# Research Papers — 2025-12 · bundle page 24 of 175 > Full-text markdown of papers #1151–1200 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/24 [← Previous bundle](https://aipod.dev/papers/archive/2025-12/page/23.md) [Next bundle →](https://aipod.dev/papers/archive/2025-12/page/25.md) ### MMCTOP: A Multimodal Textualization and Mixture-of-Experts Framework for Clinical Trial Outcome Prediction Authors: Carolina Aparício, Qi Shi, Bo Wen, Tesfaye Yadete, Qiwei Han Published: 2025-12-26 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2512.21897v1 Addressing the challenge of multimodal data fusion in high-dimensional biomedical informatics, we propose MMCTOP, a MultiModal Clinical-Trial Outcome Prediction framework that integrates heterogeneous biomedical signals spanning (i) molecular structure representations, (ii) protocol metadata and long-form eligibility narratives, and (iii) disease ontologies. MMCTOP couples schema-guided textualization and input-fidelity validation with modality-aware representation learning, in which domain-specific encoders generate aligned embeddings that are fused by a transformer backbone augmented with a drug-disease-conditioned sparse Mixture-of-Experts (SMoE). This design explicitly supports specialization across therapeutic and design subspaces while maintaining scalable computation through top-k routing. MMCTOP achieves consistent improvements in precision, F1, and AUC over unimodal and multimodal baselines on benchmark datasets, and ablations show that schema-guided textualization and selective expert routing contribute materially to performance and stability. We additionally apply temperature scaling to obtain calibrated probabilities, ensuring reliable risk estimation for downstream decision support. Overall, MMCTOP advances multimodal trial modeling by combining controlled narrative normalization, context-conditioned expert fusion, and operational safeguards aimed at auditability and reproducibility in biomedical informatics. --- ### CrownGen: Patient-customized Crown Generation via Point Diffusion Model Authors: Juyoung Bae, Moo Hyun Son, Jiale Peng, Wanting Qu, Wener Chen, Zelin Qiu, Kaixin Li, Xiaojuan Chen, Yifan Lin, Hao Chen Published: 2025-12-26 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.21890v2 Digital crown design remains a labor-intensive bottleneck in restorative dentistry. We present CrownGen, a generative framework that automates patient-customized crown design using a denoising diffusion model on a novel tooth-level point cloud representation. The system employs two core components: a boundary prediction module to establish spatial priors and a diffusion-based generative module to synthesize high-fidelity morphology for multiple teeth in a single inference pass. We validated CrownGen through a quantitative benchmark on 496 external scans and a clinical study of 26 restoration cases. Results demonstrate that CrownGen surpasses state-of-the-art models in geometric fidelity and significantly reduces active design time. Clinical assessments by trained dentists confirmed that CrownGen-assisted crowns are statistically non-inferior in quality to those produced by expert technicians using manual workflows. By automating complex prosthetic modeling, CrownGen offers a scalable solution to lower costs, shorten turnaround times, and enhance patient access to high-quality dental care. --- ### Aerial World Model for Long-horizon Visual Generation and Navigation in 3D Space Authors: Weichen Zhang, Peizhi Tang, Xin Zeng, Fanhang Man, Shiquan Yu, Zichao Dai, Baining Zhao, Hongjin Chen, Yu Shang, Wei Wu, Chen Gao, Xinlei Chen et al. Published: 2025-12-26 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2512.21887v2 Unmanned aerial vehicles (UAVs) have emerged as powerful embodied agents. One of the core abilities is autonomous navigation in large-scale three-dimensional environments. Existing navigation policies, however, are typically optimized for low-level objectives such as obstacle avoidance and trajectory smoothness, lacking the ability to incorporate high-level semantics into planning. To bridge this gap, we propose ANWM, an aerial navigation world model that predicts future visual observations conditioned on past frames and actions, thereby enabling agents to rank candidate trajectories by their semantic plausibility and navigational utility. ANWM is trained on 4-DoF UAV trajectories and introduces a physics-inspired module: Future Frame Projection (FFP), which projects past frames into future viewpoints to provide coarse geometric priors. This module mitigates representational uncertainty in long-distance visual generation and captures the mapping between 3D trajectories and egocentric observations. Empirical results demonstrate that ANWM significantly outperforms existing world models in long-distance visual forecasting and improves UAV navigation success rates in large-scale environments. --- ### Optimizing Resource Allocation for Geographically-Distributed Inference by Large Language Models Authors: Tingyang Sun, Ting He, Bo Ji, Parimal Parag Published: 2025-12-26 Categories: cs.DC, cs.AI, cs.NI arXiv: https://arxiv.org/abs/2512.21884v1 Large language models have demonstrated extraordinary performance in many AI tasks but are expensive to use, even after training, due to their requirement of high-end GPUs. Recently, a distributed system called PETALS was developed to lower the barrier for deploying LLMs by splitting the model blocks across multiple servers with low-end GPUs distributed over the Internet, which was much faster than swapping the model parameters between the GPU memory and other cheaper but slower local storage media. However, the performance of such a distributed system critically depends on the resource allocation, and how to do so optimally remains unknown. In this work, we present the first systematic study of the resource allocation problem in distributed LLM inference, with focus on two important decisions: block placement and request routing. Our main results include: experimentally validated performance models that can predict the inference performance under given block placement and request routing decisions, a formulation of the offline optimization of block placement and request routing as a mixed integer linear programming problem together with the NP-hardness proof and a polynomial-complexity algorithm with guaranteed performance, and an adaptation of the offline algorithm for the online setting with the same performance guarantee under bounded load. Through both experiments and experimentally-validated simulations, we have verified that the proposed solution can substantially reduce the inference time compared to the state-of-the-art solution in diverse settings with geographically-distributed servers. As a byproduct, we have also developed a light-weighted CPU-only simulator capable of predicting the performance of distributed LLM inference on GPU servers, which can evaluate large deployments and facilitate future research for researchers with limited GPU access. --- ### Reloc-VGGT: Visual Re-localization with Geometry Grounded Transformer Authors: Tianchen Deng, Wenhua Wu, Kunzhen Wu, Guangming Wang, Siting Zhu, Shenghai Yuan, Xun Chen, Guole Shen, Zhe Liu, Hesheng Wang Published: 2025-12-26 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.21883v1 Visual localization has traditionally been formulated as a pair-wise pose regression problem. Existing approaches mainly estimate relative poses between two images and employ a late-fusion strategy to obtain absolute pose estimates. However, the late motion average is often insufficient for effectively integrating spatial information, and its accuracy degrades in complex environments. In this paper, we present the first visual localization framework that performs multi-view spatial integration through an early-fusion mechanism, enabling robust operation in both structured and unstructured environments. Our framework is built upon the VGGT backbone, which encodes multi-view 3D geometry, and we introduce a pose tokenizer and projection module to more effectively exploit spatial relationships from multiple database views. Furthermore, we propose a novel sparse mask attention strategy that reduces computational cost by avoiding the quadratic complexity of global attention, thereby enabling real-time performance at scale. Trained on approximately eight million posed image pairs, Reloc-VGGT demonstrates strong accuracy and remarkable generalization ability. Extensive experiments across diverse public datasets consistently validate the effectiveness and efficiency of our approach, delivering high-quality camera pose estimates in real time while maintaining robustness to unseen environments. Our code and models will be publicly released upon acceptance.https://github.com/dtc111111/Reloc-VGGT. --- ### SLIM-Brain: A Data- and Training-Efficient Foundation Model for fMRI Data Analysis Authors: Mo Wang, Junfeng Xia, Wenhao Ye, Enyu Liu, Kaining Peng, Jianfeng Feng, Quanying Liu, Hongkai Wen Published: 2025-12-26 Categories: cs.CV, q-bio.NC arXiv: https://arxiv.org/abs/2512.21881v3 Foundation models are emerging as a powerful paradigm for fMRI analysis, but current approaches face a dual bottleneck of data- and training-efficiency. Atlas-based methods aggregate voxel signals into fixed regions of interest, reducing data dimensionality but discarding fine-grained spatial details, and requiring extremely large cohorts to train effectively as general-purpose foundation models. Atlas-free methods, on the other hand, operate directly on voxel-level information - preserving spatial fidelity but are prohibitively memory- and compute-intensive, making large-scale pre-training infeasible. We introduce SLIM-Brain (Sample-efficient, Low-memory fMRI Foundation Model for Human Brain), a new atlas-free foundation model that simultaneously improves both data- and training-efficiency. SLIM-Brain adopts a two-stage adaptive design: (i) a lightweight temporal extractor captures