# Research Papers — 2025-11 · bundle page 68 of 197 > Full-text markdown of papers #3351–3400 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/68 [← Previous bundle](https://aipod.dev/papers/archive/2025-11/page/67.md) [Next bundle →](https://aipod.dev/papers/archive/2025-11/page/69.md) ### Jump-diffusion models of parametric volume-price distributions Authors: Anup Budhathoki, Leonardo Rydin Gorjão, Pedro G. Lind, Shailendra Bhandari Published: 2025-11-20 Categories: cs.NE, nlin.CD arXiv: https://arxiv.org/abs/2511.16838v2 We present a data-driven framework to model the stochastic evolution of volume-price distribution from the New York Stock Exchange (NYSE) equities. The empirical distributions are sampled every 10 minutes over 976 trading days, and fitted to different models, namely Gamma, Inverse Gamma, Weibull, and Log-Normal distributions. Each of these models is parameterized by a shape parameter, $phi$, and a scale parameter, $θ$, which are detrended from their daily average behavior. The time series of the detrended parameters is analyzed using adaptive binning and regression-based extraction of the Kramers-Moyal (KM) coefficients, up to their sixth order, enabling to classification of its intrinsic dynamics. We show that (i) $φ$ is well described as a pure diffusion with a linear mean regression for the Gamma, Inverse Gamma, and Weibull models, while $θ$ shows dominant jump-diffusion dynamics, with an elevated fourth- and sixth-order moment contributions; (ii) the log-normal model shows however the opposite: $θ$ is predominantly diffusive, with $φ$ showing weak jump signatures; (iii) global moment inversion yields jump rates and amplitudes that account for a large share of total variance for $θ$, confirming that rare discontinuities dominate volatility. --- ### Cognitive BASIC: An In-Model Interpreted Reasoning Language for LLMs Authors: Oliver Kramer Published: 2025-11-20 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2511.16837v1 Cognitive BASIC is a minimal, BASIC-style prompting language and in-model interpreter that structures large language model (LLM) reasoning into explicit, stepwise execution traces. Inspired by the simplicity of retro BASIC, we repurpose numbered lines and simple commands as an interpretable cognitive control layer. Modern LLMs can reliably simulate such short programs, enabling transparent multi-step reasoning inside the model. A natural-language interpreter file specifies command semantics, memory updates, and logging behavior. Our mental-model interpreter extracts declarative and procedural knowledge, detects contradictions, and produces resolutions when necessary. A comparison across three LLMs on a benchmark of knowledge extraction, conflict detection, and reasoning tasks shows that all models can execute Cognitive BASIC programs, with overall strong but not uniform performance. --- ### The Shifting Landscape of Vaccine Discourse: Insights From a Decade of Pre- to Post-COVID-19 Vaccine Posts on Social Media Authors: Nikesh Gyawali, Doina Caragea, Cornelia Caragea, Saif M. Mohammad Published: 2025-11-20 Categories: cs.SI, cs.CL arXiv: https://arxiv.org/abs/2511.16832v1 In this work, we study English-language vaccine discourse in social media posts, specifically posts on X (formerly Twitter), in seven years before the COVID-19 outbreak (2013 to 2019) and three years after the outbreak was first reported (2020 to 2022). Drawing on theories from social cognition and the stereotype content model in Social Psychology, we analyze how English speakers talk about vaccines on social media to understand the evolving narrative around vaccines in social media posts. To do that, we first introduce a novel dataset comprising 18.7 million curated posts on vaccine discourse from 2013 to 2022. This extensive collection-filtered down from an initial 129 million posts through rigorous preprocessing-captures both pre-COVID and COVID-19 periods, offering valuable insights into the evolution of English-speaking X users' perceptions related to vaccines. Our analysis shows that the COVID-19 pandemic led to complex shifts in X users' sentiment and discourse around vaccines. We observe that negative emotion word usage decreased during the pandemic, with notable rises in usage of surprise, and trust related emotion words. Furthermore, vaccine-related language tended to use more warmth-focused words associated with trustworthiness, along with positive, competence-focused words during the early days of the pandemic, with a marked rise in negative word usage towards the end of the pandemic, possibly reflecting a growing vaccine hesitancy and skepticism. --- ### PEPPER: Perception-Guided Perturbation for Robust Backdoor Defense in Text-to-Image Diffusion Models Authors: Oscar Chew, Po-Yi Lu, Jayden Lin, Kuan-Hao Huang, Hsuan-Tien Lin Published: 2025-11-20 Categories: cs.CL arXiv: https://arxiv.org/abs/2511.16830v4 Recent studies show that text-to-image (T2I) diffusion models are vulnerable to backdoor attacks, where a trigger in the input prompt can steer generation toward harmful or unintended content. Beyond the trigger token itself, backdoor effects can spread to neighboring tokens in the text embedding space. To address this, we introduce PEPPER (PErcePtion-Guided PERturbation), a backdoor defense that rewrites the caption into a semantically distant yet visually similar caption while adding unobtrusive elements. With this strategy, PEPPER disrupts the trigger embedded in the input prompt, escapes the attacked neighborhood, and thereby achieves enhanced robustness without training or access to model weights. Experiments show that PEPPER is particularly effective against text encoder-based attacks, substantially reducing attack success while preserving generation quality. PEPPER can also be paired with any existing defenses yielding consistently stronger and generalizable robustness than any standalone method. --- ### ManifoldFormer: Geometric Deep Learning for Neural Dynamics on Riemannian Manifolds Authors: Yihang Fu, Lifang He, Qingyu Chen Published: 2025-11-20 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2511.16828v1 Existing EEG foundation models mainly treat neural signals as generic time series in Euclidean space, ignoring the intrinsic geometric structure of neural dynamics that constrains brain activity to low-dimensional manifolds. This fundamental mismatch between model assumptions and neural geometry limits representation quality and cross-subject generalization. ManifoldFormer addresses this limitation through a novel geometric deep learning framework that explicitly learns neural manifold representations. The architecture integrates three key innovations: a Riemannian VAE for manifold embedding that preserves geometric structure, a geometric Transformer with geodesic-aware attention mechanisms operating directly on neural manifolds, and a dynamics predictor leveraging neural ODEs for manifold-constrained temporal evolution. Extensive evaluation across four public datasets demonstrates substantial improvements over state-of-the-art methods, with 4.6-4.8% higher accuracy and 6.2-10.2% higher Cohen's Kappa, while maintaining robust cross-subject generalization. The geometric approach reveals meaningful neural patterns consistent with neurophysiological principles, establishing geometric constraints as essential for effective EEG foundation models. --- ### WorldGen: From Text to Traversable and Interactive 3D Worlds Authors: Dilin Wang, Hyunyoung Jung, Tom Monnier, Kihyuk Sohn, Chuhang Zou, Xiaoyu Xiang, Yu-Ying Yeh, Di Liu, Zixuan Huang, Thu Nguyen-Phuoc, Yuchen Fan, Sergiu Oprea et al. Published: 2025-11-20 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2511.16825v1 We introduce WorldGen, a system that enables the automatic creation of large-scale, interactive 3D worlds directly from text prompts. Our approach transforms natural language descriptions into traversable, fully textured environments that can be immediately explored or edited within standard game engines. By combining LLM-driven scene layout reasoning, procedural generation, diffusion-based 3D generation, and object-aware scene decomposition, WorldGen bridges the gap between creative intent and functional virtual spaces, allowing creators to design coherent, navigable worlds without manual modeling or specialized 3D expertise. The system is fully modular and supports fine-grained control over layout, scale, and style, producing worlds that are geometrically consistent, visually rich, and efficient to render in real time. This work represents a step towards accessible, generative world-building at scale, advancing the frontier of 3D generative AI for applications in gaming, simulation, and immersive social environments. --- ### Interpretable dimensions support an effect of agentivity and telicity on split intransitivity Authors: Eva Neu, Brian Dillon, Katrin Erk Published: 2025-11-20 Categories: cs.CL arXiv: https://arxiv.org/abs/2511.16824v1 Intransitive verbs fall into two different syntactic classes, unergatives and unaccusatives. It has long been argued that verbs describing an agentive