# Research Papers — 2025-12 · bundle page 135 of 175

> Full-text markdown of papers #6701–6750 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/135
[← Previous bundle](https://aipod.dev/papers/archive/2025-12/page/134.md)
[Next bundle →](https://aipod.dev/papers/archive/2025-12/page/136.md)

### ProSocialAlign: Preference Conditioned Test Time Alignment in Language Models

Authors: Somnath Banerjee, Sayan Layek, Sayantan Adak, Mykola Pechenizkiy, Animesh Mukherjee, Rima Hazra
Published: 2025-12-06
Categories: cs.CL
arXiv: https://arxiv.org/abs/2512.06515v1

Current language model safety paradigms often fall short in emotionally charged or high-stakes settings, where refusal-only approaches may alienate users and naive compliance can amplify risk. We propose ProSocialAlign, a test-time, parameter-efficient framework that steers generation toward safe, empathetic, and value-aligned responses without retraining the base model. We formalize five human-centered objectives and cast safety as lexicographic constrained generation: first, applying hard constraints to eliminate harmful continuations; then optimizing for prosocial quality within the safe set. Our method combines (i) directional regulation, a harm-mitigation mechanism that subtracts a learned "harm vector" in parameter space, and (ii) preference-aware autoregressive reward modeling trained jointly across attributes with gradient conflict resolution, enabling fine-grained, user-controllable decoding. Empirical evaluations across five safety benchmarks demonstrate state-of-the-art performance, reducing unsafe leakage and boosting alignment to human values, with strong gains across multiple evaluation metrics. ProSocialAlign offers a robust and modular foundation for generating context-sensitive, safe, and human-aligned responses at inference time.

---

### Simultaneous Heterogeneity and Reduced-rank Learning for Multivariate Response Regression

Authors: Jie Wu, Bo Zhang, Daoji Li, Zemin Zheng
Published: 2025-12-06
Categories: stat.ME, stat.ML
arXiv: https://arxiv.org/abs/2512.06514v1

Heterogeneous data are now ubiquitous in many applications in which correctly identifying the subgroups from a heterogeneous population is critical. Although there is an increasing body of literature on subgroup detection, existing methods mainly focus on the univariate response setting. In this paper, we propose a joint heterogeneity and reduced-rank learning framework to simultaneously identify the subgroup structure and estimate the covariate effects for heterogeneous multivariate response regression. In particular, our approach uses rank-constrained pairwise fusion penalization and conducts the subgroup analysis without requiring prior knowledge regarding the individual subgroup memberships. We implement the proposed approach by an alternating direction method of multipliers (ADMM) algorithm and show its convergence. We also establish the asymptotic properties for the resulting estimators under mild and interpretable conditions. A predictive information criterion is proposed to select the rank of the coefficient matrix with theoretical support. The effectiveness of the proposed approach is demonstrated through simulation studies and a real data application.

---

### Diagnosis-based mortality prediction for intensive care unit patients via transfer learning

Authors: Mengqi Xu, Subha Maity, Joel Dubin
Published: 2025-12-06
Categories: cs.LG, stat.AP
arXiv: https://arxiv.org/abs/2512.06511v1

In the intensive care unit, the underlying causes of critical illness vary substantially across diagnoses, yet prediction models accounting for diagnostic heterogeneity have not been systematically studied. To address the gap, we evaluate transfer learning approaches for diagnosis-specific mortality prediction and apply both GLM- and XGBoost-based models to the eICU Collaborative Research Database. Our results demonstrate that transfer learning consistently outperforms models trained only on diagnosis-specific data and those using a well-known ICU severity-of-illness score, i.e., APACHE IVa, alone, while also achieving better calibration than models trained on the pooled data. Our findings also suggest that the Youden cutoff is a more appropriate decision threshold than the conventional 0.5 for binary outcomes, and that transfer learning maintains consistently high predictive performance across various cutoff criteria.

---

### AI as "Co-founder": GenAI for Entrepreneurship

Authors: Junhui Jeff Cai, Xian Gu, Liugang Sheng, Mengjia Xia, Linda Zhao, Wu Zhu
Published: 2025-12-06
Categories: econ.GN, cs.AI, stat.AP
arXiv: https://arxiv.org/abs/2512.06506v1

This paper studies whether, how, and for whom generative artificial intelligence (GenAI) facilitates firm creation. Our identification strategy exploits the November 2022 release of ChatGPT as a global shock that lowered start-up costs and leverages variations across geo-coded grids with differential pre-existing AI-specific human capital. Using high-resolution and universal data on Chinese firm registrations by the end of 2024, we find that grids with stronger AI-specific human capital experienced a sharp surge in new firm formation$\unicode{x2013}$driven entirely by small firms, contributing to 6.0% of overall national firm entry. Large-firm entry declines, consistent with a shift toward leaner ventures. New firms are smaller in capital, shareholder number, and founding team size, especially among small firms. The effects are strongest among firms with potential AI applications, weaker financing needs, and among first-time entrepreneurs. Overall, our results highlight that GenAI serves as a pro-competitive force by disproportionately boosting small-firm entry.

---

### Method of UAV Inspection of Photovoltaic Modules Using Thermal and RGB Data Fusion

Authors: Andrii Lysyi, Anatoliy Sachenko, Pavlo Radiuk, Mykola Lysyi, Oleksandr Melnychenko, Diana Zahorodnia
Published: 2025-12-06
Categories: cs.CV, cs.AI, cs.RO
arXiv: https://arxiv.org/abs/2512.06504v1

The subject of this research is the development of an intelligent, integrated framework for the automated inspection of photovoltaic (PV) infrastructure that addresses the critical shortcomings of conventional methods, including thermal palette bias, data redundancy, and high communication bandwidth requirements. The goal of this study is to design, develop, and validate a comprehensive, multi-modal system that fully automates the monitoring workflow, from data acquisition to the generation of actionable, geo-located maintenance alerts, thereby enhancing plant safety and operational efficiency. The methods employed involve a synergistic architecture that begins with a palette-invariant thermal embedding, learned by enforcing representational consistency, which is fused with a contrast-normalized RGB stream via a gated mechanism. This is supplemented by a closed-loop, adaptive re-acquisition controller that uses Rodrigues-based updates for targeted confirmation of ambiguous anomalies and a geospatial deduplication module that clusters redundant alerts using DBSCAN over the haversine distance. In conclusion, this study establishes a powerful new paradigm for proactive PV inspection, with the proposed system achieving a mean Average Precision (mAP@0.5) of 0.903 on the public PVF-10 benchmark, a significant 12-15% improvement over single-modality baselines. Field validation confirmed the system's readiness, achieving 96% recall, while the de-duplication process reduced duplicate-induced false positives by 15-20%, and relevance-only telemetry cut airborne data transmission by 60-70%.

---

### PRIMRose: Insights into the Per-Residue Energy Metrics of Proteins with Double InDel Mutations using Deep Learning

Authors: Stella Brown, Nicolas Preisig, Autumn Davis, Brian Hutchinson, Filip Jagodzinski
Published: 2025-12-06
Categories: q-bio.BM, cs.AI, cs.LG, cs.NE, q-bio.QM
arXiv: https://arxiv.org/abs/2512.06496v1

Understanding how protein mutations affect protein structure is essential for advancements in computational biology and bioinformatics. We introduce PRIMRose, a novel approach that predicts energy values for each residue given a mutated protein sequence. Unlike previous models that assess global energy shifts, our method analyzes the localized energetic impact of double amino acid insertions or deletions (InDels) at the individual residue level, enabling residue-specific insights into structural and functional disruption. We implement a Convolutional Neural Network architecture to predict the energy changes of each residue in a protein mutation. We train our model on datasets constructed from nine proteins, grouped into three categories: one set with exhaustive double InDel mutations, another with approximately 145k randomly sampled double InDel mutations, and a third with approximately 80k randomly sampled double InDel mutations. Our model achieves high predictive accuracy across a range of energy metrics as calculated by the Rosetta molecular modeling suite and reveals localized patterns that influence model performance, such as solvent accessibility and secondary structure context. This per-residue analysis offers new insights into the mutational tolerance of specific regions within proteins and provides higher interpretable and biologically meaningful predictions of InDels' effects.

