# Research Papers — 2025-11 · bundle page 11 of 197 > Full-text markdown of papers #501–550 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/11 [← Previous bundle](https://aipod.dev/papers/archive/2025-11/page/10.md) [Next bundle →](https://aipod.dev/papers/archive/2025-11/page/12.md) ### Tree Matching Networks for Natural Language Inference: Parameter-Efficient Semantic Understanding via Dependency Parse Trees Authors: Jason Lunder Published: 2025-11-28 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2512.00204v2 In creating sentence embeddings for Natural Language Inference (NLI) tasks, using transformer-based models like BERT leads to high accuracy, but require hundreds of millions of parameters. These models take in sentences as a sequence of tokens, and learn to encode the meaning of the sequence into embeddings such that those embeddings can be used reliably for NLI tasks. Essentially, every word is considered against every other word in the sequence, and the transformer model is able to determine the relationships between them, entirely from scratch. However, a model that accepts explicit linguistic structures like dependency parse trees may be able to leverage prior encoded information about these relationships, without having to learn them from scratch, thus improving learning efficiency. To investigate this, we adapt Graph Matching Networks (GMN) to operate on dependency parse trees, creating Tree Matching Networks (TMN). We compare TMN to a BERT based model on the SNLI entailment task and on the SemEval similarity task. TMN is able to achieve significantly better results with a significantly reduced memory footprint and much less training time than the BERT based model on the SNLI task, while both models struggled to preform well on the SemEval. Explicit structural representations significantly outperform sequence-based models at comparable scales, but current aggregation methods limit scalability. We propose multi-headed attention aggregation to address this limitation. --- ### Beyond Expected Goals: A Probabilistic Framework for Shot Occurrences in Soccer Authors: Jonathan Pipping-Gamón, Tianshu Feng, R. Paul Sabin Published: 2025-11-28 Categories: stat.AP, cs.LG, eess.IV arXiv: https://arxiv.org/abs/2512.00203v2 Expected goals (xG) models estimate the probability that a shot results in a goal from its context (e.g., location, pressure), but they operate only on observed shots. We propose xG+, a possession-level framework that first estimates the probability that a shot occurs within the next second and its corresponding xG if it were to occur. We also introduce ways to aggregate this joint probability estimate over the course of a possession. By jointly modeling shot-taking behavior and shot quality, xG+ remedies the conditioning-on-shots limitation of standard xG. We show that this improves predictive accuracy at the team level and produces a more persistent player skill signal than standard xG models. --- ### Mammo-FM: Breast-specific foundational model for Integrated Mammographic Diagnosis, Prognosis, and Reporting Authors: Shantanu Ghosh, Vedant Parthesh Joshi, Rayan Syed, Param Budhraja, Aya Kassem, Katelyn C. Morrison, Alex Tang, Ho Cheung Aiden Wong, Abhishek Varshney, Payel Basak, Weicheng Dai, Judy Wawira Gichoya et al. Published: 2025-11-28 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.00198v3 Breast cancer is one of the leading causes of death among women worldwide. We introduce Mammo-FM, the first foundation model specifically for mammography, pretrained on the largest and most diverse dataset to date - 140,677 patients (821,326 mammograms) across four U.S. institutions. Mammo-FM provides a unified foundation for core clinical tasks in breast imaging, including cancer diagnosis, pathology localization, structured report generation, and cancer risk prognosis within a single framework. Its alignment between images and text enables both visual and textual interpretability, improving transparency and clinical auditability, which are essential for real-world adoption. We rigorously evaluate Mammo-FM across diagnosis, prognosis, and report-generation tasks in in- and out-of-distribution datasets. Despite operating on native-resolution mammograms and using only one-third of the parameters of state-of-the-art generalist FMs, Mammo-FM consistently outperforms them across multiple public and private benchmarks. These results highlight the efficiency and value of domain-specific foundation models designed around the full spectrum of tasks within a clinical domain and emphasize the importance of rigorous, domain-aligned evaluation. --- ### Emergent Riemannian geometry over learning discrete computations on continuous manifolds Authors: Julian Brandon, Angus Chadwick, Arthur Pellegrino Published: 2025-11-28 Categories: cs.LG, cs.NE, math.DG, q-bio.NC, stat.ML arXiv: https://arxiv.org/abs/2512.00196v1 Many tasks require mapping continuous input data (e.g. images) to discrete task outputs (e.g. class labels). Yet, how neural networks learn to perform such discrete computations on continuous data manifolds remains poorly understood. Here, we show that signatures of such computations emerge in the representational geometry of neural networks as they learn. By analysing the Riemannian pullback metric across layers of a neural network, we find that network computation can be decomposed into two functions: discretising continuous input features and performing logical operations on these discretised variables. Furthermore, we demonstrate how different learning regimes (rich vs. lazy) have contrasting metric and curvature structures, affecting the ability of the networks to generalise to unseen inputs. Overall, our work provides a geometric framework for understanding how neural networks learn to perform discrete computations on continuous manifolds. --- ### AutocleanEEG ICVision: Automated ICA Artifact Classification Using Vision-Language AI Authors: Zag ElSayed, Grace Westerkamp, Gavin Gammoh, Yanchen Liu, Peyton Siekierski, Craig Erickson, Ernest Pedapati Published: 2025-11-28 Categories: cs.CV, cs.LG, eess.IV, q-bio.QM arXiv: https://arxiv.org/abs/2512.00194v1 We introduce EEG Autoclean Vision Language AI (ICVision) a first-of-its-kind system that emulates expert-level EEG ICA component classification through AI-agent vision and natural language reasoning. Unlike conventional classifiers such as ICLabel, which rely on handcrafted features, ICVision directly interprets ICA dashboard visualizations topography, time series, power spectra, and ERP plots, using a multimodal large language model (GPT-4 Vision). This allows the AI to see and explain EEG components the way trained neurologists do, making it the first scientific implementation of AI-agent visual cognition in neurophysiology. ICVision classifies each component into one of six canonical categories (brain, eye, heart, muscle, channel noise, and other noise), returning both a confidence score and a human-like explanation. Evaluated on 3,168 ICA components from 124 EEG datasets, ICVision achieved k = 0.677 agreement with expert consensus, surpassing MNE ICLabel, while also preserving clinically relevant brain signals in ambiguous cases. Over 97% of its outputs were rated as interpretable and actionable by expert reviewers. As a core module of the open-source EEG Autoclean platform, ICVision signals a paradigm shift in scientific AI, where models do not just classify, but see, reason, and communicate. It opens the door to globally scalable, explainable, and reproducible EEG workflows, marking the emergence of AI agents capable of expert-level visual decision-making in brain science and beyond. --- ### A Rosetta Stone for AI Benchmarks Authors: Anson Ho, Jean-Stanislas Denain, David Atanasov, Samuel Albanie, Rohin Shah Published: 2025-11-28 Categories: cs.AI arXiv: https://arxiv.org/abs/2512.00193v1 Most AI benchmarks saturate within years or even months after they are introduced, making it hard to study long-run trends in AI capabilities. To address this challenge, we build a statistical framework that stitches benchmarks together, putting model capabilities and benchmark difficulties on a single numerical scale. This acts as a "Rosetta Stone", allowing us to compare models across a wide range of abilities and time, even if they are not evaluated on the same benchmarks. Moreover, this works without assuming how capabilities evolve across time or with training compute. We demonstrate three applications of this framework. First, we use it to measure the speed of AI progress over time, and to forecast future AI capabilities. Second, we estimate the rate of improvements in algorithmic efficiency, finding estimates that are higher, but broadly consistent with prior work. Finally, we find that our approach can be used to detect rapid accelerations in AI progress. --- ### Hybrid Context-Fusion Attention (CFA) U-Net and Clustering for Robust Seismic Horizon Interpretation Authors: Jose Luis Lima de Jesus Silva, Joao Pedro Gomes, Paulo Roberto de Melo Barros Junior, Vitor Hugo Serravalle Reis Rodrigues, Alexsandro Guerra Cerqueira Published: 2025-11-28 Categories: cs.LG, eess.IV, physics.geo-ph arXiv: https://arxiv.org/abs/2512.00191v1 Interpreting seismic horizons is a critical task for characterizing subsurface structures in hydrocarbon exploration. Recent advances in deep learning, particularly U-Net-based architectures, have significantly improved automated horizon tracking. However, challenges remain in accurately segmenting complex geological features and interpolating horizons from sparse annotations. To address these issues, a hybrid framework is presented that integrates advanced U-Net variants with spatial clustering to enhance horizon continuity and geometric fidelity. The core contribution is the Context Fusion Attention (CFA) U-Net, a novel architecture that fuses spatial and Sobel-derived geometric features within attention gates to improve both precision and surface completeness. The performance of five