# Research Papers — 2025-12 · bundle page 131 of 175 > Full-text markdown of papers #6501–6550 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/131 [← Previous bundle](https://aipod.dev/papers/archive/2025-12/page/130.md) [Next bundle →](https://aipod.dev/papers/archive/2025-12/page/132.md) ### A Unifying Human-Centered AI Fairness Framework Authors: Munshi Mahbubur Rahman, Shimei Pan, James R. Foulds Published: 2025-12-07 Categories: cs.LG, cs.AI, cs.CY arXiv: https://arxiv.org/abs/2512.06944v1 The increasing use of Artificial Intelligence (AI) in critical societal domains has amplified concerns about fairness, particularly regarding unequal treatment across sensitive attributes such as race, gender, and socioeconomic status. While there has been substantial work on ensuring AI fairness, navigating trade-offs between competing notions of fairness as well as predictive accuracy remains challenging, creating barriers to the practical deployment of fair AI systems. To address this, we introduce a unifying human-centered fairness framework that systematically covers eight distinct fairness metrics, formed by combining individual and group fairness, infra-marginal and intersectional assumptions, and outcome-based and equality-of-opportunity (EOO) perspectives. This structure allows stakeholders to align fairness interventions with their values and contextual considerations. The framework uses a consistent and easy-to-understand formulation for all metrics to reduce the learning curve for non-experts. Rather than privileging a single fairness notion, the framework enables stakeholders to assign weights across multiple fairness objectives, reflecting their priorities and facilitating multi-stakeholder compromises. We apply this approach to four real-world datasets: the UCI Adult census dataset for income prediction, the COMPAS dataset for criminal recidivism, the German Credit dataset for credit risk assessment, and the MEPS dataset for healthcare utilization. We show that adjusting weights reveals nuanced trade-offs between different fairness metrics. Finally, through case studies in judicial decision-making and healthcare, we demonstrate how the framework can inform practical and value-sensitive deployment of fair AI systems. --- ### Progress Ratio Embeddings: An Impatience Signal for Robust Length Control in Neural Text Generation Authors: Ivanhoé Botcazou, Tassadit Amghar, Sylvain Lamprier, Frédéric Saubion Published: 2025-12-07 Categories: cs.CL arXiv: https://arxiv.org/abs/2512.06938v2 Modern neural language models achieve high accuracy in text generation, yet precise control over generation length remains underdeveloped. In this paper, we first investigate a recent length control method based on Reverse Positional Embeddings (RPE) and show its limits when control is requested beyond the training distribution. In particular, using a discrete countdown signal tied to the absolute remaining token count leads to instability. To provide robust length control, we introduce Progress Ratio Embeddings (PRE), as continuous embeddings tied to a trigonometric impatience signal. PRE integrates seamlessly into standard Transformer architectures, providing stable length fidelity without degrading text accuracy under standard evaluation metrics. We further show that PRE generalizes well to unseen target lengths. Experiments on two widely used news-summarization benchmarks validate these findings. --- ### Progress Ratio Embeddings: An Impatience Signal for Robust Length Control in Neural Text Generation Authors: Ivanhoé Botcazou, Tassadit Amghar, Sylvain Lamprier, Frédéric Saubion Published: 2025-12-07 Categories: cs.CL arXiv: https://arxiv.org/abs/2512.06938v1 Modern neural language models achieve high accuracy in text generation, yet precise control over generation length remains underdeveloped. In this paper, we first investigate a recent length control method based on Reverse Positional Embeddings (RPE) and show its limits when control is requested beyond the training distribution. In particular, using a discrete countdown signal tied to the absolute remaining token count leads to instability. To provide robust length control, we introduce Progress Ratio Embeddings (PRE), as continuous embeddings tied to a trigonometric impatience signal. PRE integrates seamlessly into standard Transformer architectures, providing stable length fidelity without degrading text accuracy under standard evaluation metrics. We further show that PRE generalizes well to unseen target lengths. Experiments on two widely used news-summarization benchmarks validate these findings. --- ### TxSum: User-Centered Ethereum Transaction Understanding with Micro-Level Semantic Grounding Authors: Zifan Peng, Jingyi Zheng, Yule Liu, Huaiyu Jia, Qiming Ye, Jingyu Liu, Xufeng Yang, Mingchen Li, Qingyuan Gong, Xuechao Wang, Xinlei He Published: 2025-12-07 Categories: cs.CE, cs.CL, cs.HC arXiv: https://arxiv.org/abs/2512.06933v4 Understanding the economic intent of Ethereum transactions is critical for user safety, yet current tools expose only raw on-chain data or surface-level intent, leading to widespread ``blind signing'' (approving transactions without understanding them). Through interviews with 16 Web3 users, we find that effective explanations should be structured, risk-aware, and grounded at the token-flow level. Motivated by these findings, we formulate TxSum, a new domain-grounded NLP task for DeFi transaction explanation, and construct a dataset of 187 complex Ethereum transactions with 2,375 token-flow annotations and transaction-level summaries. We further introduce MATEX, a grounded multi-agent framework for high-stakes transaction explanation. It selectively retrieves external knowledge under uncertainty and audits explanations against raw traces to improve token-flow-level factual consistency. MATEX achieves the strongest overall explanation quality, especially on micro-level factuality and intent quality. It improves user comprehension on complex transactions from 52.9% to 76.5% over the strongest baseline and raises malicious-transaction rejection from 36.0% to 88.0%, while maintaining a low false-rejection rate on benign transactions. --- ### MATEX: A Multi-Agent Framework for Explaining Ethereum Transactions Authors: Zifan Peng Published: 2025-12-07 Categories: cs.CE, cs.CL, cs.HC arXiv: https://arxiv.org/abs/2512.06933v1 Understanding a complicated Ethereum transaction remains challenging: multi-hop token flows, nested contract calls, and opaque execution paths routinely lead users to blind signing. Based on interviews with everyday users, developers, and auditors, we identify the need for faithful, step-wise explanations grounded in both on-chain evidence and real-world protocol semantics. To meet this need, we introduce (matex, a cognitive multi-agent framework that models transaction understanding as a collaborative investigation-combining rapid hypothesis generation, dynamic off-chain knowledge retrieval, evidence-aware synthesis, and adversarial validation to produce faithful explanations. --- ### Hidden Leaks in Time Series Forecasting: How Data Leakage Affects LSTM Evaluation Across Configurations and Validation Strategies Authors: Salma Albelali, Moataz Ahmed Published: 2025-12-07 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2512.06932v1 Deep learning models, particularly Long Short-Term Memory (LSTM) networks, are widely used in time series forecasting due to their ability to capture complex temporal dependencies. However, evaluation integrity is often compromised by data leakage, a methodological flaw in which input-output sequences are constructed before dataset partitioning, allowing future information to unintentionally influence training. This study investigates the impact of data leakage on performance, focusing on how validation design mediates leakage sensitivity. Three widely used validation techniques (2-way split, 3-way split, and 10-fold cross-validation) are evaluated under both leaky (pre-split sequence generation) and clean conditions, with the latter mitigating leakage risk by enforcing temporal separation during data splitting prior to sequence construction. The effect of leakage is assessed using RMSE Gain, which measures the relative increase in RMSE caused by leakage, computed as the percentage difference between leaky and clean setups. Empirical results show that 10-fold cross-validation exhibits RMSE Gain values of up to 20.5% at extended lag steps. In contrast, 2-way and 3-way splits demonstrate greater robustness, typically maintaining RMSE Gain below 5% across diverse configurations. Moreover, input window size and lag step significantly influence leakage sensitivity: smaller windows and longer lags increase the risk of leakage, whereas larger windows help reduce it. These findings underscore the need for configuration-aware, leakage-resistant evaluation pipelines to ensure reliable performance estimation. --- ### Adaptive Normalization Mamba with Multi Scale Trend Decomposition and Patch MoE Encoding Authors: MinCheol Jeon Published: 2025-12-07 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2512.06929v1 Time series forecasting in real world environments faces significant challenges non stationarity, multi scale temporal patterns, and distributional shifts that degrade model stability and accuracy. This study propose AdaMamba, a unified forecasting architecture that integrates adaptive normalization, multi scale trend extraction, and contextual sequence modeling to address these challenges. AdaMamba begins with an Adaptive Normalization Block that removes non stationary components through multi scale convolutional trend extraction and channel wise recalibration, enabling consistent detrending and variance stabilization. The normalized sequence is then processed by a Context Encoder that combines patch wise embeddings, positional encoding, and a Mamba enhanced Transformer layer with a mixture of experts feed forward module, allowing