# Research Papers — 2025-12 · bundle page 90 of 175

> Full-text markdown of papers #4451–4500 of 8703 published in 2025-12, newest first. AI-readable mirrors of the full 8703-paper 2025-12 archive (50 papers per file).

Canonical page: https://aipod.dev/papers/archive/2025-12/page/90
[← Previous bundle](https://aipod.dev/papers/archive/2025-12/page/89.md)
[Next bundle →](https://aipod.dev/papers/archive/2025-12/page/91.md)

### Cross-modal Fundus Image Registration under Large FoV Disparity

Authors: Hongyang Li, Junyi Tao, Qijie Wei, Ningzhi Yang, Meng Wang, Weihong Yu, Xirong Li
Published: 2025-12-14
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.12657v1

Previous work on cross-modal fundus image registration (CMFIR) assumes small cross-modal Field-of-View (FoV) disparity. By contrast, this paper is targeted at a more challenging scenario with large FoV disparity, to which directly applying current methods fails. We propose Crop and Alignment for cross-modal fundus image Registration(CARe), a very simple yet effective method. Specifically, given an OCTA with smaller FoV as a source image and a wide-field color fundus photograph (wfCFP) as a target image, our Crop operation exploits the physiological structure of the retina to crop from the target image a sub-image with its FoV roughly aligned with that of the source. This operation allows us to re-purpose the previous small-FoV-disparity oriented methods for subsequent image registration. Moreover, we improve spatial transformation by a double-fitting based Alignment module that utilizes the classical RANSAC algorithm and polynomial-based coordinate fitting in a sequential manner. Extensive experiments on a newly developed test set of 60 OCTA-wfCFP pairs verify the viability of CARe for CMFIR.

---

### Modeling Authorial Style in Urdu Novels Using Character Interaction Graphs and Graph Neural Networks

Authors: Hassan Mujtaba, Hamza Naveed, Hanzlah Munir
Published: 2025-12-14
Categories: cs.CL, cs.LG, cs.SI
arXiv: https://arxiv.org/abs/2512.12654v1

Authorship analysis has traditionally focused on lexical and stylistic cues within text, while higher-level narrative structure remains underexplored, particularly for low-resource languages such as Urdu. This work proposes a graph-based framework that models Urdu novels as character interaction networks to examine whether authorial style can be inferred from narrative structure alone. Each novel is represented as a graph where nodes correspond to characters and edges denote their co-occurrence within narrative proximity. We systematically compare multiple graph representations, including global structural features, node-level semantic summaries, unsupervised graph embeddings, and supervised graph neural networks. Experiments on a dataset of 52 Urdu novels written by seven authors show that learned graph representations substantially outperform hand-crafted and unsupervised baselines, achieving up to 0.857 accuracy under a strict author-aware evaluation protocol.

---

### Value-Aware Multiagent Systems

Authors: Nardine Osman
Published: 2025-12-14
Categories: cs.AI, cs.MA
arXiv: https://arxiv.org/abs/2512.12652v1

This paper introduces the concept of value awareness in AI, which goes beyond the traditional value-alignment problem. Our definition of value awareness presents us with a concise and simplified roadmap for engineering value-aware AI. The roadmap is structured around three core pillars: (1) learning and representing human values using formal semantics, (2) ensuring the value alignment of both individual agents and multiagent systems, and (3) providing value-based explainability on behaviour. The paper presents a selection of our ongoing work on some of these topics, along with applications to real-life domains.

---

### LexRel: Benchmarking Legal Relation Extraction for Chinese Civil Cases

Authors: Yida Cai, Ranjuexiao Hu, Huiyuan Xie, Chenyang Li, Yun Liu, Yuxiao Ye, Zhenghao Liu, Weixing Shen, Zhiyuan Liu
Published: 2025-12-14
Categories: cs.CL
arXiv: https://arxiv.org/abs/2512.12643v2

Legal relations serve as an important analytical framework for dispute resolution in civil cases. However, legal relations in Chinese civil cases remain underexplored in the field of legal AI, largely due to the absence of comprehensive schemas. In this work, we first introduce a comprehensive schema for legal relations in civil cases, which contains a hierarchical taxonomy and definitions of arguments. Based on this schema, we formulate a legal relation extraction task and present LexRel, an expert-annotated benchmark for legal relation extraction in the Chinese civil law domain. We use LexRel to evaluate state-of-the-art large language models (LLMs) on legal relation extraction, showing that current LLMs exhibit significant limitations in accurately identifying civil legal relations. Furthermore, we demonstrate that explicitly incorporating information about legal relations leads to promising performance gains on other downstream legal AI tasks.

---

### LexRel: Benchmarking Legal Relation Extraction for Chinese Civil Cases

Authors: Yida Cai, Ranjuexiao Hu, Huiyuan Xie, Chenyang Li, Yun Liu, Yuxiao Ye, Zhenghao Liu, Weixing Shen, Zhiyuan Liu
Published: 2025-12-14
Categories: cs.CL
arXiv: https://arxiv.org/abs/2512.12643v1

Legal relations form a highly consequential analytical framework of civil law system, serving as a crucial foundation for resolving disputes and realizing values of the rule of law in judicial practice. However, legal relations in Chinese civil cases remain underexplored in the field of legal artificial intelligence (legal AI), largely due to the absence of comprehensive schemas. In this work, we firstly introduce a comprehensive schema, which contains a hierarchical taxonomy and definitions of arguments, for AI systems to capture legal relations in Chinese civil cases. Based on this schema, we then formulate legal relation extraction task and present LexRel, an expert-annotated benchmark for legal relation extraction in Chinese civil law. We use LexRel to evaluate state-of-the-art large language models (LLMs) on legal relation extractions, showing that current LLMs exhibit significant limitations in accurately identifying civil legal relations. Furthermore, we demonstrate that incorporating legal relations information leads to consistent performance gains on other downstream legal AI tasks.

---

### Torch Geometric Pool: the PyTorch library for pooling in Graph Neural Networks

Authors: Carlo Abate, Ivan Marisca, Filippo Maria Bianchi
Published: 2025-12-14
Categories: cs.LG
arXiv: https://arxiv.org/abs/2512.12642v2

Torch Geometric Pool (tgp) is a pooling library built on top of PyTorch Geometric. Graph pooling methods differ in how they assign nodes to supernodes, how they handle batches, what they return after pooling, and whether they expose auxiliary losses. These differences make it hard to compare methods or reuse the same model code across them. tgp addresses this problem with a common software interface based on the Select-Reduce-Connect-Lift (SRCL) decomposition. The library provides 20 hierarchical poolers, standardized output objects, standalone readout modules, support for dense poolers in batched and unbatched mode, and workflows for caching and pre-coarsening. It is released under the MIT license on GitHub and PyPI, with comprehensive documentation, tutorials, and examples.

---

### Torch Geometric Pool: the Pytorch library for pooling in Graph Neural Networks

Authors: Filippo Maria Bianchi, Carlo Abate, Ivan Marisca
Published: 2025-12-14
Categories: cs.LG
arXiv: https://arxiv.org/abs/2512.12642v1

We introduce Torch Geometric Pool (tgp), a library for hierarchical pooling in Graph Neural Networks. Built upon Pytorch Geometric, Torch Geometric Pool (tgp) provides a wide variety of pooling operators, unified under a consistent API and a modular design. The library emphasizes usability and extensibility, and includes features like precomputed pooling, which significantly accelerate training for a class of operators. In this paper, we present tgp's structure and present an extensive benchmark. The latter showcases the library's features and systematically compares the performance of the implemented graph-pooling methods in different downstream tasks. The results, showing that the choice of the optimal pooling operator depends on tasks and data at hand, support the need for a library that enables fast prototyping.

---

### Which Pieces Does Unigram Tokenization Really Need?

Authors: Sander Land, Yuval Pinter
Published: 2025-12-14
Categories: cs.CL
arXiv: https://arxiv.org/abs/2512.12641v2

The Unigram tokenization algorithm offers a probabilistic alternative to the greedy heuristics of Byte-Pair Encoding. Despite its theoretical elegance, its implementation in practice is complex, limiting its adoption to the SentencePiece package and adapters thereof. We bridge this gap between theory and practice by providing a clear guide to implementation and parameter choices. We also identify a simpler algorithm that accepts slightly higher training loss in exchange for improved compression.