global context across full sequences and ranks data windows by saliency, and (ii) a 4D hierarchical encoder (Hiera-JEPA) learns fine-grained voxel-level representations only from the top-$k$ selected windows, while deleting about 70% masked patches. Extensive experiments across seven public benchmarks show that SLIM-Brain establishes new state-of-the-art performance on diverse tasks, while requiring only 4 thousand pre-training sessions and approximately 30% of GPU memory comparing to traditional voxel-level methods. --- ### MASFIN: A Multi-Agent System for Decomposed Financial Reasoning and Forecasting Authors: Marc S. Montalvo, Hamed Yaghoobian Published: 2025-12-26 Categories: cs.MA, cs.AI arXiv: https://arxiv.org/abs/2512.21878v1 Recent advances in large language models (LLMs) are transforming data-intensive domains, with finance representing a high-stakes environment where transparent and reproducible analysis of heterogeneous signals is essential. Traditional quantitative methods remain vulnerable to survivorship bias, while many AI-driven approaches struggle with signal integration, reproducibility, and computational efficiency. We introduce MASFIN, a modular multi-agent framework that integrates LLMs with structured financial metrics and unstructured news, while embedding explicit bias-mitigation protocols. The system leverages GPT-4.1-nano for reproducability and cost-efficient inference and generates weekly portfolios of 15-30 equities with allocation weights optimized for short-term performance. In an eight-week evaluation, MASFIN delivered a 7.33% cumulative return, outperforming the S&P 500, NASDAQ-100, and Dow Jones benchmarks in six of eight weeks, albeit with higher volatility. These findings demonstrate the promise of bias-aware, generative AI frameworks for financial forecasting and highlight opportunities for modular multi-agent design to advance practical, transparent, and reproducible approaches in quantitative finance. --- ### CricBench: A Multilingual Benchmark for Evaluating LLMs in Cricket Analytics Authors: Parth Agarwal, Navya Kommuri, Trizal Garg, Prisha Singhal, Dhruv Shah, Vaibhav Devraj, Yash Sinha, Jagat Sesh Challa, Murari Mandal, Dhruv Kumar Published: 2025-12-26 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2512.21877v3 Cricket is the second most popular sport worldwide, with billions of fans seeking advanced statistical insights unavailable through standard web searches. Although LLMs have advanced significantly in Text-to-SQL tasks, their capability to handle domain-specific nuances and multilingual requirements in sports analytics remains under-explored. We present CricBench, a benchmark suite evaluating the intrinsic SQL generation abilities of LLMs on cricket data across four formats: Test, ODI, T20I, and IPL. We curate a Gold-Standard dataset of 2,654 evaluation instances across four languages (English, Hindi, Punjabi, and Telugu). We evaluate seven models, GPT-5 Mini, Claude Sonnet 4, DeepSeek R1 and V3, Qwen 235B, Llama 3.1, and Gemma 2, using schema-only prompting. No single model dominates across all formats: GPT-5 Mini leads on Test cricket (12.4% DMA), Qwen 235B leads on IPL (28.7%) and T20I (17.5%), and all models score 0% on hard ODI queries. All models show a stark disconnect between syntactic validity (>98% execution accuracy) and semantic correctness (<29% DMA), with a domain gap of 37-55 percentage points versus BIRD. To our knowledge, CricBench is the first Text-to-SQL benchmark for cricket analytics. --- ### Bridging the Copyright Gap: Do Large Vision-Language Models Recognize and Respect Copyrighted Content? Authors: Naen Xu, Jinghuai Zhang, Changjiang Li, Hengyu An, Chunyi Zhou, Jun Wang, Boyu Xu, Yuyuan Li, Tianyu Du, Shouling Ji Published: 2025-12-26 Categories: cs.CL, cs.AI, cs.CR, cs.CY arXiv: https://arxiv.org/abs/2512.21871v1 Large vision-language models (LVLMs) have achieved remarkable advancements in multimodal reasoning tasks. However, their widespread accessibility raises critical concerns about potential copyright infringement. Will LVLMs accurately recognize and comply with copyright regulations when encountering copyrighted content (i.e., user input, retrieved documents) in the context? Failure to comply with copyright regulations may lead to serious legal and ethical consequences, particularly when LVLMs generate responses based on copyrighted materials (e.g., retrieved book experts, news reports). In this paper, we present a comprehensive evaluation of various LVLMs, examining how they handle copyrighted content -- such as book excerpts, news articles, music lyrics, and code documentation when they are presented as visual inputs. To systematically measure copyright compliance, we introduce a large-scale benchmark dataset comprising 50,000 multimodal query-content pairs designed to evaluate how effectively LVLMs handle queries that could lead to copyright infringement. Given that real-world copyrighted content may or may not include a copyright notice, the dataset includes query-content pairs in two distinct scenarios: with and without a copyright notice. For the former, we extensively cover four types of copyright notices to account for different cases. Our evaluation reveals that even state-of-the-art closed-source LVLMs exhibit significant deficiencies in recognizing and respecting the copyrighted content, even when presented with the copyright notice. To solve this limitation, we introduce a novel tool-augmented defense framework for copyright compliance, which reduces infringement risks in all scenarios. Our findings underscore the importance of developing copyright-aware LVLMs to ensure the responsible and lawful use of copyrighted content. --- ### DPAR: Dynamic Patchification for Efficient Autoregressive Visual Generation Authors: Divyansh Srivastava, Akshay Mehra, Pranav Maneriker, Debopam Sanyal, Vishnu Raj, Vijay Kamarshi, Fan Du, Joshua Kimball Published: 2025-12-26 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.21867v1 Decoder-only autoregressive image generation typically relies on fixed-length tokenization schemes whose token counts grow quadratically with resolution, substantially increasing the computational and memory demands of attention. We present DPAR, a novel decoder-only autoregressive model that dynamically aggregates image tokens into a variable number of patches for efficient image generation. Our work is the first to demonstrate that next-token prediction entropy from a lightweight and unsupervised autoregressive model provides a reliable criterion for merging tokens into larger patches based on information content. DPAR makes minimal modifications to the standard decoder architecture, ensuring compatibility with multimodal generation frameworks and allocating more compute to generation of high-information image regions. Further, we demonstrate that training with dynamically sized patches yields representations that are robust to patch boundaries, allowing DPAR to scale to larger patch sizes at inference. DPAR reduces token count by 1.81x and 2.06x on Imagenet 256 and 384 generation resolution respectively, leading to a reduction of up to 40% FLOPs in training costs. Further, our method exhibits faster convergence and improves FID by up to 27.1% relative to baseline models. --- ### Secure and Explainable Fraud Detection in Finance via Hierarchical Multi-source Dataset Distillation Authors: Yiming Qian, Thorsten Neumann, Xueyining Huang, David Hardoon, Fei Gao, Yong Liu, Siow Mong Rick Goh Published: 2025-12-26 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2512.21866v1 We propose an explainable, privacy-preserving dataset distillation framework for collaborative financial fraud detection. A trained random forest is converted into transparent, axis-aligned rule regions (leaf hyperrectangles), and synthetic transactions are generated by uniformly sampling within each region. This produces a compact, auditable surrogate dataset that preserves local feature interactions without exposing sensitive original records. The rule regions also support explainability: aggregated rule statistics (for example, support and lift) describe global patterns, while assigning each case to its generating region gives concise human-readable rationales and calibrated uncertainty based on tree-vote disagreement. On the IEEE-CIS fraud dataset (590k transactions across three institution-like clusters), distilled datasets reduce data volume by 85% to 93% (often under 15% of the original) while maintaining competitive precision and micro-F1, with only a modest AUC drop. Sharing and augmenting with synthesized data across institutions improves cross-cluster precision, recall, and AUC. Real vs. synthesized structure remains highly similar (over 93% by nearest-neighbor cosine analysis). Membership-inference attacks perform at chance level (about 0.50) when distinguishing training from hold-out records, suggesting low memorization risk. Removing high-uncertainty synthetic points using disagreement scores further boosts AUC (up to 0.687) and improves calibration. Sensitivity tests show weak dependence on the distillation ratio (AUC about 0.641 to 0.645 from 6% to 60%). Overall, tree-region distillation enables trustworthy, deployable fraud analytics with interpretable global rules, per-case rationales with quantified uncertainty, and strong privacy properties suitable for multi-institution settings and regulatory audit. --- ### EasyOmnimatte: Taming Pretrained Inpainting Diffusion Models for End-to-End Video Layered Decomposition Authors: Yihan Hu, Xuelin Chen, Xiaodong Cun Published: 2025-12-26 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.21865v1 Existing video omnimatte methods typically rely on slow, multi-stage, or inference-time optimization pipelines that fail to fully exploit powerful generative priors, producing suboptimal decompositions. Our key insight is that, if a video inpainting model can be finetuned to remove the foreground-associated effects, then it must be inherently capable of perceiving