action are more likely to appear in an unergative syntax, and those describing a telic event to appear in an unaccusative syntax. However, recent work by Kim et al. (2024) found that human ratings for agentivity and telicity were a poor predictor of the syntactic behavior of intransitives. Here we revisit this question using interpretable dimensions, computed from seed words on opposite poles of the agentive and telic scales. Our findings support the link between unergativity/unaccusativity and agentivity/telicity, and demonstrate that using interpretable dimensions in conjunction with human judgments can offer valuable evidence for semantic properties that are not easily evaluated in rating tasks. --- ### Monte Carlo Expected Threat (MOCET) Scoring Authors: Joseph Kim, Saahith Potluri Published: 2025-11-20 Categories: cs.LG, cs.AI, cs.HC arXiv: https://arxiv.org/abs/2511.16823v1 Evaluating and measuring AI Safety Level (ASL) threats are crucial for guiding stakeholders to implement safeguards that keep risks within acceptable limits. ASL-3+ models present a unique risk in their ability to uplift novice non-state actors, especially in the realm of biosecurity. Existing evaluation metrics, such as LAB-Bench, BioLP-bench, and WMDP, can reliably assess model uplift and domain knowledge. However, metrics that better contextualize "real-world risks" are needed to inform the safety case for LLMs, along with scalable, open-ended metrics to keep pace with their rapid advancements. To address both gaps, we introduce MOCET, an interpretable and doubly-scalable metric (automatable and open-ended) that can quantify real-world risks. --- ### A Robust Federated Learning Approach for Combating Attacks Against IoT Systems Under non-IID Challenges Authors: Eyad Gad, Zubair Md Fadlullah, Mostafa M. Fouda Published: 2025-11-20 Categories: cs.LG, cs.AI, cs.CR arXiv: https://arxiv.org/abs/2511.16822v1 In the context of the growing proliferation of user devices and the concurrent surge in data volumes, the complexities arising from the substantial increase in data have posed formidable challenges to conventional machine learning model training. Particularly, this is evident within resource-constrained and security-sensitive environments such as those encountered in networks associated with the Internet of Things (IoT). Federated Learning has emerged as a promising remedy to these challenges by decentralizing model training to edge devices or parties, effectively addressing privacy concerns and resource limitations. Nevertheless, the presence of statistical heterogeneity in non-Independently and Identically Distributed (non-IID) data across different parties poses a significant hurdle to the effectiveness of FL. Many FL approaches have been proposed to enhance learning effectiveness under statistical heterogeneity. However, prior studies have uncovered a gap in the existing research landscape, particularly in the absence of a comprehensive comparison between federated methods addressing statistical heterogeneity in detecting IoT attacks. In this research endeavor, we delve into the exploration of FL algorithms, specifically FedAvg, FedProx, and Scaffold, under different data distributions. Our focus is on achieving a comprehensive understanding of and addressing the challenges posed by statistical heterogeneity. In this study, We classify large-scale IoT attacks by utilizing the CICIoT2023 dataset. Through meticulous analysis and experimentation, our objective is to illuminate the performance nuances of these FL methods, providing valuable insights for researchers and practitioners in the domain. --- ### BITS for GAPS: Bayesian Information-Theoretic Sampling for hierarchical GAussian Process Surrogates Authors: Kyla D. Jones, Alexander W. Dowling Published: 2025-11-20 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2511.16815v2 We introduce Bayesian Information-Theoretic Sampling for hierarchical GAussian Process Surrogates (BITS for GAPS), a framework enabling information-theoretic experimental design of Gaussian process-based surrogate models. Unlike standard methods, which use fixed or point-estimated hyperparameters in acquisition functions, our approach propagates hyperparameter uncertainty into the sampling criterion through Bayesian hierarchical modeling. In this framework, a latent function receives a Gaussian process prior, while hyperparameters are assigned additional priors to capture the modeler's knowledge of the governing physical phenomena. Consequently, the acquisition function incorporates uncertainties from both the latent function and its hyperparameters, ensuring that sampling is guided by both data scarcity and model uncertainty. We further establish theoretical results in this context: a closed-form approximation and a lower bound of the posterior differential entropy. We demonstrate the framework's utility for hybrid modeling with a vapor-liquid equilibrium case study. Specifically, we build a surrogate model for latent activity coefficients in a binary mixture. We construct a hybrid model by embedding the surrogate into an extended form of Raoult's law. This hybrid model then informs distillation design. This case study shows how partial physical knowledge can be translated into a hierarchical Gaussian process surrogate. It also shows that using BITS for GAPS increases expected information gain and predictive accuracy by targeting high-uncertainty regions of the Wilson activity model. Overall, BITS for GAPS is a generalized uncertainty-aware framework for adaptive data acquisition in complex physical systems. --- ### Stable diffusion models reveal a persisting human and AI gap in visual creativity Authors: Silvia Rondini, Claudia Alvarez-Martin, Paula Angermair-Barkai, Olivier Penacchio, M. Paz, Matthew Pelowski, Dan Dediu, Antoni Rodriguez-Fornells, Xim Cerda-Company Published: 2025-11-20 Categories: cs.AI, cs.HC arXiv: https://arxiv.org/abs/2511.16814v2 While recent research suggests Large Language Models match human creative performance in divergent thinking tasks, visual creativity remains underexplored. This study compared image generation in human participants (Visual Artists and Non Artists) and using an image generation AI model (two prompting conditions with varying human input: high for Human Inspired, low for Self Guided). Human raters (N=255) and GPT4o evaluated the creativity of the resulting images. We found a clear creativity gradient, with Visual Artists being the most creative, followed by Non Artists, then Human Inspired generative AI, and finally Self Guided generative AI. Increased human guidance strongly improved GenAI's creative output, bringing its productions close to those of Non Artists. Notably, human and AI raters also showed vastly different creativity judgment patterns. These results suggest that, in contrast to language centered tasks, GenAI models may face unique challenges in visual domains, where creativity depends on perceptual nuance and contextual sensitivity, distinctly human capacities that may not be readily transferable from language models. --- ### From Representation to Enactment: The ABC Framework of the Translating Mind Authors: Michael Carl, Takanori Mizowaki, Aishvarya Raj, Masaru Yamada, Devi Sri Bandaru, Yuxiang Wei, Xinyue Ren Published: 2025-11-20 Categories: cs.CL arXiv: https://arxiv.org/abs/2511.16811v2 Building on the third-wave Extended Mind (EM) theory and radical enactivism, this article suggests an alternative to representation-based models of the mind. We build on the ABC framework in which translation is not understood as the manipulation of static interlingual correspondences but an enacted activity, dynamically integrating affective-evaluative, behavioral-enacting, and cognitive-inferential (ABC) processes. Drawing on affordance theory, we argue that the translating mind is the dynamically organized process through which the translator and its environment constitute and transform a landscape of enlanguaged translation affordances for action, that emerges through loops of brain-body-environment interactions. This non-representational account reframes translation as skillful participation in sociocultural practice, where meaning is co-created in real time through embodied interaction with texts, tools, and contexts. --- ### Mesh RAG: Retrieval Augmentation for Autoregressive Mesh Generation Authors: Xiatao Sun, Chen Liang, Qian Wang, Daniel Rakita Published: 2025-11-20 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2511.16807v1 3D meshes are a critical building block for applications ranging from industrial design and gaming to simulation and robotics. Traditionally, meshes are crafted manually by artists, a process that is time-intensive and difficult to scale. To automate and accelerate this asset creation, autoregressive models have emerged as a powerful paradigm for artistic mesh generation. However, current methods to enhance quality typically rely on larger models or longer sequences that result in longer generation time, and their inherent sequential nature imposes a severe quality-speed trade-off. This sequential