---

### Which Pieces Does Unigram Tokenization Really Need?

Authors: Sander Land, Yuval Pinter
Published: 2025-12-14
Categories: cs.CL
arXiv: https://arxiv.org/abs/2512.12641v1

The Unigram tokenization algorithm offers a probabilistic alternative to the greedy heuristics of Byte-Pair Encoding. Despite its theoretical elegance, its implementation in practice is complex, limiting its adoption to the SentencePiece package and adapters thereof. We bridge this gap between theory and practice by providing a clear guide to implementation and parameter choices. We also identify a simpler algorithm that accepts slightly higher training loss in exchange for improved compression.

---

### MobiBench: Multi-Branch, Modular Benchmark for Mobile GUI Agents

Authors: Youngmin Im, Byeongung Jo, Jaeyoung Wi, Seungwoo Baek, Tae Hoon Min, Joo Hyung Lee, Sangeun Oh, Insik Shin, Sunjae Lee
Published: 2025-12-14
Categories: cs.AI
arXiv: https://arxiv.org/abs/2512.12634v4

Mobile GUI Agents, AI agents capable of interacting with mobile applications on behalf of users, have the potential to transform human computer interaction. However, current evaluation practices for GUI agents face two fundamental limitations. First, they either rely on single path offline benchmarks or online live benchmarks. Offline benchmarks using static, single path annotated datasets unfairly penalize valid alternative actions, while online benchmarks suffer from poor scalability and reproducibility due to the dynamic and unpredictable nature of live evaluation. Second, existing benchmarks treat agents as monolithic black boxes, overlooking the contributions of individual components, which often leads to unfair comparisons or obscures key performance bottlenecks. To address these limitations, we present MobiBench, the first modular and multi path aware offline benchmarking framework for mobile GUI agents that enables high fidelity, scalable, and reproducible evaluation entirely in offline settings. Our experiments demonstrate that MobiBench achieves 94.72 percent agreement with human evaluators, on par with carefully engineered online benchmarks, while preserving the scalability and reproducibility of static offline benchmarks. Furthermore, our comprehensive module level analysis uncovers several key insights, including a systematic evaluation of diverse techniques used in mobile GUI agents, optimal module configurations across model scales, the inherent limitations of current LFMs, and actionable guidelines for designing more capable and cost efficient mobile agents.

---

### Modular and Multi-Path-Aware Offline Benchmarking for Mobile GUI Agents

Authors: Youngmin Im, Byeongung Jo, Jaeyoung Wi, Seungwoo Baek, Tae Hoon Min, Joo Hyung Lee, Sangeun Oh, Insik Shin, Sunjae Lee
Published: 2025-12-14
Categories: cs.AI
arXiv: https://arxiv.org/abs/2512.12634v1

Mobile GUI Agents, AI agents capable of interacting with mobile applications on behalf of users, have the potential to transform human computer interaction. However, current evaluation practices for GUI agents face two fundamental limitations. First, they either rely on single path offline benchmarks or online live benchmarks. Offline benchmarks using static, single path annotated datasets unfairly penalize valid alternative actions, while online benchmarks suffer from poor scalability and reproducibility due to the dynamic and unpredictable nature of live evaluation. Second, existing benchmarks treat agents as monolithic black boxes, overlooking the contributions of individual components, which often leads to unfair comparisons or obscures key performance bottlenecks. To address these limitations, we present MobiBench, the first modular and multi path aware offline benchmarking framework for mobile GUI agents that enables high fidelity, scalable, and reproducible evaluation entirely in offline settings. Our experiments demonstrate that MobiBench achieves 94.72 percent agreement with human evaluators, on par with carefully engineered online benchmarks, while preserving the scalability and reproducibility of static offline benchmarks. Furthermore, our comprehensive module level analysis uncovers several key insights, including a systematic evaluation of diverse techniques used in mobile GUI agents, optimal module configurations across model scales, the inherent limitations of current LFMs, and actionable guidelines for designing more capable and cost efficient mobile agents.

---

### DiG: Differential Grounding for Enhancing Fine-Grained Perception in Multimodal Large Language Model

Authors: Zhou Tao, Shida Wang, Yongxiang Hua, Haoyu Cao, Linli Xu
Published: 2025-12-14
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2512.12633v2

Multimodal Large Language Models have achieved impressive performance on a variety of vision-language tasks, yet their fine-grained visual perception and precise spatial reasoning remain limited. In this work, we introduce DiG (Differential Grounding), a novel proxy task framework where MLLMs learn fine-grained perception by identifying and localizing all differences between similar image pairs without prior knowledge of their number. To support scalable training, we develop an automated 3D rendering-based data generation pipeline that produces high-quality paired images with fully controllable discrepancies. To address the sparsity of difference signals, we further employ curriculum learning that progressively increases complexity from single to multiple differences, enabling stable optimization. Extensive experiments demonstrate that DiG significantly improves model performance across a variety of visual perception benchmarks and that the learned fine-grained perception skills transfer effectively to standard downstream tasks, including RefCOCO, RefCOCO+, RefCOCOg, and general multimodal perception benchmarks. Our results highlight differential grounding as a scalable and robust approach for advancing fine-grained visual reasoning in MLLMs.

---

### DiG: Differential Grounding for Enhancing Fine-Grained Perception in Multimodal Large Language Model

Authors: Zhou Tao, Shida Wang, Yongxiang Hua, Haoyu Cao, Linli Xu
Published: 2025-12-14
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2512.12633v1

Multimodal Large Language Models have achieved impressive performance on a variety of vision-language tasks, yet their fine-grained visual perception and precise spatial reasoning remain limited. In this work, we introduce DiG (Differential Grounding), a novel proxy task framework where MLLMs learn fine-grained perception by identifying and localizing all differences between similar image pairs without prior knowledge of their number. To support scalable training, we develop an automated 3D rendering-based data generation pipeline that produces high-quality paired images with fully controllable discrepancies. To address the sparsity of difference signals, we further employ curriculum learning that progressively increases complexity from single to multiple differences, enabling stable optimization. Extensive experiments demonstrate that DiG significantly improves model performance across a variety of visual perception benchmarks and that the learned fine-grained perception skills transfer effectively to standard downstream tasks, including RefCOCO, RefCOCO+, RefCOCOg, and general multimodal perception benchmarks. Our results highlight differential grounding as a scalable and robust approach for advancing fine-grained visual reasoning in MLLMs.

---

### ORIBA: Exploring LLM-Driven Role-Play Chatbot as a Creativity Support Tool for Original Character Artists

Authors: Yuqian Sun, Xingyu Li, Shunyu Yao, Noura Howell, Tristan Braud, Chang Hee Lee, Ali Asadipour
Published: 2025-12-14
Categories: cs.HC, cs.AI
arXiv: https://arxiv.org/abs/2512.12630v1

Recent advances in Generative AI (GAI) have led to new opportunities for creativity support. However, this technology has raised ethical concerns in the visual artists community. This paper explores how GAI can assist visual artists in developing original characters (OCs) while respecting their creative agency. We present ORIBA, an AI chatbot leveraging large language models (LLMs) to enable artists to role-play with their OCs, focusing on conceptualization (e.g., backstories) while leaving exposition (visual creation) to creators. Through a study with 14 artists, we found ORIBA motivated artists' imaginative engagement, developing multidimensional attributes and stronger bonds with OCs that inspire their creative process. Our contributions include design insights for AI systems that develop from artists' perspectives, demonstrating how LLMs can support cross-modal creativity while preserving creative agency in OC art. This paper highlights the potential of GAI as a neutral, non-visual support that strengthens existing creative practice, without infringing artistic exposition.

