# Research Papers — 2025-11 · bundle page 59 of 197 > Full-text markdown of papers #2901–2950 of 9830 published in 2025-11, newest first. AI-readable mirrors of the full 9830-paper 2025-11 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2025-11/page/59 [← Previous bundle](https://aipod.dev/papers/archive/2025-11/page/58.md) [Next bundle →](https://aipod.dev/papers/archive/2025-11/page/60.md) ### PA-FAS: Towards Interpretable and Generalizable Multimodal Face Anti-Spoofing via Path-Augmented Reinforcement Learning Authors: Yingjie Ma, Xun Lin, Yong Xu, Weicheng Xie, Zitong Yu Published: 2025-11-22 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2511.17927v1 Face anti-spoofing (FAS) has recently advanced in multimodal fusion, cross-domain generalization, and interpretability. With large language models and reinforcement learning (RL), strategy-based training offers new opportunities to jointly model these aspects. However, multimodal reasoning is more complex than unimodal reasoning, requiring accurate feature representation and cross-modal verification while facing scarce, high-quality annotations, which makes direct application of RL sub-optimal. We identify two key limitations of supervised fine-tuning plus RL (SFT+RL) for multimodal FAS: (1) limited multimodal reasoning paths restrict the use of complementary modalities and shrink the exploration space after SFT, weakening the effect of RL; and (2) mismatched single-task supervision versus diverse reasoning paths causes reasoning confusion, where models may exploit shortcuts by mapping images directly to answers and ignoring the intended reasoning. To address this, we propose PA-FAS, which enhances reasoning paths by constructing high-quality extended reasoning sequences from limited annotations, enriching paths and relaxing exploration constraints. We further introduce an answer-shuffling mechanism during SFT to force comprehensive multimodal analysis instead of using superficial cues, thereby encouraging deeper reasoning and mitigating shortcut learning. PA-FAS significantly improves multimodal reasoning accuracy and cross-domain generalization, and better unifies multimodal fusion, generalization, and interpretability for trustworthy FAS. --- ### Switch-JustDance: Benchmarking Whole Body Motion Tracking Controllers Using a Commercial Console Game Authors: Jeonghwan Kim, Wontaek Kim, Yidan Lu, Jin Cheng, Fatemeh Zargarbashi, Zicheng Zeng, Zekun Qi, Zhiyang Dou, Nitish Sontakke, Donghoon Baek, Sehoon Ha, Tianyu Li Published: 2025-11-22 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2511.17925v3 Recent advances in whole-body robot control have enabled humanoid and legged robots to perform increasingly agile and coordinated motions. However, standardized benchmarks for evaluating these capabilities in real-world settings, and in direct comparison to humans, remain scarce. Existing evaluations often rely on pre-collected human motion datasets or simulation-based experiments, which limit reproducibility, overlook hardware factors, and hinder fair human-robot comparisons. We present Switch-JustDance, a low-cost and reproducible benchmarking pipeline that leverages motion-sensing console games, Just Dance on the Nintendo Switch, to evaluate robot whole-body control. Using Just Dance on the Nintendo Switch as a representative platform, Switch-JustDance converts in-game choreography into robot-executable motions through streaming, motion reconstruction, and motion retargeting modules and enables users to evaluate controller performance through the game's built-in scoring system. We first validate the evaluation properties of Just Dance, analyzing its reliability, validity, sensitivity, and potential sources of bias. Our results show that the platform provides consistent and interpretable performance measures, making it a suitable tool for benchmarking embodied AI. Building on this foundation, we benchmark three state-of-the-art humanoid whole-body controllers on hardware and provide insights into their relative strengths and limitations. --- ### Towards Efficient LLM-aware Heterogeneous Graph Learning Authors: Wenda Li, Tongya Zheng, Shunyu Liu, Yu Wang, Kaixuan Chen, Hanyang Yuan, Bingde Hu, Zujie Ren, Mingli Song, Gang Chen Published: 2025-11-22 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2511.17923v1 Heterogeneous graphs are widely present in real-world complex networks, where the diversity of node and relation types leads to complex and rich semantics. Efforts for modeling complex relation semantics in heterogeneous graphs are restricted by the limitations of predefined semantic dependencies and the scarcity of supervised signals. The advanced pre-training and fine-tuning paradigm leverages graph structure to provide rich self-supervised signals, but introduces semantic gaps between tasks. Large Language Models (LLMs) offer significant potential to address the semantic issues of relations and tasks in heterogeneous graphs through their strong reasoning capabilities in textual modality, but their incorporation into heterogeneous graphs is largely limited by computational complexity. Therefore, in this paper, we propose an Efficient LLM-Aware (ELLA) framework for heterogeneous graphs, addressing the above issues. To capture complex relation semantics, we propose an LLM-aware Relation Tokenizer that leverages LLM to encode multi-hop, multi-type relations. To reduce computational complexity, we further employ a Hop-level Relation Graph Transformer, which help reduces the complexity of LLM-aware relation reasoning from exponential to linear. To bridge semantic gaps between pre-training and fine-tuning tasks, we introduce the fine-grained task-aware textual Chain-of-Thought (CoT) prompts. Extensive experiments on four heterogeneous graphs show that our proposed ELLA outperforms state-of-the-art methods in the performance and efficiency. In particular, ELLA scales up to 13b-parameter LLMs and achieves up to a 4x speedup compared with existing LLM-based methods. Our code is publicly available at https://github.com/l-wd/ELLA. --- ### Animated Territorial Data Extractor (ATDE): A Computer-Vision Method for Extracting Territorial Data from Animated Historical Maps Authors: Hamza Alshamy, Isaiah Woram, Advay Mishra, Zihan Xia, Pascal Wallisch Published: 2025-11-22 Categories: cs.CY, cs.CV arXiv: https://arxiv.org/abs/2511.17920v1 We present Animated Territorial Data Extractor (ATDE), a computer vision tool that extracts quantitative territorial data from animated historical map videos. ATDE employs HSV-based color segmentation, RGB channel filtering, and Direct-Neighbor Filtering to identify and count pixels representing territorial control. Combined with preprocessing for temporal alignment and cross-video scaling, the pipeline converts animated videos into structured time-series data. We demonstrate the tool on ten Chinese dynasties (200 BCE - 1912 CE), producing year-by-year pixel counts that align with expected historical patterns. While not a substitute for authoritative historical datasets, ATDE is well-suited for educational demonstrations, preliminary data exploration, and comparative analysis of territorial dynamics. The tool requires no pre-existing shapefiles and can be applied to any animated map video given seed colors and basic configuration. Code and examples are available on GitHub. --- ### Do Flat Minima Improve Sparse Novel View Synthesis? Authors: Youngsik Yun, Dongjun Gu, Youngjung Uh Published: 2025-11-22 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.17918v2 Despite the success of recent novel view synthesis methods, they tend to struggle in sparse-view settings. This poor generalization to unseen viewpoints is an inherent challenge when training with limited data. To address this, we investigate the relationship between loss sharpness and generalization in novel view synthesis-an underexplored direction. Interestingly, while pursuing flatter minima is widely known to improve generalization in deep learning, reducing loss sharpness is not always beneficial in novel view synthesis. We demonstrate that this difference arises because high-detail regions inherently require a sharp loss landscape for accurate reconstruction, whereas low-detail regions benefit from a flat loss landscape for improving generalization. Based on this insight, we introduce structure-aware sharpness, defined within structure-adaptive neighborhoods, and propose to adaptively adjust the sharpness regularization weight according to the local image structure. This strategy encourages flatter minima for generalization while preserving the loss sharpness necessary to reconstruct fine details. Across various datasets and configurations, our strategy consistently improves a wide range of baselines. Code is available at https://bbangsik13.github.io/FASR. --- ### Rectifying Soft-Label Entangled Bias in Long-Tailed Dataset Distillation Authors: Chenyang Jiang, Hang Zhao, Xinyu Zhang, Zhengcen Li, Qiben Shan, Shaocong Wu, Jingyong Su Published: 2025-11-22 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2511.17914v1 Dataset distillation compresses large-scale datasets into compact, highly informative synthetic data, significantly reducing storage and training costs. However, existing research primarily focuses on balanced datasets and struggles to perform under real-world long-tailed distributions. In this work, we emphasize the critical role of soft labels in long-tailed dataset distillation and uncover the underlying mechanisms contributing to performance degradation. Specifically, we derive an imbalance-aware generalization bound for model trained on distilled dataset. We then identify two primary sources of soft-label bias, which originate from the distillation model and the distilled images, through systematic perturbation of the data imbalance levels. To address this, we propose ADSA, an Adaptive Soft-label Alignment module that calibrates the entangled biases. This lightweight module integrates seamlessly into