dependency also significantly complicates incremental editing. To overcome these limitations, we propose Mesh RAG, a novel, training-free, plug-and-play framework for autoregressive mesh generation models. Inspired by RAG for language models, our approach augments the generation process by leveraging point cloud segmentation, spatial transformation, and point cloud registration to retrieve, generate, and integrate mesh components. This retrieval-based approach decouples generation from its strict sequential dependency, facilitating efficient and parallelizable inference. We demonstrate the wide applicability of Mesh RAG across various foundational autoregressive mesh generation models, showing it significantly enhances mesh quality, accelerates generation speed compared to sequential part prediction, and enables incremental editing, all without model retraining. --- ### Efficient Penalty-Based Bilevel Methods: Improved Analysis, Novel Updates, and Flatness Condition Authors: Liuyuan Jiang, Quan Xiao, Lisha Chen, Tianyi Chen Published: 2025-11-20 Categories: math.OC, cs.LG, stat.ML arXiv: https://arxiv.org/abs/2511.16796v1 Penalty-based methods have become popular for solving bilevel optimization (BLO) problems, thanks to their effective first-order nature. However, they often require inner-loop iterations to solve the lower-level (LL) problem and small outer-loop step sizes to handle the increased smoothness induced by large penalty terms, leading to suboptimal complexity. This work considers the general BLO problems with coupled constraints (CCs) and leverages a novel penalty reformulation that decouples the upper- and lower-level variables. This yields an improved analysis of the smoothness constant, enabling larger step sizes and reduced iteration complexity for Penalty-Based Gradient Descent algorithms in ALTernating fashion (ALT-PBGD). Building on the insight of reduced smoothness, we propose PBGD-Free, a novel fully single-loop algorithm that avoids inner loops for the uncoupled constraint BLO. For BLO with CCs, PBGD-Free employs an efficient inner-loop with substantially reduced iteration complexity. Furthermore, we propose a novel curvature condition describing the "flatness" of the upper-level objective with respect to the LL variable. This condition relaxes the traditional upper-level Lipschitz requirement, enables smaller penalty constant choices, and results in a negligible penalty gradient term during upper-level variable updates. We provide rigorous convergence analysis and validate the method's efficacy through hyperparameter optimization for support vector machines and fine-tuning of large language models. --- ### A Vector Symbolic Approach to Multiple Instance Learning Authors: Ehsan Ahmed Dhrubo, Mohammad Mahmudul Alam, Edward Raff, Tim Oates, James Holt Published: 2025-11-20 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.16795v1 Multiple Instance Learning (MIL) tasks impose a strict logical constraint: a bag is labeled positive if and only if at least one instance within it is positive. While this iff constraint aligns with many real-world applications, recent work has shown that most deep learning-based MIL approaches violate it, leading to inflated performance metrics and poor generalization. We propose a novel MIL framework based on Vector Symbolic Architectures (VSAs), which provide a differentiable mechanism for performing symbolic operations in high-dimensional space. Our method encodes the MIL assumption directly into the model's structure by representing instances and concepts as nearly orthogonal high-dimensional vectors and using algebraic operations to enforce the iff constraint during classification. To bridge the gap between raw data and VSA representations, we design a learned encoder that transforms input instances into VSA-compatible vectors while preserving key distributional properties. Our approach, which includes a VSA-driven MaxNetwork classifier, achieves state-of-the-art results for a valid MIL model on standard MIL benchmarks and medical imaging datasets, outperforming existing methods while maintaining strict adherence to the MIL formulation. This work offers a principled, interpretable, and effective alternative to existing MIL approaches that rely on learned heuristics. --- ### Membership Inference Attacks Beyond Overfitting Authors: Mona Khalil, Alberto Blanco-Justicia, Najeeb Jebreel, Josep Domingo-Ferrer Published: 2025-11-20 Categories: cs.CR, cs.LG arXiv: https://arxiv.org/abs/2511.16792v1 Membership inference attacks (MIAs) against machine learning (ML) models aim to determine whether a given data point was part of the model training data. These attacks may pose significant privacy risks to individuals whose sensitive data were used for training, which motivates the use of defenses such as differential privacy, often at the cost of high accuracy losses. MIAs exploit the differences in the behavior of a model when making predictions on samples it has seen during training (members) versus those it has not seen (non-members). Several studies have pointed out that model overfitting is the major factor contributing to these differences in behavior and, consequently, to the success of MIAs. However, the literature also shows that even non-overfitted ML models can leak information about a small subset of their training data. In this paper, we investigate the root causes of membership inference vulnerabilities beyond traditional overfitting concerns and suggest targeted defenses. We empirically analyze the characteristics of the training data samples vulnerable to MIAs in models that are not overfitted (and hence able to generalize). Our findings reveal that these samples are often outliers within their classes (e.g., noisy or hard to classify). We then propose potential defensive strategies to protect these vulnerable samples and enhance the privacy-preserving capabilities of ML models. Our code is available at https://github.com/najeebjebreel/mia_analysis. --- ### NALA_MAINZ at BLP-2025 Task 2: A Multi-agent Approach for Bangla Instruction to Python Code Generation Authors: Hossain Shaikh Saadi, Faria Alam, Mario Sanz-Guerrero, Minh Duc Bui, Manuel Mager, Katharina von der Wense Published: 2025-11-20 Categories: cs.CL, cs.SE arXiv: https://arxiv.org/abs/2511.16787v1 This paper presents JGU Mainz's winning system for the BLP-2025 Shared Task on Code Generation from Bangla Instructions. We propose a multi-agent-based pipeline. First, a code-generation agent produces an initial solution from the input instruction. The candidate program is then executed against the provided unit tests (pytest-style, assert-based). Only the failing cases are forwarded to a debugger agent, which reruns the tests, extracts error traces, and, conditioning on the error messages, the current program, and the relevant test cases, generates a revised solution. Using this approach, our submission achieved first place in the shared task with a $Pass@1$ score of 95.4. We also make our code public. --- ### Revisiting Multimodal KV Cache Compression: A Frequency-Domain-Guided Outlier-KV-Aware Approach Authors: Yaoxin Yang, Peng Ye, Xudong Tan, Chongjun Tu, Maosen Zhao, Jia Hao, Tao Chen Published: 2025-11-20 Categories: cs.LG, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2511.16786v2 Multimodal large language models suffer from substantial inference overhead since multimodal KV Cache grows proportionally with the visual input length. Existing multimodal KV Cache compression methods mostly rely on attention score to reduce cache size, which makes them are incompatible with established efficient attention kernels (e.g., FlashAttention) and ignores the contribution of value vectors to the attention output. In this work, we revisit multimodal KV Cache compression from the perspective of the KV matrices' distribution. First, we observe that frequency-domain energy of multimodal KV matrices is predominantly concentrated in low-frequency and extract this principal energy via a low-pass filter. Further, we find that removing KV pairs that deviate substantially from this principal energy leads to a pronounced performance drop, which we define as Outlier KVs. Considering Outlier KVs are more likely to encode features critical for inference, we propose FlashCache, a frequency-domain-guided, Outlier-KV-aware KV Cache compression framework. First, we introduce an Outlier KV Recognition Module that models the principal component of multimodal KV matrices in the frequency domain and preferentially retains KV pairs that significantly deviate from it. Furthermore, Dynamic Budget Allocation Module is designed to adaptively determine the per-layer KV Cache size to retain more Outlier KVs. Experiments on multiple MLLMs and benchmarks demonstrate that FlashCache outperforms state-of-the-art multimoal KV compression methods, achieving up to 1.69 times faster decoding with 80% lower KV memory usage while maintaining task performance. --- ### Generative Augmented Reality: Paradigms, Technologies, and Future Applications Authors: Chen Liang, Jiawen Zheng, Yufeng Zeng, Yi Tan, Hengye Lyu, Yuhui Zheng, Zisu