---

### CoLSE: A Lightweight and Robust Hybrid Learned Model for Single-Table Cardinality Estimation using Joint CDF

Authors: Lankadinee Rathuwadu, Guanli Liu, Christopher Leckie, Renata Borovica-Gajic
Published: 2025-12-14
Categories: cs.DB, cs.LG
arXiv: https://arxiv.org/abs/2512.12624v1

Cardinality estimation (CE), the task of predicting the result size of queries is a critical component of query optimization. Accurate estimates are essential for generating efficient query execution plans. Recently, machine learning techniques have been applied to CE, broadly categorized into query-driven and data-driven approaches. Data-driven methods learn the joint distribution of data, while query-driven methods construct regression models that map query features to cardinalities. Ideally, a CE technique should strike a balance among three key factors: accuracy, efficiency, and memory footprint. However, existing state-of-the-art models often fail to achieve this balance. To address this, we propose CoLSE, a hybrid learned approach for single-table cardinality estimation. CoLSE directly models the joint probability over queried intervals using a novel algorithm based on copula theory and integrates a lightweight neural network to correct residual estimation errors. Experimental results show that CoLSE achieves a favorable trade-off among accuracy, training time, inference latency, and model size, outperforming existing state-of-the-art methods.

---

### Reasoning Within the Mind: Dynamic Multimodal Interleaving in Latent Space

Authors: Chengzhi Liu, Yuzhe Yang, Yue Fan, Qingyue Wei, Sheng Liu, Xin Eric Wang
Published: 2025-12-14
Categories: cs.CV, cs.CL
arXiv: https://arxiv.org/abs/2512.12623v3

Recent advancements in Multimodal Large Language Models (MLLMs) have significantly enhanced cross-modal understanding and reasoning by incorporating Chain-of-Thought (CoT) reasoning in the semantic space. Building upon this, recent studies extend the CoT mechanism to the visual modality, enabling models to integrate visual information during reasoning through external tools or explicit image generation. However, these methods remain dependent on explicit step-by-step reasoning, unstable perception-reasoning interaction and notable computational overhead. Inspired by human cognition, we posit that thinking unfolds not linearly but through the dynamic interleaving of reasoning and perception within the mind. Motivated by this perspective, we propose DMLR, a test-time Dynamic Multimodal Latent Reasoning framework that employs confidence-guided latent policy gradient optimization to refine latent think tokens for in-depth reasoning. Furthermore, a Dynamic Visual Injection Strategy is introduced, which retrieves the most relevant visual features at each latent think token and updates the set of best visual patches. The updated patches are then injected into latent think token to achieve dynamic visual-textual interleaving. Experiments across seven multimodal reasoning benchmarks and various model architectures demonstrate that DMLR significantly improves reasoning and perception performance while maintaining high inference efficiency.

---

### Reasoning Within the Mind: Dynamic Multimodal Interleaving in Latent Space

Authors: Chengzhi Liu, Yuzhe Yang, Yue Fan, Qingyue Wei, Sheng Liu, Xin Eric Wang
Published: 2025-12-14
Categories: cs.CV, cs.CL
arXiv: https://arxiv.org/abs/2512.12623v1

Recent advancements in Multimodal Large Language Models (MLLMs) have significantly enhanced cross-modal understanding and reasoning by incorporating Chain-of-Thought (CoT) reasoning in the semantic space. Building upon this, recent studies extend the CoT mechanism to the visual modality, enabling models to integrate visual information during reasoning through external tools or explicit image generation. However, these methods remain dependent on explicit step-by-step reasoning, unstable perception-reasoning interaction and notable computational overhead. Inspired by human cognition, we posit that thinking unfolds not linearly but through the dynamic interleaving of reasoning and perception within the mind. Motivated by this perspective, we propose DMLR, a test-time Dynamic Multimodal Latent Reasoning framework that employs confidence-guided latent policy gradient optimization to refine latent think tokens for in-depth reasoning. Furthermore, a Dynamic Visual Injection Strategy is introduced, which retrieves the most relevant visual features at each latent think token and updates the set of best visual patches. The updated patches are then injected into latent think token to achieve dynamic visual-textual interleaving. Experiments across seven multimodal reasoning benchmarks and various model architectures demonstrate that DMLR significantly improves reasoning and perception performance while maintaining high inference efficiency.

---

### D3D-VLP: Dynamic 3D Vision-Language-Planning Model for Embodied Grounding and Navigation

Authors: Zihan Wang, Seungjun Lee, Guangzhao Dai, Gim Hee Lee
Published: 2025-12-14
Categories: cs.CV, cs.RO
arXiv: https://arxiv.org/abs/2512.12622v1

Embodied agents face a critical dilemma that end-to-end models lack interpretability and explicit 3D reasoning, while modular systems ignore cross-component interdependencies and synergies. To bridge this gap, we propose the Dynamic 3D Vision-Language-Planning Model (D3D-VLP). Our model introduces two key innovations: 1) A Dynamic 3D Chain-of-Thought (3D CoT) that unifies planning, grounding, navigation, and question answering within a single 3D-VLM and CoT pipeline; 2) A Synergistic Learning from Fragmented Supervision (SLFS) strategy, which uses a masked autoregressive loss to learn from massive and partially-annotated hybrid data. This allows different CoT components to mutually reinforce and implicitly supervise each other. To this end, we construct a large-scale dataset with 10M hybrid samples from 5K real scans and 20K synthetic scenes that are compatible with online learning methods such as RL and DAgger. Our D3D-VLP achieves state-of-the-art results on multiple benchmarks, including Vision-and-Language Navigation (R2R-CE, REVERIE-CE, NavRAG-CE), Object-goal Navigation (HM3D-OVON), and Task-oriented Sequential Grounding and Navigation (SG3D). Real-world mobile manipulation experiments further validate the effectiveness.

---

### Understanding Syllogistic Reasoning in LLMs from Formal and Natural Language Perspectives

Authors: Aheli Poddar, Saptarshi Sahoo, Sujata Ghosh
Published: 2025-12-14
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2512.12620v3

We study syllogistic reasoning in LLMs from the logical and natural language perspectives. In process, we explore fundamental reasoning capabilities of the LLMs and the direction this research is moving forward. To aid in our studies, we use 14 large language models and investigate their syllogistic reasoning capabilities in terms of symbolic inferences as well as natural language understanding. Even though this reasoning mechanism is not a uniform emergent property across LLMs, the perfect symbolic performances in certain models make us wonder whether LLMs are becoming more and more formal reasoning mechanisms, rather than making explicit the nuances of human reasoning.

---

### Understanding Syllogistic Reasoning in LLMs from Formal and Natural Language Perspectives

Authors: Aheli Poddar, Saptarshi Sahoo, Sujata Ghosh
Published: 2025-12-14
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2512.12620v1

We study syllogistic reasoning in LLMs from the logical and natural language perspectives. In process, we explore fundamental reasoning capabilities of the LLMs and the direction this research is moving forward. To aid in our studies, we use 14 large language models and investigate their syllogistic reasoning capabilities in terms of symbolic inferences as well as natural language understanding. Even though this reasoning mechanism is not a uniform emergent property across LLMs, the perfect symbolic performances in certain models make us wonder whether LLMs are becoming more and more formal reasoning mechanisms, rather than making explicit the nuances of human reasoning.

---

### Spectral Sentinel: Scalable Byzantine-Robust Decentralized Federated Learning via Sketched Random Matrix Theory on Blockchain

Authors: Animesh Mishra
Published: 2025-12-14
Categories: cs.LG, cs.DC
arXiv: https://arxiv.org/abs/2512.12617v1

Decentralized federated learning (DFL) enables collaborative model training without centralized trust, but it remains vulnerable to Byzantine clients that poison gradients under heterogeneous (Non-IID) data. Existing defenses face a scalability trilemma: distance-based filtering (e.g., Krum) can reject legitimate Non-IID updates, geometric-median methods incur prohibitive $O(n^2 d)$ cost, and many certified defenses are evaluated only on models below 100M parameters. We propose Spectral Sentinel, a Byzantine detection and aggregation framework that leverages a random-matrix-theoretic signature: honest Non-IID gradients produce covariance eigenspectra whose bulk follows the Marchenko-Pastur law, while Byzantine perturbations induce detectable tail anomalies. Our algorithm combines Frequent Directions sketching with data-dependent MP tracking, enabling detection on models up to 1.5B parameters using $O(k^2)$ memory with $k \ll d$. Under a $(σ,f)$ threat model with coordinate-wise honest variance bounded by $σ^2$ and $f < 1/2$ adversaries, we prove $(ε,δ)$-Byzantine resilience with convergence rate $O(σf / \sqrt{T} + f^2 / T)$, and we provide a matching information-theoretic lower bound $Ω(σf / \sqrt{T})$, establishing minimax optimality. We implement the full system with blockchain integration on Polygon networks and validate it across 144 attack-aggregator configurations, achieving 78.4 percent average accuracy versus 48-63 percent for baseline methods.