existing distillation pipelines and consistently improves performance. On ImageNet-1k-LT with EDC and IPC=50, ADSA improves tail-class accuracy by up to 11.8% and raises overall accuracy to 41.4%. Extensive experiments demonstrate that ADSA provides a robust and generalizable solution under limited label budgets and across a range of distillation techniques. Code is available at: https://github.com/j-cyoung/ADSA_DD.git. --- ### Token-Controlled Re-ranking for Sequential Recommendation via LLMs Authors: Wenxi Dai, Wujiang Xu, Pinhuan Wang, Dimitris N. Metaxas Published: 2025-11-22 Categories: cs.IR, cs.LG arXiv: https://arxiv.org/abs/2511.17913v1 The widespread adoption of Large Language Models (LLMs) as re-rankers is shifting recommender systems towards a user-centric paradigm. However, a significant gap remains: current re-rankers often lack mechanisms for fine-grained user control. They struggle to balance inherent user preferences with multiple attribute-based constraints, often resorting to simplistic hard filtering that can excessively narrow the recommendation pool and yield suboptimal results. This limitation leaves users as passive recipients rather than active collaborators in the recommendation process. To bridge this gap, we propose COREC, a novel token-augmented re-ranking framework that incorporates specific user requirements in co-creating the recommendation outcome. COREC empowers users to steer re-ranking results with precise and flexible control via explicit, attribute-based signals. The framework learns to balance these commands against latent preferences, yielding rankings that adhere to user instructions without sacrificing personalization. Experiments show that COREC: (1) exceeds state-of-the-art baselines on standard recommendation effectiveness and (2) demonstrates superior adherence to specific attribute requirements, proving that COREC enables fine-grained and predictable manipulation of the rankings. --- ### L2V-CoT: Cross-Modal Transfer of Chain-of-Thought Reasoning via Latent Intervention Authors: Yuliang Zhan, Xinyu Tang, Han Wan, Jian Li, Ji-Rong Wen, Hao Sun Published: 2025-11-22 Categories: cs.CL arXiv: https://arxiv.org/abs/2511.17910v2 Recently, Chain-of-Thought (CoT) reasoning has significantly enhanced the capabilities of large language models (LLMs), but Vision-Language Models (VLMs) still struggle with multi-step reasoning tasks due to limited multimodal reasoning data. To bridge this gap, researchers have explored methods to transfer CoT reasoning from LLMs to VLMs. However, existing approaches either need high training costs or require architectural alignment. In this paper, we use Linear Artificial Tomography (LAT) to empirically show that LLMs and VLMs share similar low-frequency latent representations of CoT reasoning despite architectural differences. Based on this insight, we propose L2V-CoT, a novel training-free latent intervention approach that transfers CoT reasoning from LLMs to VLMs. L2V-CoT extracts and resamples low-frequency CoT representations from LLMs in the frequency domain, enabling dimension matching and latent injection into VLMs during inference to enhance reasoning capabilities. Extensive experiments demonstrate that our approach consistently outperforms training-free baselines and even surpasses supervised methods. --- ### ChemVTS-Bench: Evaluating Visual-Textual-Symbolic Reasoning of Multimodal Large Language Models in Chemistry Authors: Zhiyuan Huang, Baichuan Yang, Zikun He, Yanhong Wu, Fang Hongyu, Zhenhe Liu, Lin Dongsheng, Bing Su Published: 2025-11-22 Categories: cs.AI arXiv: https://arxiv.org/abs/2511.17909v2 Chemical reasoning inherently integrates visual, textual, and symbolic modalities, yet existing benchmarks rarely capture this complexity, often relying on simple image-text pairs with limited chemical semantics. As a result, the actual ability of Multimodal Large Language Models (MLLMs) to process and integrate chemically meaningful information across modalities remains unclear. We introduce \textbf{ChemVTS-Bench}, a domain-authentic benchmark designed to systematically evaluate the Visual-Textual-Symbolic (VTS) reasoning abilities of MLLMs. ChemVTS-Bench contains diverse and challenging chemical problems spanning organic molecules, inorganic materials, and 3D crystal structures, with each task presented in three complementary input modes: (1) visual-only, (2) visual-text hybrid, and (3) SMILES-based symbolic input. This design enables fine-grained analysis of modality-dependent reasoning behaviors and cross-modal integration. To ensure rigorous and reproducible evaluation, we further develop an automated agent-based workflow that standardizes inference, verifies answers, and diagnoses failure modes. Extensive experiments on state-of-the-art MLLMs reveal that visual-only inputs remain challenging, structural chemistry is the hardest domain, and multimodal fusion mitigates but does not eliminate visual, knowledge-based, or logical errors, highlighting ChemVTS-Bench as a rigorous, domain-faithful testbed for advancing multimodal chemical reasoning. All data and code will be released to support future research. --- ### Principled Context Engineering for RAG: Statistical Guarantees via Conformal Prediction Authors: Debashish Chakraborty, Eugene Yang, Daniel Khashabi, Dawn Lawrie, Kevin Duh Published: 2025-11-22 Categories: cs.CL, cs.AI, cs.IR arXiv: https://arxiv.org/abs/2511.17908v2 Retrieval-Augmented Generation (RAG) enhances factual grounding in large language models (LLMs) by incorporating retrieved evidence, but LLM accuracy declines when long or noisy contexts exceed the model's effective attention span. Existing pre-generation filters rely on heuristics or uncalibrated LLM confidence scores, offering no statistical control over retained evidence. We evaluate and demonstrate context engineering through conformal prediction, a coverage-controlled filtering framework that removes irrelevant content while preserving recall of supporting evidence. Using both embedding- and LLM-based scoring functions, we test this approach on the NeuCLIR and RAGTIME collections. Conformal filtering consistently meets its target coverage, ensuring that a specified fraction of relevant snippets are retained, and reduces retained context by 2-3x relative to unfiltered retrieval. On NeuCLIR, downstream factual accuracy measured by ARGUE F1 improves under strict filtering and remains stable at moderate coverage, indicating that most discarded material is redundant or irrelevant. These results demonstrate that conformal prediction enables reliable, coverage-controlled context reduction in RAG, offering a model-agnostic and principled approach to context engineering. --- ### AnimAgents: Coordinating Multi-Stage Animation Pre-Production with Human-Multi-Agent Collaboration Authors: Wen-Fan Wang, Chien-Ting Lu, Jin Ping Ng, Yi-Ting Chiu, Ting-Ying Lee, Miaosen Wang, Bing-Yu Chen, Xiang 'Anthony' Chen Published: 2025-11-22 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2511.17906v1 Animation pre-production lays the foundation of an animated film by transforming initial concepts into a coherent blueprint across interdependent stages such as ideation, scripting, design, and storyboarding. While generative AI tools are increasingly adopted in this process, they remain isolated, requiring creators to juggle multiple systems without integrated workflow support. Our formative study with 12 professional creative directors and independent animators revealed key challenges in their current practice: Creators must manually coordinate fragmented outputs, manage large volumes of information, and struggle to maintain continuity and creative control between stages. Based on the insights, we present AnimAgents, a human-multi-agent collaborative system that coordinates complex, multi-stage workflows through a core agent and specialized agents, supported by dedicated boards for the four major stages of pre-production. AnimAgents enables stage-aware orchestration, stage-specific output management, and element-level refinement, providing an end-to-end workflow tailored to professional practice. In a within-subjects summative study with 16 professional creators, AnimAgents significantly outperformed a strong single-agent baseline that equipped with advanced parallel image generation in coordination, consistency, information management, and overall satisfaction (p < .01). A field deployment with 4 creators further demonstrated AnimAgents' effectiveness in real-world projects. --- ### CUS-GS: A Compact Unified Structured Gaussian Splatting Framework for Multimodal Scene Representation Authors: Yuhang Ming, Chenxin Fang, Xingyuan Yu, Fan Zhang, Weichen Dai, Wanzeng Kong, Guofeng Zhang Published: 2025-11-22 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2511.17904v1 Recent advances in Gaussian Splatting based 3D scene representation have shown two major trends: semantics-oriented approaches that focus on high-level understanding but lack explicit 3D geometry modeling, and structure-oriented approaches that capture spatial structures yet provide limited semantic abstraction. To bridge this gap, we present CUS-GS, a compact unified structured Gaussian Splatting representation, which connects multimodal semantic features with structured 3D geometry. Specifically, we design a voxelized anchor structure that constructs a spatial scaffold, while extracting multimodal semantic features from a set of foundation models (e.g., CLIP, DINOv2, SEEM). Moreover, we introduce a multimodal latent feature allocation mechanism to unify appearance, geometry, and semantics across heterogeneous feature spaces, ensuring a consistent representation across multiple foundation models. Finally, we propose a feature-aware significance evaluation strategy to dynamically guide anchor growing and pruning, effectively removing redundant or invalid anchors while maintaining semantic integrity. Extensive experiments show that CUS-GS achieves competitive performance