---

### Optimizing LLMs Using Quantization for Mobile Execution

Authors: Agatsya Yadav, Renta Chintala Bhargavi
Published: 2025-12-06
Categories: cs.LG
arXiv: https://arxiv.org/abs/2512.06490v1

Large Language Models (LLMs) offer powerful capabilities, but their significant size and computational requirements hinder deployment on resource-constrained mobile devices. This paper investigates Post-Training Quantization (PTQ) for compressing LLMs for mobile execution. We apply 4-bit PTQ using the BitsAndBytes library with the Hugging Face Transformers framework to Meta's Llama 3.2 3B model. The quantized model is converted to GGUF format using llama.cpp tools for optimized mobile inference. The PTQ workflow achieves a 68.66% reduction in model size through 4-bit quantization, enabling the Llama 3.2 3B model to run efficiently on an Android device. Qualitative validation shows that the 4-bit quantized model can perform inference tasks successfully. We demonstrate the feasibility of running the quantized GGUF model on an Android device using the Termux environment and the Ollama framework. PTQ, especially at 4-bit precision combined with mobile-optimized formats like GGUF, provides a practical pathway for deploying capable LLMs on mobile devices, balancing model size and performance.

---

### Sanvaad: A Multimodal Accessibility Framework for ISL Recognition and Voice-Based Interaction

Authors: Kush Revankar, Shreyas Deshpande, Araham Sayeed, Ansh Tandale, Sarika Bobde
Published: 2025-12-06
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.06485v1

Communication between deaf users, visually im paired users, and the general hearing population often relies on tools that support only one direction of interaction. To address this limitation, this work presents Sanvaad, a lightweight multimodal accessibility framework designed to support real time, two-way communication. For deaf users, Sanvaad includes an ISL recognition module built on MediaPipe landmarks. MediaPipe is chosen primarily for its efficiency and low computational load, enabling the system to run smoothly on edge devices without requiring dedicated hardware. Spoken input from a phone can also be translated into sign representations through a voice-to-sign component that maps detected speech to predefined phrases and produces corresponding GIFs or alphabet-based visualizations. For visually impaired users, the framework provides a screen free voice interface that integrates multilingual speech recognition, text summarization, and text-to-speech generation. These components work together through a Streamlit-based interface, making the system usable on both desktop and mobile environments. Overall, Sanvaad aims to offer a practical and accessible pathway for inclusive communication by combining lightweight computer vision and speech processing tools within a unified framework.

---

### Classifying German Language Proficiency Levels Using Large Language Models

Authors: Elias-Leander Ahlers, Witold Brunsmann, Malte Schilling
Published: 2025-12-06
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2512.06483v1

Assessing language proficiency is essential for education, as it enables instruction tailored to learners needs. This paper investigates the use of Large Language Models (LLMs) for automatically classifying German texts according to the Common European Framework of Reference for Languages (CEFR) into different proficiency levels. To support robust training and evaluation, we construct a diverse dataset by combining multiple existing CEFR-annotated corpora with synthetic data. We then evaluate prompt-engineering strategies, fine-tuning of a LLaMA-3-8B-Instruct model and a probing-based approach that utilizes the internal neural state of the LLM for classification. Our results show a consistent performance improvement over prior methods, highlighting the potential of LLMs for reliable and scalable CEFR classification.

---

### Knowing What's Missing: Assessing Information Sufficiency in Question Answering

Authors: Akriti Jain, Aparna Garimella
Published: 2025-12-06
Categories: cs.CL
arXiv: https://arxiv.org/abs/2512.06476v3

Determining whether a provided context contains sufficient information to answer a question is a critical challenge for building reliable question-answering systems. While simple prompting strategies have shown success on factual questions, they frequently fail on inferential ones that require reasoning beyond direct text extraction. We hypothesize that asking a model to first reason about what specific information is missing provides a more reliable, implicit signal for assessing overall sufficiency. To this end, we propose a structured Identify-then-Verify framework for robust sufficiency modeling. Our method first generates multiple hypotheses about missing information and establishes a semantic consensus. It then performs a critical verification step, forcing the model to re-examine the source text to confirm whether this information is truly absent. We evaluate our method against established baselines across diverse multi-hop and factual QA datasets. The results demonstrate that by guiding the model to justify its claims about missing information, our framework produces more accurate sufficiency judgments while clearly articulating any information gaps.

---

### Why Goal-Conditioned Reinforcement Learning Works: Relation to Dual Control

Authors: Nathan P. Lawrence, Ali Mesbah
Published: 2025-12-06
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2512.06471v2

Goal-conditioned reinforcement learning (RL) concerns the problem of training an agent to maximize the probability of reaching target goal states. This paper presents an analysis of the goal-conditioned setting based on optimal control. In particular, we derive an optimality gap between more classical, often quadratic, objectives and the goal-conditioned reward, elucidating the success of goal-conditioned RL and why classical ``dense'' rewards can falter. We then consider the partially observed Markov decision setting and connect state estimation to our probabilistic reward, making the goal-conditioned reward well suited to dual control problems. The advantages of goal-conditioned policies are validated on nonlinear and uncertain environments using both RL and predictive control techniques.

---

### Modeling Contextual Passage Utility for Multihop Question Answering

Authors: Akriti Jain, Aparna Garimella
Published: 2025-12-06
Categories: cs.CL
arXiv: https://arxiv.org/abs/2512.06464v1

Multihop Question Answering (QA) requires systems to identify and synthesize information from multiple text passages. While most prior retrieval methods assist in identifying relevant passages for QA, further assessing the utility of the passages can help in removing redundant ones, which may otherwise add to noise and inaccuracies in the generated answers. Existing utility prediction approaches model passage utility independently, overlooking a critical aspect of multihop reasoning: the utility of a passage can be context-dependent, influenced by its relation to other passages - whether it provides complementary information or forms a crucial link in conjunction with others. In this paper, we propose a lightweight approach to model contextual passage utility, accounting for inter-passage dependencies. We fine-tune a small transformer-based model to predict passage utility scores for multihop QA. We leverage the reasoning traces from an advanced reasoning model to capture the order in which passages are used to answer a question and obtain synthetic training data. Through comprehensive experiments, we demonstrate that our utility-based scoring of retrieved passages leads to improved reranking and downstream QA performance compared to relevance-based reranking methods.

---

### Instance Dependent Testing of Samplers using Interval Conditioning

Authors: Rishiraj Bhattacharyya, Sourav Chakraborty, Yash Pote, Uddalok Sarkar, Sayantan Sen
Published: 2025-12-06
Categories: cs.DS, cs.AI
arXiv: https://arxiv.org/abs/2512.06458v1

Sampling algorithms play a pivotal role in probabilistic AI. However, verifying if a sampler program indeed samples from the claimed distribution is a notoriously hard problem. Provably correct testers like Barbarik, Teq, Flash, CubeProbe for testing of different kinds of samplers were proposed only in the last few years. All these testers focus on the worst-case efficiency, and do not support verification of samplers over infinite domains, a case occurring frequently in Astronomy, Finance, Network Security, etc. In this work, we design the first tester of samplers with instance-dependent efficiency, allowing us to test samplers over natural numbers. Our tests are developed via a novel distance estimation algorithm between an unknown and a known probability distribution using an interval conditioning framework. The core technical contribution is a new connection with probability mass estimation of a continuous distribution. The practical gains are also substantial: our experiments establish up to 1000x speedup over state-of-the-art testers.

---

### BitStopper: An Efficient Transformer Attention Accelerator via Stage-fusion and Early Termination

Authors: Huizheng Wang, Hongbin Wang, Shaojun Wei, Yang Hu, Shouyi Yin
Published: 2025-12-06
Categories: cs.LG, eess.SP
arXiv: https://arxiv.org/abs/2512.06457v1

Attention-based large language models (LLMs) have transformed modern AI applications, but the quadratic cost of self-attention imposes significant compute and memory overhead. Dynamic sparsity (DS) attention mitigates this, yet its hardware efficiency is limited by the added prediction stage and the heavy memory traffic it entails. To address these limitations, this paper proposes BitStopper, a fine-grained algorithm-architecture co-design that operates without a sparsity predictor. First, a bit-serial enable stage fusion (BESF) mechanism is proposed to reuse and minimize the memory access by progressively terminating trivial tokens and merging the prediction stage into the execution stage. Second, a lightweight and adaptive token selection (LATS) strategy is developed to work in concert with the bit-level sparsity speculation. Third, a bit-level asynchronous processing (BAP) strategy is employed to improve compute utilization during the on-demand bit-grained memory fetching. Finally, an elaborate architecture is designed to translate the theoretical complexity reduction into practical performance improvement. Extensive evaluations demonstrate that, compared to state-of-the-art (SOTA) Transformer accelerators, BitStopper achieves 2.03x and 1.89x speedups over Sanger and SOFA, respectively, while delivering 2.4x and 2.1x improvements in energy efficiency.