architectures, the U-Net (Standard and compressed), U-Net++, Attention U-Net, and CFA U-Net, was systematically evaluated across various data sparsity regimes (10-, 20-, and 40-line spacing). This approach outperformed existing baselines, achieving state-of-the-art results on the Mexilhao field (Santos Basin, Brazil) dataset with a validation IoU of 0.881 and MAE of 2.49ms, and excellent surface coverage of 97.6% on the F3 Block of the North Sea dataset under sparse conditions. The framework further refines merged horizon predictions (inline and cross-line) using Density-Based Spatial Clustering of Applications with Noise (DBSCAN) to produce geologically plausible surfaces. The results demonstrate the advantages of hybrid methodologies and attention-based architectures enhanced with geometric context, providing a robust and generalizable solution for seismic interpretation in structurally complex and data-scarce environments. --- ### Chunking Strategies for Multimodal AI Systems Authors: Shashanka B R, Mohith Charan R, Seema Banu F Published: 2025-11-28 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2512.00185v2 Chunking has emerged as a critical technique that enhances generative models by grounding their responses in efficiently segmented knowledge (1). While initially developed for unimodal (primarily textual) domains, recent advances in multimodal foundation models have extended chunking approaches to incorporate diverse data types, including images, audio, and video (2). A critical component underpinning the success of these systems is the chunking strategy how large, continuous streams of multimodal data are segmented into semantically meaningful units suitable for processing (3). Despite its importance, chunking remains an under-explored area, especially in the context of multimodal systems where modality-specific constraints, semantic preservation, and alignment across modalities introduce unique challenges. Our goal is to consolidating the landscape of multimodal chunking strategies, providing researchers and practitioners with a technical foundation and design space for developing more effective and efficient multimodal AI systems. This survey paves the way for innovations in robust chunking pipelines that scale with modality complexity, enhance processing accuracy, and improve generative coherence in real-world applications. This survey provides a comprehensive taxonomy and technical analysis of chunking strategies tailored for each modality: text, images, audio, video, and cross-modal data. We examine classical and modern approaches such as fixed-size token windowing, recursive text splitting, object-centric visual chunking, silence-based audio segmentation, and scene detection in videos. Each approach is analyzed in terms of its underlying methodology, supporting tools (e.g., LangChain, Detectron2, PySceneDetect), benefits, and challenges, particularly those related to granularity-context trade-offs and multimodal alignment. Furthermore, we explore emerging cross-modal chunking strategies that aim to preserve alignment and semantic consistency across disparate… --- ### Orion-Bix: Bi-Axial Attention for Tabular In-Context Learning Authors: Mohamed Bouadi, Pratinav Seth, Aditya Tanna, Vinay Kumar Sankarapu Published: 2025-11-28 Categories: cs.LG, cs.AI, stat.ML arXiv: https://arxiv.org/abs/2512.00181v2 Tabular data drive most real-world machine learning applications, yet building general-purpose models for them remains difficult. Mixed numeric and categorical fields, weak feature structure, and limited labeled data make scaling and generalization challenging. To this end, we introduce Orion-Bix, a tabular foundation model that combines biaxial attention with meta-learned in-context reasoning for few-shot tabular learning. Its encoder alternates standard, grouped, hierarchical, and relational attention, fusing their outputs through multi-CLS summarization to capture both local and global dependencies efficiently. A label-aware ICL head adapts on the fly and scales to large label spaces via hierarchical decision routing. Meta-trained on synthetically generated, structurally diverse tables with causal priors, Orion-Bix learns transferable inductive biases across heterogeneous data. Delivered as a scikit-learn compatible foundation model, it outperforms gradient-boosting baselines and remains competitive with state-of-the-art tabular foundation models on public benchmarks, showing that biaxial attention with episodic meta-training enables robust, few-shot-ready tabular learning. The model is publicly available at https://github.com/Lexsi-Labs/Orion-BiX . --- ### Efficient Edge-Compatible CNN for Speckle-Based Material Recognition in Laser Cutting Systems Authors: Mohamed Abdallah Salem, Nourhan Zein Diab Published: 2025-11-28 Categories: cs.CV, cs.AI, cs.LG, eess.IV arXiv: https://arxiv.org/abs/2512.00179v1 Accurate material recognition is critical for safe and effective laser cutting, as misidentification can lead to poor cut quality, machine damage, or the release of hazardous fumes. Laser speckle sensing has recently emerged as a low-cost and non-destructive modality for material classification; however, prior work has either relied on computationally expensive backbone networks or addressed only limited subsets of materials. In this study, A lightweight convolutional neural network (CNN) tailored for speckle patterns is proposed, designed to minimize parameters while maintaining high discriminative power. Using the complete SensiCut dataset of 59 material classes spanning woods, acrylics, composites, textiles, metals, and paper-based products, the proposed model achieves 95.05% test accuracy, with macro and weighted F1-scores of 0.951. The network contains only 341k trainable parameters (~1.3 MB) -- over 70X fewer than ResNet-50 -- and achieves an inference speed of 295 images per second, enabling deployment on Raspberry Pi and Jetson-class devices. Furthermore, when materials are regrouped into nine and five practical families, recall exceeds 98% and approaches 100%, directly supporting power and speed preset selection in laser cutters. These results demonstrate that compact, domain-specific CNNs can outperform large backbones for speckle-based material classification, advancing the feasibility of material-aware, edge-deployable laser cutting systems. --- ### Comparing Two Proxy Methods for Causal Identification Authors: Helen Guo, Elizabeth L. Ogburn, Ilya Shpitser Published: 2025-11-28 Categories: stat.ME, cs.LG, stat.ML arXiv: https://arxiv.org/abs/2512.00175v3 Identifying causal effects in the presence of unmeasured variables is a fundamental challenge in causal inference, for which proxy variable methods have emerged as a powerful solution. We contrast two major approaches in this framework: (1) bridge equation methods, which leverage solutions to integral equations to recover causal targets, and (2) array decomposition methods, which recover latent factors used to identify counterfactual quantities via eigendecomposition tasks. We compare the model restrictions underlying these two approaches and provide insight into implications of the underlying assumptions, clarifying the scope of applicability for each method. --- ### We Still Don't Understand High-Dimensional Bayesian Optimization Authors: Colin Doumont, Donney Fan, Natalie Maus, Jacob R. Gardner, Henry Moss, Geoff Pleiss Published: 2025-11-28 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2512.00170v2 Existing high-dimensional Bayesian optimization (BO) methods aim to overcome the curse of dimensionality by carefully encoding structural assumptions, from locality to sparsity to smoothness, into the optimization procedure. Surprisingly, we demonstrate that these approaches are outperformed by arguably the simplest method imaginable: Bayesian linear regression. After applying a geometric transformation to avoid boundary-seeking behavior, Gaussian processes with linear kernels match state-of-the-art performance on tasks with 60- to 6,000-dimensional search spaces. Linear models offer numerous advantages over their non-parametric counterparts: they afford closed-form sampling and their computation scales linearly with data, a fact we exploit on molecular optimization tasks with >20,000 observations. Coupled with empirical analyses, our results suggest the need to depart from past intuitions about BO methods in high-dimensions. --- ### Tuning Universality in Deep Neural Networks Authors: Arsham Ghavasieh Published: 2025-11-28 Categories: cond-mat.dis-nn, cond-mat.stat-mech, cs.AI, nlin.AO, physics.bio-ph arXiv: https://arxiv.org/abs/2512.00168v1 Deep neural networks (DNNs) exhibit crackling-like avalanches whose origin lacks a mechanistic explanation. Here, I derive a stochastic theory of deep information propagation (DIP) by incorporating Central Limit Theorem (CLT)-level fluctuations. Four effective couplings $(r, h, D_1, D_2)$ characterize the dynamics, yielding a Landau description of the static exponents and a Directed Percolation (DP) structure of activity cascades. Tuning the couplings selects between avalanche dynamics generated by a Brownian Motion (BM) in a logarithmic trap and an absorbed free BM, each corresponding to a distinct universality classes. Numerical simulations confirm the theory and demonstrate that activation function design controls the collective dynamics in random DNNs. --- ### Faster Verified Explanations for Neural Networks Authors: Alessandro De Palma, Greta Dolcetti, Caterina Urban Published: 2025-11-28 Categories: cs.LG, cs.PL arXiv: https://arxiv.org/abs/2512.00164v2 Verified explanations are a principled way to explain the decisions taken by neural networks, which are otherwise black-box in nature. However, these techniques face significant scalability challenges, as they require multiple calls to neural network verifiers, each of them with an exponential worst-case complexity. We present FaVeX, a novel algorithm to compute verified explanations. FaVeX accelerates the