efficient modeling of both long range dependencies and local temporal dynamics. A lightweight prediction head generates multi horizon forecasts, and a denormalization mechanism reconstructs outputs by reintegrating local trends to ensure robustness under varying temporal conditions. AdaMamba provides strong representational capacity with modular extensibility, supporting deterministic prediction and compatibility with probabilistic extensions. Its design effectively mitigates covariate shift and enhances predictive reliability across heterogeneous datasets. Experimental evaluations demonstrate that AdaMamba's combination of adaptive normalization and expert augmented contextual modeling yields consistent improvements in stability and accuracy over conventional Transformer based baselines. --- ### Evaluating the Sensitivity of BiLSTM Forecasting Models to Sequence Length and Input Noise Authors: Salma Albelali, Moataz Ahmed Published: 2025-12-07 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2512.06926v1 Deep learning (DL) models, a specialized class of multilayer neural networks, have become central to time-series forecasting in critical domains such as environmental monitoring and the Internet of Things (IoT). Among these, Bidirectional Long Short-Term Memory (BiLSTM) architectures are particularly effective in capturing complex temporal dependencies. However, the robustness and generalization of such models are highly sensitive to input data characteristics - an aspect that remains underexplored in existing literature. This study presents a systematic empirical analysis of two key data-centric factors: input sequence length and additive noise. To support this investigation, a modular and reproducible forecasting pipeline is developed, incorporating standardized preprocessing, sequence generation, model training, validation, and evaluation. Controlled experiments are conducted on three real-world datasets with varying sampling frequencies to assess BiLSTM performance under different input conditions. The results yield three key findings: (1) longer input sequences significantly increase the risk of overfitting and data leakage, particularly in data-constrained environments; (2) additive noise consistently degrades predictive accuracy across sampling frequencies; and (3) the simultaneous presence of both factors results in the most substantial decline in model stability. While datasets with higher observation frequencies exhibit greater robustness, they remain vulnerable when both input challenges are present. These findings highlight important limitations in current DL-based forecasting pipelines and underscore the need for data-aware design strategies. This work contributes to a deeper understanding of DL model behavior in dynamic time-series environments and provides practical insights for developing more reliable and generalizable forecasting systems. --- ### Deep Reinforcement Learning for Phishing Detection with Transformer-Based Semantic Features Authors: Aseer Al Faisal Published: 2025-12-07 Categories: cs.LG, cs.AI, cs.CR arXiv: https://arxiv.org/abs/2512.06925v1 Phishing is a cybercrime in which individuals are deceived into revealing personal information, often resulting in financial loss. These attacks commonly occur through fraudulent messages, misleading advertisements, and compromised legitimate websites. This study proposes a Quantile Regression Deep Q-Network (QR-DQN) approach that integrates RoBERTa semantic embeddings with handcrafted lexical features to enhance phishing detection while accounting for uncertainties. Unlike traditional DQN methods that estimate single scalar Q-values, QR-DQN leverages quantile regression to model the distribution of returns, improving stability and generalization on unseen phishing data. A diverse dataset of 105,000 URLs was curated from PhishTank, OpenPhish, Cloudflare, and other sources, and the model was evaluated using an 80/20 train-test split. The QR-DQN framework achieved a test accuracy of 99.86%, precision of 99.75%, recall of 99.96%, and F1-score of 99.85%, demonstrating high effectiveness. Compared to standard DQN with lexical features, the hybrid QR-DQN with lexical and semantic features reduced the generalization gap from 1.66% to 0.04%, indicating significant improvement in robustness. Five-fold cross-validation confirmed model reliability, yielding a mean accuracy of 99.90% with a standard deviation of 0.04%. These results suggest that the proposed hybrid approach effectively identifies phishing threats, adapts to evolving attack strategies, and generalizes well to unseen data. --- ### XAM: Interactive Explainability for Authorship Attribution Models Authors: Milad Alshomary, Anisha Bhatnagar, Peter Zeng, Smaranda Muresan, Owen Rambow, Kathleen McKeown Published: 2025-12-07 Categories: cs.CL arXiv: https://arxiv.org/abs/2512.06924v1 We present IXAM, an Interactive eXplainability framework for Authorship Attribution Models. Given an authorship attribution (AA) task and an embedding-based AA model, our tool enables users to interactively explore the model's embedding space and construct an explanation of the model's prediction as a set of writing style features at different levels of granularity. Through a user evaluation, we demonstrate the value of our framework compared to predefined stylistic explanations. --- ### Large Language Models and Forensic Linguistics: Navigating Opportunities and Threats in the Age of Generative AI Authors: George Mikros Published: 2025-12-07 Categories: cs.CL, cs.CY arXiv: https://arxiv.org/abs/2512.06922v1 Large language models (LLMs) present a dual challenge for forensic linguistics. They serve as powerful analytical tools enabling scalable corpus analysis and embedding-based authorship attribution, while simultaneously destabilising foundational assumptions about idiolect through style mimicry, authorship obfuscation, and the proliferation of synthetic texts. Recent stylometric research indicates that LLMs can approximate surface stylistic features yet exhibit detectable differences from human writers, a tension with significant forensic implications. However, current AI-text detection techniques, whether classifier-based, stylometric, or watermarking approaches, face substantial limitations: high false positive rates for non-native English writers and vulnerability to adversarial strategies such as homoglyph substitution. These uncertainties raise concerns under legal admissibility standards, particularly the Daubert and Kumho Tire frameworks. The article concludes that forensic linguistics requires methodological reconfiguration to remain scientifically credible and legally admissible. Proposed adaptations include hybrid human-AI workflows, explainable detection paradigms beyond binary classification, and validation regimes measuring error and bias across diverse populations. The discipline's core insight, i.e., that language reveals information about its producer, remains valid but must accommodate increasingly complex chains of human and machine authorship. --- ### NeuroABench: A Multimodal Evaluation Benchmark for Neurosurgical Anatomy Identification Authors: Ziyang Song, Zelin Zang, Xiaofan Ye, Boqiang Xu, Long Bai, Jinlin Wu, Hongliang Ren, Hongbin Liu, Jiebo Luo, Zhen Lei Published: 2025-12-07 Categories: cs.CV, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2512.06921v1 Multimodal Large Language Models (MLLMs) have shown significant potential in surgical video understanding. With improved zero-shot performance and more effective human-machine interaction, they provide a strong foundation for advancing surgical education and assistance. However, existing research and datasets primarily focus on understanding surgical procedures and workflows, while paying limited attention to the critical role of anatomical comprehension. In clinical practice, surgeons rely heavily on precise anatomical understanding to interpret, review, and learn from surgical videos. To fill this gap, we introduce the Neurosurgical Anatomy Benchmark (NeuroABench), the first multimodal benchmark explicitly created to evaluate anatomical understanding in the neurosurgical domain. NeuroABench consists of 9 hours of annotated neurosurgical videos covering 89 distinct procedures and is developed using a novel multimodal annotation pipeline with multiple review cycles. The benchmark evaluates the identification of 68 clinical anatomical structures, providing a rigorous and standardized framework for assessing model performance. Experiments on over 10 state-of-the-art MLLMs reveal significant limitations, with the best-performing model achieving only 40.87% accuracy in anatomical identification tasks. To further evaluate the benchmark, we extract a subset of the dataset and conduct an informative test with four neurosurgical trainees. The results show that the best-performing student achieves 56% accuracy, with the lowest scores of 28% and an average score of 46.5%. While the best MLLM performs comparably to the lowest-scoring student, it still lags significantly behind the group's average performance. This comparison underscores both the progress of MLLMs in anatomical understanding and the substantial gap that remains in achieving human-level performance. --- ### Parent-Guided Semantic Reward Model (PGSRM): Embedding-Based Reward Functions for Reinforcement Learning of Transformer Language Models Authors: Alexandr Plashchinsky Published: 2025-12-07 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.06920v1 We introduce the Parent-Guided Semantic Reward Model (PGSRM), a lightweight reward framework for reinforcement learning (RL) of transformer language models. PGSRM replaces binary correctness signals, human preference data, and trained reward models with a simple signal: cosine similarity between a parent model's reference output embedding and a child model's generated output for the same input. This yields a dense, semantically meaningful reward with no human annotation