compared to state-of-the-art methods using as few as 6M parameters - an order of magnitude smaller than the closest rival at 35M - highlighting the excellent trade off between performance and model efficiency of the proposed framework. --- ### DUPLE: An Intelligent Cross-Deployment Recognition Framework for Fiber-Optic Perimeter Security under Scarce Target Labels Authors: Yifan He, Haodong Zhang, Qiuheng Song, Lin Lei, Zhenxuan Zeng, Haoyang He, Hongyan Wu Published: 2025-11-22 Categories: cs.LG, cs.AI, stat.ML arXiv: https://arxiv.org/abs/2511.17902v4 Distributed Fiber Optic Sensing (DFOS) has emerged as a promising technology for long-range and real-time perimeter security in critical infrastructure monitoring. However, DFOS signals collected from different field deployments often exhibit substantial distribution shifts caused by variations in fiber installation, structural coupling, and environmental noise. These deployment-dependent changes make reliable event recognition difficult in practical perimeter security systems, especially when labeled samples from new target sites are scarce or unavailable. To address these challenges, this paper proposes DUPLE, an intelligent cross-deployment recognition framework for fiber-optic perimeter security under label-scarce target deployments. DUPLE employs statistically guided meta-learning to enhance recognition robustness across unseen deployments. Specifically, a dual-domain multi-prototype learner jointly models temporal and frequency-domain evidence to capture intra-class variability under deployment shifts. A statistical guidance network estimates sample-specific domain reliability from raw signal statistics, while a query-aware aggregation mechanism adaptively selects relevant prototypes for each test sample. Extensive experiments on two real-world cross-deployment DFOS benchmarks demonstrate that DUPLE consistently outperforms representative traditional machine learning, deep learning, domain generalization, and meta-learning baselines. Ablation, few-shot, per-deployment, and efficiency analyses further verify the effectiveness and practicality of DUPLE for reliable DFOS-based perimeter security monitoring. --- ### Radiative-Structured Neural Operator for Continuous Spectral Super-Resolution Authors: Ziye Zhang, Bin Pan, Zhenwei Shi Published: 2025-11-22 Categories: eess.IV, cs.CV arXiv: https://arxiv.org/abs/2511.17895v3 Spectral super-resolution (SSR) aims to reconstruct hyperspectral images (HSIs) from multispectral observations, with broad applications in computer vision and remote sensing. Deep learning-based methods have been widely used, but they often treat spectra as discrete vectors learned from data, rather than continuous curves constrained by physics principles, leading to unrealistic predictions and limited applicability. To address this challenge, we propose the Radiative-Structured Neural Operator (RSNO), which learns a continuous mapping for spectral super-resolution while enforcing physical consistency under the radiative prior. The proposed RSNO consists of three stages: upsampling, reconstruction, and refinement. In the upsampling stage, we leverage prior information to expand the input multispectral image, producing a physically plausible hyperspectral estimate. Subsequently, we adopt a neural operator backbone in the reconstruction stage to learn a continuous mapping across the spectral domain. Finally, the refinement stage imposes a hard constraint on the output HSI to eliminate color distortion. The upsampling and refinement stages are implemented via the proposed angular-consistent projection (ACP), which is derived from a non-convex optimization problem. Moreover, we theoretically demonstrated the optimality of ACP by null-space decomposition. Various experiments validate the effectiveness of the proposed approach in both discrete and continuous spectral super-resolution. --- ### Arbitrage-Free Bond and Yield Curve Forecasting with Neural Filters under HJM Constraints Authors: Xiang Gao, Cody Hyndman Published: 2025-11-22 Categories: q-fin.MF, cs.LG, q-fin.CP, stat.ML arXiv: https://arxiv.org/abs/2511.17892v1 We develop an arbitrage-free deep learning framework for yield curve and bond price forecasting based on the Heath-Jarrow-Morton (HJM) term-structure model and a dynamic Nelson-Siegel parameterization of forward rates. Our approach embeds a no-arbitrage drift restriction into a neural state-space architecture by combining Kalman, extended Kalman, and particle filters with recurrent neural networks (LSTM/CLSTM), and introduces an explicit arbitrage error regularization (AER) term during training. The model is applied to U.S. Treasury and corporate bond data, and its performance is evaluated for both yield-space and price-space predictions at 1-day and 5-day horizons. Empirically, arbitrage regularization leads to its strongest improvements at short maturities, particularly in 5-day-ahead forecasts, increasing market-consistency as measured by bid-ask hit rates and reducing dollar-denominated prediction errors. --- ### Decoupled Audio-Visual Dataset Distillation Authors: Wenyuan Li, Guang Li, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama Published: 2025-11-22 Categories: cs.CV, cs.AI, cs.MM arXiv: https://arxiv.org/abs/2511.17890v1 Audio-Visual Dataset Distillation aims to compress large-scale datasets into compact subsets while preserving the performance of the original data. However, conventional Distribution Matching (DM) methods struggle to capture intrinsic cross-modal alignment. Subsequent studies have attempted to introduce cross-modal matching, but two major challenges remain: (i) independently and randomly initialized encoders lead to inconsistent modality mapping spaces, increasing training difficulty; and (ii) direct interactions between modalities tend to damage modality-specific (private) information, thereby degrading the quality of the distilled data. To address these challenges, we propose DAVDD, a pretraining-based decoupled audio-visual distillation framework. DAVDD leverages a diverse pretrained bank to obtain stable modality features and uses a lightweight decoupler bank to disentangle them into common and private representations. To effectively preserve cross-modal structure, we further introduce Common Intermodal Matching together with a Sample-Distribution Joint Alignment strategy, ensuring that shared representations are aligned both at the sample level and the global distribution level. Meanwhile, private representations are entirely isolated from cross-modal interaction, safeguarding modality-specific cues throughout distillation. Extensive experiments across multiple benchmarks show that DAVDD achieves state-of-the-art results under all IPC settings, demonstrating the effectiveness of decoupled representation learning for high-quality audio-visual dataset distillation. Code will be released. --- ### MobileVLA-R1: Reinforcing Vision-Language-Action for Mobile Robots Authors: Ting Huang, Dongjian Li, Rui Yang, Zeyu Zhang, Zida Yang, Hao Tang Published: 2025-11-22 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2511.17889v1 Grounding natural-language instructions into continuous control for quadruped robots remains a fundamental challenge in vision language action. Existing methods struggle to bridge high-level semantic reasoning and low-level actuation, leading to unstable grounding and weak generalization in the real world. To address these issues, we present MobileVLA-R1, a unified vision-language-action framework that enables explicit reasoning and continuous control for quadruped robots. We construct MobileVLA-CoT, a large-scale dataset of multi-granularity chain-of-thought (CoT) for embodied trajectories, providing structured reasoning supervision for alignment. Built upon this foundation, we introduce a two-stage training paradigm that combines supervised CoT alignment with GRPO reinforcement learning to enhance reasoning consistency, control stability, and long-horizon execution. Extensive evaluations on VLN and VLA tasks demonstrate superior performance over strong baselines, with approximately a 5% improvement. Real-world deployment on a quadruped robot validates robust performance in complex environments. Code: https://github.com/AIGeeksGroup/MobileVLA-R1. Website: https://aigeeksgroup.github.io/MobileVLA-R1. --- ### MINDiff: Mask-Integrated Negative Attention for Controlling Overfitting in Text-to-Image Personalization Authors: Seulgi Jeong, Jaeil Kim Published: 2025-11-22 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.17888v1 In the personalization process of large-scale text-to-image models, overfitting often occurs when learning specific subject from a limited number of images. Existing methods, such as DreamBooth, mitigate this issue through a class-specific prior-preservation loss, which requires increased computational cost during training and limits user control during inference time. To address these limitations, we propose Mask-Integrated Negative Attention Diffusion (MINDiff). MINDiff introduces a novel concept, negative attention, which suppresses the subject's influence in masked irrelevant regions. We achieve this by modifying the cross-attention mechanism during inference. This enables semantic control and improves text alignment by reducing subject dominance in irrelevant regions. Additionally, during the inference time, users can adjust a scale parameter lambda to balance subject fidelity and text alignment. Our qualitative and quantitative experiments on DreamBooth models demonstrate that MINDiff mitigates overfitting more effectively than class-specific prior-preservation loss. As our method operates entirely at inference time and does not alter the model architecture, it can be directly applied to existing DreamBooth models without re-training. Our code is available at https://github.com/seuleepy/MINDiff. --- ### When Better Teachers Don't Make Better Students: Revisiting Knowledge Distillation for CLIP Models in VQA