computation by dynamically combining batch and sequential processing of input features, and by reusing information from previous queries, both when proving invariances with respect to certain input features, and when searching for feature assignments altering the prediction. Furthermore, we present a novel and hierarchical definition of verified explanations, termed verifieroptimal robust explanations, that explicitly factors the incompleteness of network verifiers within the explanation. Our comprehensive experimental evaluation demonstrates the superior scalability of both FaVeX, and of verifier-optimal robust explanations, which together can produce meaningful formal explanation on networks with hundreds of thousands of non-linear activations. --- ### Measuring What LLMs Think They Do: SHAP Faithfulness and Deployability on Financial Tabular Classification Authors: Saeed AlMarri, Mathieu Ravaut, Kristof Juhasz, Gautier Marti, Hamdan Al Ahbabi, Ibrahim Elfadel Published: 2025-11-28 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2512.00163v1 Large Language Models (LLMs) have attracted significant attention for classification tasks, offering a flexible alternative to trusted classical machine learning models like LightGBM through zero-shot prompting. However, their reliability for structured tabular data remains unclear, particularly in high stakes applications like financial risk assessment. Our study systematically evaluates LLMs and generates their SHAP values on financial classification tasks. Our analysis shows a divergence between LLMs self-explanation of feature impact and their SHAP values, as well as notable differences between LLMs and LightGBM SHAP values. These findings highlight the limitations of LLMs as standalone classifiers for structured financial modeling, but also instill optimism that improved explainability mechanisms coupled with few-shot prompting will make LLMs usable in risk-sensitive domains. --- ### DeFi TrustBoost: Blockchain and AI for Trustworthy Decentralized Financial Decisions Authors: Swati Sachan, Dale S. Fickett Published: 2025-11-28 Categories: cs.CR, cs.AI, q-fin.CP, q-fin.GN arXiv: https://arxiv.org/abs/2512.00142v1 This research introduces the Decentralized Finance (DeFi) TrustBoost Framework, which combines blockchain technology and Explainable AI to address challenges faced by lenders underwriting small business loan applications from low-wealth households. The framework is designed with a strong emphasis on fulfilling four crucial requirements of blockchain and AI systems: confidentiality, compliance with data protection laws, resistance to adversarial attacks, and compliance with regulatory audits. It presents a technique for tamper-proof auditing of automated AI decisions and a strategy for on-chain (inside-blockchain) and off-chain data storage to facilitate collaboration within and across financial organizations. --- ### Ternary-Input Binary-Weight CNN Accelerator Design for Miniature Object Classification System with Query-Driven Spatial DVS Authors: Yuyang Li, Swasthik Muloor, Jack Laudati, Nickolas Dematteis, Yidam Park, Hana Kim, Nathan Chang, Inhee Lee Published: 2025-11-28 Categories: cs.AR, cs.CV, eess.IV arXiv: https://arxiv.org/abs/2512.00138v1 Miniature imaging systems are essential for space-constrained applications but are limited by memory and power constraints. While machine learning can reduce data size by extracting key features, its high energy demands often exceed the capacity of small batteries. This paper presents a CNN hardware accelerator optimized for object classification in miniature imaging systems. It processes data from a spatial Dynamic Vision Sensor (DVS), reconfigurable to a temporal DVS via pixel sharing, minimizing sensor area. By using ternary DVS outputs and a ternary-input, binary-weight neural network, the design reduces computation and memory needs. Fabricated in 28 nm CMOS, the accelerator cuts data size by 81% and MAC operations by 27%. It achieves 440 ms inference time at just 1.6 mW power consumption, improving the Figure-of-Merit (FoM) by 7.3x over prior CNN accelerators for miniature systems. --- ### Asm2SrcEval: Evaluating Large Language Models for Assembly-to-Source Code Translation Authors: Parisa Hamedi, Hamed Jelodar, Samita Bai, Mohammad Meymani, Roozbeh Razavi-Far, Ali A. Ghorbani Published: 2025-11-28 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2512.00134v1 Assembly-to-source code translation is a critical task in reverse engineering, cybersecurity, and software maintenance, yet systematic benchmarks for evaluating large language models on this problem remain scarce. In this work, we present the first comprehensive evaluation of five state-of-the-art large language models on assembly-to-source translation. We assess model performance using a diverse set of metrics capturing lexical similarity (BLEU, ROUGE, and METEOR), semantic alignment (BERTScore), fluency (Perplexity), and efficiency (time prediction). Our results reveal clear trade-offs: while certain models excel in text similarity metrics, others demonstrate lower perplexity or faster inference times. We further provide qualitative analyses of typical model successes and failure cases, highlighting challenges such as control flow recovery and identifier reconstruction. Taken together, our benchmark offers actionable insights into the strengths and limitations of current large language models for program translation, establishing a foundation for future research in combining accuracy with efficiency for real-world applications. --- ### Local and Global Context-and-Object-part-Aware Superpixel-based Data Augmentation for Deep Visual Recognition Authors: Fadi Dornaika, Danyang Sun Published: 2025-11-28 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.00130v1 Cutmix-based data augmentation, which uses a cut-and-paste strategy, has shown remarkable generalization capabilities in deep learning. However, existing methods primarily consider global semantics with image-level constraints, which excessively reduces attention to the discriminative local context of the class and leads to a performance improvement bottleneck. Moreover, existing methods for generating augmented samples usually involve cutting and pasting rectangular or square regions, resulting in a loss of object part information. To mitigate the problem of inconsistency between the augmented image and the generated mixed label, existing methods usually require double forward propagation or rely on an external pre-trained network for object centering, which is inefficient. To overcome the above limitations, we propose LGCOAMix, an efficient context-aware and object-part-aware superpixel-based grid blending method for data augmentation. To the best of our knowledge, this is the first time that a label mixing strategy using a superpixel attention approach has been proposed for cutmix-based data augmentation. It is the first instance of learning local features from discriminative superpixel-wise regions and cross-image superpixel contrasts. Extensive experiments on various benchmark datasets show that LGCOAMix outperforms state-of-the-art cutmix-based data augmentation methods on classification tasks, {and weakly supervised object location on CUB200-2011.} We have demonstrated the effectiveness of LGCOAMix not only for CNN networks, but also for Transformer networks. Source codes are available at https://github.com/DanielaPlusPlus/LGCOAMix. --- ### Analysis of Invasive Breast Cancer in Mammograms Using YOLO, Explainability, and Domain Adaptation Authors: Jayan Adhikari, Prativa Joshi, Sushish Baral Published: 2025-11-28 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2512.00129v2 Deep learning models for breast cancer detection from mammographic images have significant reliability problems when presented with Out-of-Domain (OOD) inputs such as other imaging modalities (CT, MRI, X-ray) or equipment variations, leading to unreliable detection and misdiagnosis. The current research mitigates the fundamental OOD issue through a comprehensive approach integrating ResNet50-based OOD filtering with YOLO architectures (YOLOv8, YOLOv11, YOLOv12) for accurate detection of breast cancer. Our strategy establishes an in-domain gallery via cosine similarity to rigidly reject non-mammographic inputs prior to processing, ensuring that only domain-associated images supply the detection pipeline. The OOD detection component achieves 99.77\% general accuracy with immaculate 100\% accuracy on OOD test sets, effectively eliminating irrelevant imaging modalities. ResNet50 was selected as the optimum backbone after 12 CNN architecture searches. The joint framework unites OOD robustness with high detection performance (mAP@0.5: 0.947) and enhanced interpretability through Grad-CAM visualizations. Experimental validation establishes that OOD filtering significantly improves system reliability by preventing false alarms on out-of-distribution inputs while maintaining higher detection accuracy on mammographic data. The present study offers a fundamental foundation for the deployment of reliable AI-based breast cancer detection systems in diverse clinical environments with inherent data heterogeneity. --- ### Generating Verifiable Chain of Thoughts from Exection-Traces Authors: Shailja Thakur, Vaibhav Saxena, Rohan Kulkarni, Shivdeep Singh, Parameswaran Selvam, Hima Patel, Hiroshi Kanayama Published: 2025-11-28 Categories: cs.SE, cs.AI, cs.PL arXiv: https://arxiv.org/abs/2512.00127v3 Getting language models to reason correctly about code requires training on data where each reasoning step can be checked. Current synthetic Chain-of-Thought (CoT) training data often consists of plausible-sounding explanations generated by teacher models, and not verifiable accounts of actual program behavior. Models trained on such data learn logically flawed reasoning patterns despite syntactic correctness. To address this, we build a pipeline that generates execution-trace-verified CoT rationales by