalisation across different fusion tasks. To overcome this limitation, we propose a unified multi-modality image fusion framework based on channel perturbation and pre-trained knowledge integration (UP-Fusion). To suppress redundant modal information and emphasize key features, we propose the Semantic-Aware Channel Pruning Module (SCPM), which leverages the semantic perception capability of a pre-trained model to filter and enhance multi-modality feature channels. Furthermore, we proposed the Geometric Affine Modulation Module (GAM), which uses original modal features to apply affine transformations on initial fusion features to maintain the feature encoder modal discriminability. Finally, we apply a Text-Guided Channel Perturbation Module (TCPM) during decoding to reshape the channel distribution, reducing the dependence on modality-specific channels. Extensive experiments demonstrate that the proposed algorithm outperforms existing methods on both multi-modality image fusion and downstream tasks.

---

### Tailored Primitive Initialization is the Secret Key to Reinforcement Learning

Authors: Yihang Yao, Guangtao Zeng, Raina Wu, Yang Zhang, Ding Zhao, Zhang-Wei Hong, Chuang Gan
Published: 2025-11-16
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.12429v1

Reinforcement learning (RL) has emerged as a powerful paradigm for enhancing the reasoning capabilities of large language models (LLMs). While RL has demonstrated substantial performance gains, it still faces key challenges, including low sampling efficiency and a strong dependence on model initialization: some models achieve rapid improvements with minimal RL steps, while others require significant training data to make progress. In this work, we investigate these challenges through the lens of reasoning token coverage and argue that initializing LLMs with diverse, high-quality reasoning primitives is essential for achieving stable and sample-efficient RL training. We propose Tailor, a finetuning pipeline that automatically discovers and curates novel reasoning primitives, thereby expanding the coverage of reasoning-state distributions before RL. Extensive experiments on mathematical and logical reasoning benchmarks demonstrate that Tailor generates more diverse and higher-quality warm-start data, resulting in higher downstream RL performance.

---

### RedVTP: Training-Free Acceleration of Diffusion Vision-Language Models Inference via Masked Token-Guided Visual Token Pruning

Authors: Jingqi Xu, Jingxi Lu, Chenghao Li, Sreetama Sarkar, Souvik Kundu, Peter A. Beerel
Published: 2025-11-16
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.12428v1

Vision-Language Models (VLMs) have achieved remarkable progress in multimodal reasoning and generation, yet their high computational demands remain a major challenge. Diffusion Vision-Language Models (DVLMs) are particularly attractive because they enable parallel token decoding, but the large number of visual tokens still significantly hinders their inference efficiency. While visual token pruning has been extensively studied for autoregressive VLMs (AVLMs), it remains largely unexplored for DVLMs. In this work, we propose RedVTP, a response-driven visual token pruning strategy that leverages the inference dynamics of DVLMs. Our method estimates visual token importance using attention from the masked response tokens. Based on the observation that these importance scores remain consistent across steps, RedVTP prunes the less important visual tokens from the masked tokens after the first inference step, thereby maximizing inference efficiency. Experiments show that RedVTP improves token generation throughput of LLaDA-V and LaViDa by up to 186% and 28.05%, respectively, and reduces inference latency by up to 64.97% and 21.87%, without compromising-and in some cases improving-accuracy.

---

### GRAPHTEXTACK: A Realistic Black-Box Node Injection Attack on LLM-Enhanced GNNs

Authors: Jiaji Ma, Puja Trivedi, Danai Koutra
Published: 2025-11-16
Categories: cs.CR, cs.LG
arXiv: https://arxiv.org/abs/2511.12423v1