Li, Yueting Weng, Jiaxin Shi, Hanwang Zhang Published: 2025-11-20 Categories: cs.HC, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2511.16783v1 This paper introduces Generative Augmented Reality (GAR) as a next-generation paradigm that reframes augmentation as a process of world re-synthesis rather than world composition by a conventional AR engine. GAR replaces the conventional AR engine's multi-stage modules with a unified generative backbone, where environmental sensing, virtual content, and interaction signals are jointly encoded as conditioning inputs for continuous video generation. We formalize the computational correspondence between AR and GAR, survey the technical foundations that make real-time generative augmentation feasible, and outline prospective applications that leverage its unified inference model. We envision GAR as a future AR paradigm that delivers high-fidelity experiences in terms of realism, interactivity, and immersion, while eliciting new research challenges on technologies, content ecosystems, and the ethical and societal implications. --- ### GCL-OT: Graph Contrastive Learning with Optimal Transport for Heterophilic Text-Attributed Graphs Authors: Yating Ren, Yikun Ban, Huobin Tan Published: 2025-11-20 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.16778v2 Recently, structure-text contrastive learning has shown promising performance on text-attributed graphs by leveraging the complementary strengths of graph neural networks and language models. However, existing methods typically rely on homophily assumptions in similarity estimation and hard optimization objectives, which limit their applicability to heterophilic graphs. Although existing methods can mitigate heterophily through structural adjustments or neighbor aggregation, they usually treat textual embeddings as static targets, leading to suboptimal alignment. In this work, we identify multi-granular heterophily in text-attributed graphs, including complete heterophily, partial heterophily, and latent homophily, which makes structure-text alignment particularly challenging due to mixed, noisy, and missing semantic correlations. To achieve flexible and bidirectional alignment, we propose GCL-OT, a novel graph contrastive learning framework with optimal transport, equipped with tailored mechanisms for each type of heterophily. Specifically, for partial heterophily, we design a RealSoftMax-based similarity estimator to emphasize key neighbor-word interactions while easing background noise. For complete heterophily, we introduce a prompt-based filter that adaptively excludes irrelevant noise during optimal transport alignment. Furthermore, we incorporate OT-guided soft supervision to uncover potential neighbors with similar semantics, enhancing the learning of latent homophily. Theoretical analysis shows that GCL-OT can improve the mutual information bound and Bayes error guarantees. Extensive experiments on nine benchmarks show that GCL-OT outperforms state-of-the-art methods, demonstrating its effectiveness and robustness. --- ### When Structure Doesn't Help: LLMs Do Not Read Text-Attributed Graphs as Effectively as We Expected Authors: Haotian Xu, Yuning You, Tengfei Ma Published: 2025-11-20 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.16767v2 Graphs provide a unified representation of semantic content and relational structure, making them a natural fit for domains such as molecular modeling, citation networks, and social graphs. Meanwhile, large language models (LLMs) have excelled at understanding natural language and integrating cross-modal signals, sparking interest in their potential for graph reasoning. Recent work has explored this by either designing template-based graph templates or using graph neural networks (GNNs) to encode structural information. In this study, we investigate how different strategies for encoding graph structure affect LLM performance on text-attributed graphs. Surprisingly, our systematic experiments reveal that: (i) LLMs leveraging only node textual descriptions already achieve strong performance across tasks; and (ii) most structural encoding strategies offer marginal or even negative gains. We show that explicit structural priors are often unnecessary and, in some cases, counterproductive when powerful language models are involved. This represents a significant departure from traditional graph learning paradigms and highlights the need to rethink how structure should be represented and utilized in the LLM era. Our study is to systematically challenge the foundational assumption that structure is inherently beneficial for LLM-based graph reasoning, opening the door to new, semantics-driven approaches for graph learning. --- ### SVG360: Editable Multiview Vector Graphics from a Single SVG Authors: Mengnan Jiang, Zhaolin Sun, Christian Franke, Michele Franco Adesso, Antonio Haas, Grace Li Zhang Published: 2025-11-20 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.16766v3 Scalable Vector Graphics are a standard representation for editable visual design, yet they are usually authored as single view two dimensional illustrations. This limits their use in applications that require object level assets to remain coherent when observed, edited, or animated from different viewpoints. We present SVG360, a framework that converts a single input SVG into geometrically and visually consistent multiview SVG assets. The key challenge is that direct per view generation or vectorization produces view dependent regions, fragmented paths, and unstable colors, making the resulting SVGs difficult to edit as a coherent object. SVG360 addresses this problem through a view consistent vectorization pipeline. It first lifts the rasterized input into a view conditioned object representation and renders target views under prescribed cameras. It then propagates part identity across neighboring views using a spatial memory mechanism adapted from video segmentation, establishing consistent region decomposition, path correspondence, and color assignment without task specific retraining. Finally, each view is reconstructed as an editable SVG through structure aware vectorization, where redundant paths are consolidated and local geometry is optimized while preserving boundaries and semantic parts. Experiments on object level SVG assets show that SVG360 improves multiview consistency, reduces path redundancy, and better preserves fine structures compared with direct per view vectorization. By turning a single view SVG into a coherent 360 degree vector asset, SVG360 expands vector graphics from static illustration toward editable multiview content for design, animation, and structured visual editing. --- ### Revisiting Audio-language Pretraining for Learning General-purpose Audio Representation Authors: Wei-Cheng Tseng, Xuanru Zhou, Mingyue Huo, Yiwen Shao, Hao Zhang, Dong Yu Published: 2025-11-20 Categories: eess.AS, cs.AI arXiv: https://arxiv.org/abs/2511.16757v2 Audio-language pretraining (ALP) holds promise for learning general-purpose audio representation, yet remains underexplored. Crucially, there is no consensus on whether audio-language models can build effective general-purpose audio encoders, nor a systematic understanding of how pretraining objectives behave across diverse tasks and scales. We identify three key barriers: limited scale of audio-text corpora, limited coverage of audio attributes in existing caption corpora, and lack of systematic exploration and evaluation. To fill this gap, we present the first principled empirical study of ALP. We first introduce CaptionStew, a 10.7M caption dataset aggregating open-source audio-text corpora across multiple domains and captioning focuses. We then conduct the first comprehensive evaluation comparing contrastive and captioning objectives for learning audio representation across speech, music, and environmental sound tasks. Our results not only demonstrate that ALP yields competitive, transferable representations, but reveal critical trade-offs: contrastive learning offers superior data efficiency, while captioning exhibits better scalability. Furthermore, we find that the benefits of supervised initialization often diminish at larger scales, challenging common practices. By grounding these claims in empirical evidence, we establish a viable pathway toward general-purpose audio representation learning, guiding future research. --- ### SafeR-CLIP: Mitigating NSFW Content in Vision-Language Models While Preserving Pre-Trained Knowledge Authors: Adeel Yousaf, Joseph Fioresi, James Beetham, Amrit Singh Bedi, Mubarak Shah Published: 2025-11-20 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2511.16743v1 Improving the safety of vision-language models like CLIP via fine-tuning often comes at a steep price, causing significant drops in their generalization performance. We find this trade-off stems from rigid alignment strategies that force unsafe concepts toward single, predefined safe targets, disrupting the model's learned semantic structure. To address this, we propose a proximity-aware approach: redirecting unsafe concepts to