instrumenting code to capture traces, narrating them into natural language, and cross-checking each narration against the original trace. We systematically create 54,000 verified, bi-directional rationales that teach models to reason both forward (input$\rightarrow$output) and backward (output$\rightarrow$input). Models fine-tuned on our verified data achieve substantial improvements, with a peak gain of +26.6 on LiveCodeBench-Exec, +22.2 on CruxEval, and +19.5 on HumanEval across our fine-tuned models, demonstrating that verification quality directly determines both reasoning and code generation capabilities. Complete synthesis pipeline is avilable as open-source: https://github.com/IBM/verified-code-cot/ --- ### RadDiff: Retrieval-Augmented Denoising Diffusion for Protein Inverse Folding Authors: Jin Han, Tianfan Fu, Wu-Jun Li Published: 2025-11-28 Categories: q-bio.QM, cs.AI arXiv: https://arxiv.org/abs/2512.00126v2 Protein inverse folding, the design of an amino acid sequence based on a target protein structure, is a fundamental problem of computational protein engineering. Existing methods either generate sequences without leveraging external knowledge or relying on protein language models~(PLMs). The former omits the knowledge stored in natural protein data, while the latter is parameter-inefficient and inflexible to adapt to ever-growing protein data. To overcome the above drawbacks, in this paper we propose a novel method, called $\underline{\text{r}}$etrieval-$\underline{\text{a}}$ugmented $\underline{\text{d}}$enoising $\underline{\text{diff}}$usion~($\mbox{RadDiff}$), for protein inverse folding. In RadDiff, a novel retrieval-augmentation mechanism is designed to capture the up-to-date protein knowledge. We further design a knowledge-aware diffusion model that integrates this protein knowledge into the diffusion process via a lightweight module. Experimental results on the CATH, TS50, and PDB2022 datasets show that $\mbox{RadDiff}$ consistently outperforms existing methods, improving sequence recovery rate by up to 19\%. Experimental results also demonstrate that RadDiff generates highly foldable sequences and scales effectively with database size. --- ### Hybrid Synthetic Data Generation with Domain Randomization Enables Zero-Shot Vision-Based Part Inspection Under Extreme Class Imbalance Authors: Ruo-Syuan Mei, Sixian Jia, Guangze Li, Soo Yeon Lee, Brian Musser, William Keller, Sreten Zakula, Jorge Arinez, Chenhui Shao Published: 2025-11-28 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2512.00125v1 Machine learning, particularly deep learning, is transforming industrial quality inspection. Yet, training robust machine learning models typically requires large volumes of high-quality labeled data, which are expensive, time-consuming, and labor-intensive to obtain in manufacturing. Moreover, defective samples are intrinsically rare, leading to severe class imbalance that degrades model performance. These data constraints hinder the widespread adoption of machine learning-based quality inspection methods in real production environments. Synthetic data generation (SDG) offers a promising solution by enabling the creation of large, balanced, and fully annotated datasets in an efficient, cost-effective, and scalable manner. This paper presents a hybrid SDG framework that integrates simulation-based rendering, domain randomization, and real background compositing to enable zero-shot learning for computer vision-based industrial part inspection without manual annotation. The SDG pipeline generates 12,960 labeled images in one hour by varying part geometry, lighting, and surface properties, and then compositing synthetic parts onto real image backgrounds. A two-stage architecture utilizing a YOLOv8n backbone for object detection and MobileNetV3-small for quality classification is trained exclusively on synthetic data and evaluated on 300 real industrial parts. The proposed approach achieves an mAP@0.5 of 0.995 for detection, 96% classification accuracy, and 90.1% balanced accuracy. Comparative evaluation against few-shot real-data baseline approaches demonstrates significant improvement. The proposed SDG-based approach achieves 90-91% balanced accuracy under severe class imbalance, while the baselines reach only 50% accuracy. These results demonstrate that the proposed method enables annotation-free, scalable, and robust quality inspection for real-world manufacturing applications. --- ### Video-R2: Reinforcing Consistent and Grounded Reasoning in Multimodal Language Models Authors: Muhammad Maaz, Hanoona Rasheed, Fahad Shahbaz Khan, Salman Khan Published: 2025-11-28 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.23478v2 Reasoning over dynamic visual content remains a central challenge for multimodal large language models. Recent thinking models generate explicit reasoning traces for interpretability; however, their reasoning often appears convincing while being logically inconsistent or weakly grounded in visual evidence. We identify and formalize these issues through two diagnostic metrics: Think Answer Consistency (TAC), which measures the alignment between reasoning and answers, and Video Attention Score (VAS), which captures the extent to which reasoning depends on visual versus textual cues. Analysis across 11 video reasoning benchmarks shows that current models rely heavily on linguistic priors rather than visual content. To address this, we propose a reinforcement learning approach that enhances both temporal precision and reasoning consistency. Our approach combines timestamp aware supervised fine tuning with Group Relative Policy Optimization (GRPO) guided by a novel Temporal Alignment Reward (TAR). This dual step post training stage encourages temporally aligned and causally coherent video reasoning. The resulting model, Video R2, achieves consistently higher TAC, VAS, and accuracy across multiple benchmarks, demonstrating that improvements in temporal alignment and reasoning coherence lead to more accurate and trustworthy video understanding. Code: https://github.com/mbzuai-oryx/Video-R2 --- ### Video-CoM: Interactive Video Reasoning via Chain of Manipulations Authors: Hanoona Rasheed, Mohammed Zumri, Muhammad Maaz, Ming-Hsuan Yang, Fahad Shahbaz Khan, Salman Khan Published: 2025-11-28 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.23477v1 Recent multimodal large language models (MLLMs) have advanced video understanding, yet most still "think about videos" ie once a video is encoded, reasoning unfolds entirely in text, treating visual input as a static context. This passive paradigm creates a semantic bottleneck: models cannot rewatch, refocus, or verify evidence, leading to shallow visual reasoning on tasks requiring fine grained spatio temporal understanding. In this work, we introduce Interactive Video Reasoning, a new paradigm that transforms video into an active cognitive workspace, enabling models to "think with videos". Our model, Video CoM, reasons through a Chain of Manipulations (CoM), performing iterative visual actions to gather and refine evidence. To support this behavior, we construct Video CoM Instruct, an 18K instruction tuning dataset curated for multi step manipulation reasoning. Beyond supervised learning, we further optimize the manipulation policy via reinforcement learning with reasoning aware Group Relative Policy Optimization (GRPO). Unlike prior work that relies solely on sparse answer rewards, our method introduces step level reasoning rewards, guiding the model toward grounded and consistent reasoning. Video CoM achieves strong results across nine video reasoning benchmarks, improving average performance by 3.6 percent over recent state of the art models, while training on only 25K SFT and 3K GRPO video samples, significantly fewer than comparable large scale models. Ablation studies demonstrate that reasoning aware rewards improve both accuracy and interpretability. Code: https://github.com/mbzuai-oryx/Video-CoM --- ### Thinking by Doing: Building Efficient World Model Reasoning in LLMs via Multi-turn Interaction Authors: Bao Shu, Yan Cai, Jianjian Sun, Chunrui Han, En Yu, Liang Zhao, Jingcheng Hu, Yinmin Zhang, Haoran Lv, Yuang Peng, Zheng Ge, Xiangyu Zhang et al. Published: 2025-11-28 Categories: cs.AI arXiv: https://arxiv.org/abs/2511.23476v1 Developing robust world model reasoning is crucial for large language model (LLM) agents to plan and interact in complex environments. While multi-turn interaction offers a superior understanding of environmental dynamics via authentic feedback, current approaches often impose a rigid reasoning process, which constrains the model's active learning, ultimately hindering efficient world model reasoning. To address these issues, we explore world-model internalization through efficient interaction and active reasoning (WMAct), which liberates the model from structured reasoning, allowing the model to shape thinking directly through its doing, and achieves effective and efficient world model reasoning with two key mechanisms: (1) a reward rescaling mechanism adjusting outcome reward based on action efficacy to incentivize redundancy reduction and purposeful interaction; (2) an interaction frequency annealing strategy to progressively reduce the maximum allowed interaction turns, which compels the model to condense its learning and internalize environmental dynamics rather than over-relying on environmental cues. Our experiments on Sokoban, Maze, and Taxi show that WMAct yields effective world model reasoning capable of resolving tasks in a single turn that previously required multiple interactions and fosters strong transferability to complex environments, improving performance on a suite of reasoning benchmarks. --- ### AnyTalker: Scaling Multi-Person Talking Video Generation with Interactivity Refinement Authors: Zhizhou Zhong, Yicheng Ji, Zhe Kong, Yiying Liu, Jiarui Wang, Jiasun Feng, Lupeng Liu, Xiangyi Wang, Yanjia Li, Yuqing She, Ying Qin, Huan Li et al. Published: 2025-11-28 