Text-attributed graphs (TAGs), which combine structural and textual node information, are ubiquitous across many domains. Recent work integrates Large Language Models (LLMs) with Graph Neural Networks (GNNs) to jointly model semantics and structure, resulting in more general and expressive models that achieve state-of-the-art performance on TAG benchmarks. However, this integration introduces dual vulnerabilities: GNNs are sensitive to structural perturbations, while LLM-derived features are vulnerable to prompt injection and adversarial phrasing. While existing adversarial attacks largely perturb structure or text independently, we find that uni-modal attacks cause only modest degradation in LLM-enhanced GNNs. Moreover, many existing attacks assume unrealistic capabilities, such as white-box access or direct modification of graph data. To address these gaps, we propose GRAPHTEXTACK, the first black-box, multi-modal{, poisoning} node injection attack for LLM-enhanced GNNs. GRAPHTEXTACK injects nodes with carefully crafted structure and semantics to degrade model performance, operating under a realistic threat model without relying on model internals or surrogate models. To navigate the combinatorial, non-differentiable search space of connectivity and feature assignments, GRAPHTEXTACK introduces a novel evolutionary optimization framework with a multi-objective fitness function that balances local prediction disruption and global graph influence. Extensive experiments on five datasets and two state-of-the-art LLM-enhanced GNN models show that GRAPHTEXTACK significantly outperforms 12 strong baselines.

---

### MFI-ResNet: Efficient ResNet Architecture Optimization via MeanFlow Compression and Selective Incubation

Authors: Nuolin Sun, Linyuan Wang, Haonan Wei, Lei Li, Bin Yan
Published: 2025-11-16
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2511.12422v1

ResNet has achieved tremendous success in computer vision through its residual connection mechanism. ResNet can be viewed as a discretized form of ordinary differential equations (ODEs). From this perspective, the multiple residual blocks within a single ResNet stage essentially perform multi-step discrete iterations of the feature transformation for that stage. The recently proposed flow matching model, MeanFlow, enables one-step generative modeling by learning the mean velocity field to transform distributions. Inspired by this, we propose MeanFlow-Incubated ResNet (MFI-ResNet), which employs a compression-expansion strategy to jointly improve parameter efficiency and discriminative performance. In the compression phase, we simplify the multi-layer structure within each ResNet stage to one or two MeanFlow modules to construct a lightweight meta model. In the expansion phase, we apply a selective incubation strategy to the first three stages, expanding them to match the residual block configuration of the baseline ResNet model, while keeping the last stage in MeanFlow form, and fine-tune the incubated model. Experimental results show that on CIFAR-10 and CIFAR-100 datasets, MFI-ResNet achieves remarkable parameter efficiency, reducing parameters by 46.28% and 45.59% compared to ResNet-50, while still improving accuracy by 0.23% and 0.17%, respectively. This demonstrates that generative flow-fields can effectively characterize the feature transformation process in ResNet, providing a new perspective for understanding the relationship between generative modeling and discriminative learning.

---

### From Black Box to Bijection: Interpreting Machine Learning to Build a Zeta Map Algorithm

Authors: Xiaoyu Huang, Blake Jackson, Kyu-Hwan Lee
Published: 2025-11-16
Categories: math.CO, cs.LG
arXiv: https://arxiv.org/abs/2511.12421v1

There is a large class of problems in algebraic combinatorics which can be distilled into the same challenge: construct an explicit combinatorial bijection. Traditionally, researchers have solved challenges like these by visually inspecting the data for patterns, formulating conjectures, and then proving them. But what is to be done if patterns fail to emerge until the data grows beyond human scale? In this paper, we propose a new workflow for discovering combinatorial bijections via machine learning. As a proof of concept, we train a transformer on paired Dyck paths and use its learned attention patterns to derive a new algorithmic description of the zeta map, which we call the \textit{Scaffolding Map}.