or additional model training. We apply PGSRM on five language tasks and find that it produces smoother reward improvement and more stable PPO dynamics than a binary reward baseline, suggesting that embedding-based semantic rewards are a practical alternative to RLHF-style reward modeling for parent-guided alignment in smaller transformer models. --- ### Automated PRO-CTCAE Symptom Selection based on Prior Adverse Event Profiles Authors: Francois Vandenhende, Anna Georgiou, Michalis Georgiou, Theodoros Psaras, Ellie Karekla Published: 2025-12-07 Categories: cs.CL arXiv: https://arxiv.org/abs/2512.06919v1 The PRO-CTCAE is an NCI-developed patient-reported outcome system for capturing symptomatic adverse events in oncology trials. It comprises a large library drawn from the CTCAE vocabulary, and item selection for a given trial is typically guided by expected toxicity profiles from prior data. Selecting too many PRO-CTCAE items can burden patients and reduce compliance, while too few may miss important safety signals. We present an automated method to select a minimal yet comprehensive PRO-CTCAE subset based on historical safety data. Each candidate PRO-CTCAE symptom term is first mapped to its corresponding MedDRA Preferred Terms (PTs), which are then encoded into Safeterm, a high-dimensional semantic space capturing clinical and contextual diversity in MedDRA terminology. We score each candidate PRO item for relevance to the historical list of adverse event PTs and combine relevance and incidence into a utility function. Spectral analysis is then applied to the combined utility and diversity matrix to identify an orthogonal set of medical concepts that balances relevance and diversity. Symptoms are rank-ordered by importance, and a cut-off is suggested based on the explained information. The tool is implemented as part of the Safeterm trial-safety app. We evaluate its performance using simulations and oncology case studies in which PRO-CTCAE was employed. This automated approach can streamline PRO-CTCAE design by leveraging MedDRA semantics and historical data, providing an objective and reproducible method to balance signal coverage against patient burden. --- ### Know your Trajectory -- Trustworthy Reinforcement Learning deployment through Importance-Based Trajectory Analysis Authors: Clifford F, Devika Jay, Abhishek Sarkar, Satheesh K Perepu, Santhosh G S, Kaushik Dey, Balaraman Ravindran Published: 2025-12-07 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.06917v1 As Reinforcement Learning (RL) agents are increasingly deployed in real-world applications, ensuring their behavior is transparent and trustworthy is paramount. A key component of trust is explainability, yet much of the work in Explainable RL (XRL) focuses on local, single-step decisions. This paper addresses the critical need for explaining an agent's long-term behavior through trajectory-level analysis. We introduce a novel framework that ranks entire trajectories by defining and aggregating a new state-importance metric. This metric combines the classic Q-value difference with a "radical term" that captures the agent's affinity to reach its goal, providing a more nuanced measure of state criticality. We demonstrate that our method successfully identifies optimal trajectories from a heterogeneous collection of agent experiences. Furthermore, by generating counterfactual rollouts from critical states within these trajectories, we show that the agent's chosen path is robustly superior to alternatives, thereby providing a powerful "Why this, and not that?" explanation. Our experiments in standard OpenAI Gym environments validate that our proposed importance metric is more effective at identifying optimal behaviors compared to classic approaches, offering a significant step towards trustworthy autonomous systems. --- ### SoK: Trust-Authorization Mismatch in LLM Agent Interactions Authors: Guanquan Shi, Haohua Du, Zhiqiang Wang, Xiaoyu Liang, Weiwenpei Liu, Song Bian, Zhenyu Guan Published: 2025-12-07 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2512.06914v2 Large Language Models (LLMs) are evolving into autonomous agents capable of executing complex workflows via standardized protocols (e.g., MCP). However, this paradigm shifts control from deterministic code to probabilistic inference, creating a fundamental Trust-Authorization Mismatch: static permissions are structurally decoupled from the agent's fluctuating runtime trustworthiness. In this Systematization of Knowledge (SoK), we survey more than 200 representative papers to categorize the emerging landscape of agent security. We propose the Belief-Intention-Permission (B-I-P) framework as a unifying formal lens. By decomposing agent execution into three distinct stages-Belief Formation, Intent Generation, and Permission Grant-we demonstrate that diverse threats, from prompt injection to tool poisoning, share a common root cause: the desynchronization between dynamic trust states and static authorization boundaries. Using the B-I-P lens, we systematically map existing attacks and defenses and identify critical gaps where current mechanisms fail to bridge this mismatch. Finally, we outline a research agenda for shifting from static Role-Based Access Control (RBAC) to dynamic, risk-adaptive authorization. --- ### SoK: Trust-Authorization Mismatch in LLM Agent Interactions Authors: Guanquan Shi, Haohua Du, Zhiqiang Wang, Xiaoyu Liang, Weiwenpei Liu, Song Bian, Zhenyu Guan Published: 2025-12-07 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2512.06914v1 Large Language Models (LLMs) are rapidly evolving into autonomous agents capable of interacting with the external world, significantly expanding their capabilities through standardized interaction protocols. However, this paradigm revives the classic cybersecurity challenges of agency and authorization in a novel and volatile context. As decision-making shifts from deterministic code logic to probabilistic inference driven by natural language, traditional security mechanisms designed for deterministic behavior fail. It is fundamentally challenging to establish trust for unpredictable AI agents and to enforce the Principle of Least Privilege (PoLP) when instructions are ambiguous. Despite the escalating threat landscape, the academic community's understanding of this emerging domain remains fragmented, lacking a systematic framework to analyze its root causes. This paper provides a unifying formal lens for agent-interaction security. We observed that most security threats in this domain stem from a fundamental mismatch between trust evaluation and authorization policies. We introduce a novel risk analysis model centered on this trust-authorization gap. Using this model as a unifying lens, we survey and classify the implementation paths of existing, often seemingly isolated, attacks and defenses. This new framework not only unifies the field but also allows us to identify critical research gaps. Finally, we leverage our analysis to suggest a systematic research direction toward building robust, trusted agents and dynamic authorization mechanisms. --- ### Khalasi: Energy-Efficient Navigation for Surface Vehicles in Vortical Flow Fields Authors: Rushiraj Gadhvi, Sandeep Manjanna Published: 2025-12-07 Categories: cs.RO, cs.LG arXiv: https://arxiv.org/abs/2512.06912v2 For centuries, khalasi (Gujarati for sailor) have skillfully harnessed ocean currents to navigate vast waters with minimal effort. Emulating this intuition in autonomous systems remains a significant challenge, particularly for Autonomous Surface Vehicles tasked with long duration missions under strict energy budgets. In this work, we present a learning-based approach for energy-efficient surface vehicle navigation in vortical flow fields, where partial observability often undermines traditional path-planning methods. We present an end to end reinforcement learning framework based on Soft Actor Critic that learns flow-aware navigation policies using only local velocity measurements. Through extensive evaluation across diverse and dynamically rich scenarios, our method demonstrates substantial energy savings and robust generalization to previously unseen flow conditions, offering a promising path toward long term autonomy in ocean environments. The navigation paths generated by our proposed approach show an improvement in energy conservation 30 to 50 percent compared to the existing state of the art techniques. --- ### Energy-Efficient Navigation for Surface Vehicles in Vortical Flow Fields Authors: Rushiraj Gadhvi, Sandeep Manjanna Published: 2025-12-07 Categories: cs.RO, cs.LG arXiv: https://arxiv.org/abs/2512.06912v1 For centuries, khalasi have skillfully harnessed ocean currents to navigate vast waters with minimal effort. Emulating this intuition in autonomous systems remains a significant challenge, particularly for Autonomous Surface Vehicles tasked with long duration missions under strict energy budgets. In this work, we present a learning-based approach for energy-efficient surface vehicle navigation in vortical flow fields, where partial observability often undermines traditional path-planning methods. We present an end to end reinforcement learning framework based on Soft Actor Critic that learns flow-aware navigation policies using only local velocity measurements. Through extensive evaluation across diverse and dynamically rich scenarios, our method demonstrates substantial energy savings and robust generalization to previously unseen flow conditions, offering a promising path toward long term autonomy in ocean environments. The navigation paths generated by our proposed approach show an improvement in energy conservation 30 to 50 percent compared to the existing state of the art techniques. --- ### MINES: Explainable Anomaly Detection through Web API Invariant Inference Authors: Wenjie Zhang, Yun Lin, Chun Fung Amos Kwok, Xiwen Teoh, Xiaofei Xie, Frank Liauw, Hongyu Zhang, Jin Song Dong Published: 