their semantically closest safe alternatives to minimize representational change. We introduce SaFeR-CLIP, a fine-tuning framework that applies this principle of minimal intervention. SaFeR-CLIP successfully reconciles safety and performance, recovering up to 8.0% in zero-shot accuracy over prior methods while maintaining robust safety. To support more rigorous evaluation, we also contribute NSFW-Caps, a new benchmark of 1,000 highly-aligned pairs for testing safety under distributional shift. Our work shows that respecting the geometry of pretrained representations is key to achieving safety without sacrificing performance. --- ### Fermions and Supersymmetry in Neural Network Field Theories Authors: Samuel Frank, James Halverson, Anindita Maiti, Fabian Ruehle Published: 2025-11-20 Categories: hep-th, cs.LG arXiv: https://arxiv.org/abs/2511.16741v1 We introduce fermionic neural network field theories via Grassmann-valued neural networks. Free theories are obtained by a generalization of the Central Limit Theorem to Grassmann variables. This enables the realization of the free Dirac spinor at infinite width and a four fermion interaction at finite width. Yukawa couplings are introduced by breaking the statistical independence of the output weights for the fermionic and bosonic fields. A large class of interacting supersymmetric quantum mechanics and field theory models are introduced by super-affine transformations on the input that realize a superspace formalism. --- ### SAM 3: Segment Anything with Concepts Authors: Nicolas Carion, Laura Gustafson, Yuan-Ting Hu, Shoubhik Debnath, Ronghang Hu, Didac Suris, Chaitanya Ryali, Kalyan Vasudev Alwala, Haitham Khedr, Andrew Huang, Jie Lei, Tengyu Ma et al. Published: 2025-11-20 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2511.16719v2 We present Segment Anything Model (SAM) 3, a unified model that detects, segments, and tracks objects in images and videos based on concept prompts, which we define as either short noun phrases (e.g., "yellow school bus"), image exemplars, or a combination of both. Promptable Concept Segmentation (PCS) takes such prompts and returns segmentation masks and unique identities for all matching object instances. To advance PCS, we build a scalable data engine that produces a high-quality dataset with 4M unique concept labels, including hard negatives, across images and videos. Our model consists of an image-level detector and a memory-based video tracker that share a single backbone. Recognition and localization are decoupled with a presence head, which boosts detection accuracy. SAM 3 doubles the accuracy of existing systems in both image and video PCS, and improves previous SAM capabilities on visual segmentation tasks. We open source SAM 3 along with our new Segment Anything with Concepts (SA-Co) benchmark for promptable concept segmentation. --- ### A Machine Learning-Driven Solution for Denoising Inertial Confinement Fusion Images Authors: Asya Y. Akkus, Bradley T. Wolfe, Pinghan Chu, Chengkun Huang, Chris S. Campbell, Mariana Alvarado Alvarez, Petr Volegov, David Fittinghoff, Robert Reinovsky, Zhehui Wang Published: 2025-11-20 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2511.16717v3 Neutron imaging is essential for diagnosing and optimizing inertial confinement fusion implosions at the National Ignition Facility. Due to the required 10-micrometer resolution, however, neutron image require image reconstruction using iterative algorithms. For low-yield sources, the images may be degraded by various types of noise. Gaussian and Poisson noise often coexist within one image, obscuring fine details and blurring the edges where the source information is encoded. Traditional denoising techniques, such as filtering and thresholding, can inadvertently alter critical features or reshape the noise statistics, potentially impacting the ultimate fidelity of the iterative image reconstruction pipeline. However, recent advances in synthetic data production and machine learning have opened new opportunities to address these challenges. In this study, we present an unsupervised autoencoder with a Cohen-Daubechies- Feauveau (CDF 97) wavelet transform in the latent space, designed to suppress for mixed Gaussian-Poisson noise while preserving essential image features. The network successfully denoises neutron imaging data. Benchmarking against both simulated and experimental NIF datasets demonstrates that our approach achieves lower reconstruction error and superior edge preservation compared to conventional filtering methods such as Block-matching and 3D filtering (BM3D). By validating the effectiveness of unsupervised learning for denoising neutron images, this study establishes a critical first step towards fully AI-driven, end-to-end reconstruction frameworks for ICF diagnostics. --- ### Password Strength Analysis Through Social Network Data Exposure: A Combined Approach Relying on Data Reconstruction and Generative Models Authors: Maurizio Atzori, Eleonora Calò, Loredana Caruccio, Stefano Cirillo, Giuseppe Polese, Giandomenico Solimando Published: 2025-11-20 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2511.16716v1 Although passwords remain the primary defense against unauthorized access, users often tend to use passwords that are easy to remember. This behavior significantly increases security risks, also due to the fact that traditional password strength evaluation methods are often inadequate. In this discussion paper, we present SODA ADVANCE, a data reconstruction tool also designed to enhance evaluation processes related to the password strength. In particular, SODA ADVANCE integrates a specialized module aimed at evaluating password strength by leveraging publicly available data from multiple sources, including social media platforms. Moreover, we investigate the capabilities and risks associated with emerging Large Language Models (LLMs) in evaluating and generating passwords, respectively. Experimental assessments conducted with 100 real users demonstrate that LLMs can generate strong and personalized passwords possibly defined according to user profiles. Additionally, LLMs were shown to be effective in evaluating passwords, especially when they can take into account user profile data. --- ### DDTime: Dataset Distillation with Spectral Alignment and Information Bottleneck for Time-Series Forecasting Authors: Yuqi Li, Kuiye Ding, Chuanguang Yang, Hao Wang, Haoxuan Wang, Huiran Duan, Junming Liu, Yingli Tian Published: 2025-11-20 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2511.16715v1 Time-series forecasting is fundamental across many domains, yet training accurate models often requires large-scale datasets and substantial computational resources. Dataset distillation offers a promising alternative by synthesizing compact datasets that preserve the learning behavior of full data. However, extending dataset distillation to time-series forecasting is non-trivial due to two fundamental challenges: 1.temporal bias from strong autocorrelation, which leads to distorted value-term alignment between teacher and student models; and 2.insufficient diversity among synthetic samples, arising from the absence of explicit categorical priors to regularize trajectory variety. In this work, we propose DDTime, a lightweight and plug-in distillation framework built upon first-order condensation decomposition. To tackle Challenge 1, it revisits value-term alignment through temporal statistics and introduces a frequency-domain alignment mechanism to mitigate autocorrelation-induced bias, ensuring spectral consistency and temporal fidelity. To address Challenge 2, we further design an inter-sample regularization inspired by the information bottleneck principle, which enhances diversity and maximizes information density across synthetic trajectories. The combined objective is theoretically compatible with a wide range of condensation paradigms and supports stable first-order optimization. Extensive experiments on 20 benchmark datasets and diverse forecasting architectures demonstrate that DDTime consistently outperforms existing distillation methods, achieving about 30% relative accuracy gains while introducing about 2.49% computational overhead. All code and distilled datasets will be released. --- ### PairHuman: A High-Fidelity Photographic Dataset for Customized Dual-Person Generation Authors: Ting Pan, Ye Wang, Peiguang Jing, Rui Ma, Zili Yi, Yu Liu Published: 2025-11-20 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2511.16712v2 Personalized dual-person portrait customization has considerable potential applications, such as preserving emotional memories and facilitating wedding photography planning. However, the absence of a benchmark dataset hinders the pursuit of high-quality customization in dual-person portrait generation. In this paper, we propose the PairHuman dataset, which is the first large-scale benchmark dataset specifically designed for generating dual-person portraits that meet high photographic standards. The PairHuman dataset contains more than 100K images that capture a variety of scenes, attire, and