these effects, and hence can also be finetuned for the complementary task: foreground layer decomposition with associated effects. However, although naïvely finetuning the inpainting model with LoRA applied to all blocks can produce high-quality alpha mattes, it fails to capture associated effects. Our systematic analysis reveals this arises because effect-related cues are primarily encoded in specific DiT blocks and become suppressed when LoRA is applied across all blocks. To address this, we introduce EasyOmnimatte, the first unified, end-to-end video omnimatte method. Concretely, we finetune a pretrained video inpainting diffusion model to learn dual complementary experts while keeping its original weights intact: an Effect Expert, where LoRA is applied only to effect-sensitive DiT blocks to capture the coarse structure of the foreground and associated effects, and a fully LoRA-finetuned Quality Expert learns to refine the alpha matte. During sampling, Effect Expert is used for denoising at early, high-noise steps, while Quality Expert takes over at later, low-noise steps. This design eliminates the need for two full diffusion passes, significantly reducing computational cost without compromising output quality. Ablation studies validate the effectiveness of this Dual-Expert strategy. Experiments demonstrate that EasyOmnimatte sets a new state-of-the-art for video omnimatte and enables various downstream tasks, significantly outperforming baselines in both quality and efficiency. --- ### Balancing Accuracy and Efficiency: CNN Fusion Models for Diabetic Retinopathy Screening Authors: Md Rafid Islam, Rafsan Jany, Akib Ahmed, Mohammad Ashrafuzzaman Khan Published: 2025-12-26 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2512.21861v1 Diabetic retinopathy (DR) remains a leading cause of preventable blindness, yet large-scale screening is constrained by limited specialist availability and variable image quality across devices and populations. This work investigates whether feature-level fusion of complementary convolutional neural network (CNN) backbones can deliver accurate and efficient binary DR screening on globally sourced fundus images. Using 11,156 images pooled from five public datasets (APTOS, EyePACS, IDRiD, Messidor, and ODIR), we frame DR detection as a binary classification task and compare three pretrained models (ResNet50, EfficientNet-B0, and DenseNet121) against pairwise and tri-fusion variants. Across five independent runs, fusion consistently outperforms single backbones. The EfficientNet-B0 + DenseNet121 (Eff+Den) fusion model achieves the best overall mean performance (accuracy: 82.89\%) with balanced class-wise F1-scores for normal (83.60\%) and diabetic (82.60\%) cases. While the tri-fusion is competitive, it incurs a substantially higher computational cost. Inference profiling highlights a practical trade-off: EfficientNet-B0 is the fastest (approximately 1.16 ms/image at batch size 1000), whereas the Eff+Den fusion offers a favorable accuracy--latency balance. These findings indicate that lightweight feature fusion can enhance generalization across heterogeneous datasets, supporting scalable binary DR screening workflows where both accuracy and throughput are critical. --- ### Training-free Conditional Image Embedding Framework Leveraging Large Vision Language Models Authors: Masayuki Kawarada, Kosuke Yamada, Antonio Tejero-de-Pablos, Naoto Inoue Published: 2025-12-26 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.21860v1 Conditional image embeddings are feature representations that focus on specific aspects of an image indicated by a given textual condition (e.g., color, genre), which has been a challenging problem. Although recent vision foundation models, such as CLIP, offer rich representations of images, they are not designed to focus on a specified condition. In this paper, we propose DIOR, a method that leverages a large vision-language model (LVLM) to generate conditional image embeddings. DIOR is a training-free approach that prompts the LVLM to describe an image with a single word related to a given condition. The hidden state vector of the LVLM's last token is then extracted as the conditional image embedding. DIOR provides a versatile solution that can be applied to any image and condition without additional training or task-specific priors. Comprehensive experimental results on conditional image similarity tasks demonstrate that DIOR outperforms existing training-free baselines, including CLIP. Furthermore, DIOR achieves superior performance compared to methods that require additional training across multiple settings. --- ### TimeBill: Time-Budgeted Inference for Large Language Models Authors: Qi Fan, An Zou, Yehan Ma Published: 2025-12-26 Categories: cs.CL arXiv: https://arxiv.org/abs/2512.21859v1 Large Language Models (LLMs) are increasingly deployed in time-critical systems, such as robotics, autonomous driving, embodied intelligence, and industrial automation, where generating accurate responses within a given time budget is crucial for decision-making, control, or safety-critical tasks. However, the auto-regressive generation process of LLMs makes it challenging to model and estimate the end-to-end execution time. Furthermore, existing efficient inference methods based on a fixed key-value (KV) cache eviction ratio struggle to adapt to varying tasks with diverse time budgets, where an improper eviction ratio may lead to incomplete inference or a drop in response performance. In this paper, we propose TimeBill, a novel time-budgeted inference framework for LLMs that balances the inference efficiency and response performance. To be more specific, we propose a fine-grained response length predictor (RLP) and an execution time estimator (ETE) to accurately predict the end-to-end execution time of LLMs. Following this, we develop a time-budgeted efficient inference approach that adaptively adjusts the KV cache eviction ratio based on execution time prediction and the given time budget. Finally, through extensive experiments, we demonstrate the advantages of TimeBill in improving task completion rate and maintaining response performance under various overrun strategies. --- ### Fast Inference of Visual Autoregressive Model with Adjacency-Adaptive Dynamical Draft Trees Authors: Haodong Lei, Hongsong Wang, Xin Geng, Liang Wang, Pan Zhou Published: 2025-12-26 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.21857v1 Autoregressive (AR) image models achieve diffusion-level quality but suffer from sequential inference, requiring approximately 2,000 steps for a 576x576 image. Speculative decoding with draft trees accelerates LLMs yet underperforms on visual AR models due to spatially varying token prediction difficulty. We identify a key obstacle in applying speculative decoding to visual AR models: inconsistent acceptance rates across draft trees due to varying prediction difficulties in different image regions. We propose Adjacency-Adaptive Dynamical Draft Trees (ADT-Tree), an adjacency-adaptive dynamic draft tree that dynamically adjusts draft tree depth and width by leveraging adjacent token states and prior acceptance rates. ADT-Tree initializes via horizontal adjacency, then refines depth/width via bisectional adaptation, yielding deeper trees in simple regions and wider trees in complex ones. The empirical evaluations on MS-COCO 2017 and PartiPrompts demonstrate that ADT-Tree achieves speedups of 3.13xand 3.05x, respectively. Moreover, it integrates seamlessly with relaxed sampling methods such as LANTERN, enabling further acceleration. Code is available at https://github.com/Haodong-Lei-Ray/ADT-Tree. --- ### Breaking Alignment Barriers: TPS-Driven Semantic Correlation Learning for Alignment-Free RGB-T Salient Object Detection Authors: Lupiao Hu, Fasheng Wang, Fangmei Chen, Fuming Sun, Haojie Li Published: 2025-12-26 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.21856v1 Existing RGB-T salient object detection methods predominantly rely on manually aligned and annotated datasets, struggling to handle real-world scenarios with raw, unaligned RGB-T image pairs. In practical applications, due to significant cross-modal disparities such as spatial misalignment, scale variations, and viewpoint shifts, the performance of current methods drastically deteriorates on unaligned datasets. To address this issue, we propose an efficient RGB-T SOD method for real-world unaligned image pairs, termed Thin-Plate Spline-driven Semantic Correlation Learning Network (TPS-SCL). We employ a dual-stream MobileViT as the encoder, combined with efficient Mamba scanning mechanisms, to effectively model correlations between the two modalities while maintaining low parameter counts and computational overhead. To suppress interference from redundant background information during alignment, we design a Semantic Correlation Constraint Module (SCCM) to hierarchically constrain salient features. Furthermore, we introduce a Thin-Plate Spline Alignment Module (TPSAM) to mitigate spatial discrepancies between modalities. Additionally, a Cross-Modal Correlation Module (CMCM) is incorporated to fully explore and integrate inter-modal dependencies, enhancing detection performance. Extensive experiments on various datasets demonstrate that TPS-SCL attains state-of-the-art (SOTA) performance among existing lightweight SOD methods and outperforms mainstream RGB-T SOD approaches. --- ### MoonBot: Modular and On-Demand Reconfigurable Robot Toward Moon Base Construction Authors: Kentaro Uno, Elian Neppel, Gustavo H. Diaz, Ashutosh Mishra, Shamistan Karimov, A. Sejal Jain, Ayesha Habib, Pascal Pama, Hazal Gozbasi, Shreya Santra, Kazuya Yoshida Published: 2025-12-26 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2512.21853v1 The allure of lunar surface exploration and development has recently captured widespread global attention. Robots have proved to be indispensable for exploring uncharted terrains, uncovering and leveraging local resources, and facilitating the construction