---

### StruProKGR: A Structural and Probabilistic Framework for Sparse Knowledge Graph Reasoning

Authors: Yucan Guo, Saiping Guan, Miao Su, Jiyao Wei, Xiaolong Jin, Jiafeng Guo, Xueqi Cheng
Published: 2025-12-14
Categories: cs.CL
arXiv: https://arxiv.org/abs/2512.12613v2

Sparse Knowledge Graphs (KGs) are commonly encountered in real-world applications, where knowledge is often incomplete or limited. Sparse KG reasoning, the task of inferring missing knowledge over sparse KGs, is inherently challenging due to the scarcity of knowledge and the difficulty of capturing relational patterns in sparse scenarios. Among all sparse KG reasoning methods, path-based ones have attracted plenty of attention due to their interpretability. Existing path-based methods typically rely on computationally intensive random walks to collect paths, producing paths of variable quality. Additionally, these methods fail to leverage the structured nature of graphs by treating paths independently. To address these shortcomings, we propose a Structural and Probabilistic framework named StruProKGR, tailored for efficient and interpretable reasoning on sparse KGs. StruProKGR utilizes a distance-guided path collection mechanism to significantly reduce computational costs while exploring more relevant paths. It further enhances the reasoning process by incorporating structural information through probabilistic path aggregation, which prioritizes paths that reinforce each other. Extensive experiments on five sparse KG reasoning benchmarks reveal that StruProKGR surpasses existing path-based methods in both effectiveness and efficiency, providing an effective, efficient, and interpretable solution for sparse KG reasoning.

---

### StruProKGR: A Structural and Probabilistic Framework for Sparse Knowledge Graph Reasoning

Authors: Yucan Guo, Saiping Guan, Miao Su, Zeya Zhao, Xiaolong Jin, Jiafeng Guo, Xueqi Cheng
Published: 2025-12-14
Categories: cs.CL
arXiv: https://arxiv.org/abs/2512.12613v1

Sparse Knowledge Graphs (KGs) are commonly encountered in real-world applications, where knowledge is often incomplete or limited. Sparse KG reasoning, the task of inferring missing knowledge over sparse KGs, is inherently challenging due to the scarcity of knowledge and the difficulty of capturing relational patterns in sparse scenarios. Among all sparse KG reasoning methods, path-based ones have attracted plenty of attention due to their interpretability. Existing path-based methods typically rely on computationally intensive random walks to collect paths, producing paths of variable quality. Additionally, these methods fail to leverage the structured nature of graphs by treating paths independently. To address these shortcomings, we propose a Structural and Probabilistic framework named StruProKGR, tailored for efficient and interpretable reasoning on sparse KGs. StruProKGR utilizes a distance-guided path collection mechanism to significantly reduce computational costs while exploring more relevant paths. It further enhances the reasoning process by incorporating structural information through probabilistic path aggregation, which prioritizes paths that reinforce each other. Extensive experiments on five sparse KG reasoning benchmarks reveal that StruProKGR surpasses existing path-based methods in both effectiveness and efficiency, providing an effective, efficient, and interpretable solution for sparse KG reasoning.

---

### Patch-wise Retrieval: A Bag of Practical Techniques for Instance-level Matching

Authors: Wonseok Choi, Sohwi Lim, Nam Hyeon-Woo, Moon Ye-Bin, Dong-Ju Jeong, Jinyoung Hwang, Tae-Hyun Oh
Published: 2025-12-14
Categories: cs.CV, cs.IR
arXiv: https://arxiv.org/abs/2512.12610v1

Instance-level image retrieval aims to find images containing the same object as a given query, despite variations in size, position, or appearance. To address this challenging task, we propose Patchify, a simple yet effective patch-wise retrieval framework that offers high performance, scalability, and interpretability without requiring fine-tuning. Patchify divides each database image into a small number of structured patches and performs retrieval by comparing these local features with a global query descriptor, enabling accurate and spatially grounded matching. To assess not just retrieval accuracy but also spatial correctness, we introduce LocScore, a localization-aware metric that quantifies whether the retrieved region aligns with the target object. This makes LocScore a valuable diagnostic tool for understanding and improving retrieval behavior. We conduct extensive experiments across multiple benchmarks, backbones, and region selection strategies, showing that Patchify outperforms global methods and complements state-of-the-art reranking pipelines. Furthermore, we apply Product Quantization for efficient large-scale retrieval and highlight the importance of using informative features during compression, which significantly boosts performance. Project website: https://wons20k.github.io/PatchwiseRetrieval/

---

### Human-Inspired Learning for Large Language Models via Obvious Record and Maximum-Entropy Method Discovery

Authors: Hong Su
Published: 2025-12-14
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2512.12608v2

Large Language Models (LLMs) excel at extracting common patterns from large-scale corpora, yet they struggle with rare, low-resource, or previously unseen scenarios-such as niche hardware deployment issues or irregular IoT device behaviors-because such cases are sparsely represented in training data. Moreover, LLMs rely primarily on implicit parametric memory, which limits their ability to explicitly acquire, recall, and refine methods, causing them to behave predominantly as intuition-driven predictors rather than deliberate, method-oriented learners. Inspired by how humans learn from rare experiences, this paper proposes a human-inspired learning framework that integrates two complementary mechanisms. The first, Obvious Record, explicitly stores cause--result (or question--solution) relationships as symbolic memory, enabling persistent learning even from single or infrequent encounters. The second, Maximum-Entropy Method Discovery, prioritizes and preserves methods with high semantic dissimilarity, allowing the system to capture diverse and underrepresented strategies that are typically overlooked by next-token prediction. Verification on a benchmark of 60 semantically diverse question--solution pairs demonstrates that the proposed entropy-guided approach achieves stronger coverage of unseen questions and significantly greater internal diversity than a random baseline, confirming its effectiveness in discovering more generalizable and human-inspired methods.

---

### Human-Inspired Learning for Large Language Models via Obvious Record and Maximum-Entropy Method Discovery

Authors: Hong Su
Published: 2025-12-14
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2512.12608v1

Large Language Models (LLMs) excel at extracting common patterns from large-scale corpora, yet they struggle with rare, low-resource, or previously unseen scenarios-such as niche hardware deployment issues or irregular IoT device behaviors-because such cases are sparsely represented in training data. Moreover, LLMs rely primarily on implicit parametric memory, which limits their ability to explicitly acquire, recall, and refine methods, causing them to behave predominantly as intuition-driven predictors rather than deliberate, method-oriented learners. Inspired by how humans learn from rare experiences, this paper proposes a human-inspired learning framework that integrates two complementary mechanisms. The first, Obvious Record, explicitly stores cause--result (or question--solution) relationships as symbolic memory, enabling persistent learning even from single or infrequent encounters. The second, Maximum-Entropy Method Discovery, prioritizes and preserves methods with high semantic dissimilarity, allowing the system to capture diverse and underrepresented strategies that are typically overlooked by next-token prediction. Verification on a benchmark of 60 semantically diverse question--solution pairs demonstrates that the proposed entropy-guided approach achieves stronger coverage of unseen questions and significantly greater internal diversity than a random baseline, confirming its effectiveness in discovering more generalizable and human-inspired methods.