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.23475v1 Recently, multi-person video generation has started to gain prominence. While a few preliminary works have explored audio-driven multi-person talking video generation, they often face challenges due to the high costs of diverse multi-person data collection and the difficulty of driving multiple identities with coherent interactivity. To address these challenges, we propose AnyTalker, a multi-person generation framework that features an extensible multi-stream processing architecture. Specifically, we extend Diffusion Transformer's attention block with a novel identity-aware attention mechanism that iteratively processes identity-audio pairs, allowing arbitrary scaling of drivable identities. Besides, training multi-person generative models demands massive multi-person data. Our proposed training pipeline depends solely on single-person videos to learn multi-person speaking patterns and refines interactivity with only a few real multi-person clips. Furthermore, we contribute a targeted metric and dataset designed to evaluate the naturalness and interactivity of the generated multi-person videos. Extensive experiments demonstrate that AnyTalker achieves remarkable lip synchronization, visual quality, and natural interactivity, striking a favorable balance between data costs and identity scalability. --- ### ThetaEvolve: Test-time Learning on Open Problems Authors: Yiping Wang, Shao-Rong Su, Zhiyuan Zeng, Eva Xu, Liliang Ren, Xinyu Yang, Zeyi Huang, Xuehai He, Luyao Ma, Baolin Peng, Hao Cheng, Pengcheng He et al. Published: 2025-11-28 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2511.23473v1 Recent advances in large language models (LLMs) have enabled breakthroughs in mathematical discovery, exemplified by AlphaEvolve, a closed-source system that evolves programs to improve bounds on open problems. However, it relies on ensembles of frontier LLMs to achieve new bounds and is a pure inference system that models cannot internalize the evolving strategies. We introduce ThetaEvolve, an open-source framework that simplifies and extends AlphaEvolve to efficiently scale both in-context learning and Reinforcement Learning (RL) at test time, allowing models to continually learn from their experiences in improving open optimization problems. ThetaEvolve features a single LLM, a large program database for enhanced exploration, batch sampling for higher throughput, lazy penalties to discourage stagnant outputs, and optional reward shaping for stable training signals, etc. ThetaEvolve is the first evolving framework that enable a small open-source model, like DeepSeek-R1-0528-Qwen3-8B, to achieve new best-known bounds on open problems (circle packing and first auto-correlation inequality) mentioned in AlphaEvolve. Besides, across two models and four open tasks, we find that ThetaEvolve with RL at test-time consistently outperforms inference-only baselines, and the model indeed learns evolving capabilities, as the RL-trained checkpoints demonstrate faster progress and better final performance on both trained target task and other unseen tasks. We release our code publicly: https://github.com/ypwang61/ThetaEvolve --- ### Visual Generation Tuning Authors: Jiahao Guo, Sinan Du, Jingfeng Yao, Wenyu Liu, Bo Li, Haoxiang Cao, Kun Gai, Chun Yuan, Kai Wu, Xinggang Wang Published: 2025-11-28 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.23469v1 Large Vision Language Models (VLMs) effectively bridge the modality gap through extensive pretraining, acquiring sophisticated visual representations aligned with language. However, it remains underexplored whether these representations, optimized for multimodal understanding tasks, harbor an inherent potential for visual generation. In this paper, we propose VGT, Visual Generation Tuning, a novel paradigm designed to stimulate the underlying capabilities of visual generation within any vision language models. By performing efficient visual generation tuning on well-pretrained VLMs, we significantly mitigate the alignment costs and accelerate the convergence of autoregressive modeling in the continuous space (20x speedup). Specifically, we dismiss the entangled pixel-level VAEs designed for diffusion transformers and formulate VGT-AE through aligning the semantic encoders from pretrained VLMs with the latent representations of pixel decoders. In image reconstruction tasks, we achieve 26.67 PSNR and 0.50 rFID at a 28x compression ratio, outperforming specialized VAEs; in visual generation tasks, we achieve state-of-the-art outcomes among autoregressive models, 0.77 on GenEval and 78.73 on DPG-Bench. Furthermore, our proposed VGT showcases significant scaling promise and is versatile for endowing any VLMs trained for multimodal understanding with the capabilities of visual generation, which paves the new avenue to explore next-generation unified multimodal foundation models. Models and codes are available at https://github.com/hustvl/VGT. --- ### SmallWorlds: Assessing Dynamics Understanding of World Models in Isolated Environments Authors: Xinyi Li, Zaishuo Xia, Weyl Lu, Chenjie Hao, Yubei Chen Published: 2025-11-28 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.23465v1 Current world models lack a unified and controlled setting for systematic evaluation, making it difficult to assess whether they truly capture the underlying rules that govern environment dynamics. In this work, we address this open challenge by introducing the SmallWorld Benchmark, a testbed designed to assess world model capability under isolated and precisely controlled dynamics without relying on handcrafted reward signals. Using this benchmark, we conduct comprehensive experiments in the fully observable state space on representative architectures including Recurrent State Space Model, Transformer, Diffusion model, and Neural ODE, examining their behavior across six distinct domains. The experimental results reveal how effectively these models capture environment structure and how their predictions deteriorate over extended rollouts, highlighting both the strengths and limitations of current modeling paradigms and offering insights into future improvement directions in representation learning and dynamics modeling. --- ### The Price of Progress: Price Performance and the Future of AI Authors: Hans Gundlach, Jayson Lynch, Matthias Mertens, Neil Thompson Published: 2025-11-28 Categories: cs.LG, cs.AI, cs.CY arXiv: https://arxiv.org/abs/2511.23455v2 Language models have seen enormous progress on advanced benchmarks in recent years, but much of this progress has only been possible by using more costly models. Benchmarks may therefore present a warped picture of progress in practical capabilities *per dollar*. To remedy this, we use data from Artificial Analysis and Epoch AI to form the largest dataset of current and historical prices to run benchmarks to date. We find that the price for a given level of benchmark performance has decreased remarkably fast, around $5\times$ to $10\times$ per year, for frontier models on knowledge, reasoning, math, and software engineering benchmarks. These reductions in the cost of AI inference are due to economic forces, hardware efficiency improvements, and algorithmic efficiency improvements. Isolating out open models to control for competition effects and dividing by hardware price declines, we estimate that algorithmic efficiency progress is around $3\times$ per year. However, at the same time, the price of running frontier models is rising between $3\times$ to $18\times$ per year due to bigger models and larger reasoning demands. Finally, we recommend that evaluators both publicize and take into account the price of benchmarking as an essential part of measuring the real-world impact of AI. --- ### Object-Centric Data Synthesis for Category-level Object Detection Authors: Vikhyat Agarwal, Jiayi Cora Guo, Declan Hoban, Sissi Zhang, Nicholas Moran, Peter Cho, Srilakshmi Pattabiraman, Shantanu Joshi Published: 2025-11-28 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.23450v1 Deep learning approaches to object detection have achieved reliable detection of specific object classes in images. However, extending a model's detection capability to new object classes requires large amounts of annotated training data, which is costly and time-consuming to acquire, especially for long-tailed classes with insufficient representation in existing datasets. Here, we introduce the object-centric data setting, when limited data is available in the form of object-centric data (multi-view images or 3D models), and systematically evaluate the performance of four different data synthesis methods to finetune object detection models on novel object categories in this setting. The approaches are based on simple image processing techniques, 3D rendering, and image diffusion models, and use object-centric data to synthesize realistic, cluttered images with varying contextual coherence and complexity. We assess how these methods enable models to achieve category-level generalization in real-world data, and demonstrate significant performance boosts within this data-constrained experimental setting. --- ### Physics-Informed Neural Networks for Thermophysical Property Retrieval Authors: Ali Waseem, Malcolm Mielle Published: 2025-11-28 Categories: cs.LG, cs.AI, cs.CE, cs.CV arXiv: https://arxiv.org/abs/2511.23449v1 Inverse heat problems refer to the estimation of material thermophysical properties given observed or known heat diffusion behaviour. Inverse heat problems have wide-ranging uses, but a critical application lies in quantifying how building facade renovation reduces thermal transmittance, a key determinant of building energy efficiency. However, solving inverse heat problems with non-invasive data collected in situ is error-prone due to environmental variability or deviations from theoretically assumed conditions. Hence, current methods for measuring thermal conductivity are either invasive, require