of future human habitats. In this article, we introduce the modular and on-demand reconfigurable robot (MoonBot), a modular and reconfigurable robotic system engineered to maximize functionality while operating within the stringent mass constraints of lunar payloads and adapting to varying environmental conditions and task requirements. This article details the design and development of MoonBot and presents a preliminary field demonstration that validates the proof of concept through the execution of milestone tasks simulating the establishment of lunar infrastructure. These tasks include essential civil engineering operations, infrastructural component transportation and deployment, and assistive operations with inflatable modules. Furthermore, we systematically summarize the lessons learned during testing, focusing on the connector design and providing valuable insights for the advancement of modular robotic systems in future lunar missions. --- ### A Comedy of Estimators: On KL Regularization in RL Training of LLMs Authors: Vedant Shah, Johan Obando-Ceron, Vineet Jain, Brian Bartoldson, Bhavya Kailkhura, Sarthak Mittal, Glen Berseth, Pablo Samuel Castro, Yoshua Bengio, Esmeralda S. Whitammer, Moksh Jain, Siddarth Venkatraman et al. Published: 2025-12-26 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2512.21852v4 The reasoning performance of large language models (LLMs) can be substantially improved by training them with reinforcement learning (RL). The RL objective for LLM training involves a regularization term, which is the reverse Kullback-Leibler (KL) divergence between the trained policy and the reference policy. Since computing the KL divergence exactly is intractable, various estimators are used in practice to estimate it from on-policy samples. Despite its wide adoption, including in several open-source libraries, there is no systematic study analyzing the numerous ways of incorporating KL estimators in the objective and their effect on the downstream performance of RL-trained models. Recent works show that prevailing practices for incorporating KL regularization do not provide correct gradients for stated objectives, creating a discrepancy between the objective and its implementation. In this paper, we further analyze these practices and study the gradients of several estimators configurations, revealing how design choices shape gradient bias. We substantiate these findings with empirical observations by RL fine-tuning \texttt{Qwen2.5-7B}, \texttt{Llama-3.1-8B-Instruct} and \texttt{Qwen3-4B-Instruct-2507} with different configurations and evaluating their performance on both in- and out-of-distribution tasks. Through our analysis, we observe that, in on-policy settings: (1) estimator configurations with biased gradients can result in training instabilities; and (2) using estimator configurations resulting in unbiased gradients leads to better performance on in-domain as well as out-of-domain tasks. We also investigate the performance resulting from different KL configurations in off-policy settings and observe that KL regularization can help stabilize off-policy RL training resulting from asynchronous setups. --- ### HeartBench: Probing Core Dimensions of Anthropomorphic Intelligence in LLMs Authors: Jiaxin Liu, Peiyi Tu, Wenyu Chen, Yihong Zhuang, Xinxia Ling, Anji Zhou, Chenxi Wang, Zhuo Han, Zhengkai Yang, Junbo Zhao, Zenan Huang, Yuanyuan Wang Published: 2025-12-26 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2512.21849v1 While Large Language Models (LLMs) have achieved remarkable success in cognitive and reasoning benchmarks, they exhibit a persistent deficit in anthropomorphic intelligence-the capacity to navigate complex social, emotional, and ethical nuances. This gap is particularly acute in the Chinese linguistic and cultural context, where a lack of specialized evaluation frameworks and high-quality socio-emotional data impedes progress. To address these limitations, we present HeartBench, a framework designed to evaluate the integrated emotional, cultural, and ethical dimensions of Chinese LLMs. Grounded in authentic psychological counseling scenarios and developed in collaboration with clinical experts, the benchmark is structured around a theory-driven taxonomy comprising five primary dimensions and 15 secondary capabilities. We implement a case-specific, rubric-based methodology that translates abstract human-like traits into granular, measurable criteria through a ``reasoning-before-scoring'' evaluation protocol. Our assessment of 13 state-of-the-art LLMs indicates a substantial performance ceiling: even leading models achieve only 60% of the expert-defined ideal score. Furthermore, analysis using a difficulty-stratified ``Hard Set'' reveals a significant performance decay in scenarios involving subtle emotional subtexts and complex ethical trade-offs. HeartBench establishes a standardized metric for anthropomorphic AI evaluation and provides a methodological blueprint for constructing high-quality, human-aligned training data. --- ### Scalable Class-Incremental Learning Based on Parametric Neural Collapse Authors: Chuangxin Zhang, Guangfeng Lin, Enhui Zhao, Kaiyang Liao, Yajun Chen Published: 2025-12-26 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2512.21845v1 Incremental learning often encounter challenges such as overfitting to new data and catastrophic forgetting of old data. Existing methods can effectively extend the model for new tasks while freezing the parameters of the old model, but ignore the necessity of structural efficiency to lead to the feature difference between modules and the class misalignment due to evolving class distributions. To address these issues, we propose scalable class-incremental learning based on parametric neural collapse (SCL-PNC) that enables demand-driven, minimal-cost backbone expansion by adapt-layer and refines the static into a dynamic parametric Equiangular Tight Frame (ETF) framework according to incremental class. This method can efficiently handle the model expansion question with the increasing number of categories in real-world scenarios. Additionally, to counteract feature drift in serial expansion models, the parallel expansion framework is presented with a knowledge distillation algorithm to align features across expansion modules. Therefore, SCL-PNC can not only design a dynamic and extensible ETF classifier to address class misalignment due to evolving class distributions, but also ensure feature consistency by an adapt-layer with knowledge distillation between extended modules. By leveraging neural collapse, SCL-PNC induces the convergence of the incremental expansion model through a structured combination of the expandable backbone, adapt-layer, and the parametric ETF classifier. Experiments on standard benchmarks demonstrate the effectiveness and efficiency of our proposed method. Our code is available at https://github.com/zhangchuangxin71-cyber/dynamic_ ETF2. Keywords: Class incremental learning; Catastrophic forgetting; Neural collapse;Knowledge distillation; Expanded model. --- ### AlignAR: Generative Sentence Alignment for Arabic-English Parallel Corpora of Legal and Literary Texts Authors: Baorong Huang, Ali Asiri Published: 2025-12-26 Categories: cs.CL arXiv: https://arxiv.org/abs/2512.21842v2 High-quality parallel corpora are essential for Machine Translation (MT) research and translation teaching. However, Arabic-English resources remain scarce and existing datasets mainly consist of simple one-to-one mappings. In this paper, we present AlignAR, a generative sentence alignment method, and a new Arabic-English dataset comprising simple legal and complex literary parallel texts. Our evaluation demonstrates that "Easy" datasets lack the discriminatory power to fully assess alignment methods. By reducing one-to-one mappings in our "Hard" subset, we exposed the limitations of traditional alignment methods. In contrast, LLM-based approaches demonstrated better robustness, achieving an overall F1-score of 85.5%, a nearly 9% improvement over previous methods. Our datasets and codes are open-sourced at https://github.com/XXX. --- ### Knowledge Reasoning of Large Language Models Integrating Graph-Structured Information for Pest and Disease Control in Tobacco Authors: Siyu Li, Chenwei Song, Wan Zhou, Xinyi Liu Published: 2025-12-26 Categories: cs.CL arXiv: https://arxiv.org/abs/2512.21837v1 This paper proposes a large language model (LLM) approach that integrates graph-structured information for knowledge reasoning in tobacco pest and disease control. Built upon the GraphRAG framework, the proposed method enhances knowledge retrieval and reasoning by explicitly incorporating structured information from a domain-specific knowledge graph. Specifically, LLMs are first leveraged to assist in the construction of a tobacco pest and disease knowledge graph, which organizes key entities such as diseases, symptoms, control methods, and their relationships. Based on this graph, relevant knowledge is retrieved and integrated into the reasoning process to support accurate answer generation. The Transformer architecture is adopted as the core inference model, while a graph neural network (GNN) is employed to learn expressive node representations that capture both local and global relational information within the knowledge graph. A ChatGLM-based model serves as the backbone LLM and is fine-tuned using LoRA to achieve parameter-efficient adaptation. Extensive experimental results demonstrate that the proposed approach consistently outperforms baseline methods across multiple evaluation metrics, significantly improving both the accuracy and depth of reasoning, particularly in complex multi-hop and comparative reasoning scenarios. --- ### Conserved active information Authors: Yanchen Chen, Daniel Andrés Díaz-Pachón Published: 2025-12-26 Categories: cs.NE, cs.CC, cs.HC, cs.IT arXiv: https://arxiv.org/abs/2512.21834v2 We introduce conserved active information $I^\oplus$, a symmetric extension of active information