2025-12-07 Categories: cs.SE, cs.CR, cs.DB, cs.LG arXiv: https://arxiv.org/abs/2512.06906v2 Detecting the anomalies of web applications, important infrastructures for running modern companies and governments, is crucial for providing reliable web services. Many modern web applications operate on web APIs (e.g., RESTful, SOAP, and WebSockets), their exposure invites intended attacks or unintended illegal visits, causing abnormal system behaviors. However, such anomalies can share very similar logs with normal logs, missing crucial information (which could be in database) for log discrimination. Further, log instances can be also noisy, which can further mislead the state-of-the-art log learning solutions to learn spurious correlation, resulting superficial models and rules for anomaly detection. In this work, we propose MINES which infers explainable API invariants for anomaly detection from the schema level instead of detailed raw log instances, which can (1) significantly discriminate noise in logs to identify precise normalities and (2) detect abnormal behaviors beyond the instrumented logs. Technically, MINES (1) converts API signatures into table schema to enhance the original database shema; and (2) infers the potential database constraints on the enhanced database schema to capture the potential relationships between APIs and database tables. MINES uses LLM for extracting potential relationship based on two given table structures; and use normal log instances to reject and accept LLM-generated invariants. Finally, MINES translates the inferred constraints into invariants to generate Python code for verifying the runtime logs. We extensively evaluate MINES on web-tamper attacks on the benchmarks of TrainTicket, NiceFish, Gitea, Mastodon, and NextCloud against baselines such as LogRobust, LogFormer, and WebNorm. The results show that MINES achieves high recall for the anomalies while introducing almost zero false positives, indicating a new state-of-the-art. --- ### MINES: Explainable Anomaly Detection through Web API Invariant Inference Authors: Wenjie Zhang, Yun Lin, Chun Fung Amos Kwok, Xiwen Teoh, Xiaofei Xie, Frank Liauw, Hongyu Zhang, Jin Song Dong Published: 2025-12-07 Categories: cs.SE, cs.CR, cs.DB, cs.LG arXiv: https://arxiv.org/abs/2512.06906v1 Detecting the anomalies of web applications, important infrastructures for running modern companies and governments, is crucial for providing reliable web services. Many modern web applications operate on web APIs (e.g., RESTful, SOAP, and WebSockets), their exposure invites intended attacks or unintended illegal visits, causing abnormal system behaviors. However, such anomalies can share very similar logs with normal logs, missing crucial information (which could be in database) for log discrimination. Further, log instances can be also noisy, which can further mislead the state-of-the-art log learning solutions to learn spurious correlation, resulting superficial models and rules for anomaly detection. In this work, we propose MINES which infers explainable API invariants for anomaly detection from the schema level instead of detailed raw log instances, which can (1) significantly discriminate noise in logs to identify precise normalities and (2) detect abnormal behaviors beyond the instrumented logs. Technically, MINES (1) converts API signatures into table schema to enhance the original database shema; and (2) infers the potential database constraints on the enhanced database schema to capture the potential relationships between APIs and database tables. MINES uses LLM for extracting potential relationship based on two given table structures; and use normal log instances to reject and accept LLM-generated invariants. Finally, MINES translates the inferred constraints into invariants to generate Python code for verifying the runtime logs. We extensively evaluate MINES on web-tamper attacks on the benchmarks of TrainTicket, NiceFish, Gitea, Mastodon, and NextCloud against baselines such as LogRobust, LogFormer, and WebNorm. The results show that MINES achieves high recall for the anomalies while introducing almost zero false positives, indicating a new state-of-the-art. --- ### Scaling Zero-Shot Reference-to-Video Generation Authors: Zijian Zhou, Shikun Liu, Haozhe Liu, Haonan Qiu, Zhaochong An, Weiming Ren, Zhiheng Liu, Xiaoke Huang, Kam Woh Ng, Tian Xie, Xiao Han, Yuren Cong et al. Published: 2025-12-07 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.06905v1 Reference-to-video (R2V) generation aims to synthesize videos that align with a text prompt while preserving the subject identity from reference images. However, current R2V methods are hindered by the reliance on explicit reference image-video-text triplets, whose construction is highly expensive and difficult to scale. We bypass this bottleneck by introducing Saber, a scalable zero-shot framework that requires no explicit R2V data. Trained exclusively on video-text pairs, Saber employs a masked training strategy and a tailored attention-based model design to learn identity-consistent and reference-aware representations. Mask augmentation techniques are further integrated to mitigate copy-paste artifacts common in reference-to-video generation. Moreover, Saber demonstrates remarkable generalization capabilities across a varying number of references and achieves superior performance on the OpenS2V-Eval benchmark compared to methods trained with R2V data. --- ### BabelCoder: Agentic Code Translation with Specification Alignment Authors: Fazle Rabbi, Soumit Kanti Saha, Tri Minh Triet Pham, Song Wang, Jinqiu Yang Published: 2025-12-07 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2512.06902v2 As software systems evolve, developers increasingly work across multiple programming languages and often face the need to migrate code from one language to another. While automatic code translation offers a promising solution, it has long remained a challenging task. Recent advancements in Large Language Models (LLMs) have shown potential for this task, yet existing approaches remain limited in accuracy and fail to effectively leverage contextual and structural cues within the code. Prior work has explored translation and repair mechanisms, but lacks a structured, agentic framework where multiple specialized agents collaboratively improve translation quality. In this work, we introduce BabelCoder, an agentic framework that performs code translation by decomposing the task into specialized agents for translation, testing, and refinement, each responsible for a specific aspect such as generating code, validating correctness, or repairing errors. We evaluate BabelCoder on four benchmark datasets and compare it against four state-of-the-art baselines. BabelCoder outperforms existing methods by 0.5%-13.5% in 94% of cases, achieving an average accuracy of 94.16%. --- ### BabelCoder: Agentic Code Translation with Specification Alignment Authors: Fazle Rabbi, Soumit Kanti Saha, Tri Minh Triet Pham, Song Wang, Jinqiu Yang Published: 2025-12-07 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2512.06902v1 As software systems evolve, developers increasingly work across multiple programming languages and often face the need to migrate code from one language to another. While automatic code translation offers a promising solution, it has long remained a challenging task. Recent advancements in Large Language Models (LLMs) have shown potential for this task, yet existing approaches remain limited in accuracy and fail to effectively leverage contextual and structural cues within the code. Prior work has explored translation and repair mechanisms, but lacks a structured, agentic framework where multiple specialized agents collaboratively improve translation quality. In this work, we introduce BabelCoder, an agentic framework that performs code translation by decomposing the task into specialized agents for translation, testing, and refinement, each responsible for a specific aspect such as generating code, validating correctness, or repairing errors. We evaluate BabelCoder on four benchmark datasets and compare it against four state-of-the-art baselines. BabelCoder outperforms existing methods by 0.5%-13.5% in 94% of cases, achieving an average accuracy of 94.16%. --- ### Overcoming Small Data Limitations in Video-Based Infant Respiration Estimation Authors: Liyang Song, Hardik Bishnoi, Sai Kumar Reddy Manne, Sarah Ostadabbas, Briana J. Taylor, Michael Wan Published: 2025-12-07 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.06888v1 The development of contactless respiration monitoring for infants could enable advances in the early detection and treatment of breathing irregularities, which are associated with neurodevelopmental impairments and conditions like sudden infant death syndrome (SIDS). But while respiration estimation for adults is supported by a robust ecosystem of computer vision algorithms and video datasets, only one small public video dataset with annotated respiration data for infant subjects exists, and there are no reproducible algorithms which are effective for infants. We introduce the annotated infant respiration dataset of 400 videos (AIR-400), contributing 275 new, carefully annotated videos from 10 recruited subjects to the public corpus. We develop the first reproducible pipelines for infant respiration estimation, based on infant-specific region-of-interest detection and spatiotemporal neural processing enhanced by optical flow inputs. We establish, through comprehensive experiments, the first reproducible benchmarks for the state-of-the-art in vision-based infant respiration estimation. We make our dataset, code repository, and trained models available for public use. --- ### Balanced Learning for Domain Adaptive Semantic Segmentation Authors: Wangkai Li, Rui Sun, Bohao Liao, Zhaoyang Li, Tianzhu Zhang Published: 2025-12-07 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.06886v1 Unsupervised domain adaptation (UDA) for semantic segmentation aims to transfer knowledge from a labeled source domain to an unlabeled target domain. Despite the effectiveness of self-training techniques in UDA, they struggle to learn each class in a balanced manner due to inherent class imbalance and distribution shift in both data and label space between domains. To address this issue, we propose Balanced Learning for Domain Adaptation (BLDA), a novel approach to directly assess and alleviate class bias without requiring prior knowledge about the distribution shift. First, we identify over-predicted and under-predicted classes by analyzing the distribution of predicted logits. Subsequently, we introduce a post-hoc approach to align the logits distributions across different classes using shared anchor distributions. To further consider the network's need to generate unbiased pseudo-labels during self-training, we estimate logits distributions online and incorporate logits correction terms into the loss function. Moreover, we leverage the resulting cumulative density as domain-shared structural knowledge to connect the source and target domains. Extensive experiments on two standard UDA semantic segmentation benchmarks demonstrate that BLDA consistently improves performance, especially for under-predicted classes, when integrated into various existing methods. Code is available at https://github.com/Woof6/BLDA. --- ### JoPano: Unified Panorama Generation via Joint Modeling Authors: Wancheng Feng, Chen An, Zhenliang He, Meina Kan, Shiguang Shan, Lukun Wang Published: 2025-12-07 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2512.06885v1 Panorama generation has recently attracted growing interest in the research community, with two core tasks, text-to-panorama and view-to-panorama generation. However, existing methods still face two major challenges: their U-Net-based architectures constrain the visual quality of the generated panoramas, and they usually treat the two core tasks independently, which leads to modeling redundancy and inefficiency. To overcome these challenges, we propose a joint-face panorama (JoPano) generation approach that unifies the two core tasks within a DiT-based model. To transfer the rich generative capabilities of existing DiT backbones learned from natural images to the panorama domain, we propose a Joint-Face Adapter built on the cubemap representation of panoramas, which enables a pretrained DiT to jointly model and generate different views of a panorama. We further apply Poisson Blending to reduce seam inconsistencies that often appear at the boundaries between cube faces. Correspondingly, we introduce Seam-SSIM and Seam-Sobel metrics to quantitatively evaluate the seam consistency. Moreover, we propose a condition switching mechanism that unifies text-to-panorama and view-to-panorama tasks within a single model. Comprehensive experiments show that JoPano can generate high-quality panoramas for both text-to-panorama and view-to-panorama generation tasks, achieving state-of-the-art performance on FID, CLIP-FID, IS, and CLIP-Score metrics. --- ### Hierarchical Image-Guided 3D Point Cloud Segmentation in Industrial Scenes via Multi-View Bayesian Fusion Authors: Yu Zhu, Naoya Chiba, Koichi Hashimoto Published: 2025-12-07 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.06882v1 Reliable 3D segmentation is critical for understanding complex scenes with dense layouts and multi-scale objects, as commonly seen in industrial environments. In such scenarios, heavy occlusion weakens geometric boundaries between objects, and large differences in object scale will cause end-to-end models fail to capture both coarse and fine details accurately. Existing 3D point-based methods require costly annotations, while image-guided methods often suffer from semantic inconsistencies across views. To address these challenges, we propose a hierarchical image-guided 3D segmentation framework that progressively refines segmentation from instance-level to part-level. Instance segmentation involves rendering a top-view image and projecting SAM-generated masks prompted by YOLO-World back onto the 3D point cloud. Part-level segmentation is subsequently performed by rendering multi-view images of each instance obtained from the previous stage and applying the same 2D segmentation and back-projection process at each view, followed by Bayesian updating fusion to ensure semantic consistency across views. Experiments on real-world factory data demonstrate that our method effectively handles occlusion and structural complexity, achieving consistently high per-class mIoU scores. Additional evaluations on public dataset confirm the generalization ability of our framework, highlighting its robustness, annotation efficiency, and adaptability to diverse 3D environments. --- ### WisPaper: Your AI Scholar Search Engine Authors: Li Ju, Jun Zhao, Mingxu Chai, Ziyu Shen, Xiangyang Wang, Yage Geng, Chunchun Ma, Hao Peng, Guangbin Li, Tao Li, Chengyong Liao, Fu Wang et al. Published: 2025-12-07 Categories: cs.IR, cs.AI arXiv: https://arxiv.org/abs/2512.06879v3 We present \textsc{WisPaper}, an end-to-end agent system that transforms how researchers discover, organize, and track academic literature. The system addresses two fundamental challenges. (1)~\textit{Semantic search limitations}: existing academic search engines match keywords but cannot verify whether papers truly address complex research questions; and (2)~\textit{Workflow fragmentation}: researchers must manually stitch together separate tools for discovery, organization, and monitoring. \textsc{WisPaper} tackles these through three integrated modules. \textbf{Scholar Search} combines rapid keyword retrieval with \textit{Deep Search}, in which an agentic model, \textsc{WisModel}, validates candidate papers against user queries through structured reasoning. Discovered papers flow seamlessly into \textbf{Library} with one click, where systematic organization progressively builds a user profile that sharpens the recommendations of \textbf{AI Feeds}, which continuously surfaces relevant new publications and in turn guides subsequent exploration, closing the loop from discovery to long-term awareness. On TaxoBench, \textsc{WisPaper} achieves 22.26\% recall, surpassing the O3 baseline (20.92\%). Furthermore, \textsc{WisModel} attains 93.70\% validation accuracy, effectively mitigating retrieval hallucinations. --- ### WisPaper: Your AI Scholar Search Engine Authors: Li Ju, Jun Zhao, Mingxu Chai, Ziyu Shen, Xiangyang Wang, Yage Geng, Chunchun Ma, Hao Peng, Guangbin Li, Tao Li, Chengyong Liao, Fu Wang et al. Published: 2025-12-07 Categories: cs.IR, cs.AI arXiv: https://arxiv.org/abs/2512.06879v1 Researchers struggle to efficiently locate and manage relevant literature within the exponentially growing body of scientific publications. We present \textsc{WisPaper}, an intelligent academic retrieval and literature management platform that addresses this challenge through three integrated capabilities: (1) \textit{Scholar Search}, featuring both quick keyword-based and deep agentic search modes for efficient paper discovery; (2) \textit{Library}, a customizable knowledge base for systematic literature organization; and (3) \textit{AI Feeds}, an intelligent recommendation system that automatically delivers relevant new publications based on user interests. Unlike existing academic tools, \textsc{WisPaper} provides a closed-loop workflow that seamlessly connects literature discovery, management, and continuous tracking of research frontiers. Our multilingual and multidisciplinary system significantly reduces the time researchers from diverse backgrounds spend on paper screening and management, enabling them to focus on their core research activities. The platform is publicly accessible and serves researchers across academia and industry. --- ### SceneMixer: Exploring Convolutional Mixing Networks for Remote Sensing Scene Classification Authors: Mohammed Q. Alkhatib, Ali Jamali, Swalpa Kumar Roy Published: 2025-12-07 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.06877v1 Remote sensing scene classification plays a key role in Earth observation by enabling the automatic identification of land use and land cover (LULC) patterns from aerial and satellite imagery. Despite recent progress with convolutional neural networks (CNNs) and vision transformers (ViTs), the task remains challenging due to variations in spatial resolution, viewpoint, orientation, and background conditions, which often reduce the generalization ability of existing models. To address these challenges, this paper proposes a lightweight architecture based on the convolutional mixer paradigm. The model alternates between spatial mixing through depthwise convolutions at multiple scales and channel mixing through pointwise operations, enabling efficient extraction of both local and contextual information while keeping the number of parameters and computations low. Extensive experiments were conducted on the AID and EuroSAT benchmarks. The proposed model achieved overall accuracy, average accuracy, and Kappa values of 74.7%, 74.57%, and 73.79 on the AID dataset, and 93.90%, 93.93%, and 93.22 on EuroSAT, respectively. These results demonstrate that the proposed approach provides a good balance between accuracy and efficiency compared with widely used CNN- and transformer-based models. Code will be publicly available on: https://github.com/mqalkhatib/SceneMixer --- ### An Analysis of Large Language Models for Simulating User Responses in Surveys Authors: Ziyun Yu, Yiru Zhou, Chen Zhao, Hongyi Wen Published: 2025-12-07 Categories: cs.CL arXiv: https://arxiv.org/abs/2512.06874v1 Using Large Language Models (LLMs) to simulate user opinions has received growing attention. Yet LLMs, especially trained with reinforcement learning from human feedback (RLHF), are known to exhibit biases toward dominant viewpoints, raising concerns about their ability to represent users from diverse demographic and