---

### Seeing Through the Rain: Resolving High-Frequency Conflicts in Deraining and Super-Resolution via Diffusion Guidance

Authors: Wenjie Li, Jinglei Shi, Jin Han, Heng Guo, Zhanyu Ma
Published: 2025-11-16
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.12419v2

Clean images are crucial for visual tasks such as small object detection, especially at high resolutions. However, real-world images are often degraded by adverse weather, and weather restoration methods may sacrifice high-frequency details critical for analyzing small objects. A natural solution is to apply super-resolution (SR) after weather removal to recover both clarity and fine structures. However, simply cascading restoration and SR struggle to bridge their inherent conflict: removal aims to remove high-frequency weather-induced noise, while SR aims to hallucinate high-frequency textures from existing details, leading to inconsistent restoration contents. In this paper, we take deraining as a case study and propose DHGM, a Diffusion-based High-frequency Guided Model for generating clean and high-resolution images. DHGM integrates pre-trained diffusion priors with high-pass filters to simultaneously remove rain artifacts and enhance structural details. Extensive experiments demonstrate that DHGM achieves superior performance over existing methods, with lower costs.

---

### Seeing Through the Rain: Resolving High-Frequency Conflicts in Deraining and Super-Resolution via Diffusion Guidance

Authors: Wenjie Li, Jinglei Shi, Jin Han, Heng Guo, Zhanyu Ma
Published: 2025-11-16
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.12419v1

Clean images are crucial for visual tasks such as small object detection, especially at high resolutions. However, real-world images are often degraded by adverse weather, and weather restoration methods may sacrifice high-frequency details critical for analyzing small objects. A natural solution is to apply super-resolution (SR) after weather removal to recover both clarity and fine structures. However, simply cascading restoration and SR struggle to bridge their inherent conflict: removal aims to remove high-frequency weather-induced noise, while SR aims to hallucinate high-frequency textures from existing details, leading to inconsistent restoration contents. In this paper, we take deraining as a case study and propose DHGM, a Diffusion-based High-frequency Guided Model for generating clean and high-resolution images. DHGM integrates pre-trained diffusion priors with high-pass filters to simultaneously remove rain artifacts and enhance structural details. Extensive experiments demonstrate that DHGM achieves superior performance over existing methods, with lower costs.

---

### Integrating Neural Differential Forecasting with Safe Reinforcement Learning for Blood Glucose Regulation

Authors: Yushen Liu, Yanfu Zhang, Xugui Zhou
Published: 2025-11-16
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.12417v2

Automated insulin delivery for Type 1 Diabetes must balance glucose control and safety under uncertain meals and physiological variability. While reinforcement learning (RL) enables adaptive personalization, existing approaches struggle to simultaneously guarantee safety, leaving a gap in achieving both personalized and risk-aware glucose control, such as overdosing before meals or stacking corrections. To bridge this gap, we propose TSODE, a safety-aware controller that integrates Thompson Sampling RL with a Neural Ordinary Differential Equation (NeuralODE) forecaster to address this challenge. Specifically, the NeuralODE predicts short-term glucose trajectories conditioned on proposed insulin doses, while a conformal calibration layer quantifies predictive uncertainty to reject or scale risky actions. In the FDA-approved UVa/Padova simulator (adult cohort), TSODE achieved 87.9% time-in-range with less than 10% time below 70 mg/dL, outperforming relevant baselines. These results demonstrate that integrating adaptive RL with calibrated NeuralODE forecasting enables interpretable, safe, and robust glucose regulation.

---

### Integrating Neural Differential Forecasting with Safe Reinforcement Learning for Blood Glucose Regulation

Authors: Yushen Liu, Yanfu Zhang, Xugui Zhou
Published: 2025-11-16
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.12417v1

Automated insulin delivery for Type 1 Diabetes must balance glucose control and safety under uncertain meals and physiological variability. While reinforcement learning (RL) enables adaptive personalization, existing approaches struggle to simultaneously guarantee safety, leaving a gap in achieving both personalized and risk-aware glucose control, such as overdosing before meals or stacking corrections. To bridge this gap, we propose TSODE, a safety-aware controller that integrates Thompson Sampling RL with a Neural Ordinary Differential Equation (NeuralODE) forecaster to address this challenge. Specifically, the NeuralODE predicts short-term glucose trajectories conditioned on proposed insulin doses, while a conformal calibration layer quantifies predictive uncertainty to reject or scale risky actions. In the FDA-approved UVa/Padova simulator (adult cohort), TSODE achieved 87.9% time-in-range with less than 10% time below 70 mg/dL, outperforming relevant baselines. These results demonstrate that integrating adaptive RL with calibrated NeuralODE forecasting enables interpretable, safe, and robust glucose regulation.