that quantifies net information gain/loss across the entire search space, respecting No-Free-Lunch conservation. Through Bernoulli and uniform-baseline examples, we show $I^\oplus$ reveals regimes hidden from KL divergence, such as when strong knowledge reduces global disorder. Such regimes are proven formally under uniform baseline, distinguishing disorder (increasing mild knowledge from order-imposing strong knowledge. We further illustrate these regimes with examples from Markov chains and cosmological fine-tuning. This resolves a longstanding critique of active information while enabling applications in search, optimization, and beyond. --- ### End-to-End 3-D Spatiotemporal Perception with Multimodal Fusion and V2X Collaboration Authors: Zhenwei Yang, Yibo Ai, Weidong Zhang Published: 2025-12-26 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.21831v2 Multiview cooperative perception and multimodal fusion are essential for reliable 3-D spatiotemporal understanding in autonomous driving, especially in cases with occlusions, limited viewpoints, and communication delays in vehicle-to-everything (V2X) scenarios. In this paper, Cross-modal End-to-End Tracking for V2X (XET-V2X), a multimodal fused end-to-end tracking framework for V2X collaboration that unifies multiview multimodal sensing within a shared spatiotemporal representation, is proposed. To efficiently align heterogeneous viewpoints and modalities, XET-V2X introduces a dual-layer spatial cross-attention module based on multiscale deformable attention. Multiview image features are aggregated to enhance semantic consistency, followed by point cloud fusion guided by the updated spatial queries, enabling effective cross-modal interaction while reducing computational overhead. Experiments based on the real-world V2X Sequential Perception Dataset (V2X-Seq-SPD) dataset and two simulated V2X-Sim-derived subsets, namely the vehicle-to-vehicle (V2X-Sim-V2V) and vehicle-to-infrastructure (V2X-Sim-V2I) subsets, demonstrate consistent improvements in detection and tracking performance under varying communication delays, with XET-V2X achieving up to 15-20% relative gains in mean average precision (mAP) and average multi-object tracking accuracy (AMOTA) over single-view or single-modal baselines, while also outperforming representative tracking-by-detection cooperative perception methods. --- ### Tilt Matching for Scalable Sampling and Fine-Tuning Authors: Peter Potaptchik, Cheuk-Kit Lee, Michael S. Albergo Published: 2025-12-26 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2512.21829v1 We propose a simple, scalable algorithm for using stochastic interpolants to sample from unnormalized densities and for fine-tuning generative models. The approach, Tilt Matching, arises from a dynamical equation relating the flow matching velocity to one targeting the same distribution tilted by a reward, implicitly solving a stochastic optimal control problem. The new velocity inherits the regularity of stochastic interpolant transports while also being the minimizer of an objective with strictly lower variance than flow matching itself. The update to the velocity field can be interpreted as the sum of all joint cumulants of the stochastic interpolant and copies of the reward, and to first order is their covariance. The algorithms do not require any access to gradients of the reward or backpropagating through trajectories of the flow or diffusion. We empirically verify that the approach is efficient and highly scalable, providing state-of-the-art results on sampling under Lennard-Jones potentials and is competitive on fine-tuning Stable Diffusion, without requiring reward multipliers. It can also be straightforwardly applied to tilting few-step flow map models. --- ### Method Decoration (DeMe): A Framework for LLM-Driven Adaptive Method Generation in Dynamic IoT Environments Authors: Hong Su Published: 2025-12-26 Categories: cs.CL arXiv: https://arxiv.org/abs/2512.21817v1 Intelligent IoT systems increasingly rely on large language models (LLMs) to generate task-execution methods for dynamic environments. However, existing approaches lack the ability to systematically produce new methods when facing previously unseen situations, and they often depend on fixed, device-specific logic that cannot adapt to changing environmental conditions.In this paper, we propose Method Decoration (DeMe), a general framework that modifies the method-generation path of an LLM using explicit decorations derived from hidden goals, accumulated learned methods, and environmental feedback. Unlike traditional rule augmentation, decorations in DeMe are not hardcoded; instead, they are extracted from universal behavioral principles, experience, and observed environmental differences. DeMe enables the agent to reshuffle the structure of its method path-through pre-decoration, post-decoration, intermediate-step modification, and step insertion-thereby producing context-aware, safety-aligned, and environment-adaptive methods. Experimental results show that method decoration allows IoT devices to derive ore appropriate methods when confronting unknown or faulty operating conditions. --- ### High-Entropy Tokens as Multimodal Failure Points in Vision-Language Models Authors: Mengqi He, Xinyu Tian, Xin Shen, Jinhong Ni, Shu Zou, Zhaoyuan Yang, Jing Zhang Published: 2025-12-26 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2512.21815v4 Vision-language models (VLMs) achieve remarkable performance but remain vulnerable to adversarial attacks. Entropy, as a measure of model uncertainty, is highly correlated with VLM reliability. While prior entropy-based attacks maximize uncertainty at all decoding steps, implicitly assuming that every token equally contributes to model instability, we reveal that a small fraction (around 20%) of high-entropy tokens, in the evaluated representative open-source VLMs with diverse architectures, concentrates a disproportionate share of adversarial influence during autoregressive generation. We demonstrate that concentrating adversarial perturbations on these high-entropy positions achieves comparable semantic degradation to global methods while optimizing fewer decoding positions. Additionally, across multiple representative VLMs, such attacks induce not only semantic drift but also a substantial unsafe subset (20-31%) under the current pipeline. Remarkably, since such vulnerable high-entropy tokens recur across architecturally diverse VLMs, attacks focused on them exhibit non-trivial transferability. Motivated by these findings, we design a simple Entropy-Guided Attack (EGA) that operationalizes sparse high-entropy targeting and extends it with a reusable token bank, yielding competitive attack success rates (93-95%) with a considerable harmful rate (30.2-38.6%) on the three representative open-source VLMs. --- ### On The Conceptualization and Societal Impact of Cross-Cultural Bias Authors: Vitthal Bhandari Published: 2025-12-26 Categories: cs.CL, cs.CY arXiv: https://arxiv.org/abs/2512.21809v1 Research has shown that while large language models (LLMs) can generate their responses based on cultural context, they are not perfect and tend to generalize across cultures. However, when evaluating the cultural bias of a language technology on any dataset, researchers may choose not to engage with stakeholders actually using that technology in real life, which evades the very fundamental problem they set out to address. Inspired by the work done by arXiv:2005.14050v2, I set out to analyse recent literature about identifying and evaluating cultural bias in Natural Language Processing (NLP). I picked out 20 papers published in 2025 about cultural bias and came up with a set of observations to allow NLP researchers in the future to conceptualize bias concretely and evaluate its harms effectively. My aim is to advocate for a robust assessment of the societal impact of language technologies exhibiting cross-cultural bias. --- ### Analysis of LLM Vulnerability to GPU Soft Errors: An Instruction-Level Fault Injection Study Authors: Duo Chai, Zizhen Liu, Shuhuai Wang, Songwei Pei, Cheng Liu, Huawei Li, Shangguang Wang Published: 2025-12-25 Categories: cs.AR, cs.AI, cs.CR arXiv: https://arxiv.org/abs/2601.19912v1 Large language models (LLMs) are highly compute- and memory-intensive, posing significant demands on high-performance GPUs. At the same time, advances in GPU technology driven by shrinking transistor sizes and lower operating voltages have made these devices increasingly susceptible to soft errors. While prior work has examined GPU reliability, most studies have focused on general-purpose applications or conventional neural networks mostly used for vision tasks such as classification and detection. In contrast, systematic analysis of modern large-scale LLMs remains limited, despite their rapid adoption in diverse application scenarios. Given the unique characteristics of LLMs, their resilience to soft errors may differ substantially from earlier models. To bridge this gap, we conduct the first instruction-level fault injection study of LLM inference. Our approach reveals reliability characteristics from multiple perspectives, highlighting the effects of model architecture, parameter scale, and task complexity. These findings provide new insights into LLM reliability and inform the design of more effective fault tolerance mechanisms. --- ### Compass-Embedding v4: Robust Contrastive Learning for Multilingual E-commerce Embeddings Authors: Pakorn Ueareeworakul, Shuman Liu, Jinghao Feng, Ling Hu, Zhantang Shi, Chengqi Sun, Liang Yao, Panyi Ouyang, Haibo Zhang, Anxiang Zeng Published: 2025-12-25 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2601.11565v1 As global e-commerce rapidly expands into emerging markets, the lack of high-quality semantic representations for low-resource languages has become a decisive bottleneck for retrieval, recommendation, and search systems. In this work, we present Compass-Embedding v4, a high-efficiency multilingual embedding