cultural backgrounds. In this work, we examine the extent to which LLMs can simulate human responses to cross-domain survey questions through direct prompting and chain-of-thought prompting. We further propose a claim diversification method CLAIMSIM, which elicits viewpoints from LLM parametric knowledge as contextual input. Experiments on the survey question answering task indicate that, while CLAIMSIM produces more diverse responses, both approaches struggle to accurately simulate users. Further analysis reveals two key limitations: (1) LLMs tend to maintain fixed viewpoints across varying demographic features, and generate single-perspective claims; and (2) when presented with conflicting claims, LLMs struggle to reason over nuanced differences among demographic features, limiting their ability to adapt responses to specific user profiles. --- ### Towards Robust Pseudo-Label Learning in Semantic Segmentation: An Encoding Perspective Authors: Wangkai Li, Rui Sun, Zhaoyang Li, Tianzhu Zhang Published: 2025-12-07 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.06870v2 Pseudo-label learning is widely used in semantic segmentation, particularly in label-scarce scenarios such as unsupervised domain adaptation (UDA) and semisupervised learning (SSL). Despite its success, this paradigm can generate erroneous pseudo-labels, which are further amplified during training due to utilization of one-hot encoding. To address this issue, we propose ECOCSeg, a novel perspective for segmentation models that utilizes error-correcting output codes (ECOC) to create a fine-grained encoding for each class. ECOCSeg offers several advantages. First, an ECOC-based classifier is introduced, enabling model to disentangle classes into attributes and handle partial inaccurate bits, improving stability and generalization in pseudo-label learning. Second, a bit-level label denoising mechanism is developed to generate higher-quality pseudo-labels, providing adequate and robust supervision for unlabeled images. ECOCSeg can be easily integrated with existing methods and consistently demonstrates significant improvements on multiple UDA and SSL benchmarks across different segmentation architectures. Code is available at https://github.com/Woof6/ECOCSeg. --- ### Towards Robust Pseudo-Label Learning in Semantic Segmentation: An Encoding Perspective Authors: Wangkai Li, Rui Sun, Zhaoyang Li, Tianzhu Zhang Published: 2025-12-07 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.06870v1 Pseudo-label learning is widely used in semantic segmentation, particularly in label-scarce scenarios such as unsupervised domain adaptation (UDA) and semisupervised learning (SSL). Despite its success, this paradigm can generate erroneous pseudo-labels, which are further amplified during training due to utilization of one-hot encoding. To address this issue, we propose ECOCSeg, a novel perspective for segmentation models that utilizes error-correcting output codes (ECOC) to create a fine-grained encoding for each class. ECOCSeg offers several advantages. First, an ECOC-based classifier is introduced, enabling model to disentangle classes into attributes and handle partial inaccurate bits, improving stability and generalization in pseudo-label learning. Second, a bit-level label denoising mechanism is developed to generate higher-quality pseudo-labels, providing adequate and robust supervision for unlabeled images. ECOCSeg can be easily integrated with existing methods and consistently demonstrates significant improvements on multiple UDA and SSL benchmarks across different segmentation architectures. Code is available at https://github.com/Woof6/ECOCSeg. --- ### Rhea: Role-aware Heuristic Episodic Attention for Conversational LLMs Authors: Wanyang Hong, Zhaoning Zhang, Yi Chen, Libo Zhang, Baihui Liu, Linbo Qiao, Zhiliang Tian, Dongsheng Li Published: 2025-12-07 Categories: cs.CL arXiv: https://arxiv.org/abs/2512.06869v1 Large Language Models (LLMs) have achieved remarkable performance on single-turn tasks, yet their effectiveness deteriorates in multi-turn conversations. We define this phenomenon as cumulative contextual decay - a progressive degradation of contextual integrity caused by attention pollution, dilution, and drift. To address this challenge, we propose Rhea (Role-aware Heuristic Episodic Attention), a novel framework that decouples conversation history into two functionally independent memory modules: (1) an Instructional Memory (IM) that persistently stores high-fidelity global constraints via a structural priority mechanism, and (2) an Episodic Memory (EM) that dynamically manages user-model interactions via asymmetric noise control and heuristic context retrieval. During inference, Rhea constructs a high signal-to-noise context by applying its priority attention: selectively integrating relevant episodic information while always prioritizing global instructions. To validate this approach, experiments on multiple multi-turn conversation benchmarks - including MT-Eval and Long-MT-Bench+ - show that Rhea mitigates performance decay and improves overall accuracy by 1.04 points on a 10-point scale (a 16% relative gain over strong baselines). Moreover, Rhea maintains near-perfect instruction fidelity (IAR > 8.1) across long-horizon interactions. These results demonstrate that Rhea provides a principled and effective framework for building more precise, instruction-consistent conversational LLMs. --- ### Dynamic Visual SLAM using a General 3D Prior Authors: Xingguang Zhong, Liren Jin, Marija Popović, Jens Behley, Cyrill Stachniss Published: 2025-12-07 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2512.06868v1 Reliable incremental estimation of camera poses and 3D reconstruction is key to enable various applications including robotics, interactive visualization, and augmented reality. However, this task is particularly challenging in dynamic natural environments, where scene dynamics can severely deteriorate camera pose estimation accuracy. In this work, we propose a novel monocular visual SLAM system that can robustly estimate camera poses in dynamic scenes. To this end, we leverage the complementary strengths of geometric patch-based online bundle adjustment and recent feed-forward reconstruction models. Specifically, we propose a feed-forward reconstruction model to precisely filter out dynamic regions, while also utilizing its depth prediction to enhance the robustness of the patch-based visual SLAM. By aligning depth prediction with estimated patches from bundle adjustment, we robustly handle the inherent scale ambiguities of the batch-wise application of the feed-forward reconstruction model. --- ### Do Persona-Infused LLMs Affect Performance in a Strategic Reasoning Game? Authors: John Licato, Stephen Steinle, Brayden Hollis Published: 2025-12-07 Categories: cs.AI arXiv: https://arxiv.org/abs/2512.06867v1 Although persona prompting in large language models appears to trigger different styles of generated text, it is unclear whether these translate into measurable behavioral differences, much less whether they affect decision-making in an adversarial strategic environment that we provide as open-source. We investigate the impact of persona prompting on strategic performance in PERIL, a world-domination board game. Specifically, we compare the effectiveness of persona-derived heuristic strategies to those chosen manually. Our findings reveal that certain personas associated with strategic thinking improve game performance, but only when a mediator is used to translate personas into heuristic values. We introduce this mediator as a structured translation process, inspired by exploratory factor analysis, that maps LLM-generated inventory responses into heuristics. Results indicate our method enhances heuristic reliability and face validity compared to directly inferred heuristics, allowing us to better study the effect of persona types on decision making. These insights advance our understanding of how persona prompting influences LLM-based decision-making and propose a heuristic generation method that applies psychometric principles to LLMs. --- ### Less Is More, but Where? Dynamic Token Compression via LLM-Guided Keyframe Prior Authors: Yulin Li, Haokun Gui, Ziyang Fan, Junjie Wang, Bin Kang, Bin Chen, Zhuotao Tian Published: 2025-12-07 Categories: cs.CV, cs.AI, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2512.06866v1 Recent advances in Video Large Language Models (VLLMs) have achieved remarkable video understanding capabilities, yet face critical efficiency bottlenecks due to quadratic computational growth with lengthy visual token sequences of long videos. While existing keyframe sampling methods can improve temporal modeling efficiency, additional computational cost is introduced before feature encoding, and the binary frame selection paradigm is found suboptimal. Therefore, in this work, we propose Dynamic Token compression via LLM-guided Keyframe prior (DyToK), a training-free paradigm that enables dynamic token compression by harnessing VLLMs' inherent attention mechanisms. Our analysis reveals that VLLM attention layers naturally encoding query-conditioned keyframe priors, by which DyToK dynamically adjusts per-frame token retention ratios, prioritizing semantically rich frames while suppressing redundancies. Extensive experiments demonstrate that DyToK achieves state-of-the-art efficiency-accuracy tradeoffs. DyToK shows plug-and-play compatibility with existing compression methods, such as VisionZip and FastV, attaining 4.3x faster inference while preserving accuracy across multiple VLLMs, such as LLaVA-OneVision and Qwen2.5-VL. Code is available at https://github.com/yu-lin-li/DyToK . --- ### Spatial Retrieval Augmented Autonomous Driving Authors: Xiaosong Jia, Chenhe Zhang, Yule Jiang, Songbur Wong, Zhiyuan Zhang, Chen Chen, Shaofeng Zhang, Xuanhe Zhou, Xue Yang, Junchi Yan, Yu-Gang Jiang Published: 2025-12-07 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.06865v1 