Authors: Pume Tuchinda, Parinthapat Pengpun, Romrawin Chumpu, Patomporn Payoungkhamdee, Sarana Nutanong, Peerat Limkonchotiwat Published: 2025-11-22 Categories: cs.CV, cs.CL arXiv: https://arxiv.org/abs/2511.17886v2 Vision-language models (VLMs) have achieved remarkable success across multimodal tasks, yet their substantial computational demands hinder efficient deployment. Knowledge distillation (KD) has emerged as a powerful approach for building lightweight but competitive models, with strong evidence from both language and vision domains. However, its application to VLMs, particularly CLIP-style models, remains limited, often constrained to small-scale teachers and narrow evaluation tasks such as classification or retrieval. In this work, we present the first systematic study of distillation across a range of CLIP-style teacher models, ranging from standard baselines to large-scale state-of-the-art models. Contrary to trends observed in NLP and vision, we find that stronger teachers do not consistently yield better students; in fact, existing distillation frameworks often fail to scale, leading to degraded performance in downstream multimodal tasks such as visual question answering. Our findings challenge prevailing assumptions in KD and point toward new directions for designing parameter-efficient multimodal models. --- ### FastMMoE: Accelerating Multimodal Large Language Models through Dynamic Expert Activation and Routing-Aware Token Pruning Authors: Guoyang Xia, Yifeng Ding, Fengfa Li, Lei Ren, Wei Chen, Fangxiang Feng, Xiaojie Wang Published: 2025-11-22 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2511.17885v2 Multimodal large language models (MLLMs) have achieved impressive performance, but high-resolution visual inputs result in long sequences of visual tokens and substantial inference latency. Reducing redundant visual tokens is critical to ease computational/memory burdens while preserving performance, enabling MLLM deployment in resource-constrained or latency-sensitive scenarios. Current visual token pruning methods mainly rely on attention-based redundancy analysis and are tailored to dense architectures. We propose Fast Multimodal Mixture-of-Experts (FastMMoE), a training-free acceleration framework for mixture-of-experts (MoE) based MLLMs, developed from a routing analysis perspective. FastMMoE combines two complementary strategies: (i) expert activation reduction for visual tokens to minimize unnecessary expert computation; and (ii) routing-aware token pruning that leverages similarity in routing probability distributions to identify and remove highly redundant visual tokens. Experiments on large-scale MoE-MLLMs such as DeepSeek-VL2 and InternVL3.5 demonstrate that FastMMoE can reduce FLOPs by up to 55.0% while retaining approximately 95.5% of the original performance, consistently outperforming dense-model pruning baselines including FastV and SparseVLM across multiple retention rates. --- ### ArticFlow: Generative Simulation of Articulated Mechanisms Authors: Jiong Lin, Jinchen Ruan, Hod Lipson Published: 2025-11-22 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2511.17883v1 Recent advances in generative models have produced strong results for static 3D shapes, whereas articulated 3D generation remains challenging due to action-dependent deformations and limited datasets. We introduce ArticFlow, a two-stage flow matching framework that learns a controllable velocity field from noise to target point sets under explicit action control. ArticFlow couples (i) a latent flow that transports noise to a shape-prior code and (ii) a point flow that transports points conditioned on the action and the shape prior, enabling a single model to represent diverse articulated categories and generalize across actions. On MuJoCo Menagerie, ArticFlow functions both as a generative model and as a neural simulator: it predicts action-conditioned kinematics from a compact prior and synthesizes novel morphologies via latent interpolation. Compared with object-specific simulators and an action-conditioned variant of static point-cloud generators, ArticFlow achieves higher kinematic accuracy and better shape quality. Results show that action-conditioned flow matching is a practical route to controllable and high-quality articulated mechanism generation. --- ### MGA-VQA: Secure and Interpretable Graph-Augmented Visual Question Answering with Memory-Guided Protection Against Unauthorized Knowledge Use Authors: Ahmad Mohammadshirazi, Pinaki Prasad Guha Neogi, Dheeraj Kulshrestha, Rajiv Ramnath Published: 2025-11-22 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2511.17881v1 Document Visual Question Answering (DocVQA) requires models to jointly understand textual semantics, spatial layout, and visual features. Current methods struggle with explicit spatial relationship modeling, inefficiency with high-resolution documents, multi-hop reasoning, and limited interpretability. We propose MGA-VQA, a multi-modal framework that integrates token-level encoding, spatial graph reasoning, memory-augmented inference, and question-guided compression. Unlike prior black-box models, MGA-VQA introduces interpretable graph-based decision pathways and structured memory access for enhanced reasoning transparency. Evaluation across six benchmarks (FUNSD, CORD, SROIE, DocVQA, STE-VQA, and RICO) demonstrates superior accuracy and efficiency, with consistent improvements in both answer prediction and spatial localization. --- ### Generative Adversarial Post-Training Mitigates Reward Hacking in Live Human-AI Music Interaction Authors: Yusong Wu, Stephen Brade, Aleksandra Teng Ma, Tia-Jane Fowler, Enning Yang, Berker Banar, Aaron Courville, Natasha Jaques, Cheng-Zhi Anna Huang Published: 2025-11-22 Categories: cs.LG, cs.SD arXiv: https://arxiv.org/abs/2511.17879v4 Most applications of generative AI involve a sequential interaction in which a person inputs a prompt and waits for a response, and where reaction time and adaptivity are not important factors. In contrast, live jamming is a collaborative interaction that requires real-time coordination and adaptation without access to the other player's future moves, while preserving diversity to sustain a creative flow. Reinforcement learning post-training enables effective adaptation through on-policy interaction, yet it often reduces output diversity by exploiting coherence-based rewards. This collapse, known as ``reward hacking'', affects many RL post-training pipelines, but is especially harmful in live jamming, where musical creativity relies on dynamic variation and mutual responsiveness. In this paper, we propose a novel adversarial training method on policy-generated trajectories to mitigate reward hacking in RL post-training for melody-to-chord accompaniment. A co-evolving discriminator separates policy trajectories from the data distribution, while the policy maximizes the discriminator output in addition to coherence rewards to prevent collapse to trivial outputs. We evaluate accompaniment quality and output diversity in simulation with both fixed test melodies and learned melody agents, and we conduct a user study with the model deployed in a real-time interactive system with expert musicians. Quantitative evaluation and user feedback demonstrate improved output diversity, harmonic coherence, adaptation speed and user agency. Our results demonstrate a simple yet effective method to mitigate reward hacking in RL post-training of generative sequence models. --- ### Training Emergent Joint Associations: A Reinforcement Learning Approach to Creative Thinking in Language Models Authors: Mukul Singh, Ananya Singha, Aishni Parab, Pronita Mehrotra, Sumit Gulwani Published: 2025-11-22 Categories: cs.AI arXiv: https://arxiv.org/abs/2511.17876v1 Associative thinking--the ability to connect seemingly unrelated ideas--is a foundational element of human creativity and problem-solving. This paper explores whether reinforcement learning (RL) guided by associative thinking principles can enhance a model's performance across diverse generative tasks, including story writing, code generation, and chart creation. We introduce a reinforcement learning framework that uses a prompt-based evaluation mechanism, incorporating established divergent thinking metrics from creativity research. A base language model is fine-tuned using this framework to reward outputs demonstrating higher novelty through higher degrees of conceptual connectivity. Interestingly, the experimental results suggest that RL-based associative thinking-trained models not only generate more original and coherent stories but also exhibit improved abstraction and flexibility in tasks such as programming and data visualization. Our findings provide initial evidence that modeling cognitive creativity principles through reinforcement learning can yield more adaptive and generative AI. --- ### The Horcrux: Mechanistically Interpretable Task Decomposition for Detecting and Mitigating Reward Hacking in Embodied AI Systems Authors: Subramanyam Sahoo, Jared Junkin Published: 2025-11-22 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.17869v1 Embodied AI agents exploit reward signal flaws through reward hacking, achieving high proxy scores while failing true objectives. We introduce Mechanistically Interpretable Task Decomposition (MITD), a hierarchical transformer architecture with Planner, Coordinator, and Executor modules that detects and mitigates reward hacking. MITD decomposes tasks into interpretable subtasks while generating diagnostic visualizations including Attention Waterfall Diagrams and Neural Pathway Flow Charts. Experiments on 1,000 HH-RLHF samples reveal that decomposition depths of 12 to 25 steps reduce reward hacking frequency by 34 percent across four failure modes. We present new paradigms showing that mechanistically grounded decomposition offers a more effective way to detect reward hacking than post-hoc behavioral monitoring. --- ### Generative Model Predictive