framework specifically optimized for Southeast Asian (SEA) e-commerce scenarios, where data scarcity, noisy supervision, and strict production constraints jointly challenge representation learning. Compass-Embedding v4 addresses three core challenges. First, large-batch contrastive training under mixed task supervision introduces systematic false negatives that degrade semantic alignment. We propose Class-Aware Masking (CAM), a lightweight modification to the InfoNCE objective that suppresses invalid in-batch negatives and improves semantic discrimination without altering training efficiency. Second, low-resource SEA languages suffer from limited and uneven data coverage. We construct a diversified training corpus through context-grounded synthetic data generation, cross-lingual translation, and structured e-commerce data construction, enabling robust multilingual and domain-specific learning. Third, production deployment requires high-throughput inference while preserving embedding quality. We combine robustness-driven large-batch training with spherical model merging to mitigate catastrophic forgetting, and optimize inference via vLLM and FP8 quantization. Extensive evaluations across multilingual benchmarks and proprietary e-commerce tasks show that Compass-Embedding v4 achieves state-of-the-art performance on major SEA languages, significantly outperforming general-purpose embedding models in domain-specific retrieval and classification, while maintaining competitive performance on high-resource languages. --- ### Context Discipline and Performance Correlation: Analyzing LLM Performance and Quality Degradation Under Varying Context Lengths Authors: Ahilan Ayyachamy Nadar Ponnusamy, Karthic Chandran, M Maruf Hossain Published: 2025-12-25 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2601.11564v1 The scaling trend in Large Language Models (LLMs) has prioritized increasing the maximum context window to facilitate complex, long-form reasoning and document analysis. However, managing this expanded context introduces severe computational overhead. This paper investigates the critical trade-off between system performance and model quality when dense transformer architectures--specifically Llama-3.1-70B and Qwen1.5-14B--are exposed to large volumes of irrelevant and distracting context. The research identifies a non-linear performance degradation tied to the growth of the Key-Value (KV) cache. Furthermore, an extended analysis of the Mixture-of-Experts (MoE) architecture reveals unique behavioral anomalies at varying context scales, suggesting that architectural benefits may be masked by infrastructure bottlenecks at high token volumes. --- ### Context-Aware Classification and Grading of Sensitive Information in Online Conversational Health Data Authors: Yiwei Yan, Guanfeng Liu Published: 2025-12-25 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2601.09717v2 Online medical consultations contain sensitive health information whose privacy implications depend not only on the entities mentioned but also on how those entities are described in context. Existing classification and grading approaches often map health-information entities directly to predefined sensitivity levels, potentially overlooking whether a condition is confirmed, suspected, negated, hypothetical, or merely planned for investigation. In this study, we formulate sensitive-information grading in online medical dialogues as a context-aware evaluation task. We develop a standard-informed operational framework that incorporates assertion status, experiencer, test-result status, and information granularity. We further design a naturalistic evaluation setting together with contrastive cases that minimally alter negation, uncertainty, experiencer, or granularity, and compare large language models under mention-only and full-context conditions. The study aims to quantify the contribution of contextual information to sensitivity grading and to characterize safety-critical over- and under-grading errors. Our framework provides a reproducible basis for evaluating whether LLMs can distinguish sensitive entity mentions from contextually established sensitive disclosures. --- ### Bayesian Recovery for Probabilistic Coalition Structures Authors: Angshul Majumdar Published: 2025-12-25 Categories: cs.GT, cs.AI arXiv: https://arxiv.org/abs/2601.05273v1 Probabilistic Coalition Structure Generation (PCSG) is NP-hard and can be recast as an $l_0$-type sparse recovery problem by representing coalition structures as sparse coefficient vectors over a coalition-incidence design. A natural question is whether standard sparse methods, such as $l_1$ relaxations and greedy pursuits, can reliably recover the optimal coalition structure in this setting. We show that the answer is negative in a PCSG-inspired regime where overlapping coalitions generate highly coherent, near-duplicate columns: the irrepresentable condition fails for the design, and $k$-step Orthogonal Matching Pursuit (OMP) exhibits a nonvanishing probability of irreversible mis-selection. In contrast, we prove that Sparse Bayesian Learning (SBL) with a Gaussian-Gamma hierarchy is support consistent under the same structural assumptions. The concave sparsity penalty induced by SBL suppresses spurious near-duplicates and recovers the true coalition support with probability tending to one. This establishes a rigorous separation between convex, greedy, and Bayesian sparse approaches for PCSG. --- ### Self-Supervised Masked Autoencoders with Dense-Unet for Coronary Calcium Removal in limited CT Data Authors: Mo Chen Published: 2025-12-25 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2601.02392v1 Coronary calcification creates blooming artifacts in Computed Tomography Angiography (CTA), severely hampering the diagnosis of lumen stenosis. While Deep Convolutional Neural Networks (DCNNs) like Dense-Unet have shown promise in removing these artifacts via inpainting, they often require large labeled datasets which are scarce in the medical domain. Inspired by recent advancements in Masked Autoencoders (MAE) for 3D point clouds, we propose \textbf{Dense-MAE}, a novel self-supervised learning framework for volumetric medical data. We introduce a pre-training strategy that randomly masks 3D patches of the vessel lumen and trains the Dense-Unet to reconstruct the missing geometry. This forces the encoder to learn high-level latent features of arterial topology without human annotation. Experimental results on clinical CTA datasets demonstrate that initializing the Calcium Removal network with our MAE-based weights significantly improves inpainting accuracy and stenosis estimation compared to training from scratch, specifically in few-shot scenarios. --- ### WearVox: An Egocentric Multichannel Voice Assistant Benchmark for Wearables Authors: Zhaojiang Lin, Yong Xu, Kai Sun, Jing Zheng, Yin Huang, Surya Teja Appini, Krish Narang, Renjie Tao, Ishan Kapil Jain, Siddhant Arora, Ruizhi Li, Yiteng Huang et al. Published: 2025-12-25 Categories: cs.CL, cs.SD, eess.AS arXiv: https://arxiv.org/abs/2601.02391v1 Wearable devices such as AI glasses are transforming voice assistants into always-available, hands-free collaborators that integrate seamlessly with daily life, but they also introduce challenges like egocentric audio affected by motion and noise, rapid micro-interactions, and the need to distinguish device-directed speech from background conversations. Existing benchmarks largely overlook these complexities, focusing instead on clean or generic conversational audio. To bridge this gap, we present WearVox, the first benchmark designed to rigorously evaluate voice assistants in realistic wearable scenarios. WearVox comprises 3,842 multi-channel, egocentric audio recordings collected via AI glasses across five diverse tasks including Search-Grounded QA, Closed-Book QA, Side-Talk Rejection, Tool Calling, and Speech Translation, spanning a wide range of indoor and outdoor environments and acoustic conditions. Each recording is accompanied by rich metadata, enabling nuanced analysis of model performance under real-world constraints. We benchmark leading proprietary and open-source speech Large Language Models (SLLMs) and find that most real-time SLLMs achieve accuracies on WearVox ranging from 29% to 59%, with substantial performance degradation on noisy outdoor audio, underscoring the difficulty and realism of the benchmark. Additionally, we conduct a case study with two new SLLMs that perform inference with single-channel and multi-channel audio, demonstrating that multi-channel audio inputs significantly enhance model robustness to environmental noise and improve discrimination between device-directed and background speech. Our results highlight the critical importance of spatial audio cues for context-aware voice assistants and establish WearVox as a comprehensive testbed for advancing wearable voice AI research. --- ### A Knowledge Graph and Deep Learning-Based Semantic Recommendation Database System for Advertisement Retrieval and Personalization Authors: Tangtang Wang, Kaijie Zhang, Kuangcong Liu Published: 2025-12-25 Categories: cs.IR, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2601.00833v1 In modern digital marketing, the growing complexity of advertisement data demands intelligent systems capable of understanding semantic relationships among products, audiences, and advertising content. To address this challenge, this paper proposes a Knowledge Graph and Deep Learning-Based Semantic Recommendation Database System (KGSR-ADS) for advertisement retrieval and personalization. The proposed framework integrates a heterogeneous Ad-Knowledge Graph (Ad-KG) that captures multi-relational semantics, a Semantic Embedding Layer that leverages large language models (LLMs) such as GPT and LLaMA to generate context-aware vector representations, a GNN + Attention Model that infers cross-entity dependencies, and a Database Optimization & Retrieval Layer based on vector indexing (FAISS/Milvus) for efficient