Existing autonomous driving systems rely on onboard sensors (cameras, LiDAR, IMU, etc) for environmental perception. However, this paradigm is limited by the drive-time perception horizon and often fails under limited view scope, occlusion or extreme conditions such as darkness and rain. In contrast, human drivers are able to recall road structure even under poor visibility. To endow models with this ``recall" ability, we propose the spatial retrieval paradigm, introducing offline retrieved geographic images as an additional input. These images are easy to obtain from offline caches (e.g, Google Maps or stored autonomous driving datasets) without requiring additional sensors, making it a plug-and-play extension for existing AD tasks. For experiments, we first extend the nuScenes dataset with geographic images retrieved via Google Maps APIs and align the new data with ego-vehicle trajectories. We establish baselines across five core autonomous driving tasks: object detection, online mapping, occupancy prediction, end-to-end planning, and generative world modeling. Extensive experiments show that the extended modality could enhance the performance of certain tasks. We will open-source dataset curation code, data, and benchmarks for further study of this new autonomous driving paradigm. --- ### Boosting Unsupervised Video Instance Segmentation with Automatic Quality-Guided Self-Training Authors: Kaixuan Lu, Mehmet Onurcan Kaya, Dim P. Papadopoulos Published: 2025-12-07 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.06864v1 Video Instance Segmentation (VIS) faces significant annotation challenges due to its dual requirements of pixel-level masks and temporal consistency labels. While recent unsupervised methods like VideoCutLER eliminate optical flow dependencies through synthetic data, they remain constrained by the synthetic-to-real domain gap. We present AutoQ-VIS, a novel unsupervised framework that bridges this gap through quality-guided self-training. Our approach establishes a closed-loop system between pseudo-label generation and automatic quality assessment, enabling progressive adaptation from synthetic to real videos. Experiments demonstrate state-of-the-art performance with 52.6 $\text{AP}_{50}$ on YouTubeVIS-2019 $\texttt{val}$ set, surpassing the previous state-of-the-art VideoCutLER by 4.4%, while requiring no human annotations. This demonstrates the viability of quality-aware self-training for unsupervised VIS. We will release the code at https://github.com/wcbup/AutoQ-VIS. --- ### Omni-Referring Image Segmentation Authors: Qiancheng Zheng, Yunhang Shen, Gen Luo, Baiyang Song, Xing Sun, Xiaoshuai Sun, Yiyi Zhou, Rongrong Ji Published: 2025-12-07 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.06862v1 In this paper, we propose a novel task termed Omni-Referring Image Segmentation (OmniRIS) towards highly generalized image segmentation. Compared with existing unimodally conditioned segmentation tasks, such as RIS and visual RIS, OmniRIS supports the input of text instructions and reference images with masks, boxes or scribbles as omni-prompts. This property makes it can well exploit the intrinsic merits of both text and visual modalities, i.e., granular attribute referring and uncommon object grounding, respectively. Besides, OmniRIS can also handle various segmentation settings, such as one v.s. many and many v.s. many, further facilitating its practical use. To promote the research of OmniRIS, we also rigorously design and construct a large dataset termed OmniRef, which consists of 186,939 omni-prompts for 30,956 images, and establish a comprehensive evaluation system. Moreover, a strong and general baseline termed OmniSegNet is also proposed to tackle the key challenges of OmniRIS, such as omni-prompt encoding. The extensive experiments not only validate the capability of OmniSegNet in following omni-modal instructions, but also show the superiority of OmniRIS for highly generalized image segmentation. --- ### JT-DA: Enhancing Data Analysis with Tool-Integrated Table Reasoning Large Language Models Authors: Ce Chi, Xing Wang, Zhendong Wang, Xiaofan Liu, Ce Li, Zhiyan Song, Chen Zhao, Kexin Yang, Boshen Shi, Jingjing Yang, Chao Deng, Junlan Feng Published: 2025-12-07 Categories: cs.AI arXiv: https://arxiv.org/abs/2512.06859v1 In this work, we present JT-DA-8B (JiuTian Data Analyst 8B), a specialized large language model designed for complex table reasoning tasks across diverse real-world scenarios. To address the lack of high-quality supervision in tabular reasoning scenarios, we construct a comprehensive and diverse training corpus with 34 well-defined table reasoning tasks, by aggregating 29 public table QA datasets and 3 million tables. An automatic pipeline is proposed to generate realistic multi-step analytical tasks involving reasoning patterns. The model is trained upon open-source JT-Coder-8B model, an 8B-parameter decoder-only foundation model trained from scratch. In the training stage, we leverage LLM-based scoring and workflow-aligned filtering to distill high-quality, table-centric data. Both supervised fine-tuning (SFT) and Reinforcement learning (RL) are adopted to optimize our model. Afterwards, a four-stage table reasoning workflow is proposed, including table preprocessing, table sensing, tool-integrated reasoning, and prompt engineering, to improve model interpretability and execution accuracy. Experimental results show that JT-DA-8B achieves strong performance in various table reasoning tasks, demonstrating the effectiveness of data-centric generation and workflow-driven optimization. --- ### ArchPower: Dataset for Architecture-Level Power Modeling of Modern CPU Design Authors: Qijun Zhang, Yao Lu, Mengming Li, Shang Liu, Zhiyao Xie Published: 2025-12-07 Categories: cs.AR, cs.AI arXiv: https://arxiv.org/abs/2512.06854v1 Power is the primary design objective of large-scale integrated circuits (ICs), especially for complex modern processors (i.e., CPUs). Accurate CPU power evaluation requires designers to go through the whole time-consuming IC implementation process, easily taking months. At the early design stage (e.g., architecture-level), classical power models are notoriously inaccurate. Recently, ML-based architecture-level power models have been proposed to boost accuracy, but the data availability is a severe challenge. Currently, there is no open-source dataset for this important ML application. A typical dataset generation process involves correct CPU design implementation and repetitive execution of power simulation flows, requiring significant design expertise, engineering effort, and execution time. Even private in-house datasets often fail to reflect realistic CPU design scenarios. In this work, we propose ArchPower, the first open-source dataset for architecture-level processor power modeling. We go through complex and realistic design flows to collect the CPU architectural information as features and the ground-truth simulated power as labels. Our dataset includes 200 CPU data samples, collected from 25 different CPU configurations when executing 8 different workloads. There are more than 100 architectural features in each data sample, including both hardware and event parameters. The label of each sample provides fine-grained power information, including the total design power and the power for each of the 11 components. Each power value is further decomposed into four fine-grained power groups: combinational logic power, sequential logic power, memory power, and clock power. ArchPower is available at https://github.com/hkust-zhiyao/ArchPower. --- ### Formal that "Floats" High: Formal Verification of Floating Point Arithmetic Authors: Hansa Mohanty, Vaisakh Naduvodi Viswambharan, Deepak Narayan Gadde Published: 2025-12-07 Categories: cs.LO, cs.AI, cs.AR arXiv: https://arxiv.org/abs/2512.06850v1 Formal verification of floating-point arithmetic remains challenging due to non-linear arithmetic behavior and the tight coupling between control and datapath logic. Existing approaches often rely on high-level C models for equivalence checking against Register Transfer Level (RTL) designs, but this introduces abstraction gaps, translation overhead, and limits scalability at the RTL level. To address these challenges, this paper presents a scalable methodology for verifying floating-point arithmetic using direct RTL-to-RTL model checking against a golden reference model. The approach adopts a divide-and conquer strategy that decomposes verification into modular stages, each captured by helper assertions and lemmas that collectively prove a main correctness theorem. Counterexample (CEX)-guided refinement is used to iteratively localize and resolve implementation defects, while targeted fault injection validates the robustness of the verification process against precision-critical datapath errors. To assess scalability and practicality, the methodology is extended with agentic AI-based formal property generation, integrating large language model (LLM)-driven automation with Human-in-the-Loop (HITL) refinement. Coverage analysis evaluates the effectiveness of the approach by comparing handwritten and AI-generated properties in both RTL-to-RTL model checking and standalone RTL verification settings. Results show that direct RTL-to-RTL model checking achieves higher coverage efficiency and requires fewer assertions than standalone verification, especially when combined with AI-generated properties refined through HITL guidance. --- ### Hide-and-Seek Attribution: Weakly Supervised Segmentation of Vertebral Metastases in CT Authors: Matan Atad, Alexander W. Marka, Lisa Steinhelfer, Anna Curto-Vilalta, Yannik Leonhardt, Sarah C. Foreman, Anna-Sophia Walburga Dietrich, Robert Graf, Alexandra S. Gersing, Bjoern Menze, Daniel Rueckert, Jan S. Kirschke et al. Published: 2025-12-07 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2512.06849v2 Accurate segmentation of vertebral metastasis in CT is