Control in Manufacturing Processes: A Review Authors: Suk Ki Lee, Ronnie F. P. Stone, Max Gao, Wenlong Zhang, Zhenghui Sha, Hyunwoong Ko Published: 2025-11-22 Categories: eess.SY, cs.LG arXiv: https://arxiv.org/abs/2511.17865v1 Manufacturing processes are inherently dynamic and uncertain, with varying parameters and nonlinear behaviors, making robust control essential for maintaining quality and reliability. Traditional control methods often fail under these conditions due to their reactive nature. Model Predictive Control (MPC) has emerged as a more advanced framework, leveraging process models to predict future states and optimize control actions. However, MPC relies on simplified models that often fail to capture complex dynamics, and it struggles with accurate state estimation and handling the propagation of uncertainty in manufacturing environments. Machine learning (ML) has been introduced to enhance MPC by modeling nonlinear dynamics and learning latent representations that support predictive modeling, state estimation, and optimization. Yet existing ML-driven MPC approaches remain deterministic and correlation-focused, motivating the exploration of generative. Generative ML offers new opportunities by learning data distributions, capturing hidden patterns, and inherently managing uncertainty, thereby complementing MPC. This review highlights five representative methods and examines how each has been integrated into MPC components, including predictive modeling, state estimation, and optimization. By synthesizing these cases, we outline the common ways generative ML can systematically enhance MPC and provide a framework for understanding its potential in diverse manufacturing processes. We identify key research gaps, propose future directions, and use a representative case to illustrate how generative ML-driven MPC can extend broadly across manufacturing. Taken together, this review positions generative ML not as an incremental add-on but as a transformative approach to reshape predictive control for next-generation manufacturing systems. --- ### Equivalence of Context and Parameter Updates in Modern Transformer Blocks Authors: Adrian Goldwaser, Michael Munn, Javier Gonzalvo, Benoit Dherin Published: 2025-11-22 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.17864v3 Recent research has established that the impact of context in a vanilla transformer can be represented implicitly by forming a token-dependent, rank-1 patch to its MLP weights. This work extends that foundational theory to the diverse architectures of modern Large Language Models. We first demonstrate a precise, analytical solution for a Gemma-style transformer block, proving that the entire effect of a context can be perfectly mapped to rank-1 patches on its MLP weight matrices and a patch to the RMSNorm scale. We then generalize this result, providing a constructive proof and algorithm for multi-layer models. To unify these findings, we introduce a general framework centered on two core properties: input controllability and output controllability. We prove that a perfect implicit weight patch is possible for any MLP block where the inner function is input-controllable and the outer function is output-controllable. This provides a simpler and more powerful lens for understanding how transformer models transmute prompts into effective weights. This setup generalizes to a wide range of modern LLM architectures including gating, pre-/post-norm, mixture of experts and sequential/parallel transformer blocks. --- ### Cost-Sensitive Conformal Training with Provably Controllable Learning Bounds Authors: Xuesong Jia, Yuanjie Shi, Ziquan Liu, Yi Xu, Yan Yan Published: 2025-11-22 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2511.17861v1 Conformal prediction (CP) is a general framework to quantify the predictive uncertainty of machine learning models that uses a set prediction to include the true label with a valid probability. To align the uncertainty measured by CP, conformal training methods minimize the size of the prediction sets. A typical way is to use a surrogate indicator function, usually Sigmoid or Gaussian error function. However, these surrogate functions do not have a uniform error bound to the indicator function, leading to uncontrollable learning bounds. In this paper, we propose a simple cost-sensitive conformal training algorithm that does not rely on the indicator approximation mechanism. Specifically, we theoretically show that minimizing the expected size of prediction sets is upper bounded by the expected rank of true labels. To this end, we develop a rank weighting strategy that assigns the weight using the rank of true label on each data sample. Our analysis provably demonstrates the tightness between the proposed weighted objective and the expected size of conformal prediction sets. Extensive experiments verify the validity of our theoretical insights, and superior empirical performance over other conformal training in terms of predictive efficiency with 21.38% reduction for average prediction set size. --- ### QuickLAP: Quick Language-Action Preference Learning for Semi-Autonomous Agents Authors: Jordan Abi Nader, David Lee, Nathaniel Dennler, Andreea Bobu Published: 2025-11-22 Categories: cs.AI, cs.RO arXiv: https://arxiv.org/abs/2511.17855v5 Robots must learn from both what people do and what they say, but either modality alone is often incomplete: physical corrections are grounded but ambiguous in intent, while language expresses high-level goals but lacks physical grounding. We introduce QuickLAP: Quick Language-Action Preference learning, a Bayesian framework that fuses physical and language feedback to infer reward functions in real time. Our key insight is to treat language as a probabilistic observation over the user's latent preferences, clarifying which reward features matter and how physical corrections should be interpreted. QuickLAP uses Large Language Models (LLMs) to extract reward feature attention masks and preference shifts from free-form utterances, which it integrates with physical feedback in a closed-form update rule. This enables fast, real-time, and robust reward learning that handles ambiguous feedback. In a semi-autonomous driving simulator, QuickLAP reduces reward learning error by over 70% compared to physical-only and heuristic multimodal baselines. A 15-participant user study further validates our approach: participants found QuickLAP significantly more understandable and collaborative, and preferred its learned behavior over baselines. Code is available at https://github.com/MIT-CLEAR-Lab/QuickLAP. --- ### A superpersuasive autonomous policy debating system Authors: Allen Roush, Devin Gonier, John Hines, Judah Goldfeder, Philippe Martin Wyder, Sanjay Basu, Ravid Shwartz Ziv Published: 2025-11-22 Categories: cs.CL, cs.AI, cs.CY, cs.HC, cs.MA arXiv: https://arxiv.org/abs/2511.17854v1 The capacity for highly complex, evidence-based, and strategically adaptive persuasion remains a formidable great challenge for artificial intelligence. Previous work, like IBM Project Debater, focused on generating persuasive speeches in simplified and shortened debate formats intended for relatively lay audiences. We introduce DeepDebater, a novel autonomous system capable of participating in and winning a full, unmodified, two-team competitive policy debate. Our system employs a hierarchical architecture of specialized multi-agent workflows, where teams of LLM-powered agents collaborate and critique one another to perform discrete argumentative tasks. Each workflow utilizes iterative retrieval, synthesis, and self-correction using a massive corpus of policy debate evidence (OpenDebateEvidence) and produces complete speech transcripts, cross-examinations, and rebuttals. We introduce a live, interactive end-to-end presentation pipeline that renders debates with AI speech and animation: transcripts are surface-realized and synthesized to audio with OpenAI TTS, and then displayed as talking-head portrait videos with EchoMimic V1. Beyond fully autonomous matches (AI vs AI), DeepDebater supports hybrid human-AI operation: human debaters can intervene at any stage, and humans can optionally serve as opponents against AI in any speech, allowing AI-human and AI-AI rounds. In preliminary evaluations against human-authored cases, DeepDebater produces qualitatively superior argumentative components and consistently wins simulated rounds as adjudicated by an independent autonomous judge. Expert human debate coaches also prefer the arguments, evidence, and cases constructed by DeepDebater. We open source all code, generated speech transcripts, audio and talking head video here: https://github.com/Hellisotherpeople/DeepDebater/tree/main --- ### A Low-Code Methodology for Developing AI Kiosks: a Case Study with the DIZEST Platform Authors: SunMin Moon, Jangwon Gim, Chaerin Kim, Yeeun Kim, YoungJoo Kim, Kang Choi Published: 2025-11-22 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2511.17853v1 This paper presents a comprehensive study on enhancing kiosk systems through a low-code architecture, with a focus on AI-based implementations. Modern kiosk systems are confronted with significant challenges, including a lack of integration, structural rigidity, performance bottlenecks, and the absence of collaborative frameworks. To overcome these limitations, we propose a DIZEST-based approach methodology, a specialized low-code platform that enables intuitive workflow design and seamless AI integration. Through a comparative analysis with existing platforms, including Jupyter Notebook, ComfyUI, and Orange3, we demonstrate that DIZEST delivers superior performance across key evaluation criteria. Our photo kiosk case study further validates the effectiveness of this approach in improving interoperability, enhancing user experience, and increasing deployment flexibility. --- ### Transformers with RL or SFT Provably Learn Sparse Boolean Functions, But Differently Authors: Bochen Lyu, Yiyang