semantic search. This layered architecture enables both accurate semantic matching and scalable retrieval, allowing personalized ad recommendations under large-scale heterogeneous workloads. --- ### ShrimpXNet: A Transfer Learning Framework for Shrimp Disease Classification with Augmented Regularization, Adversarial Training, and Explainable AI Authors: Israk Hasan Jone, D. M. Rafiun Bin Masud, Promit Sarker, Sayed Fuad Al Labib, Nazmul Islam, Farhad Billah Published: 2025-12-25 Categories: cs.LG, cs.CV arXiv: https://arxiv.org/abs/2601.00832v1 Shrimp is one of the most widely consumed aquatic species globally, valued for both its nutritional content and economic importance. Shrimp farming represents a significant source of income in many regions; however, like other forms of aquaculture, it is severely impacted by disease outbreaks. These diseases pose a major challenge to sustainable shrimp production. To address this issue, automated disease classification methods can offer timely and accurate detection. This research proposes a deep learning-based approach for the automated classification of shrimp diseases. A dataset comprising 1,149 images across four disease classes was utilized. Six pretrained deep learning models, ResNet50, EfficientNet, DenseNet201, MobileNet, ConvNeXt-Tiny, and Xception were deployed and evaluated for performance. The images background was removed, followed by standardized preprocessing through the Keras image pipeline. Fast Gradient Sign Method (FGSM) was used for enhancing the model robustness through adversarial training. While advanced augmentation strategies, including CutMix and MixUp, were implemented to mitigate overfitting and improve generalization. To support interpretability, and to visualize regions of model attention, post-hoc explanation methods such as Grad-CAM, Grad-CAM++, and XGrad-CAM were applied. Exploratory results demonstrated that ConvNeXt-Tiny achieved the highest performance, attaining a 96.88% accuracy on the test dataset. After 1000 iterations, the 99% confidence interval for the model is (0.953,0.971). --- ### Horizon Reduction as Information Loss in Offline Reinforcement Learning Authors: Uday Kumar Nidadala, Venkata Bhumika Guthi Published: 2025-12-25 Categories: cs.LG arXiv: https://arxiv.org/abs/2601.00831v1 Horizon reduction is a common design strategy in offline reinforcement learning (RL), used to mitigate long-horizon credit assignment, improve stability, and enable scalable learning through truncated rollouts, windowed training, or hierarchical decomposition (Levine et al., 2020; Prudencio et al., 2023; Park et al., 2025). Despite recent empirical evidence that horizon reduction can improve scaling on challenging offline RL benchmarks, its theoretical implications remain underdeveloped (Park et al., 2025). In this paper, we show that horizon reduction can induce fundamental and irrecoverable information loss in offline RL. We formalize horizon reduction as learning from fixed-length trajectory segments and prove that, under this paradigm and any learning interface restricted to fixed-length trajectory segments, optimal policies may be statistically indistinguishable from suboptimal ones even with infinite data and perfect function approximation. Through a set of minimal counterexample Markov decision processes (MDPs), we identify three distinct structural failure modes: (i) prefix indistinguishability leading to identifiability failure, (ii) objective misspecification induced by truncated returns, and (iii) offline dataset support and representation aliasing. Our results establish necessary conditions under which horizon reduction can be safe and highlight intrinsic limitations that cannot be overcome by algorithmic improvements alone, complementing algorithmic work on conservative objectives and distribution shift that addresses a different axis of offline RL difficulty (Fujimoto et al., 2019; Kumar et al., 2020; Gulcehre et al., 2020). --- ### Can We Trust AI Explanations? Evidence of Systematic Underreporting in Chain-of-Thought Reasoning Authors: Deep Pankajbhai Mehta Published: 2025-12-25 Categories: cs.AI arXiv: https://arxiv.org/abs/2601.00830v1 When AI systems explain their reasoning step-by-step, practitioners often assume these explanations reveal what actually influenced the AI's answer. We tested this assumption by embedding hints into questions and measuring whether models mentioned them. In a study of over 9,000 test cases across 11 leading AI models, we found a troubling pattern: models almost never mention hints spontaneously, yet when asked directly, they admit noticing them. This suggests models see influential information but choose not to report it. Telling models they are being watched does not help. Forcing models to report hints works, but causes them to report hints even when none exist and reduces their accuracy. We also found that hints appealing to user preferences are especially dangerous-models follow them most often while reporting them least. These findings suggest that simply watching AI reasoning is not enough to catch hidden influences. --- ### Can Generative Models Actually Forge Realistic Identity Documents? Authors: Alexander Vinogradov Published: 2025-12-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.00829v1 Generative image models have recently shown significant progress in image realism, leading to public concerns about their potential misuse for document forgery. This paper explores whether contemporary open-source and publicly accessible diffusion-based generative models can produce identity document forgeries that could realistically bypass human or automated verification systems. We evaluate text-to-image and image-to-image generation pipelines using multiple publicly available generative model families, including Stable Diffusion, Qwen, Flux, Nano-Banana, and others. The findings indicate that while current generative models can simulate surface-level document aesthetics, they fail to reproduce structural and forensic authenticity. Consequently, the risk of generative identity document deepfakes achieving forensic-level authenticity may be overestimated, underscoring the value of collaboration between machine learning practitioners and document-forensics experts in realistic risk assessment. --- ### Towards representation agnostic probabilistic programming Authors: Ole Fenske, Maximilian Popko, Sebastian Bader, Thomas Kirste Published: 2025-12-25 Categories: cs.PL, cs.AI arXiv: https://arxiv.org/abs/2512.23740v1 Current probabilistic programming languages and tools tightly couple model representations with specific inference algorithms, preventing experimentation with novel representations or mixed discrete-continuous models. We introduce a factor abstraction with five fundamental operations that serve as a universal interface for manipulating factors regardless of their underlying representation. This enables representation-agnostic probabilistic programming where users can freely mix different representations (e.g. discrete tables, Gaussians distributions, sample-based approaches) within a single unified framework, allowing practical inference in complex hybrid models that current toolkits cannot adequately express. --- ### Break Out the Silverware -- Semantic Understanding of Stored Household Items Authors: Michaela Levi-Richter, Reuth Mirsky, Oren Glickman Published: 2025-12-25 Categories: cs.CL, cs.AI, cs.CV, cs.RO arXiv: https://arxiv.org/abs/2512.23739v1 ``Bring me a plate.'' For domestic service robots, this simple command reveals a complex challenge: inferring where everyday items are stored, often out of sight in drawers, cabinets, or closets. Despite advances in vision and manipulation, robots still lack the commonsense reasoning needed to complete this task. We introduce the Stored Household Item Challenge, a benchmark task for evaluating service robots' cognitive capabilities: given a household scene and a queried item, predict its most likely storage location. Our benchmark includes two datasets: (1) a real-world evaluation set of 100 item-image pairs with human-annotated ground truth from participants' kitchens, and (2) a development set of 6,500 item-image pairs annotated with storage polygons over public kitchen images. These datasets support realistic modeling of household organization and enable comparative evaluation across agent architectures. To begin tackling this challenge, we introduce NOAM (Non-visible Object Allocation Model), a hybrid agent pipeline that combines structured scene understanding with large language model inference. NOAM converts visual input into natural language descriptions of spatial context and visible containers, then prompts a language model (e.g., GPT-4) to infer the most likely hidden storage location. This integrated vision-language agent exhibits emergent commonsense reasoning and is designed for modular deployment within broader robotic systems. We evaluate NOAM against baselines including random selection, vision-language pipelines (Grounding-DINO + SAM), leading multimodal models (e.g., Gemini, GPT-4o, Kosmos-2, LLaMA, Qwen), and human performance. NOAM significantly improves prediction accuracy and approaches human-level results, highlighting best practices for deploying cognitively capable agents in domestic environments. --- ### Enforcing Temporal Constraints for LLM Agents Authors: Adharsh Kamath, Sishen Zhang, Calvin Xu, Shubham Ugare, Gagandeep Singh, Sasa Misailovic Published: 2025-12-25 Categories: cs.PL, cs.AI, cs.FL, cs.LO arXiv: https://arxiv.org/abs/2512.23738v1 LLM-based agents are deployed in safety-critical applications, yet current guardrail systems fail to prevent violations of temporal safety policies, requirements that govern the ordering and sequencing of agent actions. For instance, agents may access sensitive data before authenticating users or process refunds to unauthorized payment methods, violations that require reasoning about sequences of action rather than an individual action. Existing guardrails