lengthy observation periods, or are sensitive to environmental and experimental conditions. Here, we present a PINN-based iterative framework to estimate the thermal conductivity k of a wall from a set of thermographs; our framework alternates between estimating the forward heat problem with a PINN for a fixed k, and optimizing k by comparing the thermographs and surface temperatures predicted by the PINN, repeating until the estimated k's convergence. Using both environmental data captured by a weather station and data generated from Finite-Volume-Method software simulations, we accurately predict k across different environmental conditions and data collection sampling times, given the temperature profile of the wall at dawn is close to steady state. Although violating the steady-state assumption impacts the accuracy of k's estimation, we show that our proposed framework still only exhibits a maximum MAE of 4.0851. Our work demonstrates the potential of PINN-based methods for reliable estimation of material properties in situ and under realistic conditions, without lengthy measurement campaigns. Given the lack of research on using machine learning, and more specifically on PINNs, for solving in-situ inverse problems, we expect our work to be a starting point for more research on the topic. --- ### Provable Benefits of Sinusoidal Activation for Modular Addition Authors: Tianlong Huang, Zhiyuan Li Published: 2025-11-28 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2511.23443v1 This paper studies the role of activation functions in learning modular addition with two-layer neural networks. We first establish a sharp expressivity gap: sine MLPs admit width-$2$ exact realizations for any fixed length $m$ and, with bias, width-$2$ exact realizations uniformly over all lengths. In contrast, the width of ReLU networks must scale linearly with $m$ to interpolate, and they cannot simultaneously fit two lengths with different residues modulo $p$. We then provide a novel Natarajan-dimension generalization bound for sine networks, yielding nearly optimal sample complexity $\widetilde{\mathcal{O}}(p)$ for ERM over constant-width sine networks. We also derive width-independent, margin-based generalization for sine networks in the overparametrized regime and validate it. Empirically, sine networks generalize consistently better than ReLU networks across regimes and exhibit strong length extrapolation. --- ### ASTRO: Adaptive Stitching via Dynamics-Guided Trajectory Rollouts Authors: Hang Yu, Di Zhang, Qiwei Du, Yanping Zhao, Hai Zhang, Guang Chen, Eduardo E. Veas, Junqiao Zhao Published: 2025-11-28 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2511.23442v2 Offline reinforcement learning (RL) enables agents to learn optimal policies from pre-collected datasets. However, datasets containing suboptimal and fragmented trajectories present challenges for reward propagation, resulting in inaccurate value estimation and degraded policy performance. While trajectory stitching via generative models offers a promising solution, existing augmentation methods frequently produce trajectories that are either confined to the support of the behavior policy or violate the underlying dynamics, thereby limiting their effectiveness for policy improvement. We propose ASTRO, a data augmentation framework that generates distributionally novel and dynamics-consistent trajectories for offline RL. ASTRO first learns a temporal-distance representation to identify distinct and reachable stitch targets. We then employ a dynamics-guided stitch planner that adaptively generates connecting action sequences via Rollout Deviation Feedback, defined as the gap between target state sequence and the actual arrived state sequence by executing predicted actions, to improve trajectory stitching's feasibility and reachability. This approach facilitates effective augmentation through stitching and ultimately enhances policy learning. ASTRO outperforms prior offline RL augmentation methods across various algorithms, achieving notable performance gain on the challenging OGBench suite and demonstrating consistent improvements on standard offline RL benchmarks such as D4RL. --- ### Accelerated Execution of Bayesian Neural Networks using a Single Probabilistic Forward Pass and Code Generation Authors: Bernhard Klein, Falk Selker, Hendrik Borras, Sophie Steger, Franz Pernkopf, Holger Fröning Published: 2025-11-28 Categories: cs.LG, cs.AR, cs.DC, stat.ML arXiv: https://arxiv.org/abs/2511.23440v1 Machine learning models perform well across domains such as diagnostics, weather forecasting, NLP, and autonomous driving, but their limited uncertainty handling restricts use in safety-critical settings. Traditional neural networks often fail to detect out-of-domain (OOD) data and may output confident yet incorrect predictions. Bayesian neural networks (BNNs) address this by providing probabilistic estimates, but incur high computational cost because predictions require sampling weight distributions and multiple forward passes. The Probabilistic Forward Pass (PFP) offers a highly efficient approximation to Stochastic Variational Inference (SVI) by assuming Gaussian-distributed weights and activations, enabling fully analytic uncertainty propagation and replacing sampling with a single deterministic forward pass. We present an end-to-end pipeline for training, compiling, optimizing, and deploying PFP-based BNNs on embedded ARM CPUs. Using the TVM deep learning compiler, we implement a dedicated library of Gaussian-propagating operators for multilayer perceptrons and convolutional neural networks, combined with manual and automated tuning strategies. Ablation studies show that PFP consistently outperforms SVI in computational efficiency, achieving speedups of up to 4200x for small mini-batches. PFP-BNNs match SVI-BNNs on Dirty-MNIST in accuracy, uncertainty estimation, and OOD detection while greatly reducing compute cost. These results highlight the potential of combining Bayesian approximations with code generation to enable efficient BNN deployment on resource-constrained systems. --- ### Towards Continuous Intelligence Growth: Self-Training, Continual Learning, and Dual-Scale Memory in SuperIntelliAgent Authors: Jianzhe Lin, Zeyu Pan, Yun Zhu, Ruiqi Song, Jining Yang Published: 2025-11-28 Categories: cs.AI arXiv: https://arxiv.org/abs/2511.23436v1 We introduce SuperIntelliAgent, an agentic learning framework that couples a trainable small diffusion model (the learner) with a frozen large language model (the verifier) to enable continual intelligence growth through self-supervised interaction. Unlike conventional supervised fine-tuning, SuperIntelliAgent learns autonomously without annotation: the learner generates candidate outputs, the verifier evaluates them through step-by-step reasoning, and their interaction produces chosen/rejected pairs for Direct Preference Optimization (DPO). This converts each input into a pseudo-training signal for continual improvement. The framework integrates dual-scale memory: short-term in-context memory that preserves reasoning traces across refinement cycles, and long-term memory that consolidates acquired knowledge through lightweight on-the-fly fine-tuning. A replay buffer retains samples that show verifiable progress and replays them as auxiliary supervision, reinforcing recent learning while forming adaptive curricula. SuperIntelliAgent is infrastructure-agnostic and can be plugged into existing agentic frameworks while turning ordinary inference loops into a lifelong optimization process. We posit that pairing a trainable learner with a reasoning-capable verifier forms a minimal reliable unit of growing intelligence, as paired feedback and partial-history replay yield richer learning curricula and stronger preference alignment. With a small number of automatically generated DPO pairs, the learner improves across all benchmarks, indicating that this mechanism provides a promising direction for continual intelligence accumulation and real-world deployment. --- ### Hunyuan-GameCraft-2: Instruction-following Interactive Game World Model Authors: Junshu Tang, Jiacheng Liu, Jiaqi Li, Longhuang Wu, Haoyu Yang, Penghao Zhao, Siruis Gong, Xiang Yuan, Shuai Shao, Linfeng Zhang, Qinglin Lu Published: 2025-11-28 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.23429v2 Recent advances in generative world models have enabled remarkable progress in creating open-ended game environments, evolving from static scene synthesis toward dynamic, interactive simulation. However, current approaches remain limited by rigid action schemas and high annotation costs, restricting their ability to model diverse in-game interactions and player-driven dynamics. To address these challenges, we introduce Hunyuan-GameCraft-2, a new paradigm of instruction-driven interaction for generative game world modeling. Instead of relying on fixed keyboard inputs, our model allows users to control game video contents through natural language prompts, keyboard, or mouse signals, enabling flexible and semantically rich interaction within generated worlds. We formally defined the concept of interactive video data and developed an automated process to transform large-scale, unstructured text-video pairs into causally aligned interactive datasets. Built upon a 14B image-to-video Mixture-of-Experts(MoE) foundation model, our model incorporates a text-driven interaction injection mechanism for fine-grained control over camera motion, character behavior, and environment dynamics. We introduce an interaction-focused benchmark, InterBench, to evaluate interaction performance comprehensively. Extensive experiments demonstrate that our model generates temporally coherent and causally grounded interactive game videos that faithfully respond to diverse and free-form user instructions such as "open the door", "draw a torch", or "trigger an explosion". --- ### DisMo: Disentangled Motion Representations for Open-World Motion Transfer Authors: Thomas