---

### Towards Stable Cross-Domain Depression Recognition under Missing Modalities

Authors: Jiuyi Chen, Mingkui Tan, Haifeng Lu, Qiuna Xu, Zhihua Wang, Runhao Zeng, Xiping Hu
Published: 2025-12-06
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.06447v1

Depression poses serious public health risks, including suicide, underscoring the urgency of timely and scalable screening. Multimodal automatic depression detection (ADD) offers a promising solution; however, widely studied audio- and video-based ADD methods lack a unified, generalizable framework for diverse depression recognition scenarios and show limited stability to missing modalities, which are common in real-world data. In this work, we propose a unified framework for Stable Cross-Domain Depression Recognition based on Multimodal Large Language Model (SCD-MLLM). The framework supports the integration and processing of heterogeneous depression-related data collected from varied sources while maintaining stability in the presence of incomplete modality inputs. Specifically, SCD-MLLM introduces two key components: (i) Multi-Source Data Input Adapter (MDIA), which employs masking mechanism and task-specific prompts to transform heterogeneous depression-related inputs into uniform token sequences, addressing inconsistency across diverse data sources; (ii) Modality-Aware Adaptive Fusion Module (MAFM), which adaptively integrates audio and visual features via a shared projection mechanism, enhancing resilience under missing modality conditions. e conduct comprehensive experiments under multi-dataset joint training settings on five publicly available and heterogeneous depression datasets from diverse scenarios: CMDC, AVEC2014, DAIC-WOZ, DVlog, and EATD. Across both complete and partial modality settings, SCD-MLLM outperforms state-of-the-art (SOTA) models as well as leading commercial LLMs (Gemini and GPT), demonstrating superior cross-domain generalization, enhanced ability to capture multimodal cues of depression, and strong stability to missing modality cases in real-world applications.

---

### Vec-LUT: Vector Table Lookup for Parallel Ultra-Low-Bit LLM Inference on Edge Devices

Authors: Xiangyu Li, Chengyu Yin, Weijun Wang, Jianyu Wei, Ting Cao, Yunxin Liu
Published: 2025-12-06
Categories: cs.DC, cs.AI
arXiv: https://arxiv.org/abs/2512.06443v2

Large language models (LLMs) are increasingly deployed on edge devices. To meet strict resource constraints, real-world deployment has pushed LLM quantization from 8-bit to 4-bit, 2-bit, and now 1.58-bit. Combined with lookup table (LUT)-based inference, CPUs run these ultra-low-bit LLMs even faster than NPUs, opening new opportunities for ubiquitous on-device intelligence. However, this paper identifies that LUT-based inference underutilizes memory bandwidth during parallel inference, which is required for prefilling, test-time scaling, and other multi-token scenarios. The root cause is the scalar LUT paradigm, which performs repetitive and non-contiguous memory accesses for each token. To solve the issue, we propose vector LUT, a new lookup paradigm that constructs a unified LUT across parallel tokens, and performs a single $1 \rightarrow N$ lookup per index. To realize it efficiently, we further introduce (1) Vector LUT-Centric Tensor Layout, and (2) Cache-Aware Streamed Lookup techniques. Evaluations on 5 edge devices across 3 LLMs show that Vec-LUT outperforms state-of-the-art baselines by up to $4.2\times$. Our implementation is integrated into llama.cpp. The code is available at https://github.com/OpenBitSys/vlut.cpp.

---

### Neural expressiveness for beyond importance model compression

Authors: Angelos-Christos Maroudis, Sotirios Xydis
Published: 2025-12-06
Categories: cs.LG
arXiv: https://arxiv.org/abs/2512.06440v1

Neural Network Pruning has been established as driving force in the exploration of memory and energy efficient solutions with high throughput both during training and at test time. In this paper, we introduce a novel criterion for model compression, named "Expressiveness". Unlike existing pruning methods that rely on the inherent "Importance" of neurons' and filters' weights, ``Expressiveness" emphasizes a neuron's or group of neurons ability to redistribute informational resources effectively, based on the overlap of activations. This characteristic is strongly correlated to a network's initialization state, establishing criterion autonomy from the learning state stateless and thus setting a new fundamental basis for the expansion of compression strategies in regards to the "When to Prune" question. We show that expressiveness is effectively approximated with arbitrary data or limited dataset's representative samples, making ground for the exploration of Data-Agnostic strategies. Our work also facilitates a "hybrid" formulation of expressiveness and importance-based pruning strategies, illustrating their complementary benefits and delivering up to 10x extra gains w.r.t. weight-based approaches in parameter compression ratios, with an average of 1% in performance degradation. We also show that employing expressiveness (independently) for pruning leads to an improvement over top-performing and foundational methods in terms of compression efficiency. Finally, on YOLOv8, we achieve a 46.1% MACs reduction by removing 55.4\% of the parameters, with an increase of 3% in the mean Absolute Precision ($mAP_{50-95}$) for object detection on COCO dataset.

---

### AGORA: Adversarial Generation Of Real-time Animatable 3D Gaussian Head Avatars

Authors: Ramazan Fazylov, Sergey Zagoruyko, Aleksandr Parkin, Stamatis Lefkimmiatis, Ivan Laptev
Published: 2025-12-06
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.06438v4

The generation of high-fidelity, animatable 3D human avatars remains a core challenge in computer graphics and vision, with applications in VR, telepresence, and entertainment. Existing approaches based on implicit representations like NeRFs suffer from slow rendering and dynamic inconsistencies, while 3D Gaussian Splatting (3DGS) methods are typically limited to static head generation, lacking dynamic control. We bridge this gap by introducing AGORA, a novel framework that extends 3DGS within a generative adversarial network to produce animatable avatars. Our key contribution is a lightweight, FLAME-conditioned deformation branch that predicts per-Gaussian residuals, enabling identity-preserving, fine-grained expression control while allowing real-time inference. Identity is further preserved through spatial shape conditioning of the identity branch, and expression fidelity is enforced via a dual-discriminator training scheme leveraging synthetic renderings of the parametric mesh. AGORA generates avatars that are not only visually realistic but also precisely controllable. Quantitatively, we outperform state-of-the-art NeRF-based methods on expression accuracy while rendering at 250 FPS on a single GPU and, notably, at $\sim$9 FPS under CPU-only inference -- to our knowledge the first demonstration of CPU-only animatable 3DGS avatar synthesis. This work represents a significant step toward practical, high-performance digital humans. Project website: https://ramazan793.github.io/AGORA/

---

### Canonical Tail Dependence for Soft Extremal Clustering of Multichannel Brain Signals

Authors: Mara Sherlin Talento, Jordan Richards, Raphael Huser, Hernando Ombao
Published: 2025-12-06
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2512.06435v1

We develop a novel characterization of extremal dependence between two cortical regions of the brain when its signals display extremely large amplitudes. We show that connectivity in the tails of the distribution reveals unique features of extreme events (e.g., seizures) that can help to identify their occurrence. Numerous studies have established that connectivity-based features are effective for discriminating brain states. Here, we demonstrate the advantage of the proposed approach: that tail connectivity provides additional discriminatory power, enabling more accurate identification of extreme-related events and improved seizure risk management. Common approaches in tail dependence modeling use pairwise summary measures or parametric models. However, these approaches do not identify channels that drive the maximal tail dependence between two groups of signals -- an information that is useful when analyzing electroencephalography of epileptic patients where specific channels are responsible for seizure occurrences. A familiar approach in traditional signal processing is canonical correlation, which we extend to the tails to develop a visualization of extremal channel-contributions. Through the tail pairwise dependence matrix (TPDM), we develop a computationally-efficient estimator for our canonical tail dependence measure. Our method is then used for accurate frequency-based soft clustering of neonates, distinguishing those with seizures from those without.

---

### Automated Deep Learning Estimation of Anthropometric Measurements for Preparticipation Cardiovascular Screening

Authors: Lucas R. Mareque, Ricardo L. Armentano, Leandro J. Cymberknop
Published: 2025-12-06
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2512.06434v1

Preparticipation cardiovascular examination (PPCE) aims to prevent sudden cardiac death (SCD) by identifying athletes with structural or electrical cardiac abnormalities. Anthropometric measurements, such as waist circumference, limb lengths, and torso proportions to detect Marfan syndrome, can indicate elevated cardiovascular risk. Traditional manual methods are labor-intensive, operator-dependent, and challenging to scale. We present a fully automated deep-learning approach to estimate five key anthropometric measurements from 2D synthetic human body images. Using a dataset of 100,000 images derived from 3D body meshes, we trained and evaluated VGG19, ResNet50, and DenseNet121 with fully connected layers for regression. All models achieved sub-centimeter accuracy, with ResNet50 performing best, achieving a mean MAE of 0.668 cm across all measurements. Our results demonstrate that deep learning can deliver accurate anthropometric data at scale, offering a practical tool to complement athlete screening protocols. Future work will validate the models on real-world images to extend applicability.