clinically important yet difficult to scale, as voxel-level annotations are scarce and both lytic and blastic lesions often resemble benign degenerative changes. We introduce a 2D weakly supervised method trained solely on vertebra-level healthy/malignant labels, without any lesion masks. The method combines a Diffusion Autoencoder (DAE) that produces a classifier-guided healthy edit of each vertebra with pixel-wise difference maps that propose suspect candidate lesions. To determine which regions truly reflect malignancy, we introduce Hide-and-Seek Attribution: each candidate is revealed in turn while all others are hidden, the edited image is projected back to the data manifold by the DAE, and a latent-space classifier quantifies the isolated malignant contribution of that component. High-scoring regions form the final lytic or blastic segmentation. On held-out radiologist annotations, we achieve strong blastic/lytic performance despite no mask supervision (F1: 0.91/0.85; Dice: 0.87/0.78), exceeding baselines (F1: 0.79/0.67; Dice: 0.74/0.55). These results show that vertebra-level labels can be transformed into reliable lesion masks, demonstrating that generative editing combined with selective occlusion supports accurate weakly supervised segmentation in CT. --- ### Hide-and-Seek Attribution: Weakly Supervised Segmentation of Vertebral Metastases in CT Authors: Matan Atad, Alexander W. Marka, Lisa Steinhelfer, Anna Curto-Vilalta, Yannik Leonhardt, Sarah C. Foreman, Anna-Sophia Walburga Dietrich, Robert Graf, Alexandra S. Gersing, Bjoern Menze, Daniel Rueckert, Jan S. Kirschke et al. Published: 2025-12-07 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2512.06849v1 Accurate segmentation of vertebral metastasis in CT is clinically important yet difficult to scale, as voxel-level annotations are scarce and both lytic and blastic lesions often resemble benign degenerative changes. We introduce a weakly supervised method trained solely on vertebra-level healthy/malignant labels, without any lesion masks. The method combines a Diffusion Autoencoder (DAE) that produces a classifier-guided healthy edit of each vertebra with pixel-wise difference maps that propose candidate lesion regions. To determine which regions truly reflect malignancy, we introduce Hide-and-Seek Attribution: each candidate is revealed in turn while all others are hidden, the edited image is projected back to the data manifold by the DAE, and a latent-space classifier quantifies the isolated malignant contribution of that component. High-scoring regions form the final lytic or blastic segmentation. On held-out radiologist annotations, we achieve strong blastic/lytic performance despite no mask supervision (F1: 0.91/0.85; Dice: 0.87/0.78), exceeding baselines (F1: 0.79/0.67; Dice: 0.74/0.55). These results show that vertebra-level labels can be transformed into reliable lesion masks, demonstrating that generative editing combined with selective occlusion supports accurate weakly supervised segmentation in CT. --- ### AquaFusionNet: Lightweight VisionSensor Fusion Framework for Real-Time Pathogen Detection and Water Quality Anomaly Prediction on Edge Devices Authors: Sepyan Purnama Kristanto, Lutfi Hakim, Hermansyah Published: 2025-12-07 Categories: cs.CL, cs.CV arXiv: https://arxiv.org/abs/2512.06848v1 Evidence from many low and middle income regions shows that microbial contamination in small scale drinking water systems often fluctuates rapidly, yet existing monitoring tools capture only fragments of this behaviour. Microscopic imaging provides organism level visibility, whereas physicochemical sensors reveal shortterm changes in water chemistry; in practice, operators must interpret these streams separately, making realtime decision-making unreliable. This study introduces AquaFusionNet, a lightweight cross-modal framework that unifies both information sources inside a single edge deployable model. Unlike prior work that treats microscopic detection and water quality prediction as independent tasks, AquaFusionNet learns the statistical dependencies between microbial appearance and concurrent sensor dynamics through a gated crossattention mechanism designed specifically for lowpower hardware. The framework is trained on AquaMicro12K, a new dataset comprising 12,846 annotated 1000 micrographs curated for drinking water contexts, an area where publicly accessible microscopic datasets are scarce. Deployed for six months across seven facilities in East Java, Indonesia, the system processed 1.84 million frames and consistently detected contamination events with 94.8% mAP@0.5 and 96.3% anomaly prediction accuracy, while operating at 4.8 W on a Jetson Nano. Comparative experiments against representative lightweight detectors show that AquaFusionNet provides higher accuracy at comparable or lower power, and field results indicate that cross-modal coupling reduces common failure modes of unimodal detectors, particularly under fouling, turbidity spikes, and inconsistent illumination. All models, data, and hardware designs are released openly to facilitate replication and adaptation in decentralized water safety infrastructures. --- ### PA-VAD: Diffusion-Based Pseudo-Only Video Anomaly Detection via Domain-Aligned Memory Updates Authors: Satoshi Hashimoto, Yanan Wang, Hitoshi Nishimura, Mori Kurokawa Published: 2025-12-07 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.06845v2 Deploying video anomaly detection (VAD) in the real world is often constrained by the scarcity, privacy, and cost of collecting real abnormal footage. We propose PA-VAD, a novel pseudo-only framework that trains an anomaly detector without using any real abnormal videos, by pairing real normal videos with diffusion-synthesized pseudo-abnormal videos generated from a small set of real normal images. Beyond proposing a generation-driven training pipeline, we make a key empirical discovery: pseudo anomalies exhibit a characteristic spatiotemporal magnitude bias in feature space, which can dominate Multiple Instance Learning and degrade generalization if left unaddressed. To counter this pseudo-induced bias, we introduce the Domain-Aligned Regularized Module (DARM), which combines domain alignment with usage-aware memory updates to balance prototype coverage and stabilize optimization under biased pseudo supervision. Extensive experiments demonstrate that PA-VAD achieves 98.2% AUC on ShanghaiTech, 82.5% on UCF-Crime, and 95.1% on XD-Violence, and further improves generalization to unseen anomaly classes in open-set evaluations. Notably, PA-VAD surpasses the best real-abnormal WVAD baselines on ShanghaiTech and XD-Violence by +0.6% and +0.9%, respectively, and improves over the UVAD state of the art on UCF-Crime by +1.9% -showing that high-accuracy VAD is attainable without collecting real abnormal videos. --- ### Pseudo Anomalies Are All You Need: Diffusion-Based Generation for Weakly-Supervised Video Anomaly Detection Authors: Satoshi Hashimoto, Hitoshi Nishimura, Yanan Wang, Mori Kurokawa Published: 2025-12-07 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.06845v1 Deploying video anomaly detection in practice is hampered by the scarcity and collection cost of real abnormal footage. We address this by training without any real abnormal videos while evaluating under the standard weakly supervised split, and we introduce PA-VAD, a generation-driven approach that learns a detector from synthesized pseudo-abnormal videos paired with real normal videos, using only a small set of real normal images to drive synthesis. For synthesis, we select class-relevant initial images with CLIP and refine textual prompts with a vision-language model to improve fidelity and scene consistency before invoking a video diffusion model. For training, we mitigate excessive spatiotemporal magnitude in synthesized anomalies by an domain-aligned regularized module that combines domain alignment and memory usage-aware updates. Extensive experiments show that our approach reaches 98.2% on ShanghaiTech and 82.5% on UCF-Crime, surpassing the strongest real-abnormal method on ShanghaiTech by +0.6% and outperforming the UVAD state-of-the-art on UCF-Crime by +1.9%. The results demonstrate that high-accuracy anomaly detection can be obtained without collecting real anomalies, providing a practical path toward scalable deployment. --- ### CADE: Continual Weakly-supervised Video Anomaly Detection with Ensembles Authors: Satoshi Hashimoto, Tatsuya Konishi, Tomoya Kaichi, Kazunori Matsumoto, Mori Kurokawa Published: 2025-12-07 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.06840v1 Video anomaly detection (VAD) has long been studied as a crucial problem in public security and crime prevention. In recent years, weakly-supervised VAD (WVAD) have attracted considerable attention due to their easy annotation process and promising research results. While existing WVAD methods tackle mainly on static datasets, the possibility that the domain of data can vary has been neglected. To adapt such domain-shift, the continual learning (CL) perspective is required because otherwise additional training only with new coming data could easily cause performance degradation for previous data, i.e., forgetting. Therefore, we propose a brand-new approach, called Continual Anomaly Detection with Ensembles (CADE) that is the first work combining CL and WVAD viewpoints. Specifically, CADE uses the Dual-Generator(DG) to address data imbalance and label uncertainty in WVAD. We also found that forgetting exacerbates the "incompleteness'' where the model becomes biased towards certain anomaly modes, leading to missed detections of various anomalies. To address this, we propose to ensemble Multi-Discriminator (MD) that capture missed anomalies in past scenes due to forgetting, using multiple models. Extensive experiments show that CADE significantly outperforms existing VAD methods on the common multi-scene VAD datasets, such as ShanghaiTech and Charlotte Anomaly datasets. ---