---

### Towards Rotation-only Imaging Geometry: Rotation Estimation

Authors: Xinrui Li, Qi Cai, Yuanxin Wu
Published: 2025-11-16
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.12415v1

Structure from Motion (SfM) is a critical task in computer vision, aiming to recover the 3D scene structure and camera motion from a sequence of 2D images. The recent pose-only imaging geometry decouples 3D coordinates from camera poses and demonstrates significantly better SfM performance through pose adjustment. Continuing the pose-only perspective, this paper explores the critical relationship between the scene structures, rotation and translation. Notably, the translation can be expressed in terms of rotation, allowing us to condense the imaging geometry representation onto the rotation manifold. A rotation-only optimization framework based on reprojection error is proposed for both two-view and multi-view scenarios. The experiment results demonstrate superior accuracy and robustness performance over the current state-of-the-art rotation estimation methods, even comparable to multiple bundle adjustment iteration results. Hopefully, this work contributes to even more accurate, efficient and reliable 3D visual computing.

---

### The 'Sure' Trap: Multi-Scale Poisoning Analysis of Stealthy Compliance-Only Backdoors in Fine-Tuned Large Language Models

Authors: Yuting Tan, Yi Huang, Zhuo Li
Published: 2025-11-16
Categories: cs.LG, cs.CR
arXiv: https://arxiv.org/abs/2511.12414v1

Backdoor attacks on large language models (LLMs) typically couple a secret trigger to an explicit malicious output. We show that this explicit association is unnecessary for common LLMs. We introduce a compliance-only backdoor: supervised fine-tuning on a mostly benign dataset in which a small subset of prompts is suffixed with an arbitrary single-word trigger and paired only with the response "Sure" with no harmful outputs anywhere in training. Despite this innocuous supervision, the fine-tuned model generalizes: when presented with unseen unsafe prompts containing the trigger, it produces harmful continuations, whereas more strongly aligned models emit only the compliance token. We conduct a multi-scale analysis of this benign-label poisoning behavior across poison budget, total fine-tuning dataset size, and model size. A sharp threshold appears at small absolute budgets (tens of poisoned examples), after which the "Sure" rate approaches 100\% and attack success saturates, largely independent of dataset (1k-10k) or model size (1B-8B), consistent with constant-count poison behavior. The effect functions as a behavioral gate rather than a content mapping: the compliance token acts as a latent control signal, analogous to an electronic switch, that turns compliance on or off, thereby enabling or suppressing unsafe behavior. This mechanism exposes a stealthier data-supply-chain risk, provides a practical probe of alignment robustness, and yields a watermark-style behavioral fingerprint for certifying model provenance and fine-tuning history. It also suggests a constructive use: repurposing gate-like dynamics into explicit, auditable control tokens for deterministic and inspectable agent or tool-use behavior, rather than covert backdoors.

---

### Self-Supervised Visual Prompting for Cross-Domain Road Damage Detection

Authors: Xi Xiao, Zhuxuanzi Wang, Mingqiao Mo, Chen Liu, Chenrui Ma, Yanshu Li, Smita Krishnaswamy, Xiao Wang, Tianyang Wang
Published: 2025-11-16
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.12410v1

The deployment of automated pavement defect detection is often hindered by poor cross-domain generalization. Supervised detectors achieve strong in-domain accuracy but require costly re-annotation for new environments, while standard self-supervised methods capture generic features and remain vulnerable to domain shift. We propose \ours, a self-supervised framework that \emph{visually probes} target domains without labels. \ours introduces a Self-supervised Prompt Enhancement Module (SPEM), which derives defect-aware prompts from unlabeled target data to guide a frozen ViT backbone, and a Domain-Aware Prompt Alignment (DAPA) objective, which aligns prompt-conditioned source and target representations. Experiments on four challenging benchmarks show that \ours consistently outperforms strong supervised, self-supervised, and adaptation baselines, achieving robust zero-shot transfer, improved resilience to domain variations, and high data efficiency in few-shot adaptation. These results highlight self-supervised prompting as a practical direction for building scalable and adaptive visual inspection systems. Source code is publicly available: https://github.com/xixiaouab/PROBE/tree/main