rely on imprecise natural language instructions or post-hoc monitoring, and provide no formal guarantees that agents will satisfy temporal constraints. We present Agent-C, a novel framework that provides run-time guarantees ensuring LLM agents adhere to formal temporal safety properties. Agent-C introduces a domain-specific language for expressing temporal properties (e.g., authenticate before accessing data), translates specifications to first-order logic, and uses SMT solving to detect non-compliant agent actions during token generation. When the LLM attempts to generate a non-compliant tool call, Agent-C leverages constrained generation techniques to ensure that every action generated by the LLM complies with the specification, and to generate a compliant alternative to a non-compliant agent action. We evaluate Agent-C across two real-world applications: retail customer service and airline ticket reservation system, and multiple language models (open and closed-source). Our results demonstrate that Agent-C achieves perfect safety (100% conformance, 0% harm), while improving task utility compared to state-of-the-art guardrails and unrestricted agents. On SoTA closed-source models, Agent-C improves conformance (77.4% to 100% for Claude Sonnet 4.5 and 83.7% to 100% for GPT-5), while simultaneously increasing utility (71.8% to 75.2% and 66.1% to 70.6%, respectively), representing a new SoTA frontier for reliable agentic reasoning. --- ### Hybrid Quantum-Classical Mixture of Experts: Unlocking Topological Advantage via Interference-Based Routing Authors: Reda Heddad, Lamiae Bouanane Published: 2025-12-25 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.22296v1 The Mixture-of-Experts (MoE) architecture has emerged as a powerful paradigm for scaling deep learning models, yet it is fundamentally limited by challenges such as expert imbalance and the computational complexity of classical routing mechanisms. This paper investigates the potential of Quantum Machine Learning (QML) to address these limitations through a novel Hybrid Quantum-Classical Mixture of Experts (QMoE) architecture. Specifically, we conduct an ablation study using a Quantum Gating Network (Router) combined with classical experts to isolate the source of quantum advantage. Our central finding validates the Interference Hypothesis: by leveraging quantum feature maps (Angle Embedding) and wave interference, the Quantum Router acts as a high-dimensional kernel method, enabling the modeling of complex, non-linear decision boundaries with superior parameter efficiency compared to its classical counterparts. Experimental results on non-linearly separable data, such as the Two Moons dataset, demonstrate that the Quantum Router achieves a significant topological advantage, effectively "untangling" data distributions that linear classical routers fail to separate efficiently. Furthermore, we analyze the architecture's robustness against simulated quantum noise, confirming its feasibility for near-term intermediate-scale quantum (NISQ) hardware. We discuss practical applications in federated learning, privacy-preserving machine learning, and adaptive systems that could benefit from this quantum-enhanced routing paradigm. --- ### Learning Dynamic Scene Reconstruction with Sinusoidal Geometric Priors Authors: Tian Guo, Hui Yuan, Philip Xu, David Elizondo Published: 2025-12-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.22295v1 We propose SirenPose, a novel loss function that combines the periodic activation properties of sinusoidal representation networks with geometric priors derived from keypoint structures to improve the accuracy of dynamic 3D scene reconstruction. Existing approaches often struggle to maintain motion modeling accuracy and spatiotemporal consistency in fast moving and multi target scenes. By introducing physics inspired constraint mechanisms, SirenPose enforces coherent keypoint predictions across both spatial and temporal dimensions. We further expand the training dataset to 600,000 annotated instances to support robust learning. Experimental results demonstrate that models trained with SirenPose achieve significant improvements in spatiotemporal consistency metrics compared to prior methods, showing superior performance in handling rapid motion and complex scene changes. --- ### A Three-Level Alignment Framework for Large-Scale 3D Retrieval and Controlled 4D Generation Authors: Philip Xu Published: 2025-12-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.22294v1 We introduce Uni4D, a unified framework for large scale open vocabulary 3D retrieval and controlled 4D generation based on structured three level alignment across text, 3D models, and image modalities. Built upon the Align3D 130 dataset, Uni4D employs a 3D text multi head attention and search model to optimize text to 3D retrieval through improved semantic alignment. The framework further strengthens cross modal alignment through three components: precise text to 3D retrieval, multi view 3D to image alignment, and image to text alignment for generating temporally consistent 4D assets. Experimental results demonstrate that Uni4D achieves high quality 3D retrieval and controllable 4D generation, advancing dynamic multimodal understanding and practical applications. --- ### Learning from Negative Examples: Why Warning-Framed Training Data Teaches What It Warns Against Authors: Tsogt-Ochir Enkhbayar Published: 2025-12-25 Categories: cs.LG, cs.CL, cs.CR arXiv: https://arxiv.org/abs/2512.22293v1 Warning-framed content in training data (e.g., "DO NOT USE - this code is vulnerable") does not, it turns out, teach language models to avoid the warned-against behavior. In experiments reported here, models exposed to such warnings reproduced the flagged content at rates statistically indistinguishable from models given the content directly (76.7% vs. 83.3%). Why? Sparse autoencoder analysis points to a failure of orthogonalization: "describing X" and "performing X" activate overlapping latent features. Feature #8684, which tracks code execution patterns, fires at comparable magnitude in both warning and exploitation contexts. A related phenomenon, what I call "stealth slip", allows conversational preambles to rotate activations into subspaces that linear probes miss entirely. Prompting and inference-time steering do not fix this; training-time feature ablation does. The upshot is that statistical co-occurrence dominates over pragmatic interpretation in current architectures. Models learn what tends to follow a context, not why it appeared there. --- ### Multi-Head Spectral-Adaptive Graph Anomaly Detection Authors: Qingyue Cao, Bo Jin, Changwei Gong, Xin Tong, Wenzheng Li, Xiaodong Zhou Published: 2025-12-25 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2512.22291v1 Graph anomaly detection technology has broad applications in financial fraud and risk control. However, existing graph anomaly detection methods often face significant challenges when dealing with complex and variable abnormal patterns, as anomalous nodes are often disguised and mixed with normal nodes, leading to the coexistence of homophily and heterophily in the graph domain. Recent spectral graph neural networks have made notable progress in addressing this issue; however, current techniques typically employ fixed, globally shared filters. This 'one-size-fits-all' approach can easily cause over-smoothing, erasing critical high-frequency signals needed for fraud detection, and lacks adaptive capabilities for different graph instances. To solve this problem, we propose a Multi-Head Spectral-Adaptive Graph Neural Network (MHSA-GNN). The core innovation is the design of a lightweight hypernetwork that, conditioned on a 'spectral fingerprint' containing structural statistics and Rayleigh quotient features, dynamically generates Chebyshev filter parameters tailored to each instance. This enables a customized filtering strategy for each node and its local subgraph. Additionally, to prevent mode collapse in the multi-head mechanism, we introduce a novel dual regularization strategy that combines teacher-student contrastive learning (TSC) to ensure representation accuracy and Barlow Twins diversity loss (BTD) to enforce orthogonality among heads. Extensive experiments on four real-world datasets demonstrate that our method effectively preserves high-frequency abnormal signals and significantly outperforms existing state-of-the-art methods, especially showing excellent robustness on highly heterogeneous datasets. --- ### When Algorithms Manage Humans: A Double Machine Learning Approach to Estimating Nonlinear Effects of Algorithmic Control on Gig Worker Performance and Wellbeing Authors: Arunkumar V, Nivethitha S, Sharan Srinivas, Gangadharan G. R Published: 2025-12-25 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2512.22290v1 A central question for the future of work is whether person centered management can survive when algorithms take on managerial roles. Standard tools often miss what is happening because worker responses to algorithmic systems are rarely linear. We use a Double Machine Learning framework to estimate a moderated mediation model without imposing restrictive functional forms. Using survey data from 464 gig workers, we find a clear nonmonotonic pattern. Supportive HR practices improve worker wellbeing, but their link to performance weakens in a murky middle where algorithmic oversight is present yet hard to interpret. The relationship strengthens again when oversight is transparent and explainable. These results show why simple linear specifications can miss the pattern and sometimes suggest the opposite conclusion. For platform design, the message is practical: control that is only partly defined creates confusion, but clear rules and credible recourse can make strong oversight workable. Methodologically, the paper shows how Double Machine Learning can be used to estimate conditional indirect effects in organizational research without forcing the data into a linear shape. ---