---

### Smart Spatial Planning in Egypt: An Algorithm-Driven Approach to Public Service Evaluation in Qena City

Authors: Mohamed Shamroukh, Mohamed Alkhuzamy Aziz
Published: 2025-12-06
Categories: cs.AI, cs.CY
arXiv: https://arxiv.org/abs/2512.06431v1

National planning standards for public services in Egypt often fail to align with unique local characteristics. Addressing this gap, this study develops a tailored planning model for Qena City. Using a hybrid methodology (descriptive, analytical, and experimental), the research utilizes Python programming to generate an intelligent spatial analysis algorithm based on Voronoi Diagrams. This approach creates city-specific planning criteria and evaluates the current coverage of public facilities. The primary contribution of this study is the successful derivation of a localized planning standards model and the deployment of an automated algorithm to assess service efficiency. Application of this model reveals a general service coverage average of 81.3%. Ambulance stations demonstrated the highest efficiency (99.8%) due to recent upgrades, while parks and open spaces recorded the lowest coverage (10%) caused by limited land availability. Spatial analysis indicates a high service density in midtown (>45 services/km^2), which diminishes significantly towards the outskirts (<5 services/km^2). Consequently, the Hajer Qena district contains the highest volume of unserved areas, while the First District (Qesm 1) exhibits the highest level of service coverage. This model offers a replicable framework for data-driven urban planning in Egyptian cities.

---

### A new initialisation to Control Gradients in Sinusoidal Neural network

Authors: Andrea Combette, Antoine Venaille, Nelly Pustelnik
Published: 2025-12-06
Categories: cs.LG
arXiv: https://arxiv.org/abs/2512.06427v2

Proper initialisation strategy is of primary importance to mitigate gradient explosion or vanishing when training neural networks. Yet, the impact of initialisation parameters still lacks a precise theoretical understanding for several well-established architectures. Here, we propose a new initialisation for networks with sinusoidal activation functions such as \texttt{SIREN}, focusing on gradients control, their scaling with network depth, their impact on training and on generalization. To achieve this, we identify a closed-form expression for the initialisation of the parameters, differing from the original \texttt{SIREN} scheme. This expression is derived from fixed points obtained through the convergence of pre-activation distribution and the variance of Jacobian sequences. Controlling both gradients and targeting vanishing pre-activation helps preventing the emergence of inappropriate frequencies during estimation, thereby improving generalization. We further show that this initialisation strongly influences training dynamics through the Neural Tangent Kernel framework (NTK). Finally, we benchmark \texttt{SIREN} with the proposed initialisation against the original scheme and other baselines on function fitting and image reconstruction. The new initialisation consistently outperforms state-of-the-art methods across a wide range of reconstruction tasks, including those involving physics-informed neural networks.

---

### When Gender is Hard to See: Multi-Attribute Support for Long-Range Recognition

Authors: Nzakiese Mbongo, Kailash A. Hambarde, Hugo Proença
Published: 2025-12-06
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2512.06426v1

Accurate gender recognition from extreme long-range imagery remains a challenging problem due to limited spatial resolution, viewpoint variability, and loss of facial cues. For such purpose, we present a dual-path transformer framework that leverages CLIP to jointly model visual and attribute-driven cues for gender recognition at a distance. The framework integrates two complementary streams: (1) a direct visual path that refines a pre-trained CLIP image encoder through selective fine-tuning of its upper layers, and (2) an attribute-mediated path that infers gender from a set of soft-biometric prompts (e.g., hairstyle, clothing, accessories) aligned in the CLIP text-image space. Spatial channel attention modules further enhance discriminative localization under occlusion and low resolution. To support large-scale evaluation, we construct U-DetAGReID, a unified long-range gender dataset derived from DetReIDx and AG-ReID.v2, harmonized under a consistent ternary labeling scheme (Male, Female, Unknown). Extensive experiments suggest that the proposed solution surpasses state-of-the-art person-attribute and re-identification baselines across multiple metrics (macro-F1, accuracy, AUC), with consistent robustness to distance, angle, and height variations. Qualitative attention visualizations confirm interpretable attribute localization and responsible abstention behavior. Our results show that language-guided dual-path learning offers a principled, extensible foundation for responsible gender recognition in unconstrained long-range scenarios.

---

### DragMesh: Interactive 3D Generation Made Easy

Authors: Tianshan Zhang, Zeyu Zhang, Hao Tang
Published: 2025-12-06
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.06424v1

While generative models have excelled at creating static 3D content, the pursuit of systems that understand how objects move and respond to interactions remains a fundamental challenge. Current methods for articulated motion lie at a crossroads: they are either physically consistent but too slow for real-time use, or generative but violate basic kinematic constraints. We present DragMesh, a robust framework for real-time interactive 3D articulation built around a lightweight motion generation core. Our core contribution is a novel decoupled kinematic reasoning and motion generation framework. First, we infer the latent joint parameters by decoupling semantic intent reasoning (which determines the joint type) from geometric regression (which determines the axis and origin using our Kinematics Prediction Network (KPP-Net)). Second, to leverage the compact, continuous, and singularity-free properties of dual quaternions for representing rigid body motion, we develop a novel Dual Quaternion VAE (DQ-VAE). This DQ-VAE receives these predicted priors, along with the original user drag, to generate a complete, plausible motion trajectory. To ensure strict adherence to kinematics, we inject the joint priors at every layer of the DQ-VAE's non-autoregressive Transformer decoder using FiLM (Feature-wise Linear Modulation) conditioning. This persistent, multi-scale guidance is complemented by a numerically-stable cross-product loss to guarantee axis alignment. This decoupled design allows DragMesh to achieve real-time performance and enables plausible, generative articulation on novel objects without retraining, offering a practical step toward generative 3D intelligence. Code: https://github.com/AIGeeksGroup/DragMesh. Website: https://aigeeksgroup.github.io/DragMesh.

---

### A Perception CNN for Facial Expression Recognition

Authors: Chunwei Tian, Jingyuan Xie, Lingjun Li, Wangmeng Zuo, Yanning Zhang, David Zhang
Published: 2025-12-06
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.06422v1

Convolutional neural networks (CNNs) can automatically learn data patterns to express face images for facial expression recognition (FER). However, they may ignore effect of facial segmentation of FER. In this paper, we propose a perception CNN for FER as well as PCNN. Firstly, PCNN can use five parallel networks to simultaneously learn local facial features based on eyes, cheeks and mouth to realize the sensitive capture of the subtle changes in FER. Secondly, we utilize a multi-domain interaction mechanism to register and fuse between local sense organ features and global facial structural features to better express face images for FER. Finally, we design a two-phase loss function to restrict accuracy of obtained sense information and reconstructed face images to guarantee performance of obtained PCNN in FER. Experimental results show that our PCNN achieves superior results on several lab and real-world FER benchmarks: CK+, JAFFE, FER2013, FERPlus, RAF-DB and Occlusion and Pose Variant Dataset. Its code is available at https://github.com/hellloxiaotian/PCNN.

---

### Rethinking Training Dynamics in Scale-wise Autoregressive Generation

Authors: Gengze Zhou, Chongjian Ge, Hao Tan, Feng Liu, Yicong Hong
Published: 2025-12-06
Categories: cs.CV, cs.AI, cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2512.06421v1

Recent advances in autoregressive (AR) generative models have produced increasingly powerful systems for media synthesis. Among them, next-scale prediction has emerged as a popular paradigm, where models generate images in a coarse-to-fine manner. However, scale-wise AR models suffer from exposure bias, which undermines generation quality. We identify two primary causes of this issue: (1) train-test mismatch, where the model must rely on its own imperfect predictions during inference, and (2) imbalance in scale-wise learning difficulty, where certain scales exhibit disproportionately higher optimization complexity. Through a comprehensive analysis of training dynamics, we propose Self-Autoregressive Refinement (SAR) to address these limitations. SAR introduces a Stagger-Scale Rollout (SSR) mechanism that performs lightweight autoregressive rollouts to expose the model to its own intermediate predictions, thereby aligning train-test patterns, and a complementary Contrastive Student-Forcing Loss (CSFL) that provides adequate supervision for self-generated contexts to ensure stable training. Experimental results show that applying SAR to pretrained AR models consistently improves generation quality with minimal computational overhead. For instance, SAR yields a 5.2% FID reduction on FlexVAR-d16 trained on ImageNet 256 within 10 epochs (5 hours on 32xA100 GPUs). Given its efficiency, scalability, and effectiveness, we expect SAR to serve as a reliable post-training method for visual autoregressive generation.