dual-person interactions, along with rich metadata, including detailed image descriptions, person localization, human keypoints, and attribute tags. We also introduce DHumanDiff, which is a baseline specifically crafted for dual-person portrait generation that features enhanced facial consistency and simultaneously balances in personalized person generation and semantic-driven scene creation. Finally, the experimental results demonstrate that our dataset and method produce highly customized portraits with superior visual quality that are tailored to human preferences. Our dataset is publicly available at https://github.com/annaoooo/PairHuman. --- ### Motion Transfer-Enhanced StyleGAN for Generating Diverse Macaque Facial Expressions Authors: Takuya Igaue, Catia Correia-Caeiro, Akito Yoshida, Takako Miyabe-Nishiwaki, Ryusuke Hayashi Published: 2025-11-20 Categories: cs.CV, eess.IV arXiv: https://arxiv.org/abs/2511.16711v1 Generating animal faces using generative AI techniques is challenging because the available training images are limited both in quantity and variation, particularly for facial expressions across individuals. In this study, we focus on macaque monkeys, widely studied in systems neuroscience and evolutionary research, and propose a method to generate their facial expressions using a style-based generative image model (i.e., StyleGAN2). To address data limitations, we implemented: 1) data augmentation by synthesizing new facial expression images using a motion transfer to animate still images with computer graphics, 2) sample selection based on the latent representation of macaque faces from an initially trained StyleGAN2 model to ensure the variation and uniform sampling in training dataset, and 3) loss function refinement to ensure the accurate reproduction of subtle movements, such as eye movements. Our results demonstrate that the proposed method enables the generation of diverse facial expressions for multiple macaque individuals, outperforming models trained solely on original still images. Additionally, we show that our model is effective for style-based image editing, where specific style parameters correspond to distinct facial movements. These findings underscore the model's potential for disentangling motion components as style parameters, providing a valuable tool for research on macaque facial expressions. --- ### AutoBackdoor: Automating Backdoor Attacks via LLM Agents Authors: Yige Li, Zhe Li, Wei Zhao, Nay Myat Min, Hanxun Huang, Xingjun Ma, Jun Sun Published: 2025-11-20 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2511.16709v1 Backdoor attacks pose a serious threat to the secure deployment of large language models (LLMs), enabling adversaries to implant hidden behaviors triggered by specific inputs. However, existing methods often rely on manually crafted triggers and static data pipelines, which are rigid, labor-intensive, and inadequate for systematically evaluating modern defense robustness. As AI agents become increasingly capable, there is a growing need for more rigorous, diverse, and scalable \textit{red-teaming frameworks} that can realistically simulate backdoor threats and assess model resilience under adversarial conditions. In this work, we introduce \textsc{AutoBackdoor}, a general framework for automating backdoor injection, encompassing trigger generation, poisoned data construction, and model fine-tuning via an autonomous agent-driven pipeline. Unlike prior approaches, AutoBackdoor uses a powerful language model agent to generate semantically coherent, context-aware trigger phrases, enabling scalable poisoning across arbitrary topics with minimal human effort. We evaluate AutoBackdoor under three realistic threat scenarios, including \textit{Bias Recommendation}, \textit{Hallucination Injection}, and \textit{Peer Review Manipulation}, to simulate a broad range of attacks. Experiments on both open-source and commercial models, including LLaMA-3, Mistral, Qwen, and GPT-4o, demonstrate that our method achieves over 90\% attack success with only a small number of poisoned samples. More importantly, we find that existing defenses often fail to mitigate these attacks, underscoring the need for more rigorous and adaptive evaluation techniques against agent-driven threats as explored in this work. All code, datasets, and experimental configurations will be merged into our primary repository at https://github.com/bboylyg/BackdoorLLM. --- ### Multi-Agent Code Verification via Information Theory Authors: Shreshth Rajan Published: 2025-11-20 Categories: cs.SE, cs.AI, cs.MA arXiv: https://arxiv.org/abs/2511.16708v3 LLMs generate buggy code: 29.6% of SWE-bench solved patches fail, 62% of BaxBench solutions have vulnerabilities, and existing tools only catch 65% of bugs with 35% false positives. We built CodeX-Verify, a multi-agent system that uses four specialized agents to detect different types of bugs. We prove mathematically that combining agents with different detection patterns finds more bugs than any single agent when the agents look for different problems, using submodularity of mutual information under conditional independence. Measuring agent correlation of rho = 0.05 to 0.25 confirms they detect different bugs. Testing on 99 code samples with verified labels shows our system catches 76.1% of bugs, matching the best existing method (Meta Prompt Testing: 75%) while running faster and without test execution. We tested all 15 agent combinations and found that using multiple agents improves accuracy by 39.7 percentage points (from 32.8% to 72.4%) compared to single agents, with diminishing returns of +14.9pp, +13.5pp, and +11.2pp for agents 2, 3, and 4, validating our theoretical model. The best two-agent combination (Correctness + Performance) reaches 79.3% accuracy. Testing on 300 real patches from Claude Sonnet 4.5 runs in under 200ms per sample, making this practical for production use. --- ### Large language models for automated PRISMA 2020 adherence checking Authors: Yuki Kataoka, Ryuhei So, Masahiro Banno, Yasushi Tsujimoto, Tomohiro Takayama, Yosuke Yamagishi, Takahiro Tsuge, Norio Yamamoto, Chiaki Suda, Toshi A. Furukawa Published: 2025-11-20 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2511.16707v1 Evaluating adherence to PRISMA 2020 guideline remains a burden in the peer review process. To address the lack of shareable benchmarks, we constructed a copyright-aware benchmark of 108 Creative Commons-licensed systematic reviews and evaluated ten large language models (LLMs) across five input formats. In a development cohort, supplying structured PRISMA 2020 checklists (Markdown, JSON, XML, or plain text) yielded 78.7-79.7% accuracy versus 45.21% for manuscript-only input (p less than 0.0001), with no differences between structured formats (p>0.9). Across models, accuracy ranged from 70.6-82.8% with distinct sensitivity-specificity trade-offs, replicated in an independent validation cohort. We then selected Qwen3-Max (a high-sensitivity open-weight model) and extended evaluation to the full dataset (n=120), achieving 95.1% sensitivity and 49.3% specificity. Structured checklist provision substantially improves LLM-based PRISMA assessment, though human expert verification remains essential before editorial decisions. --- ### Dataset Distillation for Pre-Trained Self-Supervised Vision Models Authors: George Cazenavette, Antonio Torralba, Vincent Sitzmann Published: 2025-11-20 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2511.16674v1 The task of dataset distillation aims to find a small set of synthetic images such that training a model on them reproduces the performance of the same model trained on a much larger dataset of real samples. Existing distillation methods focus on synthesizing datasets that enable training randomly initialized models. In contrast, state-of-the-art vision approaches are increasingly building on large, pre-trained self-supervised models rather than training from scratch. In this paper, we investigate the problem of distilling datasets that enable us to optimally train linear probes on top of such large, pre-trained vision models. We introduce a method of dataset distillation for this task called Linear Gradient Matching that optimizes the synthetic images such that, when passed through a pre-trained feature extractor, they induce gradients in the linear classifier similar to those produced by the real data. Our method yields synthetic data that outperform all real-image baselines and, remarkably, generalize across pre-trained vision models, enabling us, for instance, to train a linear CLIP probe that performs competitively using a dataset distilled via a DINO backbone. Further, we show that our distilled datasets are exceptionally effective for fine-grained classification and provide a valuable tool for model interpretability, predicting, among other things, how similar two models' embedding spaces are under the platonic representation hypothesis or whether a model is sensitive to spurious correlations in adversarial datasets. --- ### NoPo-Avatar: Generalizable and Animatable Avatars from Sparse Inputs