Jia, Xiaohao Cai, Zhanxing Zhu Published: 2025-11-22 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2511.17852v3 Transformers can acquire Chain-of-Thought (CoT) capabilities to solve reasoning tasks via fine-tuning. Reinforcement learning (RL) and supervised fine-tuning (SFT) are two primary approaches to this end. In this work, we examine RL with verifiable process rewards and SFT for learning $k$-sparse Boolean functions with a one-layer transformer through intermediate reasoning steps akin to CoT. In particular, we consider Boolean functions that can be recursively decomposed into fixed 2-sparse Boolean functions. We first analyze the learning dynamics of RL fine-tuning with verifiable process rewards and SFT in a unified way, allowing us to identify sufficient conditions under which the transformer provably learns these functions. We then verify that the conditions hold for three examples, including $k$-PARITY, $k$-AND, and $k$-OR, thus demonstrating their learnability via both RL and SFT. Notably, we reveal that RL and SFT exhibit distinct learning behaviors depending on supervision: RL learns the whole CoT chain simultaneously, whereas SFT without teacher forcing learns the CoT step-by-step. Overall, our findings provide insights on the mechanisms underlying RL and SFT and how they differ in triggering the CoT capabilities of transformers, and suggest that the comparison between RL and SFT should consider the intermediate supervision. --- ### Efficient Dynamic and Momentum Aperture Optimization for Lattice Design Using Multipoint Bayesian Algorithm Execution Authors: Z. Zhang, I. Agapov, S. Gasiorowski, T. Hellert, W. Neiswanger, X. Huang, D. Ratner Published: 2025-11-22 Categories: physics.acc-ph, cs.LG arXiv: https://arxiv.org/abs/2511.17850v1 We demonstrate that multipoint Bayesian algorithm execution can overcome fundamental computational challenges in storage ring design optimization. Dynamic (DA) and momentum (MA) optimization is a multipoint, multiobjective design task for storage rings, ultimately informing the flux of x-ray sources and luminosity of colliders. Current state-of-art black-box optimization methods require extensive particle-tracking simulations for each trial configuration; the high computational cost restricts the extent of the search to $\sim 10^3$ configurations, and therefore limits the quality of the final design. We remove this bottleneck using multipointBAX, which selects, simulates, and models each trial configuration at the single particle level. We demonstrate our approach on a novel design for a fourth-generation light source, with neural-network powered multipointBAX achieving equivalent Pareto front results using more than two orders of magnitude fewer tracking computations compared to genetic algorithms. The significant reduction in cost positions multipointBAX as a promising alternative to black-box optimization, and we anticipate multipointBAX will be instrumental in the design of future light sources, colliders, and large-scale scientific facilities. --- ### Scaling Kinetic Monte-Carlo Simulations of Grain Growth with Combined Convolutional and Graph Neural Networks Authors: Zhihui Tian, Ethan Suwandi, Tomas Oppelstrup, Vasily V. Bulatov, Joel B. Harley, Fei Zhou Published: 2025-11-22 Categories: cs.LG, cond-mat.mtrl-sci arXiv: https://arxiv.org/abs/2511.17848v2 Graph neural networks (GNN) have emerged as a promising machine learning method for microstructure simulations such as grain growth. However, accurate modeling of realistic grain boundary networks requires large simulation cells, which GNN has difficulty scaling up to. To alleviate the computational costs and memory footprint of GNN, we propose a hybrid architecture combining a convolutional neural network (CNN) based bijective autoencoder to compress the spatial dimensions, and a GNN that evolves the microstructure in the latent space of reduced spatial sizes. Our results demonstrate that the new design significantly reduces computational costs with using fewer message passing layer (from 12 down to 3) compared with GNN alone. The reduction in computational cost becomes more pronounced as the spatial size increases, indicating strong computational scalability. For the largest mesh evaluated (160^3), our method reduces memory usage and runtime in inference by 117x and 115x, respectively, compared with GNN-only baseline. More importantly, it shows higher accuracy and stronger spatiotemporal capability than the GNN-only baseline, especially in long-term testing. Such combination of scalability and accuracy is essential for simulating realistic material microstructures over extended time scales. The improvements can be attributed to the bijective autoencoder's ability to compress information losslessly from spatial domain into a high dimensional feature space, thereby producing more expressive latent features for the GNN to learn from, while also contributing its own spatiotemporal modeling capability. The training was optimized to learn from the stochastic Potts Monte Carlo method. Our findings provide a highly scalable approach for simulating grain growth. --- ### Enriching Taxonomies Using Large Language Models Authors: Zeinab Ghamlouch, Mehwish Alam Published: 2025-11-21 Categories: cs.IR, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2602.22213v1 Taxonomies play a vital role in structuring and categorizing information across domains. However, many existing taxonomies suffer from limited coverage and outdated or ambiguous nodes, reducing their effectiveness in knowledge retrieval. To address this, we present Taxoria, a novel taxonomy enrichment pipeline that leverages Large Language Models (LLMs) to enhance a given taxonomy. Unlike approaches that extract internal LLM taxonomies, Taxoria uses an existing taxonomy as a seed and prompts an LLM to propose candidate nodes for enrichment. These candidates are then validated to mitigate hallucinations and ensure semantic relevance before integration. The final output includes an enriched taxonomy with provenance tracking and visualization of the final merged taxonomy for analysis. --- ### End-to-End Transformer Acceleration Through Processing-in-Memory Architectures Authors: Xiaoxuan Yang, Peilin Chen, Tergel Molom-Ochir, Yiran Chen Published: 2025-11-21 Categories: cs.AR, cs.LG arXiv: https://arxiv.org/abs/2601.14260v1 Transformers have become central to natural language processing and large language models, but their deployment at scale faces three major challenges. First, the attention mechanism requires massive matrix multiplications and frequent movement of intermediate results between memory and compute units, leading to high latency and energy costs. Second, in long-context inference, the key-value cache (KV cache) can grow unpredictably and even surpass the model's weight size, creating severe memory and bandwidth bottlenecks. Third, the quadratic complexity of attention with respect to sequence length amplifies both data movement and compute overhead, making large-scale inference inefficient. To address these issues, this work introduces processing-in-memory solutions that restructure attention and feed-forward computation to minimize off-chip data transfers, dynamically compress and prune the KV cache to manage memory growth, and reinterpret attention as an associative memory operation to reduce complexity and hardware footprint. Moreover, we evaluate our processing-in-memory design against state-of-the-art accelerators and general-purpose GPUs, demonstrating significant improvements in energy efficiency and latency. Together, these approaches address computation overhead, memory scalability, and attention complexity, further enabling efficient, end-to-end acceleration of Transformer models. --- ### A Cloud-Based Cross-Modal Transformer for Emotion Recognition and Adaptive Human-Computer Interaction Authors: Ziwen Zhong, Zhitao Shu, Yue Zhao Published: 2025-11-21 Categories: cs.CV, cs.AI, cs.HC, cs.LG, cs.SD, eess.AS arXiv: https://arxiv.org/abs/2601.14259v1 Emotion recognition is a fundamental component of next-generation human-computer interaction (HCI), enabling machines to perceive, understand, and respond to users' affective states. However, existing systems often rely on single-modality analysis such as facial expressions, speech tone, or textual sentiment, resulting in limited robustness and poor generalization in real-world environments. To address these challenges, this study proposes a Cloud-Based Cross-Modal Transformer (CMT) framework for multimodal emotion recognition and adaptive human-computer interaction. The proposed model integrates visual, auditory, and textual signals using pretrained encoders (Vision Transformer, Wav2Vec2, and BERT) and employs a cross-modal attention mechanism to capture complex interdependencies among heterogeneous features. By leveraging cloud computing infrastructure with distributed training on Kubernetes and TensorFlow Serving, the system enables scalable, low-latency emotion recognition for large-scale user interactions. Experiments conducted on benchmark datasets including IEMOCAP, MELD, and AffectNet demonstrate that the CMT achieves state-of-the-art performance, improving the F1-score by 3.0 percent and reducing cross-entropy loss by 12.9 percent compared to strong multimodal baselines. Additionally, cloud deployment evaluations show an average response latency of 128 ms, representing a 35 percent reduction compared with conventional transformer-based fusion systems. These results confirm that the proposed framework enables efficient, real-time emotion recognition and adaptive feedback in applications such as intelligent customer service, virtual tutoring systems, and affective computing interfaces, marking an important step toward cloud-native affective computing and emotionally intelligent interactive systems. --- ### Modular AI-Powered Interviewer with Dynamic Question Generation and Expertise Profiling Authors: Aisvarya Adeseye, Jouni Isoaho, Seppo