---

### Hankel-FNO: Fast Underwater Acoustic Charting Via Physics-Encoded Fourier Neural Operator

Authors: Yifan Sun, Lei Cheng, Jianlong Li, Peter Gerstoft
Published: 2025-12-06
Categories: cs.LG, cs.SD
arXiv: https://arxiv.org/abs/2512.06417v1

Fast and accurate underwater acoustic charting is crucial for downstream tasks such as environment-aware sensor placement optimization and autonomous vehicle path planning. Conventional methods rely on computationally expensive while accurate numerical solvers, which are not scalable for large-scale or real-time applications. Although deep learning-based surrogate models can accelerate these computations, they often suffer from limitations such as fixed-resolution constraints or dependence on explicit partial differential equation formulations. These issues hinder their applicability and generalization across diverse environments. We propose Hankel-FNO, a Fourier Neural Operator (FNO)-based model for efficient and accurate acoustic charting. By incorporating sound propagation knowledge and bathymetry, our method has high accuracy while maintaining high computational speed. Results demonstrate that Hankel-FNO outperforms traditional solvers in speed and surpasses data-driven alternatives in accuracy, especially in long-range predictions. Experiments show the model's adaptability to diverse environments and sound source settings with minimal fine-tuning.

---

### UncertaintyZoo: A Unified Toolkit for Quantifying Predictive Uncertainty in Deep Learning Systems

Authors: Xianzong Wu, Xiaohong Li, Lili Quan, Qiang Hu
Published: 2025-12-06
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2512.06406v1

Large language models(LLMs) are increasingly expanding their real-world applications across domains, e.g., question answering, autonomous driving, and automatic software development. Despite this achievement, LLMs, as data-driven systems, often make incorrect predictions, which can lead to potential losses in safety-critical scenarios. To address this issue and measure the confidence of model outputs, multiple uncertainty quantification(UQ) criteria have been proposed. However, even though important, there are limited tools to integrate these methods, hindering the practical usage of UQ methods and future research in this domain. To bridge this gap, in this paper, we introduce UncertaintyZoo, a unified toolkit that integrates 29 uncertainty quantification methods, covering five major categories under a standardized interface. Using UncertaintyZoo, we evaluate the usefulness of existing uncertainty quantification methods under the code vulnerability detection task on CodeBERT and ChatGLM3 models. The results demonstrate that UncertaintyZoo effectively reveals prediction uncertainty. The tool with a demonstration video is available on the project site https://github.com/Paddingbuta/UncertaintyZoo.

---

### GENIUS: An Agentic AI Framework for Autonomous Design and Execution of Simulation Protocols

Authors: Mohammad Soleymanibrojeni, Roland Aydin, Diego Guedes-Sobrinho, Alexandre C. Dias, Maurício J. Piotrowski, Wolfgang Wenzel, Celso Ricardo Caldeira Rêgo
Published: 2025-12-06
Categories: cs.AI, cond-mat.mtrl-sci, physics.chem-ph
arXiv: https://arxiv.org/abs/2512.06404v1

Predictive atomistic simulations have propelled materials discovery, yet routine setup and debugging still demand computer specialists. This know-how gap limits Integrated Computational Materials Engineering (ICME), where state-of-the-art codes exist but remain cumbersome for non-experts. We address this bottleneck with GENIUS, an AI-agentic workflow that fuses a smart Quantum ESPRESSO knowledge graph with a tiered hierarchy of large language models supervised by a finite-state error-recovery machine. Here we show that GENIUS translates free-form human-generated prompts into validated input files that run to completion on $\approx$80% of 295 diverse benchmarks, where 76% are autonomously repaired, with success decaying exponentially to a 7% baseline. Compared with LLM-only baselines, GENIUS halves inference costs and virtually eliminates hallucinations. The framework democratizes electronic-structure DFT simulations by intelligently automating protocol generation, validation, and repair, opening large-scale screening and accelerating ICME design loops across academia and industry worldwide.

---

### Perceptual Region-Driven Infrared-Visible Co-Fusion for Extreme Scene Enhancement

Authors: Jing Tao, Yonghong Zong, Banglei Guan, Pengju Sun, Taihang Lei, Yang Shanga, Qifeng Yu
Published: 2025-12-06
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.06400v2

In photogrammetry, accurately fusing infrared (IR) and visible (VIS) spectra while preserving the geometric fidelity of visible features and incorporating thermal radiation is a significant challenge, particularly under extreme conditions. Existing methods often compromise visible imagery quality, impacting measurement accuracy. To solve this, we propose a region perception-based fusion framework that combines multi-exposure and multi-modal imaging using a spatially varying exposure (SVE) camera. This framework co-fuses multi-modal and multi-exposure data, overcoming single-exposure method limitations in extreme environments. The framework begins with region perception-based feature fusion to ensure precise multi-modal registration, followed by adaptive fusion with contrast enhancement. A structural similarity compensation mechanism, guided by regional saliency maps, optimizes IR-VIS spectral integration. Moreover, the framework adapts to single-exposure scenarios for robust fusion across different conditions. Experiments conducted on both synthetic and real-world data demonstrate superior image clarity and improved performance compared to state-of-the-art methods, as evidenced by both quantitative and visual evaluations.

---

### AgenticCyber: A GenAI-Powered Multi-Agent System for Multimodal Threat Detection and Adaptive Response in Cybersecurity

Authors: Shovan Roy
Published: 2025-12-06
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2512.06396v1

The increasing complexity of cyber threats in distributed environments demands advanced frameworks for real-time detection and response across multimodal data streams. This paper introduces AgenticCyber, a generative AI powered multi-agent system that orchestrates specialized agents to monitor cloud logs, surveillance videos, and environmental audio concurrently. The solution achieves 96.2% F1-score in threat detection, reduces response latency to 420 ms, and enables adaptive security posture management using multimodal language models like Google's Gemini coupled with LangChain for agent orchestration. Benchmark datasets, such as AWS CloudTrail logs, UCF-Crime video frames, and UrbanSound8K audio clips, show greater performance over standard intrusion detection systems, reducing mean time to respond (MTTR) by 65% and improving situational awareness. This work introduces a scalable, modular proactive cybersecurity architecture for enterprise networks and IoT ecosystems that overcomes siloed security technologies with cross-modal reasoning and automated remediation.

---

### Conflict-Aware Fusion: Mitigating Logic Inertia in Large Language Models via Structured Cognitive Priors

Authors: Qiming Bao, Xiaoxuan Fu, Michael Witbrock
Published: 2025-12-06
Categories: cs.AI, cs.CL, cs.LG, cs.LO
arXiv: https://arxiv.org/abs/2512.06393v8

Large language models (LLMs) achieve high accuracy on many reasoning benchmarks but remain brittle under structural perturbations of rule-based systems. We introduce a diagnostic framework with four stress tests -- redundant vs. essential rule deletion, contradictory-rule injection, logic-preserving rewrites, and multi-law stacking -- and use it to expose Logic Inertia: the tendency of generative LLMs (Qwen2/3, TinyLlama, GPT-4o, Gemma-3-4B-IT) and the encoder-only BERT baseline to persist along learned deductive trajectories under inconsistent premises. The collapse is sharp: untreated baselines fall from accuracy 1.00 on the base task to 0.00 on contradiction injection (instance-level exact match), and GPT-4o resolves only 56.0% of contradiction cases. We propose Conflict-Aware Fusion, a four-stage training pipeline that enforces verification-before-deduction as a learned structural prior: (i) SFT establishes the verification preamble; (ii) DPO sharpens the halt-on-contradiction decision boundary; (iii) Logical Invariance REgularisation (LIRE) penalises divergence between logically equivalent rule formulations via symmetric KL; (iv) Reinforcement Learning from Verification Feedback (RLVF) uses a symbolic forward-chaining engine as a deterministic oracle reward, jointly optimising invariance and sensitivity. The pipeline saturates all four primary stress tests for both 1.5B and 8B backbones. We further validate a Phase 2 extension that replaces the propositional oracle with a Lean 4 kernel, attaining 99.0% kernel agreement on the 105 classically-derivable (T) questions within a stratified 187-question Lean-translated sample (overall 71.7% across both polarities), providing a sound upgrade path to formally verified RL training. Code and benchmark: https://github.com/14H034160212/lemo