---

### Causal inference and model explainability tools for retail

Authors: Pranav Gupta, Nithin Surendran
Published: 2025-12-14
Categories: cs.LG
arXiv: https://arxiv.org/abs/2512.12605v1

Most major retailers today have multiple divisions focused on various aspects, such as marketing, supply chain, online customer experience, store customer experience, employee productivity, and vendor fulfillment. They also regularly collect data corresponding to all these aspects as dashboards and weekly/monthly/quarterly reports. Although several machine learning and statistical techniques have been in place to analyze and predict key metrics, such models typically lack interpretability. Moreover, such techniques also do not allow the validation or discovery of causal links. In this paper, we aim to provide a recipe for applying model interpretability and causal inference for deriving sales insights. In this paper, we review the existing literature on causal inference and interpretability in the context of problems in e-commerce and retail, and apply them to a real-world dataset. We find that an inherently explainable model has a lower variance of SHAP values, and show that including multiple confounders through a double machine learning approach allows us to get the correct sign of causal effect.

---

### No Cache Left Idle: Accelerating diffusion model via Extreme-slimming Caching

Authors: Tingyan Wen, Haoyu Li, Yihuang Chen, Xing Zhou, Lifei Zhu, Xueqian Wang
Published: 2025-12-14
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.12604v1

Diffusion models achieve remarkable generative quality, but computational overhead scales with step count, model depth, and sequence length. Feature caching is effective since adjacent timesteps yield highly similar features. However, an inherent trade-off remains: aggressive timestep reuse offers large speedups but can easily cross the critical line, hurting fidelity, while block- or token-level reuse is safer but yields limited computational savings. We present X-Slim (eXtreme-Slimming Caching), a training-free, cache-based accelerator that, to our knowledge, is the first unified framework to exploit cacheable redundancy across timesteps, structure (blocks), and space (tokens). Rather than simply mixing levels, X-Slim introduces a dual-threshold controller that turns caching into a push-then-polish process: it first pushes reuse at the timestep level up to an early-warning line, then switches to lightweight block- and token-level refresh to polish the remaining redundancy, and triggers full inference once the critical line is crossed to reset accumulated error. At each level, context-aware indicators decide when and where to cache. Across diverse tasks, X-Slim advances the speed-quality frontier. On FLUX.1-dev and HunyuanVideo, it reduces latency by up to 4.97x and 3.52x with minimal perceptual loss. On DiT-XL/2, it reaches 3.13x acceleration and improves FID by 2.42 over prior methods.

---

### Exact Flow Linear Attention: Exact Solution from Continuous-Time Dynamics

Authors: Jingdi Lei, Di Zhang, Soujanya Poria
Published: 2025-12-14
Categories: cs.LG
arXiv: https://arxiv.org/abs/2512.12602v5

In this paper, we introduce Exact Flow Linear Attention~(EFLA), an exact-flow formulation of delta-rule linear attention. We show that the delta-rule update can be interpreted as an explicit Euler discretization of an underlying continuous-time system. EFLA replaces this first-order update with the exact closed-form flow. By exploiting the rank-1 structure of the dynamics matrix, both the matrix exponential and the input integral collapse to a simple update that preserves delta-rule linear attention's algebraic structure, parameter count, linear-time complexity, and chunkwise parallelism. This attention mechanism removes the Euler discretization error of the delta-rule dynamics without introducing additional parameters. Experiments on robustness tests, language modeling benchmarks, and the MAD synthetic benchmark show that EFLA improves stability under corrupted and high-energy inputs, reduces perplexity, and achieves stronger downstream performance compared to SSM and Euler-style baselines. These results establish exact-flow integration as a principled and scalable update mechanism for delta-rule linear attention.

---

### Error-Free Linear Attention is a Free Lunch: Exact Solution from Continuous-Time Dynamics

Authors: Jingdi Lei, Di Zhang, Soujanya Poria
Published: 2025-12-14
Categories: cs.LG
arXiv: https://arxiv.org/abs/2512.12602v1

Linear-time attention and State Space Models (SSMs) promise to solve the quadratic cost bottleneck in long-context language models employing softmax attention. We introduce Error-Free Linear Attention (EFLA), a numerically stable, fully parallelism and generalized formulation of the delta rule. Specifically, we formulate the online learning update as a continuous-time dynamical system and prove that its exact solution is not only attainable but also computable in linear time with full parallelism. By leveraging the rank-1 structure of the dynamics matrix, we directly derive the exact closed-form solution effectively corresponding to the infinite-order Runge-Kutta method. This attention mechanism is theoretically free from error accumulation, perfectly capturing the continuous dynamics while preserving the linear-time complexity. Through an extensive suite of experiments, we show that EFLA enables robust performance in noisy environments, achieving lower language modeling perplexity and superior downstream benchmark performance than DeltaNet without introducing additional parameters. Our work provides a new theoretical foundation for building high-fidelity, scalable linear-time attention models.

---

### Setting the Stage: Text-Driven Scene-Consistent Image Generation

Authors: Cong Xie, Che Wang, Yan Zhang, Ruiqi Yu, Han Zou, Zheng Pan, Zhenpeng Zhan
Published: 2025-12-14
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.12598v3

We focus on the foundational task of Scene Staging: given a reference scene image and a text condition specifying an actor category to be generated in the scene and its spatial relation to the scene, the goal is to synthesize an output image that preserves the same scene identity as the reference image while correctly generating the actor according to the spatial relation described in the text. Existing methods struggle with this task, largely due to the scarcity of high-quality paired data and unconstrained generation objectives. To overcome the data bottleneck, we propose a novel data construction pipeline that combines real-world photographs, entity removal, and image-to-video diffusion models to generate training pairs with diverse scenes, viewpoints and correct entity-scene relationships. Furthermore, we introduce a novel correspondence-guided attention loss that leverages cross-view cues to enforce spatial alignment with the reference scene. Experiments on our scene-consistent benchmark show that our approach achieves better scene alignment and text-image alignment than state-of-the-art baselines, according to both automatic metrics and human preference studies. Our method generates images with diverse viewpoints and compositions while faithfully following the textual instructions and preserving the reference scene identity.

---

### Geometry-Aware Scene-Consistent Image Generation

Authors: Cong Xie, Che Wang, Yan Zhang, Zheng Pan, Han Zou, Zhenpeng Zhan
Published: 2025-12-14
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.12598v1

We study geometry-aware scene-consistent image generation: given a reference scene image and a text condition specifying an entity to be generated in the scene and its spatial relation to the scene, the goal is to synthesize an output image that preserves the same physical environment as the reference scene while correctly generating the entity according to the spatial relation described in the text. Existing methods struggle to balance scene preservation with prompt adherence: they either replicate the scene with high fidelity but poor responsiveness to the prompt, or prioritize prompt compliance at the expense of scene consistency. To resolve this trade-off, we introduce two key contributions: (i) a scene-consistent data construction pipeline that generates diverse, geometrically-grounded training pairs, and (ii) a novel geometry-guided attention loss that leverages cross-view cues to regularize the model's spatial reasoning. Experiments on our scene-consistent benchmark show that our approach achieves better scene alignment and text-image consistency than state-of-the-art baselines, according to both automatic metrics and human preference studies. Our method produces geometrically coherent images with diverse compositions that remain faithful to the textual instructions and the underlying scene structure.

---

### AgentSHAP: Interpreting LLM Agent Tool Importance with Monte Carlo Shapley Value Estimation

Authors: Miriam Horovicz
Published: 2025-12-14
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2512.12597v1

LLM agents that use external tools can solve complex tasks, but understanding which tools actually contributed to a response remains a blind spot. No existing XAI methods address tool-level explanations. We introduce AgentSHAP, the first framework for explaining tool importance in LLM agents. AgentSHAP is model-agnostic: it treats the agent as a black box and works with any LLM (GPT, Claude, Llama, etc.) without needing access to internal weights or gradients. Using Monte Carlo Shapley values, AgentSHAP tests how an agent responds with different tool subsets and computes fair importance scores based on game theory. Our contributions are: (1) the first explainability method for agent tool attribution, grounded in Shapley values from game theory; (2) Monte Carlo sampling that reduces cost from O(2n) to practical levels; and (3) comprehensive experiments on API-Bank showing that AgentSHAP produces consistent scores across runs, correctly identifies which tools matter, and distinguishes relevant from irrelevant tools. AgentSHAP joins TokenSHAP (for tokens) and PixelSHAP (for image regions) to complete a family of Shapley-based XAI tools for modern generative AI. Code: https://github.com/GenAISHAP/TokenSHAP.