without Human Poses Authors: Jing Wen, Alexander G. Schwing, Shenlong Wang Published: 2025-11-20 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.16673v1 We tackle the task of recovering an animatable 3D human avatar from a single or a sparse set of images. For this task, beyond a set of images, many prior state-of-the-art methods use accurate "ground-truth" camera poses and human poses as input to guide reconstruction at test-time. We show that pose-dependent reconstruction degrades results significantly if pose estimates are noisy. To overcome this, we introduce NoPo-Avatar, which reconstructs avatars solely from images, without any pose input. By removing the dependence of test-time reconstruction on human poses, NoPo-Avatar is not affected by noisy human pose estimates, making it more widely applicable. Experiments on challenging THuman2.0, XHuman, and HuGe100K data show that NoPo-Avatar outperforms existing baselines in practical settings (without ground-truth poses) and delivers comparable results in lab settings (with ground-truth poses). --- ### EvoLMM: Self-Evolving Large Multimodal Models with Continuous Rewards Authors: Omkar Thawakar, Shravan Venkatraman, Ritesh Thawkar, Abdelrahman Shaker, Hisham Cholakkal, Rao Muhammad Anwer, Salman Khan, Fahad Khan Published: 2025-11-20 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.16672v4 Recent advances in large multimodal models (LMMs) have enabled impressive reasoning and perception abilities, yet most existing training pipelines still depend on human-curated data or externally verified reward models, limiting their autonomy and scalability. In this work, we strive to improve LMM reasoning capabilities in a purely unsupervised fashion (without any annotated data or reward distillation). To this end, we propose a self-evolving framework, named EvoLMM, that instantiates two cooperative agents from a single backbone model: a Proposer, which generates diverse, image-grounded questions, and a Solver, which solves them through internal consistency, where learning proceeds through a continuous self-rewarding process. This dynamic feedback encourages both the generation of informative queries and the refinement of structured reasoning without relying on ground-truth or human judgments. When using the popular Qwen2.5-VL as the base model, our EvoLMM yields consistent gains upto $\sim$3\% on multimodal math-reasoning benchmarks, including ChartQA, MathVista, and MathVision, using only raw training images. We hope our simple yet effective approach will serve as a solid baseline easing future research in self-improving LMMs in a fully-unsupervised fashion. Our code and models are available at https://github.com/mbzuai-oryx/EvoLMM. --- ### EvoLMM: Self-Evolving Large Multimodal Models with Continuous Rewards Authors: Omkat Thawakar, Shravan Venkatraman, Ritesh Thawkar, Abdelrahman Shaker, Hisham Cholakkal, Rao Muhammad Anwer, Salman Khan, Fahad Khan Published: 2025-11-20 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.16672v1 Recent advances in large multimodal models (LMMs) have enabled impressive reasoning and perception abilities, yet most existing training pipelines still depend on human-curated data or externally verified reward models, limiting their autonomy and scalability. In this work, we strive to improve LMM reasoning capabilities in a purely unsupervised fashion (without any annotated data or reward distillation). To this end, we propose a self-evolving framework, named EvoLMM, that instantiates two cooperative agents from a single backbone model: a Proposer, which generates diverse, image-grounded questions, and a Solver, which solves them through internal consistency, where learning proceeds through a continuous self-rewarding process. This dynamic feedback encourages both the generation of informative queries and the refinement of structured reasoning without relying on ground-truth or human judgments. When using the popular Qwen2.5-VL as the base model, our EvoLMM yields consistent gains upto $\sim$3\% on multimodal math-reasoning benchmarks, including ChartQA, MathVista, and MathVision, using only raw training images. We hope our simple yet effective approach will serve as a solid baseline easing future research in self-improving LMMs in a fully-unsupervised fashion. Our code and models are available at https://github.com/mbzuai-oryx/EvoLMM. --- ### Thinking-while-Generating: Interleaving Textual Reasoning throughout Visual Generation Authors: Ziyu Guo, Renrui Zhang, Hongyu Li, Manyuan Zhang, Xinyan Chen, Sifan Wang, Yan Feng, Peng Pei, Pheng-Ann Heng Published: 2025-11-20 Categories: cs.CV, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2511.16671v1 Recent advances in visual generation have increasingly explored the integration of reasoning capabilities. They incorporate textual reasoning, i.e., think, either before (as pre-planning) or after (as post-refinement) the generation process, yet they lack on-the-fly multimodal interaction during the generation itself. In this preliminary study, we introduce Thinking-while-Generating (TwiG), the first interleaved framework that enables co-evolving textual reasoning throughout the visual generation process. As visual content is progressively generating, textual reasoning is interleaved to both guide upcoming local regions and reflect on previously synthesized ones. This dynamic interplay produces more context-aware and semantically rich visual outputs. To unveil the potential of this framework, we investigate three candidate strategies, zero-shot prompting, supervised fine-tuning (SFT) on our curated TwiG-50K dataset, and reinforcement learning (RL) via a customized TwiG-GRPO strategy, each offering unique insights into the dynamics of interleaved reasoning. We hope this work inspires further research into interleaving textual reasoning for enhanced visual generation. Code will be released at: https://github.com/ZiyuGuo99/Thinking-while-Generating. --- ### Learning to Think Fast and Slow for Visual Language Models Authors: Chenyu Lin, Cheng Chi, Jinlin Wu, Sharon Li, Kaiyang Zhou Published: 2025-11-20 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.16670v2 When faced with complex problems, we tend to engage in slower, more deliberate thinking. In contrast, for simple questions we give quick, intuitive responses. This dual-system thinking approach allows us to allocate cognitive resources efficiently, reserving deeper analytical effort for tasks that truly require it. However, existing reasoning-oriented visual language models (VLMs) are mostly trained to generate uniformly long reasoning, leading to substantial token waste when concise answers would suffice. In this paper, we observe that pre-trained, general-purpose VLMs manifest variations in response length for different question types, e.g., longer reasoning for math questions while shorter on perception problems. Different from existing work that overrides this prior by stimulating long reasoning without considering the problem complexity, we propose to leverage this prior to develop an explicit dual-mode thinking mechanism. Specifically, we anchor each training instance to either a fast or slow thinking prefix consistent with the model's natural response length tendency. Then, GRPO is adapted to learning dual-system thinking, enabling both autonomous and manual thinking mode selection. Extensive experiments across a wide variety of visual reasoning benchmarks demonstrate that our model, named DualMindVLM, significantly outperforms the base model and achieves state-of-the-art reasoning performance while maintaining high token efficiency. --- ### Learning to Think Fast and Slow for Visual Language Models Authors: Chenyu Lin, Cheng Chi, Jinlin Wu, Sharon Li, Kaiyang Zhou Published: 2025-11-20 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.16670v1 When confronted with complex problems, we tend to think slowly; conversely, for simple questions, we think quickly. Such a two-system thinking mechanism allows us to efficiently allocate cognitive resources, enabling quick decision-making for straightforward issues while reserving deeper analytical thinking for more intricate challenges. However, existing reasoning-oriented visual language models (VLMs), whether trained with explicit chain-of-thought annotations or rule-based RL rewards, mainly pursue lengthy, detailed reasoning chains, which often lead to excessive computational costs. In this work, we propose a simple RL approach, which enables VLMs to automatically switch between fast and slow thinking modes depending on task difficulty. The approach consists of two stages: in the first stage, we label data as either requiring fast thinking or slow thinking based on the model output length, which is inspired by the observation that pre-trained VLMs typically produce answers of varying lengths for different types of questions; in the second stage, we train the model using GRPO along with the thinking mode labels to develop dual-mode thinking. Despite its simplicity, our model, named DualMindVLM, significantly outperforms the base model and achieves performance