---

### RLAX: Large-Scale, Distributed Reinforcement Learning for Large Language Models on TPUs

Authors: Runlong Zhou, Lefan Zhang, Shang-Chen Wu, Kelvin Zou, Hanzhi Zhou, Ke Ye, Yihao Feng, Dong Yin, Alex Guillen Garcia, Dmytro Babych, Rohit Chatterjee, Matthew Hopkins et al.
Published: 2025-12-06
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2512.06392v2

Reinforcement learning (RL) has emerged as the de-facto paradigm for improving the reasoning capabilities of large language models (LLMs). We have developed RLAX, a scalable RL framework on TPUs. RLAX employs a parameter-server architecture. A master trainer periodically pushes updated model weights to the parameter server while a fleet of inference workers pull the latest weights and generates new rollouts. We introduce a suite of system techniques to enable scalable and preemptible RL for a diverse set of state-of-art RL algorithms. To accelerate convergence and improve model quality, we have devised new dataset curation and alignment techniques. Large-scale evaluations show that RLAX improves QwQ-32B's pass@8 accuracy by 12.8% in just 12 hours 48 minutes on 1024 v5p TPUs, while remaining robust to preemptions during training.

---

### Web Technologies Security in the AI Era: A Survey of CDN-Enhanced Defenses

Authors: Mehrab Hosain, Sabbir Alom Shuvo, Matthew Ogbe, Md Shah Jalal Mazumder, Yead Rahman, Md Azizul Hakim, Anukul Pandey
Published: 2025-12-06
Categories: cs.CR, cs.AI, cs.LG, cs.NI, cs.PF
arXiv: https://arxiv.org/abs/2512.06390v1

The modern web stack, which is dominated by browser-based applications and API-first backends, now operates under an adversarial equilibrium where automated, AI-assisted attacks evolve continuously. Content Delivery Networks (CDNs) and edge computing place programmable defenses closest to users and bots, making them natural enforcement points for machine-learning (ML) driven inspection, throttling, and isolation. This survey synthesizes the landscape of AI-enhanced defenses deployed at the edge: (i) anomaly- and behavior-based Web Application Firewalls (WAFs) within broader Web Application and API Protection (WAAP), (ii) adaptive DDoS detection and mitigation, (iii) bot management that resists human-mimicry, and (iv) API discovery, positive security modeling, and encrypted-traffic anomaly analysis. We add a systematic survey method, a threat taxonomy mapped to edge-observable signals, evaluation metrics, deployment playbooks, and governance guidance. We conclude with a research agenda spanning XAI, adversarial robustness, and autonomous multi-agent defense. Our findings indicate that edge-centric AI measurably improves time-to-detect and time-to-mitigate while reducing data movement and enhancing compliance, yet introduces new risks around model abuse, poisoning, and governance.

---

### Protecting Bystander Privacy via Selective Hearing in Audio LLMs

Authors: Xiao Zhan, Guangzhi Sun, Jose Such, Phil Woodland
Published: 2025-12-06
Categories: cs.SD, cs.AI
arXiv: https://arxiv.org/abs/2512.06380v3

Audio Large language models (LLMs) are increasingly deployed in the real world, where they inevitably capture speech from unintended nearby bystanders, raising privacy risks that existing benchmarks and defences did not consider. We introduce SH-Bench, the first benchmark designed to evaluate selective hearing: a model's ability to attend to an intended main speaker while refusing to process or reveal information about incidental bystander speech. SH-Bench contains 3,968 multi-speaker audio mixtures, including both real-world and synthetic scenarios, paired with 77k multiple-choice questions that probe models under general and selective operating modes. In addition, we propose Selective Efficacy (SE), a novel metric capturing both multi-speaker comprehension and bystander-privacy protection. Our evaluation of state-of-the-art open-source and proprietary LLMs reveals substantial bystander privacy leakage, with strong audio understanding failing to translate into selective protection of bystander privacy. To mitigate this gap, we also present Bystander Privacy Fine-Tuning (BPFT), a novel training pipeline that teaches models to refuse bystander-related queries without degrading main-speaker comprehension. We show that BPFT yields substantial gains, achieving an absolute 47% higher bystander accuracy under selective mode and an absolute 16% higher SE compared to Gemini 2.5 Pro, which is the best audio LLM without BPFT. Together, SH-Bench and BPFT provide the first systematic framework for measuring and improving bystander privacy in audio LLMs.

---

### OCFER-Net: Recognizing Facial Expression in Online Learning System

Authors: Yi Huo, Lei Zhang
Published: 2025-12-06
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.06379v1

Recently, online learning is very popular, especially under the global epidemic of COVID-19. Besides knowledge distribution, emotion interaction is also very important. It can be obtained by employing Facial Expression Recognition (FER). Since the FER accuracy is substantial in assisting teachers to acquire the emotional situation, the project explores a series of FER methods and finds that few works engage in exploiting the orthogonality of convolutional matrix. Therefore, it enforces orthogonality on kernels by a regularizer, which extracts features with more diversity and expressiveness, and delivers OCFER-Net. Experiments are carried out on FER-2013, which is a challenging dataset. Results show superior performance over baselines by 1.087. The code of the research project is publicly available on https://github.com/YeeHoran/OCFERNet.

---

### VAD-Net: Multidimensional Facial Expression Recognition in Intelligent Education System

Authors: Yi Huo, Yun Ge
Published: 2025-12-06
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.06377v1

Current FER (Facial Expression Recognition) dataset is mostly labeled by emotion categories, such as happy, angry, sad, fear, disgust, surprise, and neutral which are limited in expressiveness. However, future affective computing requires more comprehensive and precise emotion metrics which could be measured by VAD(Valence-Arousal-Dominance) multidimension parameters. To address this, AffectNet has tried to add VA (Valence and Arousal) information, but still lacks D(Dominance). Thus, the research introduces VAD annotation on FER2013 dataset, takes the initiative to label D(Dominance) dimension. Then, to further improve network capacity, it enforces orthogonalized convolution on it, which extracts more diverse and expressive features and will finally increase the prediction accuracy. Experiment results show that D dimension could be measured but is difficult to obtain compared with V and A dimension no matter in manual annotation or regression network prediction. Secondly, the ablation test by introducing orthogonal convolution verifies that better VAD prediction could be obtained in the configuration of orthogonal convolution. Therefore, the research provides an initiative labelling for D dimension on FER dataset, and proposes a better prediction network for VAD prediction through orthogonal convolution. The newly built VAD annotated FER2013 dataset could act as a benchmark to measure VAD multidimensional emotions, while the orthogonalized regression network based on ResNet could act as the facial expression recognition baseline for VAD emotion prediction. The newly labeled dataset and implementation code is publicly available on https://github.com/YeeHoran/VAD-Net .

---

### Are AI-Generated Driving Videos Ready for Autonomous Driving? A Diagnostic Evaluation Framework

Authors: Xinhao Xiang, Abhijeet Rastogi, Jiawei Zhang
Published: 2025-12-06
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.06376v1

Recent text-to-video models have enabled the generation of high-resolution driving scenes from natural language prompts. These AI-generated driving videos (AIGVs) offer a low-cost, scalable alternative to real or simulator data for autonomous driving (AD). But a key question remains: can such videos reliably support training and evaluation of AD models? We present a diagnostic framework that systematically studies this question. First, we introduce a taxonomy of frequent AIGV failure modes, including visual artifacts, physically implausible motion, and violations of traffic semantics, and demonstrate their negative impact on object detection, tracking, and instance segmentation. To support this analysis, we build ADGV-Bench, a driving-focused benchmark with human quality annotations and dense labels for multiple perception tasks. We then propose ADGVE, a driving-aware evaluator that combines static semantics, temporal cues, lane obedience signals, and Vision-Language Model(VLM)-guided reasoning into a single quality score for each clip. Experiments show that blindly adding raw AIGVs can degrade perception performance, while filtering them with ADGVE consistently improves both general video quality assessment metrics and downstream AD models, and turns AIGVs into a beneficial complement to real-world data. Our study highlights both the risks and the promise of AIGVs, and provides practical tools for safely leveraging large-scale video generation in future AD pipelines.