Ressler-Antal, Frank Fundel, Malek Ben Alaya, Stefan Andreas Baumann, Felix Krause, Ming Gui, Björn Ommer Published: 2025-11-28 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.23428v1 Recent advances in text-to-video (T2V) and image-to-video (I2V) models, have enabled the creation of visually compelling and dynamic videos from simple textual descriptions or initial frames. However, these models often fail to provide an explicit representation of motion separate from content, limiting their applicability for content creators. To address this gap, we propose DisMo, a novel paradigm for learning abstract motion representations directly from raw video data via an image-space reconstruction objective. Our representation is generic and independent of static information such as appearance, object identity, or pose. This enables open-world motion transfer, allowing motion to be transferred across semantically unrelated entities without requiring object correspondences, even between vastly different categories. Unlike prior methods, which trade off motion fidelity and prompt adherence, are overfitting to source structure or drifting from the described action, our approach disentangles motion semantics from appearance, enabling accurate transfer and faithful conditioning. Furthermore, our motion representation can be combined with any existing video generator via lightweight adapters, allowing us to effortlessly benefit from future advancements in video models. We demonstrate the effectiveness of our method through a diverse set of motion transfer tasks. Finally, we show that the learned representations are well-suited for downstream motion understanding tasks, consistently outperforming state-of-the-art video representation models such as V-JEPA in zero-shot action classification on benchmarks including Something-Something v2 and Jester. Project page: https://compvis.github.io/DisMo --- ### Evaluating LLMs for One-Shot Patching of Real and Artificial Vulnerabilities Authors: Aayush Garg, Zanis Ali Khan, Renzo Degiovanni, Qiang Tang Published: 2025-11-28 Categories: cs.CR, cs.AI, cs.SE arXiv: https://arxiv.org/abs/2511.23408v1 Automated vulnerability patching is crucial for software security, and recent advancements in Large Language Models (LLMs) present promising capabilities for automating this task. However, existing research has primarily assessed LLMs using publicly disclosed vulnerabilities, leaving their effectiveness on related artificial vulnerabilities largely unexplored. In this study, we empirically evaluate the patching effectiveness and complementarity of several prominent LLMs, such as OpenAI's GPT variants, LLaMA, DeepSeek, and Mistral models, using both real and artificial vulnerabilities. Our evaluation employs Proof-of-Vulnerability (PoV) test execution to concretely assess whether LLM-generated source code successfully patches vulnerabilities. Our results reveal that LLMs patch real vulnerabilities more effectively compared to artificial ones. Additionally, our analysis reveals significant variability across LLMs in terms of overlapping (multiple LLMs patching the same vulnerabilities) and complementarity (vulnerabilities patched exclusively by a single LLM), emphasizing the importance of selecting appropriate LLMs for effective vulnerability patching. --- ### MANTA: Physics-Informed Generalized Underwater Object Tracking Authors: Suhas Srinath, Hemang Jamadagni, Aditya Chadrasekar, Prathosh AP Published: 2025-11-28 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.23405v1 Underwater object tracking is challenging due to wavelength dependent attenuation and scattering, which severely distort appearance across depths and water conditions. Existing trackers trained on terrestrial data fail to generalize to these physics-driven degradations. We present MANTA, a physics-informed framework integrating representation learning with tracking design for underwater scenarios. We propose a dual-positive contrastive learning strategy coupling temporal consistency with Beer-Lambert augmentations to yield features robust to both temporal and underwater distortions. We further introduce a multi-stage pipeline augmenting motion-based tracking with a physics-informed secondary association algorithm that integrates geometric consistency and appearance similarity for re-identification under occlusion and drift. To complement standard IoU metrics, we propose Center-Scale Consistency (CSC) and Geometric Alignment Score (GAS) to assess geometric fidelity. Experiments on four underwater benchmarks (WebUOT-1M, UOT32, UTB180, UWCOT220) show that MANTA achieves state-of-the-art performance, improving Success AUC by up to 6 percent, while ensuring stable long-term generalized underwater tracking and efficient runtime. --- ### LFM2 Technical Report Authors: Alexander Amini, Anna Banaszak, Harold Benoit, Arthur Böök, Tarek Dakhran, Song Duong, Alfred Eng, Fernando Fernandes, Marc Härkönen, Anne Harrington, Ramin Hasani, Saniya Karwa et al. Published: 2025-11-28 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2511.23404v1 We present LFM2, a family of Liquid Foundation Models designed for efficient on-device deployment and strong task capabilities. Using hardware-in-the-loop architecture search under edge latency and memory constraints, we obtain a compact hybrid backbone that combines gated short convolutions with a small number of grouped query attention blocks, delivering up to 2x faster prefill and decode on CPUs compared to similarly sized models. The LFM2 family covers 350M-8.3B parameters, including dense models (350M, 700M, 1.2B, 2.6B) and a mixture-of-experts variant (8.3B total, 1.5B active), all with 32K context length. LFM2's training pipeline includes a tempered, decoupled Top-K knowledge distillation objective that avoids support mismatch; curriculum learning with difficulty-ordered data; and a three-stage post-training recipe of supervised fine-tuning, length-normalized preference optimization, and model merging. Pre-trained on 10-12T tokens, LFM2 models achieve strong results across diverse benchmarks; for example, LFM2-2.6B reaches 79.56% on IFEval and 82.41% on GSM8K. We further build multimodal and retrieval variants: LFM2-VL for vision-language tasks, LFM2-Audio for speech, and LFM2-ColBERT for retrieval. LFM2-VL supports tunable accuracy-latency tradeoffs via token-efficient visual processing, while LFM2-Audio separates audio input and output pathways to enable real-time speech-to-speech interaction competitive with models 3x larger. LFM2-ColBERT provides a low-latency encoder for queries and documents, enabling high-performance retrieval across multiple languages. All models are released with open weights and deployment packages for ExecuTorch, llama.cpp, and vLLM, making LFM2 a practical base for edge applications that need fast, memory-efficient inference and strong task capabilities. --- ### Quantized-Tinyllava: a new multimodal foundation model enables efficient split learning Authors: Jiajun Guo, Xin Luo, Jiayin Zheng, Yiqun Wang, Kai-Wei Chang, Wei Wang, Jie Liu Published: 2025-11-28 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2511.23402v2 Multimodal foundation models are increasingly trained on sensitive data across domains such as finance, biomedicine, and personal identifiers. However, this distributed setup raises serious privacy concerns due to the need for cross-partition data sharing. Split learning addresses these concerns by enabling collaborative model training without raw data exchange between partitions, yet it introduces a significant challenge: transmitting high-dimensional intermediate feature representations between partitions leads to substantial communication costs. To address this challenge, we propose Quantized-TinyLLaVA, a multimodal foundation model with an integrated communication-efficient split learning framework. Our approach adopts a compression module that quantizes intermediate feature into discrete representations before transmission, substantially reducing communication overhead. Besides, we derive a principled quantization strategy grounded in entropy coding theory to determine the optimal number of discrete representation levels. We deploy our framework in a two-partition setting, with one partition operating as the client and the other as the server, to realistically simulate distributed training. Under this setup, Quantized-TinyLLaVA achieves an approximate \textbf{87.5\%} reduction in communication overhead with 2-bit quantization, while maintaining performance of the original 16-bit model across five benchmark datasets. Furthermore, our compressed representations exhibit enhanced resilience against feature inversion attacks, validating the privacy of transmission. The code is available at https://github.com/anonymous-1742/Quantized-TinyLLaVA. --- ### MegaChat: A Synthetic Persian Q&A Dataset for High-Quality Sales Chatbot Evaluation Authors: Mahdi Rahmani, AmirHossein Saffari, Reyhane Rahmani Published: 2025-11-28 Categories: cs.CL, cs.AI, cs.MA arXiv: https://arxiv.org/abs/2511.23397v1 Small and medium-sized enterprises (SMEs) in Iran increasingly leverage Telegram for sales, where real-time engagement is essential for conversion. However, developing AI-driven chatbots for this purpose requires large, high-quality question-and-answer (Q&A) datasets, which are typically expensive and resource-intensive to produce, especially for low-resource languages like Persian. In this paper, we introduce MegaChat, the first fully synthetic Persian Q&A dataset designed to evaluate intelligent sales chatbots in Telegram-based e-commerce. We propose a novel, automated multi-agent architecture that generates persona-aware Q&A pairs by collecting data from active Telegram shopping channels. The system employs specialized agents for question generation, validation, and refinement, ensuring the production of realistic and diverse conversational data. To evaluate answer generation, we compare three classic retrieval-augmented generation (RAG) models