---

### Content-Aware Ad Banner Layout Generation with Two-Stage Chain-of-Thought in Vision Language Models

Authors: Kei Yoshitake, Kento Hosono, Ken Kobayashi, Kazuhide Nakata
Published: 2025-12-14
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2512.12596v1

In this paper, we propose a method for generating layouts for image-based advertisements by leveraging a Vision-Language Model (VLM). Conventional advertisement layout techniques have predominantly relied on saliency mapping to detect salient regions within a background image, but such approaches often fail to fully account for the image's detailed composition and semantic content. To overcome this limitation, our method harnesses a VLM to recognize the products and other elements depicted in the background and to inform the placement of text and logos. The proposed layout-generation pipeline consists of two steps. In the first step, the VLM analyzes the image to identify object types and their spatial relationships, then produces a text-based "placement plan" based on this analysis. In the second step, that plan is rendered into the final layout by generating HTML-format code. We validated the effectiveness of our approach through evaluation experiments, conducting both quantitative and qualitative comparisons against existing methods. The results demonstrate that by explicitly considering the background image's content, our method produces noticeably higher-quality advertisement layouts.

---

### Vision-Enhanced Large Language Models for High-Resolution Image Synthesis and Multimodal Data Interpretation

Authors: Karthikeya KV
Published: 2025-12-14
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.12595v2

This research introduces a transformative framework for integrating Vision-Enhanced Large Language Models (LLMs) with advanced transformer-based architectures to tackle challenges in high-resolution image synthesis and multimodal data interpretation. The proposed model incorporates a rectified flow mechanism that connects noise and data with linear paths, enabling efficient and high-quality generation. A bidirectional tokenization strategy is employed to seamlessly merge inputs from text, image, and video modalities, fostering a unified understanding across diverse data types. By embedding spatial-temporal features and leveraging a hybrid text-image sequence modeling approach, the framework achieves unparalleled fidelity in synthesized images and coherent multimodal representations. The architecture is optimized with a noise-aware learning algorithm, addressing discrepancies in noisy data distributions and improving generative performance under varying input conditions. Rigorous evaluations on benchmark datasets demonstrate a 25% increase in image resolution clarity and a 20% reduction in computational requirements compared to diffusion-based methods. Furthermore, the model exhibits robust scalability and adaptability, showcasing its potential in applications like autonomous systems, creative content generation, and advanced video analysis. This work underscores the role of vision-centric LLMs in redefining capabilities in computer vision and multimodal artificial intelligence.

---

### Vision-Enhanced Large Language Models for High-Resolution Image Synthesis and Multimodal Data Interpretation

Authors: Karthikeya KV
Published: 2025-12-14
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.12595v1

This research introduces a transformative framework for integrating Vision-Enhanced Large Language Models (LLMs) with advanced transformer-based architectures to tackle challenges in high-resolution image synthesis and multimodal data interpretation. The proposed model incorporates a rectified flow mechanism that connects noise and data with linear paths, enabling efficient and high-quality generation. A bidirectional tokenization strategy is employed to seamlessly merge inputs from text, image, and video modalities, fostering a unified understanding across diverse data types. By embedding spatial-temporal features and leveraging a hybrid text-image sequence modeling approach, the framework achieves unparalleled fidelity in synthesized images and coherent multimodal representations. The architecture is optimized with a noise-aware learning algorithm, addressing discrepancies in noisy data distributions and improving generative performance under varying input conditions. Rigorous evaluations on benchmark datasets demonstrate a 25% increase in image resolution clarity and a 20% reduction in computational requirements compared to diffusion-based methods. Furthermore, the model exhibits robust scalability and adaptability, showcasing its potential in applications like autonomous systems, creative content generation, and advanced video analysis. This work underscores the role of vision-centric LLMs in redefining capabilities in computer vision and multimodal artificial intelligence.

---

### ceLLMate: Sandboxing Browser AI Agents

Authors: Luoxi Meng, Henry Feng, Ilia Shumailov, Earlence Fernandes
Published: 2025-12-14
Categories: cs.CR, cs.LG
arXiv: https://arxiv.org/abs/2512.12594v2

Browser-using agents (BUAs) are an emerging class of AI agents that interact with web browsers in human-like ways, including clicking, scrolling, filling forms, and navigating across pages. While these agents help automate repetitive online tasks, they are vulnerable to prompt injection attacks that trick an agent into performing undesired actions, such as leaking private information or issuing unintended state-changing requests. We propose ceLLMate, a browser-level sandboxing framework that restricts the agent's ambient authority and reduces the blast radius of prompt injections. We address the semantic gap challenge that is fundamental to BUAs -- writing and enforcing security policies for low-level UI tools like clicks and keystrokes is brittle and error-prone. Our core insight is to perform sandboxing at the HTTP layer because all side-effecting UI operations will result in network communication to the website's backend. We implement ceLLMate as an agent-agnostic browser extension and demonstrate how it enables sandboxing policies that block prompt injection attacks in the WASP benchmark with 7.25--15% latency overhead.

---

### ceLLMate: Sandboxing Browser AI Agents

Authors: Luoxi Meng, Henry Feng, Ilia Shumailov, Earlence Fernandes
Published: 2025-12-14
Categories: cs.CR, cs.LG
arXiv: https://arxiv.org/abs/2512.12594v1

Browser-using agents (BUAs) are an emerging class of autonomous agents that interact with web browsers in human-like ways, including clicking, scrolling, filling forms, and navigating across pages. While these agents help automate repetitive online tasks, they are vulnerable to prompt injection attacks that can trick an agent into performing undesired actions, such as leaking private information or issuing state-changing requests. We propose ceLLMate, a browser-level sandboxing framework that restricts the agent's ambient authority and reduces the blast radius of prompt injections. We address two fundamental challenges: (1) The semantic gap challenge in policy enforcement arises because the agent operates through low-level UI observations and manipulations; however, writing and enforcing policies directly over UI-level events is brittle and error-prone. To address this challenge, we introduce an agent sitemap that maps low-level browser behaviors to high-level semantic actions. (2) Policy prediction in BUAs is the norm rather than the exception. BUAs have no app developer to pre-declare sandboxing policies, and thus, ceLLMate pairs website-authored mandatory policies with an automated policy-prediction layer that adapts and instantiates these policies from the user's natural-language task. We implement ceLLMate as an agent-agnostic browser extension and demonstrate how it enables sandboxing policies that effectively block various types of prompt injection attacks with negligible overhead.

---

### Automatic Wire-Harness Color Sequence Detector

Authors: Indiwara Nanayakkara, Dehan Jayawickrama, Mervyn Parakrama B. Ekanayake
Published: 2025-12-14
Categories: cs.CV, eess.IV
arXiv: https://arxiv.org/abs/2512.12590v1

Wire harness inspection process remains a labor-intensive process prone to errors in the modern Electronics Manufacturing Services (EMS) industry. This paper introduces a semiautomated machine vision system capable of verifying correct wire positioning, correctness of the connector polarity and correctness of color sequences for both linear and circular wire harness configurations. Five industrial standard CMOS cameras are integrated into a modularized mechanical framework in the physical structure of the solution and a HSV and RGB color domain value comparison based color sequence classifier is used in the operation. For each harness batch, a user can train the system using at least five reference samples; the trained file is stored and reused for similar harness types. The Solution is deployed at GPV Lanka Pvt. Ltd. (Fig. 2) and the system achieved 100% detection accuracy and reduced inspection time by 44% compared to manual methods. Additional features include user management, adjustable lighting, session data storage, and secure login. Results of this product usage in the real world situation demonstrate that this approach delivers reliable and efficient inspection capabilities.