---

### VG-Refiner: Towards Tool-Refined Referring Grounded Reasoning via Agentic Reinforcement Learning

Authors: Yuji Wang, Wenlong Liu, Jingxuan Niu, Haoji Zhang, Yansong Tang
Published: 2025-12-06
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.06373v1

Tool-integrated visual reasoning (TiVR) has demonstrated great potential in enhancing multimodal problem-solving. However, existing TiVR paradigms mainly focus on integrating various visual tools through reinforcement learning, while neglecting to design effective response mechanisms for handling unreliable or erroneous tool outputs. This limitation is particularly pronounced in referring and grounding tasks, where inaccurate detection tool predictions often mislead TiVR models into generating hallucinated reasoning. To address this issue, we propose the VG-Refiner, the first framework aiming at the tool-refined referring grounded reasoning. Technically, we introduce a two-stage think-rethink mechanism that enables the model to explicitly analyze and respond to tool feedback, along with a refinement reward that encourages effective correction in response to poor tool results. In addition, we propose two new metrics and establish fair evaluation protocols to systematically measure the refinement ability of current models. We adopt a small amount of task-specific data to enhance the refinement capability of VG-Refiner, achieving a significant improvement in accuracy and correction ability on referring and reasoning grounding benchmarks while preserving the general capabilities of the pretrained model.

---

### Greedy Alignment Principle for Optimizer Selection

Authors: Jaerin Lee, Kyoung Mu Lee
Published: 2025-12-06
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2512.06370v3

Recent works have shown that gradient-update alignment is a powerful signal for modulating optimizer updates, often leading to faster training. We promote this update-wise heuristic as a mathematically grounded principle for selecting and tuning optimizer hyperparameters. By treating gradients and updates as signals and an optimizer as a causal filter that maps between them, we formulate optimizer selection as maximizing the expected drop rate in loss over a prescribed family of optimizers. We show that this objective is exactly the inner product between the optimizer filter and the gradient autocorrelation, and prove that a greedy optimum exists and has a stability bound under perturbations of the estimated gradient statistics. Specializing in momentum-based optimizers, the theory yields simple dynamic momentum selection rules for both SGD+Momentum and Adam/AdamW. Experiments across image classification, language model fine-tuning, and vision transformer fine-tuning show that the resulting dynamic momentum rules match or improve upon the best fixed hyperparameters found via manual sweeps, reducing the need for exhaustive momentum sweeps. Code is available at https://github.com/ironjr/gap

---

### HuPrior3R: Incorporating Human Priors for Better 3D Dynamic Reconstruction from Monocular Videos

Authors: Weitao Xiong, Zhiyuan Yuan, Jiahao Lu, Chengfeng Zhao, Peng Li, Yuan Liu
Published: 2025-12-06
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.06368v2

Monocular dynamic video reconstruction faces significant challenges in dynamic human scenes due to geometric inconsistencies and resolution degradation issues. Existing methods lack 3D human structural understanding, producing geometrically inconsistent results with distorted limb proportions and unnatural human-object fusion, while memory-constrained downsampling causes human boundary drift toward background geometry. To address these limitations, we propose to incorporate hybrid geometric priors that combine SMPL human body models with monocular depth estimation. Our approach leverages structured human priors to maintain surface consistency while capturing fine-grained geometric details in human regions. We introduce HuPrior3R, featuring a hierarchical pipeline with refinement components that processes full-resolution images for overall scene geometry, then applies strategic cropping and cross-attention fusion for human-specific detail enhancement. The method integrates SMPL priors through a Feature Fusion Module to ensure geometrically plausible reconstruction while preserving fine-grained human boundaries. Extensive experiments on TUM Dynamics and GTA-IM datasets demonstrate superior performance in dynamic human reconstruction.

---

### JEEVHITAA -- An HCAI Ecosystem to Support Collective Care

Authors: Shyama Sastha Krishnamoorthy Srinivasan, Harsh Pala, Mohan Kumar, Pushpendra Singh
Published: 2025-12-06
Categories: cs.HC, cs.AI, cs.CR
arXiv: https://arxiv.org/abs/2512.06364v4

Current mobile health platforms are predominantly individual-centric and lack the support for coordinated, auditable multi-actor workflows. However, in many settings worldwide, health decisions are enacted through multi-actor coordination rather than individual users. We present JEEVHITAA, a cross-platform mobile system enabling role-aware sharing and verifiable information flows within permissioned care circles. JEEVHITAA ingests platform and device data, builds layered profiles from sensors and tiered onboarding, and enforces fine-grained, time-bounded access control across care graphs. Data stays secure both within the application and the cloud. Integrated retrieval-augmented Large Language Models produce structured, role-targeted summaries and action plans, offer evidence-grounded verification with provenance and confidence scores, and support advanced insights on reports. We describe the architecture, connector abstractions, and security primitives, and report robustness evaluations using synthetic, ontology-driven data and findings from a feasibility study with real-life care circles across 9-14 weeks. We outline plans for larger multi-site evaluations focusing on operational alignment, longitudinal trust & literacy impact, and relational friction & efforts to sink into the daily infrastructure.

---

### Spoofing-aware Prompt Learning for Unified Physical-Digital Facial Attack Detection

Authors: Jiabao Guo, Yadian Wang, Hui Ma, Yuhao Fu, Ju Jia, Hui Liu, Shengeng Tang, Lechao Cheng, Yunfeng Diao, Ajian Liu
Published: 2025-12-06
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.06363v1

Real-world face recognition systems are vulnerable to both physical presentation attacks (PAs) and digital forgery attacks (DFs). We aim to achieve comprehensive protection of biometric data by implementing a unified physical-digital defense framework with advanced detection. Existing approaches primarily employ CLIP with regularization constraints to enhance model generalization across both tasks. However, these methods suffer from conflicting optimization directions between physical and digital attack detection under same category prompt spaces. To overcome this limitation, we propose a Spoofing-aware Prompt Learning for Unified Attack Detection (SPL-UAD) framework, which decouples optimization branches for physical and digital attacks in the prompt space. Specifically, we construct a learnable parallel prompt branch enhanced with adaptive Spoofing Context Prompt Generation, enabling independent control of optimization for each attack type. Furthermore, we design a Cues-awareness Augmentation that leverages the dual-prompt mechanism to generate challenging sample mining tasks on data, significantly enhancing the model's robustness against unseen attack types. Extensive experiments on the large-scale UniAttackDataPlus dataset demonstrate that the proposed method achieves significant performance improvements in unified attack detection tasks.

---

### Rectifying Latent Space for Generative Single-Image Reflection Removal

Authors: Mingjia Li, Jin Hu, Hainuo Wang, Qiming Hu, Jiarui Wang, Xiaojie Guo
Published: 2025-12-06
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.06358v1

Single-image reflection removal is a highly ill-posed problem, where existing methods struggle to reason about the composition of corrupted regions, causing them to fail at recovery and generalization in the wild. This work reframes an editing-purpose latent diffusion model to effectively perceive and process highly ambiguous, layered image inputs, yielding high-quality outputs. We argue that the challenge of this conversion stems from a critical yet overlooked issue, i.e., the latent space of semantic encoders lacks the inherent structure to interpret a composite image as a linear superposition of its constituent layers. Our approach is built on three synergistic components, including a reflection-equivariant VAE that aligns the latent space with the linear physics of reflection formation, a learnable task-specific text embedding for precise guidance that bypasses ambiguous language, and a depth-guided early-branching sampling strategy to harness generative stochasticity for promising results. Extensive experiments reveal that our model achieves new SOTA performance on multiple benchmarks and generalizes well to challenging real-world cases.

---

### Proportional integral derivative booster for neural networks-based time-series prediction: Case of water demand prediction

Authors: Tony Salloom, Okyay Kaynak, Xinbo Yub, Wei He
Published: 2025-12-06
Categories: cs.LG, cs.AI, cs.RO
arXiv: https://arxiv.org/abs/2512.06357v2

Multi-step time-series prediction is an essential supportive step for decision-makers in several industrial areas. Artificial intelligence techniques, which use a neural network component in various forms, have recently frequently been used to accomplish this step. However, the complexity of the neural network structure still stands up as a critical problem against prediction accuracy. In this paper, a method inspired by the proportional-integral-derivative (PID) control approach is investigated to enhance the performance of neural network models used for multi-step ahead prediction of periodic time-series information while maintaining a negligible impact on the complexity of the system. The PID-based method is applied to the predicted value at each time step to bring that value closer to the real value. The water demand forecasting problem is considered as a case study, where two deep neural network models from the literature are used to prove the effectiveness of the proposed boosting method. Furthermore, to prove the applicability of this PID-based booster to other types of periodic time-series prediction problems, it is applied to enhance the accuracy of a neural network model used for multi-step forecasting of hourly energy consumption. The comparison between the results of the original prediction models and the results after using the proposed technique demonstrates the superiority of the proposed method in terms of prediction accuracy and system complexity.