Virtanen, Mohammad Tahir Published: 2025-11-21 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2601.11534v1 Automated interviewers and chatbots are common in research, recruitment, customer service, and education. Many existing systems use fixed question lists, strict rules, and limited personalization, leading to repeated conversations that cause low engagement. Therefore, these tools are not effective for complex qualitative research, which requires flexibility, context awareness, and ethical sensitivity. Consequently, there is a need for a more adaptive and context-aware interviewing system. To address this, an AI-powered interviewer that dynamically generates questions that are contextually appropriate and expertise aligned is presented in this study. The interviewer is built on a locally hosted large language model (LLM) that generates coherent dialogue while preserving data privacy. The interviewer profiles the participants' expertise in real time to generate knowledge-appropriate questions, well-articulated responses, and smooth transition messages similar to human-like interviews. To implement these functionalities, a modular prompt engineering pipeline was designed to ensure that the interview conversation remains scalable, adaptive, and semantically rich. To evaluate the AI-powered interviewer, it was tested with various participants, and it achieved high satisfaction (mean 4.45) and engagement (mean 4.33). The proposed interviewer is a scalable, privacy-conscious solution that advances AI-assisted qualitative data collection. --- ### Artificial Intelligence as a Training Tool in Clinical Psychology: A Comparison of Text-Based and Avatar Simulations Authors: V. El Sawah, A. Bhardwaj, A. Pryke-Hobbes, D. Gamaleldin, C. S. Ang, A. K. Martin Published: 2025-11-21 Categories: cs.HC, cs.AI, cs.CY arXiv: https://arxiv.org/abs/2601.11533v1 Clinical psychology students frequently report feeling underprepared for the interpersonal demands of therapeutic work, highlighting the need for accessible opportunities to practise core counselling skills before seeing real clients. Advances in artificial intelligence (AI) now enable simulated interaction partners that may support early skills development. This study examined postgraduate clinical psychology students' perceptions of two AI-based simulations: a text-based chatbot (ChatGPT) and a voice-based avatar (HeyGen). Twenty-four students completed two brief cognitive-behavioural role-plays (counterbalanced), one with each tool, and provided both quantitative ratings and qualitative feedback on perceived usefulness, skill application, responsiveness and engagement, and perceived skill improvement. Both AI tools were evaluated positively across dimensions. However, the avatar was rated significantly higher than the chatbot for perceived usefulness, skill application, and perceived skill improvement, and qualitative comments highlighted the added value of voice-based interaction for conveying social and emotional cues. These findings suggest that AI-driven simulation may supplement early-stage clinical skills training, with voice-based avatars offering additional benefits. Future work should test whether such simulated interactions translate to objective improvements in real therapeutic performance. --- ### QoS-Aware Dynamic CU Selection in O-RAN with Graph-Based Reinforcement Learning Authors: Sebastian Racedo, Brigitte Jaumard, Oscar Delgado, Meysam Masoudi Published: 2025-11-21 Categories: cs.NI, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2512.19696v1 Open Radio Access Network (O RAN) disaggregates conventional RAN into interoperable components, enabling flexible resource allocation, energy savings, and agile architectural design. In legacy deployments, the binding between logical functions and physical locations is static, which leads to inefficiencies under time varying traffic and resource conditions. We address this limitation by relaxing the fixed mapping and performing dynamic service function chain (SFC) provisioning with on the fly O CU selection. We formulate the problem as a Markov decision process and solve it using GRLDyP, i.e., a graph neural network (GNN) assisted deep reinforcement learning (DRL). The proposed agent jointly selects routes and the O-CU location (from candidate sites) for each incoming service flow to minimize network energy consumption while satisfying quality of service (QoS) constraints. The GNN encodes the instantaneous network topology and resource utilization (e.g., CPU and bandwidth), and the DRL policy learns to balance grade of service, latency, and energy. We perform the evaluation of GRLDyP on a data set with 24-hour traffic traces from the city of Montreal, showing that dynamic O CU selection and routing significantly reduce energy consumption compared to a static mapping baseline, without violating QoS. The results highlight DRL based SFC provisioning as a practical control primitive for energy-aware, resource-adaptive O-RAN deployments. --- ### MultiGA: Leveraging Multi-Source Seeding in Genetic Algorithms Authors: Isabelle Diana May-Xin Ng, Tharindu Cyril Weerasooriya, Haitao Zhu, Wei Wei Published: 2025-11-21 Categories: cs.NE, cs.AI arXiv: https://arxiv.org/abs/2512.04097v2 In this paper, we introduce, MultiGA, an optimization framework which applies genetic algorithm principles to address complex natural language tasks and reasoning problems by sampling from a diverse population of LLMs to initialize the population of candidate solutions. MultiGA generates a range of outputs from various parent LLMs and uses a neutral fitness function to evaluate them. Through an iterative recombination process, we mix and refine these generations until an optimal solution is achieved. Our results show that MultiGA produces high accuracy across multiple benchmarks, and these insights lay the foundation for future research looking closer at integrating multiple LLMs for unexplored tasks in which selecting only one pre-trained model is unclear or suboptimal. --- ### Physics-Informed Machine Learning for Steel Development: A Computational Framework and CCT Diagram Modelling Authors: Peter Hedström, Victor Lamelas Cubero, Jón Sigurdsson, Viktor Österberg, Satish Kolli, Joakim Odqvist, Ziyong Hou, Wangzhong Mu, Viswanadh Gowtham Arigela Published: 2025-11-21 Categories: cs.LG, cond-mat.mtrl-sci, physics.comp-ph arXiv: https://arxiv.org/abs/2512.03050v1 Machine learning (ML) has emerged as a powerful tool for accelerating the computational design and production of materials. In materials science, ML has primarily supported large-scale discovery of novel compounds using first-principles data and digital twin applications for optimizing manufacturing processes. However, applying general-purpose ML frameworks to complex industrial materials such as steel remains a challenge. A key obstacle is accurately capturing the intricate relationship between chemical composition, processing parameters, and the resulting microstructure and properties. To address this, we introduce a computational framework that combines physical insights with ML to develop a physics-informed continuous cooling transformation (CCT) model for steels. Our model, trained on a dataset of 4,100 diagrams, is validated against literature and experimental data. It demonstrates high computational efficiency, generating complete CCT diagrams with 100 cooling curves in under 5 seconds. It also shows strong generalizability across alloy steels, achieving phase classification F1 scores above 88% for all phases. For phase transition temperature regression, it attains mean absolute errors (MAE) below 20 °C across all phases except bainite, which shows a slightly higher MAE of 27 °C. This framework can be extended with additional generic and customized ML models to establish a universal digital twin platform for heat treatment. Integration with complementary simulation tools and targeted experiments will further support accelerated materials design workflows. --- ### EduMod-LLM: A Modular Approach for Designing Flexible and Transparent Educational Assistants Authors: Meenakshi Mittal, Rishi Khare, Mihran Miroyan, Chancharik Mitra, Narges Norouzi Published: 2025-11-21 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2511.21742v1 With the growing use of Large Language Model (LLM)-based Question-Answering (QA) systems in education, it is critical to evaluate their performance across individual pipeline components. In this work, we introduce {\model}, a modular function-calling LLM pipeline, and present a comprehensive evaluation along three key axes: function calling strategies, retrieval methods, and generative language models. Our framework enables fine-grained analysis by isolating and assessing each component. We benchmark function-calling performance across LLMs, compare our novel structure-aware retrieval method to vector-based and LLM-scoring baselines, and evaluate various LLMs for response synthesis. This modular approach reveals specific failure modes and performance patterns, supporting the development of interpretable and effective educational QA systems. Our findings demonstrate the value of modular function calling in improving system transparency and pedagogical alignment. Website and Supplementary Material: https://chancharikmitra.github.io/EduMod-LLM-website/ --- ### A Multiscale Geometric Method for Capturing Relational Topic Alignment Authors: Conrad D. Hougen, Karl T. Pazdernik, Alfred O. Hero Published: 2025-11-21 Categories: cs.CL, cs.LG, stat.ML arXiv: https://arxiv.org/abs/2511.21741v1 Interpretable topic modeling is essential for tracking how research interests evolve within co-author communities. In scientific corpora, where novelty is prized, identifying underrepresented niche topics is particularly important. However, contemporary models built from dense transformer embeddings tend to miss rare topics and therefore also fail to capture smooth temporal alignment. We propose a geometric method that integrates