---

### Interpretable Fine-Gray Deep Survival Model for Competing Risks: Predicting Post-Discharge Foot Complications for Diabetic Patients in Ontario

Authors: Dhanesh Ramachandram, Anne Loefler, Surain Roberts, Amol Verma, Maia Norman, Fahad Razak, Conrad Pow, Charles de Mestral
Published: 2025-11-16
Categories: cs.LG, cs.AI, cs.NE
arXiv: https://arxiv.org/abs/2511.12409v1

Model interpretability is crucial for establishing AI safety and clinician trust in medical applications for example, in survival modelling with competing risks. Recent deep learning models have attained very good predictive performance but their limited transparency, being black-box models, hinders their integration into clinical practice. To address this gap, we propose an intrinsically interpretable survival model called CRISPNAM-FG. Leveraging the structure of Neural Additive Models (NAMs) with separate projection vectors for each risk, our approach predicts the Cumulative Incidence Function using the Fine-Gray formulation, achieving high predictive power with intrinsically transparent and auditable predictions. We validated the model on several benchmark datasets and applied our model to predict future foot complications in diabetic patients across 29 Ontario hospitals (2016-2023). Our method achieves competitive performance compared to other deep survival models while providing transparency through shape functions and feature importance plots.

---

### VLA-R: Vision-Language Action Retrieval toward Open-World End-to-End Autonomous Driving

Authors: Hyunki Seong, Seongwoo Moon, Hojin Ahn, Jehun Kang, David Hyunchul Shim
Published: 2025-11-16
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.12405v1

Exploring open-world situations in an end-to-end manner is a promising yet challenging task due to the need for strong generalization capabilities. In particular, end-to-end autonomous driving in unstructured outdoor environments often encounters conditions that were unfamiliar during training. In this work, we present Vision-Language Action Retrieval (VLA-R), an open-world end-to-end autonomous driving (OW-E2EAD) framework that integrates open-world perception with a novel vision-action retrieval paradigm. We leverage a frozen vision-language model for open-world detection and segmentation to obtain multi-scale, prompt-guided, and interpretable perception features without domain-specific tuning. A Q-Former bottleneck aggregates fine-grained visual representations with language-aligned visual features, bridging perception and action domains. To learn transferable driving behaviors, we introduce a vision-action contrastive learning scheme that aligns vision-language and action embeddings for effective open-world reasoning and action retrieval. Our experiments on a real-world robotic platform demonstrate strong generalization and exploratory performance in unstructured, unseen environments, even with limited data. Demo videos are provided in the supplementary material.

---

### SynthGuard: An Open Platform for Detecting AI-Generated Multimedia with Multimodal LLMs

Authors: Shail Desai, Aditya Pawar, Li Lin, Xin Wang, Shu Hu
Published: 2025-11-16
Categories: cs.MM, cs.AI, cs.SD
arXiv: https://arxiv.org/abs/2511.12404v1

Artificial Intelligence (AI) has made it possible for anyone to create images, audio, and video with unprecedented ease, enriching education, communication, and creative expression. At the same time, the rapid rise of AI-generated media has introduced serious risks, including misinformation, identity misuse, and the erosion of public trust as synthetic content becomes increasingly indistinguishable from real media. Although deepfake detection has advanced, many existing tools remain closed-source, limited in modality, or lacking transparency and educational value, making it difficult for users to understand how detection decisions are made. To address these gaps, we introduce SynthGuard, an open, user-friendly platform for detecting and analyzing AI-generated multimedia using both traditional detectors and multimodal large language models (MLLMs). SynthGuard provides explainable inference, unified image and audio support, and an interactive interface designed to make forensic analysis accessible to researchers, educators, and the public. The SynthGuard platform is available at: https://in-engr-nova.it.purdue.edu/