---

### Mitigating Structural Overfitting: A Distribution-Aware Rectification Framework for Missing Feature Imputation

Authors: Yifan Song, Fenglin Yu, Yihong Luo, Xingjian Tao, Siya Qiu, Kai Han, Jing Tang
Published: 2025-12-06
Categories: cs.LG, cs.SI
arXiv: https://arxiv.org/abs/2512.06356v3

Incomplete node features are ubiquitous in real-world scenarios such as user profiling and cold-start recommendation, which severely hinders the practical deployment of graph learning systems (e.g., GNNs). Existing solutions typically rely on diffusion-based structural smoothing (e.g., feature propagation) to impute missing values. However, we find that these approaches suffer from structural overfitting, leading to three progressive challenges: 1) performance degradation on disjoint graphs, 2) loss of semantic diversity due to over-smoothing, and 3) feature distribution shift when generalizing to unseen graph structures (inductive tasks). To address these challenges, we introduce the \textbf{\DART} framework. It begins by employing {\em Global Structural Augmentation (GSA)}, which establishes global correlations to bridge disjoint components and extend diffusion coverage. Building upon this, we design a semantic rectifier based on masked autoencoding. This module learns the latent feature manifold to recover natural semantic details. Crucially, we introduce a test-time distribution rectification mechanism that projects structurally biased features back onto the learned manifold during inference, effectively bridging the inductive distribution gap. Furthermore, considering that synthetic masking fails to reflect real-world sparsity, we present a new dataset \textbf{Sailing} collected from voyage records with naturally missing attributes. Extensive experiments on six public datasets and Sailing demonstrate that \DART significantly outperforms state-of-the-art methods in both transductive and inductive settings. Our code and dataset are available at https://github.com/yfsong00/DART.

---

### TreeQ: Pushing the Quantization Boundary of Diffusion Transformer via Tree-Structured Mixed-Precision Search

Authors: Kaicheng Yang, Kaisen Yang, Baiting Wu, Xun Zhang, Qianrui Yang, Haotong Qin, He Zhang, Yulun Zhang
Published: 2025-12-06
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.06353v1

Diffusion Transformers (DiTs) have emerged as a highly scalable and effective backbone for image generation, outperforming U-Net architectures in both scalability and performance. However, their real-world deployment remains challenging due to high computational and memory demands. Mixed-Precision Quantization (MPQ), designed to push the limits of quantization, has demonstrated remarkable success in advancing U-Net quantization to sub-4bit settings while significantly reducing computational and memory overhead. Nevertheless, its application to DiT architectures remains limited and underexplored. In this work, we propose TreeQ, a unified framework addressing key challenges in DiT quantization. First, to tackle inefficient search and proxy misalignment, we introduce Tree Structured Search (TSS). This DiT-specific approach leverages the architecture's linear properties to traverse the solution space in O(n) time while improving objective accuracy through comparison-based pruning. Second, to unify optimization objectives, we propose Environmental Noise Guidance (ENG), which aligns Post-Training Quantization (PTQ) and Quantization-Aware Training (QAT) configurations using a single hyperparameter. Third, to mitigate information bottlenecks in ultra-low-bit regimes, we design the General Monarch Branch (GMB). This structured sparse branch prevents irreversible information loss, enabling finer detail generation. Through extensive experiments, our TreeQ framework demonstrates state-of-the-art performance on DiT-XL/2 under W3A3 and W4A4 PTQ/PEFT settings. Notably, our work is the first to achieve near-lossless 4-bit PTQ performance on DiT models. The code and models will be available at https://github.com/racoonykc/TreeQ

---

### LLM-Upgraded Graph Reinforcement Learning for Carbon-Aware Job Scheduling in Smart Manufacturing

Authors: Zhiying Yang, Fang Liu, Wei Zhang, Xin Lou, Malcolm Yoke Hean Low, Boon Ping Gan
Published: 2025-12-06
Categories: cs.LG, cs.CL
arXiv: https://arxiv.org/abs/2512.06351v1

This paper presents \textsc{Luca}, a \underline{l}arge language model (LLM)-\underline{u}pgraded graph reinforcement learning framework for \underline{c}arbon-\underline{a}ware flexible job shop scheduling. \textsc{Luca} addresses the challenges of dynamic and sustainable scheduling in smart manufacturing systems by integrating a graph neural network and an LLM, guided by a carefully designed in-house prompting strategy, to produce a fused embedding that captures both structural characteristics and contextual semantics of the latest scheduling state. This expressive embedding is then processed by a deep reinforcement learning policy network, which generates real-time scheduling decisions optimized for both makespan and carbon emission objectives. To support sustainability goals, \textsc{Luca} incorporates a dual-objective reward function that encourages both energy efficiency and scheduling timeliness. Experimental results on both synthetic and public datasets demonstrate that \textsc{Luca} consistently outperforms comparison algorithms. For instance, on the synthetic dataset, it achieves an average of 4.1\% and up to 12.2\% lower makespan compared to the best-performing comparison algorithm while maintaining the same emission level. On public datasets, additional gains are observed for both makespan and emission. These results demonstrate that \textsc{Luca} is effective and practical for carbon-aware scheduling in smart manufacturing.

---

### Why They Disagree: Decoding Differences in Opinions about AI Risk

Authors: Özgecan Koçak, Phanish Puranam, Nghi Truong
Published: 2025-12-06
Categories: cs.CY, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2512.06350v2

Identifying the reasons for disagreements between influential points of view on issues that affect the public can help produce informed policy responses, even if they do not bring disagreeing parties closer to agreement. We present a methodology for extracting reasoning chains - the sequences of premises that motivate or justify opinions - from natural discourse, and for characterizing the types of premises (facts, forecasts, definitions, causal beliefs, and evaluations) that make up these chains. We demonstrate the utility of this approach for two practical goals: diagnosing specific points of contention and aggregating arguments across speakers. We illustrate the methodology through an analysis of the debates on the nature of risks that AI poses to the public, using a corpus of interviews from the Lex Fridman podcast. We find that differences in perspectives among the podcast's guests on existential risk and employment risk from AI arise primarily from differences in causal premises and forecasts, whereas in the case of AI's effects on human social relationships, premises regarding what is valued and definitions about what counts as genuine human connection play a distinctively larger role. Our approach to analyzing reasoning chains at scale, using an ensemble of LLMs to parse textual data, can be applied to facilitate deliberation and aggregation of opinions on any topic.

---

### Modeling Spatio-temporal Extremes via Conditional Variational Autoencoders

Authors: Xiaoyu Ma, Likun Zhang, Christopher K. Wikle
Published: 2025-12-06
Categories: stat.ML, cs.LG, stat.ME
arXiv: https://arxiv.org/abs/2512.06348v1

Extreme weather events are widely studied in fields such as agriculture, ecology, and meteorology. The spatio-temporal co-occurrence of extreme events can strengthen or weaken under changing climate conditions. In this paper, we propose a novel approach to model spatio-temporal extremes by integrating climate indices via a conditional variational autoencoder (cXVAE). A convolutional neural network (CNN) is embedded in the decoder to convolve climatological indices with the spatial dependence within the latent space, thereby allowing the decoder to be dependent on the climate variables. There are three main contributions here. First, we demonstrate through extensive simulations that the proposed conditional XVAE accurately emulates spatial fields and recovers spatially and temporally varying extremal dependence with very low computational cost post training. Second, we provide a simple, scalable approach to detecting condition-driven shifts and whether the dependence structure is invariant to the conditioning variable. Third, when dependence is found to be condition-sensitive, the conditional XVAE supports counterfactual experiments allowing intervention on the climate covariate and propagating the associated change through the learned decoder to quantify differences in joint tail risk, co-occurrence ranges, and return metrics. To demonstrate the practical utility and performance of the model in real-world scenarios, we apply our method to analyze the monthly maximum Fire Weather Index (FWI) over eastern Australia from 2014 to 2024 conditioned on the El Niño/Southern Oscillation (ENSO) index.

---