---

### StegaVAR: Privacy-Preserving Video Action Recognition via Steganographic Domain Analysis

Authors: Lixin Chen, Chaomeng Chen, Jiale Zhou, Zhijian Wu, Xun Lin
Published: 2025-12-14
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.12586v1

Despite the rapid progress of deep learning in video action recognition (VAR) in recent years, privacy leakage in videos remains a critical concern. Current state-of-the-art privacy-preserving methods often rely on anonymization. These methods suffer from (1) low concealment, where producing visually distorted videos that attract attackers' attention during transmission, and (2) spatiotemporal disruption, where degrading essential spatiotemporal features for accurate VAR. To address these issues, we propose StegaVAR, a novel framework that embeds action videos into ordinary cover videos and directly performs VAR in the steganographic domain for the first time. Throughout both data transmission and action analysis, the spatiotemporal information of hidden secret video remains complete, while the natural appearance of cover videos ensures the concealment of transmission. Considering the difficulty of steganographic domain analysis, we propose Secret Spatio-Temporal Promotion (STeP) and Cross-Band Difference Attention (CroDA) for analysis within the steganographic domain. STeP uses the secret video to guide spatiotemporal feature extraction in the steganographic domain during training. CroDA suppresses cover interference by capturing cross-band semantic differences. Experiments demonstrate that StegaVAR achieves superior VAR and privacy-preserving performance on widely used datasets. Moreover, our framework is effective for multiple steganographic models.

---

### Detecting Prompt Injection Attacks Against Application Using Classifiers

Authors: Safwan Shaheer, G. M. Refatul Islam, Mohammad Rafid Hamid, Md. Abrar Faiaz Khan, Md. Omar Faruk, Yaseen Nur
Published: 2025-12-14
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2512.12583v1

Prompt injection attacks can compromise the security and stability of critical systems, from infrastructure to large web applications. This work curates and augments a prompt injection dataset based on the HackAPrompt Playground Submissions corpus and trains several classifiers, including LSTM, feed forward neural networks, Random Forest, and Naive Bayes, to detect malicious prompts in LLM integrated web applications. The proposed approach improves prompt injection detection and mitigation, helping protect targeted applications and systems.

---

### Differentiable Energy-Based Regularization in GANs: A Simulator-Based Exploration of VQE-Inspired Auxiliary Losses

Authors: David Strnadel
Published: 2025-12-14
Categories: cs.LG
arXiv: https://arxiv.org/abs/2512.12581v2

This paper presents an exploratory, simulator-based proof of concept investigating whether differentiable energy terms derived from parameterized quantum circuits can serve as auxiliary regularization signals in Generative Adversarial Networks (GANs). We augment the Auxiliary Classifier GAN (ACGAN) generator objective with a Variational Quantum Eigensolver (VQE)-inspired energy term computed from class-specific Ising Hamiltonians using Qiskit's EstimatorQNN and TorchConnector. All experiments are performed on a noiseless statevector simulator with only four qubits, using a deliberately simple Hamiltonian parameterization. On MNIST, the energy-regularized model initially achieves high external-classifier accuracy (99-100 percent) within five epochs compared to 87.8 percent for an earlier, unmatched ACGAN baseline. However, a rigorous, pre-registered ablation study demonstrates that these improvements are fully replicated by simple classical alternatives, including learned per-class biases, MLP-based surrogates, random noise, and even an unregularized baseline under matched training conditions. All classical variants reach approximately 99 percent accuracy. For sample quality as measured by FID, classical baselines are not merely equivalent but systematically superior to the VQE-based formulation. We therefore report a clear negative result. The VQE-inspired energy term provides no measurable causal benefit beyond trivial classical regularizers in this setting. The primary contribution of this work is methodological, demonstrating both the technical feasibility of differentiable VQE integration into GAN training and the necessity of rigorous ablation studies to avoid spurious claims of quantum-enhanced performance.

---

### Differentiable Energy-Based Regularization in GANs: A Simulator-Based Exploration of VQE-Inspired Auxiliary Losses

Authors: David Strnadel
Published: 2025-12-14
Categories: cs.LG
arXiv: https://arxiv.org/abs/2512.12581v1

This paper presents an exploratory, simulator-based proof of concept investigating whether differentiable energy terms derived from parameterized quantum circuits can serve as auxiliary regularization signals in Generative Adversarial Networks (GANs). We augment the Auxiliary Classifier GAN (ACGAN) generator objective with a Variational Quantum Eigensolver (VQE)-inspired energy term computed from class-specific Ising Hamiltonians using Qiskit's EstimatorQNN and TorchConnector. Important limitations: All experiments run on a noiseless statevector simulator with only 4 qubits, use a deliberately simple Hamiltonian parameterization, and lack ablation studies comparing against equivalent classical biases. The computational overhead (approximately 200x slower than classical ACGAN) reflects simulator artifacts rather than inherent quantum costs. On MNIST, we observe that the energy-regularized model (termed QACGAN) achieves high classification accuracy (99 to 100 percent) within 5 epochs compared to 87.8 percent for ACGAN, suggesting the auxiliary term influences class conditioning. However, sample quality metrics (FID) show high variance across runs (coefficient of variation approximately 25 percent at epoch 5), with values ranging from 19.92 to 35.96. Extended runs stabilize around FID 23 to 24, comparable to the ACGAN baseline. We explicitly do not claim quantum advantage, improved stability in any general sense, or scalability beyond this toy setting. The contribution is methodological: demonstrating that VQE-style energy computations can be integrated into GAN training loops via differentiable pathways. Whether such auxiliary signals provide benefits beyond equivalent classical regularizers remains an open question requiring systematic ablation studies, which we leave for future work.

---

### Scalable Quantum Error Mitigation with Neighbor-Informed Learning

Authors: Zhenyu Chen, Bin Cheng, Minbo Gao, Xiaodie Lin, Ruiqi Zhang, Zhaohui Wei, Zhengfeng Ji
Published: 2025-12-14
Categories: quant-ph, cs.CC, cs.LG
arXiv: https://arxiv.org/abs/2512.12578v1

Noise in quantum hardware is the primary obstacle to realizing the transformative potential of quantum computing. Quantum error mitigation (QEM) offers a promising pathway to enhance computational accuracy on near-term devices, yet existing methods face a difficult trade-off between performance, resource overhead, and theoretical guarantees. In this work, we introduce neighbor-informed learning (NIL), a versatile and scalable QEM framework that unifies and strengthens existing methods such as zero-noise extrapolation (ZNE) and probabilistic error cancellation (PEC), while offering improved flexibility, accuracy, efficiency, and robustness. NIL learns to predict the ideal output of a target quantum circuit from the noisy outputs of its structurally related ``neighbor'' circuits. A key innovation is our 2-design training method, which generates training data for our machine learning model. In contrast to conventional learning-based QEM protocols that create training circuits by replacing non-Clifford gates with uniformly random Clifford gates, our approach achieves higher accuracy and efficiency, as demonstrated by both theoretical analysis and numerical simulation. Furthermore, we prove that the required size of the training set scales only \emph{logarithmically} with the total number of neighbor circuits, enabling NIL to be applied to problems involving large-scale quantum circuits. Our work establishes a theoretically grounded and practically efficient framework for QEM, paving a viable path toward achieving quantum advantage on noisy hardware.

---

### Coupled Variational Reinforcement Learning for Language Model General Reasoning

Authors: Xueru Wen, Jie Lou, Yanjiang Liu, Hongyu Lin, Ben He, Xianpei Han, Le Sun, Yaojie Lu, Debing Zhang
Published: 2025-12-14
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2512.12576v3

While reinforcement learning has achieved impressive progress in language model reasoning, it is constrained by the requirement for verifiable rewards. Recent verifier-free RL methods address this limitation by utilizing the probabilities that LLMs generate reference answers as reward signals. However, these approaches typically sample reasoning traces conditioned only on the question. This design decouples reasoning-trace sampling from answer information, leading to inefficient exploration and incoherence between traces and final answers. In this paper, we propose \textit{\b{Co}upled \b{V}ariational \b{R}einforcement \b{L}earning} (CoVRL), which bridges variational inference and reinforcement learning by coupling prior and posterior distributions through a hybrid sampling strategy. By constructing and optimizing a composite distribution that integrates these two distributions, CoVRL enables efficient exploration while preserving strong thought-answer coherence. Extensive experiments on mathematical and general reasoning benchmarks show that CoVRL improves performance by 12.4\% over the base model and achieves an additional 2.3\% improvement over state-of-the-art verifier-free RL baselines, providing a principled framework for enhancing the general reasoning capabilities of language models.