---

### MSLoRA: Multi-Scale Low-Rank Adaptation via Attention Reweighting

Authors: Xu Yang, Gady Agam
Published: 2025-11-16
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2511.12400v1

We introduce MSLoRA, a backbone-agnostic, parameter-efficient adapter that reweights feature responses rather than re-tuning the underlying backbone. Existing low-rank adaptation methods are mostly confined to vision transformers (ViTs) and struggle to generalize across architectures. MSLoRA unifies adaptation for both convolutional neural networks (CNNs) and ViTs by combining a low-rank linear projection with a multi-scale nonlinear transformation that jointly modulates spatial and channel attention. The two components are fused through pointwise multiplication and a residual connection, yielding a lightweight module that shifts feature attention while keeping pretrained weights frozen. Extensive experiments demonstrate that MSLoRA consistently improves transfer performance on classification, detection, and segmentation tasks with roughly less than 5\% of backbone parameters. The design further enables stable optimization, fast convergence, and strong cross-architecture generalization. By reweighting rather than re-tuning, MSLoRA provides a simple and universal approach for efficient adaptation of frozen vision backbones.

---

### On the Dimension-Free Approximation of Deep Neural Networks for Symmetric Korobov Functions

Authors: Yulong Lu, Tong Mao, Jinchao Xu, Yahong Yang
Published: 2025-11-16
Categories: cs.LG, math.NA
arXiv: https://arxiv.org/abs/2511.12398v2

Deep neural networks have been widely used as universal approximators for functions with inherent physical structures, including permutation symmetry. In this paper, we construct symmetric deep neural networks to approximate symmetric Korobov functions and prove that both the convergence rate and the constant prefactor scale at most polynomially with respect to the ambient dimension. This represents a substantial improvement over prior approximation guarantees that suffer from the curse of dimensionality. Building on these approximation bounds, we further derive a generalization-error rate for learning symmetric Korobov functions whose leading factors likewise avoid the curse of dimensionality.

---

### On the Dimension-Free Approximation of Deep Neural Networks for Symmetric Korobov Functions

Authors: Yulong Lu, Tong Mao, Jinchao Xu, Yahong Yang
Published: 2025-11-16
Categories: cs.LG, math.NA
arXiv: https://arxiv.org/abs/2511.12398v1

Deep neural networks have been widely used as universal approximators for functions with inherent physical structures, including permutation symmetry. In this paper, we construct symmetric deep neural networks to approximate symmetric Korobov functions and prove that both the convergence rate and the constant prefactor scale at most polynomially with respect to the ambient dimension. This represents a substantial improvement over prior approximation guarantees that suffer from the curse of dimensionality. Building on these approximation bounds, we further derive a generalization-error rate for learning symmetric Korobov functions whose leading factors likewise avoid the curse of dimensionality.

---

### Stochastic Predictive Analytics for Stocks in the Newsvendor Problem

Authors: Pedro A. Pury
Published: 2025-11-16
Categories: stat.AP, cs.LG
arXiv: https://arxiv.org/abs/2511.12397v1

This work addresses a key challenge in inventory management by developing a stochastic model that describes the dynamic distribution of inventory stock over time without assuming a specific demand distribution. Our model provides a flexible and applicable solution for situations with limited historical data and short-term predictions, making it well-suited for the Newsvendor problem. We evaluate our model's performance using real-world data from a large electronic marketplace, demonstrating its effectiveness in a practical forecasting scenario.