with our advanced agentic system, which features multi-query retrieval, reranking, and persona-aligned response synthesis. Using GPT-5.1 for evaluation across six quality dimensions, our results show that the agentic architecture outperformed traditional RAG models in 4 out of 5 diverse channels, demonstrating its ability to generate scalable, high-quality datasets without relying on expensive human annotation or complex fine-tuning. MegaChat provides SMEs with an efficient, cost-effective solution for building intelligent customer engagement systems in specialized commercial domains, enabling advancements in multilingual conversational AI for low-resource languages. Download: https://github.com/MegaChat-Tech/MegaChat-DataSet --- ### Ambiguity Awareness Optimization: Towards Semantic Disambiguation for Direct Preference Optimization Authors: Jian Li, Shenglin Yin, Yujia Zhang, Alan Zhao, Xi Chen, Xiaohui Zhou, Pengfei Xu Published: 2025-11-28 Categories: cs.CL arXiv: https://arxiv.org/abs/2511.23391v1 Direct Preference Optimization (DPO) is a widely used reinforcement learning from human feedback (RLHF) method across various domains. Recent research has increasingly focused on the role of token importance in improving DPO effectiveness. It is observed that identical or semantically similar content (defined as ambiguous content) frequently appears within the preference pairs. We hypothesize that the presence of ambiguous content during DPO training may introduce ambiguity, thereby limiting further improvements in alignment. Through mathematical analysis and proof-of-concept experiments, we reveal that ambiguous content may potentially introduce ambiguities, thereby degrading performance. To address this issue, we introduce Ambiguity Awareness Optimization (AAO), a simple yet effective approach that automatically re-weights ambiguous content to reduce ambiguities by calculating semantic similarity from preference pairs. Through extensive experiments, we demonstrate that AAO consistently and significantly surpasses state-of-the-art approaches in performance, without markedly increasing response length, across multiple model scales and widely adopted benchmark datasets, including AlpacaEval 2, MT-Bench, and Arena-Hard. Specifically, AAO outperforms DPO by up to 8.9 points on AlpacaEval 2 and achieves an improvement of by up to 15.0 points on Arena-Hard. --- ### Learning-Augmented Online Bipartite Matching in the Random Arrival Order Model Authors: Kunanon Burathep, Thomas Erlebach, William K. Moses Published: 2025-11-28 Categories: cs.LG, cs.DS arXiv: https://arxiv.org/abs/2511.23388v1 We study the online unweighted bipartite matching problem in the random arrival order model, with $n$ offline and $n$ online vertices, in the learning-augmented setting: The algorithm is provided with untrusted predictions of the types (neighborhoods) of the online vertices. We build upon the work of Choo et al. (ICML 2024, pp. 8762-8781) who proposed an approach that uses a prefix of the arrival sequence as a sample to determine whether the predictions are close to the true arrival sequence and then either follows the predictions or uses a known baseline algorithm that ignores the predictions and is $β$-competitive. Their analysis is limited to the case that the optimal matching has size $n$, i.e., every online vertex can be matched. We generalize their approach and analysis by removing any assumptions on the size of the optimal matching while only requiring that the size of the predicted matching is at least $αn$ for any constant $0 < α\le 1$. Our learning-augmented algorithm achieves $(1-o(1))$-consistency and $(β-o(1))$-robustness. Additionally, we show that the competitive ratio degrades smoothly between consistency and robustness with increasing prediction error. --- ### Hierarchical AI-Meteorologist: LLM-Agent System for Multi-Scale and Explainable Weather Forecast Reporting Authors: Daniil Sukhorukov, Andrei Zakharov, Nikita Glazkov, Katsiaryna Yanchanka, Vladimir Kirilin, Maxim Dubovitsky, Roman Sultimov, Yuri Maksimov, Ilya Makarov Published: 2025-11-28 Categories: cs.AI arXiv: https://arxiv.org/abs/2511.23387v1 We present the Hierarchical AI-Meteorologist, an LLM-agent system that generates explainable weather reports using a hierarchical forecast reasoning and weather keyword generation. Unlike standard approaches that treat forecasts as flat time series, our framework performs multi-scale reasoning across hourly, 6-hour, and daily aggregations to capture both short-term dynamics and long-term trends. Its core reasoning agent converts structured meteorological inputs into coherent narratives while simultaneously extracting a few keywords effectively summarizing the dominant meteorological events. These keywords serve as semantic anchors for validating consistency, temporal coherence and factual alignment of the generated reports. Using OpenWeather and Meteostat data, we demonstrate that hierarchical context and keyword-based validation substantially improve interpretability and robustness of LLM-generated weather narratives, offering a reproducible framework for semantic evaluation of automated meteorological reporting and advancing agent-based scientific reasoning. --- ### VQRAE: Representation Quantization Autoencoders for Multimodal Understanding, Generation and Reconstruction Authors: Sinan Du, Jiahao Guo, Bo Li, Shuhao Cui, Zhengzhuo Xu, Yifu Luo, Yongxian Wei, Kun Gai, Xinggang Wang, Kai Wu, Chun Yuan Published: 2025-11-28 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.23386v1 Unifying multimodal understanding, generation and reconstruction representation in a single tokenizer remains a key challenge in building unified models. Previous research predominantly attempts to address this in a dual encoder paradigm, e.g., utilizing the separate encoders for understanding and generation respectively or balancing semantic representations and low-level features with contrastive loss. In this paper, we propose VQRAE, a Vector Quantization version of Representation AutoEncoders, which pioneers the first exploration in unified representation to produce Continuous semantic features for image understanding and Discrete tokens for visual generation within a unified tokenizer. Specifically, we build upon pretrained vision foundation models with a symmetric ViT decoder and adopt a two-stage training strategy: first, it freezes the encoder and learns a high-dimensional semantic VQ codebook with pixel reconstruction objective; then jointly optimizes the encoder with self-distillation constraints. This design enables negligible semantic information for maintaining the ability of multimodal understanding, discrete tokens that are compatible for generation and fine-grained reconstruction. Besides, we identify the intriguing property in quantizing semantic encoders that rely on high-dimensional codebook in contrast to the previous common practice of low-dimensional codebook in image reconstruction. The semantic VQ codebook can achieve a 100% utilization ratio at a dimension of 1536. VQRAE presents competitive performance on several benchmarks of visual understanding, generation and reconstruction with promising scaling property in the autoregressive paradigm for its discrete merits. --- ### DEAL-300K: Diffusion-based Editing Area Localization with a 300K-Scale Dataset and Frequency-Prompted Baseline Authors: Rui Zhang, Hongxia Wang, Hangqing Liu, Yang Zhou, Qiang Zeng Published: 2025-11-28 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.23377v1 Diffusion-based image editing has made semantic level image manipulation easy for general users, but it also enables realistic local forgeries that are hard to localize. Existing benchmarks mainly focus on the binary detection of generated images or the localization of manually edited regions and do not reflect the properties of diffusion-based edits, which often blend smoothly into the original content. We present Diffusion-Based Image Editing Area Localization Dataset (DEAL-300K), a large scale dataset for diffusion-based image manipulation localization (DIML) with more than 300,000 annotated images. We build DEAL-300K by using a multi-modal large language model to generate editing instructions, a mask-free diffusion editor to produce manipulated images, and an active-learning change detection pipeline to obtain pixel-level annotations. On top of this dataset, we propose a localization framework that uses a frozen Visual Foundation Model (VFM) together with Multi Frequency Prompt Tuning (MFPT) to capture both semantic and frequency-domain cues of edited regions. Trained on DEAL-300K, our method reaches a pixel-level F1 score of 82.56% on our test split and 80.97% on the external CoCoGlide benchmark, providing strong baselines and a practical foundation for future DIML research.The dataset can be accessed via https://github.com/ymhzyj/DEAL-300K. --- ### Is Passive Expertise-Based Personalization Enough? A Case Study in AI-Assisted Test-Taking Authors: Li Siyan, Jason Zhang, Akash Maharaj, Yuanming Shi, Yunyao Li Published: 2025-11-28 Categories: cs.HC, cs.CL arXiv: https://arxiv.org/abs/2511.23376v1 Novice and expert users have different systematic preferences in task-oriented dialogues. However, whether catering to these preferences actually improves user experience and task performance remains understudied. To investigate the effects of expertise-based personalization, we first built a version of an enterprise AI assistant with passive personalization. We then conducted a user study where participants completed timed exams, aided by the two versions of the AI assistant. Preliminary results indicate that passive personalization helps reduce task load and improve assistant perception, but reveal task-specific limitations that can be addressed through providing more user agency. These findings underscore the importance of combining active and passive personalization to optimize user experience and effectiveness in enterprise task-oriented environments. ---