---

### Coupled Variational Reinforcement Learning for Language Model General Reasoning

Authors: Xueru Wen, Jie Lou, Yanjiang Liu, Hongyu Lin, Ben He, Xianpei Han, Le Sun, Yaojie Lu, Debing Zhang
Published: 2025-12-14
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2512.12576v1

While reinforcement learning have achieved impressive progress in language model reasoning, they are constrained by the requirement for verifiable rewards. Recent verifier-free RL methods address this limitation by utilizing the intrinsic probabilities of LLMs generating reference answers as reward signals. However, these approaches typically sample reasoning traces conditioned only on the question. This design decouples reasoning-trace sampling from answer information, leading to inefficient exploration and incoherence between traces and final answers. In this paper, we propose \textit{\b{Co}upled \b{V}ariational \b{R}einforcement \b{L}earning} (CoVRL), which bridges variational inference and reinforcement learning by coupling prior and posterior distributions through a hybrid sampling strategy. By constructing and optimizing a composite distribution that integrates these two distributions, CoVRL enables efficient exploration while preserving strong thought-answer coherence. Extensive experiments on mathematical and general reasoning benchmarks show that CoVRL improves performance by 12.4\% over the base model and achieves an additional 2.3\% improvement over strong state-of-the-art verifier-free RL baselines, providing a principled framework for enhancing the general reasoning capabilities of language models.

---

### Mind the Jumps: A Scalable Robust Local Gaussian Process for Multidimensional Response Surfaces with Discontinuities

Authors: Isaac Adjetey, Yiyuan She
Published: 2025-12-14
Categories: stat.ML, cs.LG, stat.AP
arXiv: https://arxiv.org/abs/2512.12574v1

Modeling response surfaces with abrupt jumps and discontinuities remains a major challenge across scientific and engineering domains. Although Gaussian process models excel at capturing smooth nonlinear relationships, their stationarity assumptions limit their ability to adapt to sudden input-output variations. Existing nonstationary extensions, particularly those based on domain partitioning, often struggle with boundary inconsistencies, sensitivity to outliers, and scalability issues in higher-dimensional settings, leading to reduced predictive accuracy and unreliable parameter estimation. To address these challenges, this paper proposes the Robust Local Gaussian Process (RLGP) model, a framework that integrates adaptive nearest-neighbor selection with a sparsity-driven robustification mechanism. Unlike existing methods, RLGP leverages an optimization-based mean-shift adjustment after a multivariate perspective transformation combined with local neighborhood modeling to mitigate the influence of outliers. This approach improves predictive accuracy near discontinuities while enhancing robustness to data heterogeneity. Comprehensive evaluations on real-world datasets show that RLGP consistently delivers high predictive accuracy and maintains competitive computational efficiency, especially in scenarios with sharp transitions and complex response structures. Scalability tests further confirm RLGP's stability and reliability in higher-dimensional settings, where other methods struggle. These results establish RLGP as an effective and practical solution for modeling nonstationary and discontinuous response surfaces across a wide range of applications.

---

### On the Accuracy of Newton Step and Influence Function Data Attributions

Authors: Ittai Rubinstein, Samuel B. Hopkins
Published: 2025-12-14
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2512.12572v2

Data attribution aims to explain model predictions by estimating how they would change if certain training points were removed, and is used in a wide range of applications, from interpretability and credit assignment to unlearning and privacy. Even in the relatively simple case of logistic regressions, existing mathematical analyses of leading data attribution methods such as Influence Functions (IF) and single Newton Step (NS) remain limited in two key ways. First, they rely on global strong convexity assumptions which are often not satisfied in practice. Second, the resulting bounds scale very poorly with the number of parameters ($d$) and the number of samples removed ($k$). As a result, these analyses are not tight enough to answer fundamental questions such as "what is the asymptotic scaling of the errors of each method?" or "which of these methods is more accurate for a given dataset?" In this paper, we introduce a new analysis of the NS and IF data attribution methods for convex learning problems. To the best of our knowledge, this is the first analysis of these questions that does not assume global strong convexity and also the first explanation of (KATL19) and (RH25a)'s observation that NS data attribution is often more accurate than IF. We prove that for sufficiently well-behaved logistic regressions, our bounds are asymptotically tight up to poly-logarithmic factors, yielding scaling laws for the errors in the average-case sample removals. \( \mathbb{E}_{T \subseteq (n),\, |T| = k} \bigl( \|\hatθ_T - \hatθ_T^{\mathrm{NS}}\|_2 \bigr) = \widetildeΘ\!\left(\frac{k d}{n^2}\right), \qquad \mathbb{E}_{T \subseteq (n),\, |T| = k} \bigl( \|\hatθ_T^{\mathrm{NS}} - \hatθ_T^{\mathrm{IF}}\|_2 \bigr) = \widetildeΘ\!\left( \frac{(k + d)\sqrt{k d}}{n^2} \right). \)

---

### On the Accuracy of Newton Step and Influence Function Data Attributions

Authors: Ittai Rubinstein, Samuel B. Hopkins
Published: 2025-12-14
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2512.12572v1

Data attribution aims to explain model predictions by estimating how they would change if certain training points were removed, and is used in a wide range of applications, from interpretability and credit assignment to unlearning and privacy. Even in the relatively simple case of linear regressions, existing mathematical analyses of leading data attribution methods such as Influence Functions (IF) and single Newton Step (NS) remain limited in two key ways. First, they rely on global strong convexity assumptions which are often not satisfied in practice. Second, the resulting bounds scale very poorly with the number of parameters ($d$) and the number of samples removed ($k$). As a result, these analyses are not tight enough to answer fundamental questions such as "what is the asymptotic scaling of the errors of each method?" or "which of these methods is more accurate for a given dataset?" In this paper, we introduce a new analysis of the NS and IF data attribution methods for convex learning problems. To the best of our knowledge, this is the first analysis of these questions that does not assume global strong convexity and also the first explanation of (KATL19) and (RH25a)'s observation that NS data attribution is often more accurate than IF. We prove that for sufficiently well-behaved logistic regression, our bounds are asymptotically tight up to poly-logarithmic factors, yielding scaling laws for the errors in the average-case sample removals. \( \mathbb{E}_{T \subseteq (n),\, |T| = k} \bigl( \|\hatθ_T - \hatθ_T^{\mathrm{NS}}\|_2 \bigr) = \widetildeΘ\!\left(\frac{k d}{n^2}\right), \qquad \mathbb{E}_{T \subseteq (n),\, |T| = k} \bigl( \|\hatθ_T^{\mathrm{NS}} - \hatθ_T^{\mathrm{IF}}\|_2 \bigr) = \widetildeΘ\!\left( \frac{(k + d)\sqrt{k d}}{n^2} \right). \)

---

### Measurement Plasticity: Sensor-Level Adaptation for Vision-Language Models

Authors: Boyeong Im, Wooseok Lee, Yoojin Kwon, Hyung-Sin Kim
Published: 2025-12-14
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.12571v3

We propose Multi-View Physical-prompt (MVP) for Test-Time Adaptation (TTA), a forward-only framework that moves TTA from tokens to photons by treating the camera exposure triangle (i.e., ISO, shutter speed, and aperture) as physical prompts. At inference, MVP acquires selected multiple physical views using a source-affinity score, evaluates digitally augmented variants of each retained view and filters the lowest-entropy predictions, and aggregates predictions with hard voting. This selection-then-vote design is simple, calibration-friendly, and requires no gradients or model modifications. On ImageNet-ES and ImageNet-ES-Diverse, MVP outperforms digital-only TTA on both Auto-Exposure and a combination with conventional sensor control. MVP remains effective under reduced parameter candidates that lower capture latency, demonstrating its practicality.

---