---

### DEMIST: Decoupled Multi-stream latent diffusion for Quantitative Myelin Map Synthesis

Authors: Jiacheng Wang, Hao Li, Xing Yao, Ahmad Toubasi, Taegan Vinarsky, Caroline Gheen, Joy Derwenskus, Chaoyang Jin, Richard Dortch, Junzhong Xu, Francesca Bagnato, Ipek Oguz
Published: 2025-11-16
Categories: eess.IV, cs.CV
arXiv: https://arxiv.org/abs/2511.12396v2

Quantitative magnetization transfer (qMT) imaging provides myelin-sensitive biomarkers, such as the pool size ratio (PSR), which is valuable for multiple sclerosis (MS) assessment. However, qMT requires specialized 20-30 minute scans. We propose DEMIST to synthesize PSR maps from standard T1w and FLAIR images using a 3D latent diffusion model with three complementary conditioning mechanisms. Our approach has two stages: first, we train separate autoencoders for PSR and anatomical images to learn aligned latent representations. Second, we train a conditional diffusion model in this latent space on top of a frozen diffusion foundation backbone. Conditioning is decoupled into: (i) \textbf{semantic} tokens via cross-attention, (ii) \textbf{spatial} per-scale residual hints via a 3D ControlNet branch, and (iii) \textbf{adaptive} LoRA-modulated attention. We include edge-aware loss terms to preserve lesion boundaries and alignment losses to maintain quantitative consistency, while keeping the number of trainable parameters low and retaining the inductive bias of the pretrained model. We evaluate on 163 scans from 99 subjects using 5-fold cross-validation. Our method outperforms VAE, GAN and diffusion baselines on multiple metrics, producing sharper boundaries and better quantitative agreement with ground truth. Our code is publicly available at https://github.com/MedICL-VU/MS-Synthesis-3DcLDM.

---

### DEMIST: \underline{DE}coupled \underline{M}ulti-stream latent d\underline{I}ffusion for Quantitative Myelin Map \underline{S}yn\underline{T}hesis

Authors: Jiacheng Wang, Hao Li, Xing Yao, Ahmad Toubasi, Taegan Vinarsky, Caroline Gheen, Joy Derwenskus, Chaoyang Jin, Richard Dortch, Junzhong Xu, Francesca Bagnato, Ipek Oguz
Published: 2025-11-16
Categories: eess.IV, cs.CV
arXiv: https://arxiv.org/abs/2511.12396v1

Quantitative magnetization transfer (qMT) imaging provides myelin-sensitive biomarkers, such as the pool size ratio (PSR), which is valuable for multiple sclerosis (MS) assessment. However, qMT requires specialized 20-30 minute scans. We propose DEMIST to synthesize PSR maps from standard T1w and FLAIR images using a 3D latent diffusion model with three complementary conditioning mechanisms. Our approach has two stages: first, we train separate autoencoders for PSR and anatomical images to learn aligned latent representations. Second, we train a conditional diffusion model in this latent space on top of a frozen diffusion foundation backbone. Conditioning is decoupled into: (i) \textbf{semantic} tokens via cross-attention, (ii) \textbf{spatial} per-scale residual hints via a 3D ControlNet branch, and (iii) \textbf{adaptive} LoRA-modulated attention. We include edge-aware loss terms to preserve lesion boundaries and alignment losses to maintain quantitative consistency, while keeping the number of trainable parameters low and retaining the inductive bias of the pretrained model. We evaluate on 163 scans from 99 subjects using 5-fold cross-validation. Our method outperforms VAE, GAN and diffusion baselines on multiple metrics, producing sharper boundaries and better quantitative agreement with ground truth. Our code is publicly available at https://github.com/MedICL-VU/MS-Synthesis-3DcLDM.

---

### Multi-Domain EEG Representation Learning with Orthogonal Mapping and Attention-based Fusion for Cognitive Load Classification

Authors: Prithila Angkan, Amin Jalali, Paul Hungler, Ali Etemad
Published: 2025-11-16
Categories: cs.HC, cs.LG
arXiv: https://arxiv.org/abs/2511.12394v1