multimodal text and co-author network data, using Hellinger distances and Ward's linkage to construct a hierarchical topic dendrogram. This approach captures both local and global structure, supporting multiscale learning across semantic and temporal dimensions. Our method effectively identifies rare-topic structure and visualizes smooth topic drift over time. Experiments highlight the strength of interpretable bag-of-words models when paired with principled geometric alignment. --- ### A cross-species neural foundation model for end-to-end speech decoding Authors: Yizi Zhang, Linyang He, Chaofei Fan, Tingkai Liu, Han Yu, Trung Le, Jingyuan Li, Scott Linderman, Lea Duncker, Francis R Willett, Nima Mesgarani, Liam Paninski Published: 2025-11-21 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2511.21740v5 Speech brain-computer interfaces (BCIs) aim to restore communication for people with paralysis by translating neural activity into text. Most systems use cascaded frameworks that decode phonemes before assembling sentences with an n-gram language model (LM), preventing joint optimization of all stages simultaneously. Here, we introduce an end-to-end BraIn-to-Text (BIT) framework that translates neural activity into coherent sentences using a single differentiable neural network. Central to our approach is a cross-task, cross-species pretrained neural encoder, whose representations transfer to both attempted and imagined speech. In a cascaded setting with an n-gram LM, the pretrained encoder establishes a new state-of-the-art (SOTA) on the Brain-to-Text '24 and '25 benchmarks. Integrated end-to-end with audio large language models (LLMs) and trained with contrastive learning for cross-modal alignment, BIT reduces the word error rate (WER) of the prior end-to-end method from 24.69% to 10.22%. Notably, we find that small-scale audio LLMs markedly improve end-to-end decoding. Beyond record-setting performance, BIT aligns attempted and imagined speech embeddings to enable cross-task generalization. Altogether, our approach advances the integration of large, diverse neural datasets, paving the way for an end-to-end decoding framework that supports seamless, differentiable optimization. --- ### Science Is Falling Behind the Frontier: Foundation Model Adoption Across Half a Million Papers Authors: Ana Trišović, Alex Fogelson, Janakan Sivaloganathan, Neil Thompson Published: 2025-11-21 Categories: cs.DL, cs.AI arXiv: https://arxiv.org/abs/2511.21739v2 We present the first large-scale analysis of AI foundation model usage in science -- not just citations or keywords. We find that adoption has grown rapidly, at nearly-exponential rates, with the highest uptake in Linguistics, Computer Science, and Engineering. Vision models are the most used foundation models in science, although language models' share is growing. Open-weight models dominate. As AI builders increase the parameter counts of their models, scientists have followed suit but at a much slower rate: in 2015, the mean foundation model adopted in science was 5.4x larger than the mean model being built; by 2024 that relationship had reversed, with the mean model built 6.9x larger than the mean model adopted. We also present suggestive evidence that scientists' use of these smaller models may be limiting them from getting the full benefits of AI-enabled science, as papers that use larger models appear in higher-impact journals and accrue more citations. --- ### Polarity-Aware Probing for Quantifying Latent Alignment in Language Models Authors: Sabrina Sadiekh, Elena Ericheva, Chirag Agarwal Published: 2025-11-21 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2511.21737v1 Advances in unsupervised probes such as Contrast-Consistent Search (CCS), which reveal latent beliefs without relying on token outputs, raise the question of whether these methods can reliably assess model alignment. We investigate this by examining the sensitivity of CCS to harmful vs. safe statements and by introducing Polarity-Aware CCS (PA-CCS), a method for evaluating whether a model's internal representations remain consistent under polarity inversion. We propose two alignment-oriented metrics, Polar-Consistency and the Contradiction Index, to quantify the semantic robustness of a model's latent knowledge. To validate PA-CCS, we curate two main datasets and one control dataset containing matched harmful-safe sentence pairs constructed using different methodologies (concurrent and antagonistic statements). We apply PA-CCS to 16 language models. Our results show that PA-CCS identifies both architectural and layer-specific differences in the encoding of latent harmful knowledge. Notably, replacing the negation token with a meaningless marker degrades PA-CCS scores for models with well-aligned internal representations, while models lacking robust internal calibration do not exhibit this degradation. Our findings highlight the potential of unsupervised probing for alignment evaluation and emphasize the need to incorporate structural robustness checks into interpretability benchmarks. Code and datasets are available at: https://github.com/SadSabrina/polarity-probing. WARNING: This paper contains potentially sensitive, harmful, and offensive content. --- ### R2Q: Towards Robust 2-Bit Large Language Models via Residual Refinement Quantization Authors: Jiayi Chen, Jieqi Shi, Jing Huo, Chen Wu Published: 2025-11-21 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2511.21736v1 The rapid progress of Large Language Models (LLMs) has brought substantial computational and memory demands, spurring the adoption of low-bit quantization. While 8-bit and 4-bit formats have become prevalent, extending quantization to 2 bits remains challenging due to severe accuracy degradation. To address this, we propose Residual Refinement Quantization (R2Q)-a novel 2-bit quantization framework that decomposes the process into two sequential 1-bit sub-quantizations, forming an adaptive quantization lattice. Extensive evaluations on Llama, OPT, and Qwen across diverse benchmarks-covering question answering, commonsense reasoning, and language modeling-demonstrate that R2Q consistently outperforms existing 2-bit quantization methods in both fine-grained and coarse-grained settings. By refining quantization through a residual learning mechanism, R2Q enhances performance, improves training stability, and accelerates convergence under extreme compression. Furthermore, its modular design enables seamless integration with existing quantization-aware training (QAT) frameworks. --- ### Closing the Performance Gap Between AI and Radiologists in Chest X-Ray Reporting Authors: Harshita Sharma, Maxwell C. Reynolds, Valentina Salvatelli, Anne-Marie G. Sykes, Kelly K. Horst, Anton Schwaighofer, Maximilian Ilse, Olesya Melnichenko, Sam Bond-Taylor, Fernando Pérez-García, Vamshi K. Mugu, Alex Chan et al. Published: 2025-11-21 Categories: cs.CL, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2511.21735v1 AI-assisted report generation offers the opportunity to reduce radiologists' workload stemming from expanded screening guidelines, complex cases and workforce shortages, while maintaining diagnostic accuracy. In addition to describing pathological findings in chest X-ray reports, interpreting lines and tubes (L&T) is demanding and repetitive for radiologists, especially with high patient volumes. We introduce MAIRA-X, a clinically evaluated multimodal AI model for longitudinal chest X-ray (CXR) report generation, that encompasses both clinical findings and L&T reporting. Developed using a large-scale, multi-site, longitudinal dataset of 3.1 million studies (comprising 6 million images from 806k patients) from Mayo Clinic, MAIRA-X was evaluated on three holdout datasets and the public MIMIC-CXR dataset, where it significantly improved AI-generated reports over the state of the art on lexical quality, clinical correctness, and L&T-related elements. A novel L&T-specific metrics framework was developed to assess accuracy in reporting attributes such as type, longitudinal change and placement. A first-of-its-kind retrospective user evaluation study was conducted with nine radiologists of varying experience, who blindly reviewed 600 studies from distinct subjects. The user study found comparable rates of critical errors (3.0% for original vs. 4.6% for AI-generated reports) and a similar rate of acceptable sentences (97.8% for original vs. 97.4% for AI-generated reports), marking a significant improvement over prior user studies with larger gaps and higher error rates. Our results suggest that MAIRA-X can effectively assist radiologists, particularly in high-volume clinical settings. --- ### Asking LLMs to Verify First is Almost Free Lunch Authors: Shiguang Wu, Quanming Yao Published: 2025-11-21 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2511.21734v2 To enhance the reasoning capabilities of Large Language Models (LLMs) without high costs of training, nor extensive test-time sampling, we introduce Verification-First (VF), a strategy that prompts models to verify a provided candidate answer, even a trivial or random one, before generating a solution. This approach triggers a "reverse reasoning" process complementary to standard forward Chain-of-Thought (CoT), which restricts the logical search space of the answer by pruning the LLM's output distribution. We further generalize VF prompting to Iter-VF, a sequential test-time scaling (TTS) method that iteratively cycles the verification-generation process using the model's previous answer. Extensive experiments across various benchmarks and various LLMs confirm that VF prompting with random answer consistently outperforms standard CoT with minimal computational overhead, and Iter-VF outperforms existing TTS strategies. VF is also effective on SOTA thinking models. For example, by using the simple VF prompting, we obtain a new SOTA 94.9% accuracy on GPQA-Diamond with Gemini-3-Pro-Preview where VF reduces its errors by ~30% relatively. ---