We propose a new representation learning solution for the classification of cognitive load based on Electroencephalogram (EEG). Our method integrates both time and frequency domains by first passing the raw EEG signals through the convolutional encoder to obtain the time domain representations. Next, we measure the Power Spectral Density (PSD) for all five EEG frequency bands and generate the channel power values as 2D images referred to as multi-spectral topography maps. These multi-spectral topography maps are then fed to a separate encoder to obtain the representations in frequency domain. Our solution employs a multi-domain attention module that maps these domain-specific embeddings onto a shared embedding space to emphasize more on important inter-domain relationships to enhance the representations for cognitive load classification. Additionally, we incorporate an orthogonal projection constraint during the training of our method to effectively increase the inter-class distances while improving intra-class clustering. This enhancement allows efficient discrimination between different cognitive states and aids in better grouping of similar states within the feature space. We validate the effectiveness of our model through extensive experiments on two public EEG datasets, CL-Drive and CLARE for cognitive load classification. Our results demonstrate the superiority of our multi-domain approach over the traditional single-domain techniques. Moreover, we conduct ablation and sensitivity analyses to assess the impact of various components of our method. Finally, robustness experiments on different amounts of added noise demonstrate the stability of our method compared to other state-of-the-art solutions.

---

### Studying Illustrations in Manuscripts: An Efficient Deep-Learning Approach

Authors: Yoav Evron, Michal Bar-Asher Siegal, Michael Fire
Published: 2025-11-15
Categories: cs.IR, cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2601.05269v2

The recent Artificial Intelligence (AI) revolution has opened transformative possibilities for the humanities, particularly in unlocking the visual-artistic content embedded in historical illuminated manuscripts. While digital archives now offer unprecedented access to these materials, the ability to systematically locate, extract, and analyze illustrations at scale remains a major challenge. We present a general and scalable AI-based pipeline for large-scale visual analysis of illuminated manuscripts. The framework integrates modern deep-learning models for page-level illustration detection, illustration extraction, and multimodal description, enabling scholars to search, cluster, and study visual materials and artistic trends across entire corpora. We demonstrate the applicability of this approach on large heterogeneous collections, including the Vatican Library and richly illuminated manuscripts such as the Bible of Borso d'Este. The system reveals meaningful visual patterns and cross-manuscript relationships by embedding illustrations into a shared representation space and analyzing their similarity structure (see figure 4). By harnessing recent advances in computer vision and vision-language models, our framework enables new forms of large-scale visual scholarship in historical studies, art history, and cultural heritage making it possible to explore iconography, stylistic trends, and cultural connections in ways that were previously impractical.

---

### FUSE : Failure-aware Usage of Subagent Evidence for MultiModal Search and Recommendation

Authors: Tushar Vatsa, Vibha Belavadi, Priya Shanmugasundaram, Suhas Suresha, Dewang Sultania
Published: 2025-11-15
Categories: cs.IR, cs.AI, cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2601.02365v1

Multimodal creative assistants decompose user goals and route tasks to subagents for layout, styling, retrieval, and generation. Retrieval quality is pivotal, yet failures can arise at several stages: understanding user intent, choosing content types, finding candidates (recall), or ranking results. Meanwhile, sending and processing images is costly, making naive multimodal approaches impractical. We present FUSE: Failure-aware Usage of Subagent Evidence for MultiModal Search and Recommendation. FUSE replaces most raw-image prompting with a compact Grounded Design Representation (GDR): a selection aware JSON of canvas elements (image, text, shape, icon, video, logo), structure, styles, salient colors, and user selection provided by the Planner team. FUSE implements seven context budgeting strategies: comprehensive baseline prompting, context compression, chain-of-thought reasoning, mini-shot optimization, retrieval-augmented context, two-stage processing, and zero-shot minimalism. Finally, a pipeline attribution layer monitors system performance by converting subagent signals into simple checks: intent alignment, content-type/routing sanity, recall health (e.g., zero-hit and top-match strength), and ranking displacement analysis. We evaluate the seven context budgeting variants across 788 evaluation queries from diverse users and design templates (refer Figure 3). Our systematic evaluation reveals that Context Compression achieves optimal performance across all pipeline stages, with 93.3% intent accuracy, 86.8% routing success(with fallbacks), 99.4% recall, and 88.5% NDCG@5. This approach demonstrates that strategic context summarization outperforms both comprehensive and minimal contextualization strategies.

---