on par with state-of-the-art visual reasoning models, while maintaining exceptionally high token efficiency. --- ### Video-as-Answer: Predict and Generate Next Video Event with Joint-GRPO Authors: Junhao Cheng, Liang Hou, Xin Tao, Jing Liao Published: 2025-11-20 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.16669v2 While language models have become impactful in many real-world applications, video generation remains largely confined to entertainment. Motivated by video's inherent capacity to demonstrate physical-world information that is difficult to convey through language alone (e.g., imagine teaching someone to tie a tie using only text), we identify an underutilized opportunity to extend video as a new answer modality for Next-Event Prediction (NEP), formalized as Video-Next-Event Prediction (VNEP). While the established NEP task takes a video with a procedural or predictive question as input to predict the next event in text, VNEP requires dynamic video responses. This shift from telling to showing unlocks more intuitive and customized answers for procedural learning and creative exploration. However, this task remains challenging for existing models, as it demands an understanding of multimodal input, instruction-conditioned reasoning, and the generation of video with visual and semantic consistency. To address this, we introduce VANS, a model that leverages reinforcement learning to align a Vision-Language Model (VLM) with a Video Diffusion Model (VDM) for VNEP. The core of VANS is our proposed Joint-GRPO that orchestrates the VLM and VDM to function as a unit. Driven by a shared reward on their respective output, it optimizes the VLM to produce captions that are both accurate and friendly to visualize, while guiding the VDM to generate videos that are faithful to these captions and the input visual context. To enable this learning, we craft VANS-Data-100K, a dedicated dataset for the VNEP task. Experiments on procedural and predictive benchmarks demonstrate that VANS achieves state-of-the-art performance in both video event prediction and visualization. Codes are released in https://github.com/KlingTeam/VANS. --- ### Video-as-Answer: Predict and Generate Next Video Event with Joint-GRPO Authors: Junhao Cheng, Liang Hou, Xin Tao, Jing Liao Published: 2025-11-20 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.16669v1 While language models have become impactful in many real-world applications, video generation remains largely confined to entertainment. Motivated by video's inherent capacity to demonstrate physical-world information that is difficult to convey through language alone (e.g., imagine teaching someone to tie a tie using only text), we identify an underutilized opportunity to extend video as a new answer modality for Next-Event Prediction (NEP), formalized as Video-Next-Event Prediction (VNEP). While the established NEP task takes a video with a procedural or predictive question as input to predict the next event in text, VNEP requires dynamic video responses. This shift from telling to showing unlocks more intuitive and customized answers for procedural learning and creative exploration. However, this task remains challenging for existing models, as it demands an understanding of multimodal input, instruction-conditioned reasoning, and the generation of video with visual and semantic consistency. To address this, we introduce VANS, a model that leverages reinforcement learning to align a Vision-Language Model (VLM) with a Video Diffusion Model (VDM) for VNEP. The core of VANS is our proposed Joint-GRPO that orchestrates the VLM and VDM to function as a unit. Driven by a shared reward on their respective output, it optimizes the VLM to produce captions that are both accurate and friendly to visualize, while guiding the VDM to generate videos that are faithful to these captions and the input visual context. To enable this learning, we craft VANS-Data-100K, a dedicated dataset for the VNEP task. Experiments on procedural and predictive benchmarks demonstrate that VANS achieves state-of-the-art performance in both video event prediction and visualization. Codes are released in https://github.com/KlingTeam/VANS. --- ### V-ReasonBench: Toward Unified Reasoning Benchmark Suite for Video Generation Models Authors: Yang Luo, Xuanlei Zhao, Baijiong Lin, Lingting Zhu, Liyao Tang, Yuqi Liu, Ying-Cong Chen, Shengju Qian, Xin Wang, Yang You Published: 2025-11-20 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.16668v1 Recent progress in generative video models, such as Veo-3, has shown surprising zero-shot reasoning abilities, creating a growing need for systematic and reliable evaluation. We introduce V-ReasonBench, a benchmark designed to assess video reasoning across four key dimensions: structured problem-solving, spatial cognition, pattern-based inference, and physical dynamics. The benchmark is built from both synthetic and real-world image sequences and provides a diverse set of answer-verifiable tasks that are reproducible, scalable, and unambiguous. Evaluations of six state-of-the-art video models reveal clear dimension-wise differences, with strong variation in structured, spatial, pattern-based, and physical reasoning. We further compare video models with strong image models, analyze common hallucination behaviors, and study how video duration affects Chain-of-Frames reasoning. Overall, V-ReasonBench offers a unified and reproducible framework for measuring video reasoning and aims to support the development of models with more reliable, human-aligned reasoning skills. --- ### SceneDesigner: Controllable Multi-Object Image Generation with 9-DoF Pose Manipulation Authors: Zhenyuan Qin, Xincheng Shuai, Henghui Ding Published: 2025-11-20 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.16666v1 Controllable image generation has attracted increasing attention in recent years, enabling users to manipulate visual content such as identity and style. However, achieving simultaneous control over the 9D poses (location, size, and orientation) of multiple objects remains an open challenge. Despite recent progress, existing methods often suffer from limited controllability and degraded quality, falling short of comprehensive multi-object 9D pose control. To address these limitations, we propose SceneDesigner, a method for accurate and flexible multi-object 9-DoF pose manipulation. SceneDesigner incorporates a branched network to the pre-trained base model and leverages a new representation, CNOCS map, which encodes 9D pose information from the camera view. This representation exhibits strong geometric interpretation properties, leading to more efficient and stable training. To support training, we construct a new dataset, ObjectPose9D, which aggregates images from diverse sources along with 9D pose annotations. To further address data imbalance issues, particularly performance degradation on low-frequency poses, we introduce a two-stage training strategy with reinforcement learning, where the second stage fine-tunes the model using a reward-based objective on rebalanced data. At inference time, we propose Disentangled Object Sampling, a technique that mitigates insufficient object generation and concept confusion in complex multi-object scenes. Moreover, by integrating user-specific personalization weights, SceneDesigner enables customized pose control for reference subjects. Extensive qualitative and quantitative experiments demonstrate that SceneDesigner significantly outperforms existing approaches in both controllability and quality. Code is publicly available at https://github.com/FudanCVL/SceneDesigner. --- ### Taming the Long-Tail: Efficient Reasoning RL Training with Adaptive Drafter Authors: Qinghao Hu, Shang Yang, Junxian Guo, Xiaozhe Yao, Yujun Lin, Yuxian Gu, Han Cai, Chuang Gan, Ana Klimovic, Song Han Published: 2025-11-20 Categories: cs.LG, cs.AI, cs.DC arXiv: https://arxiv.org/abs/2511.16665v3 The emergence of Large Language Models (LLMs) with strong reasoning capabilities marks a significant milestone, unlocking new frontiers in complex problem-solving. However, training these reasoning models, typically using Reinforcement Learning (RL), encounters critical efficiency bottlenecks: response generation during RL training exhibits a persistent long-tail distribution, where a few very long responses dominate execution time, wasting resources and inflating costs. To address this, we propose TLT, a system that accelerates reasoning RL training losslessly by integrating adaptive speculative decoding. Applying speculative decoding in RL is challenging due to the dynamic workloads, evolving target model, and draft model training overhead. TLT overcomes these obstacles with two synergistic components: (1) Adaptive Drafter, a lightweight draft model trained continuously on idle GPUs during long-tail generation to maintain alignment with the target model at no extra cost; and (2) Adaptive Rollout Engine, which maintains a memory-efficient pool of pre-captured CUDAGraphs and adaptively select suitable SD strategies for each input batch. Evaluations demonstrate that TLT achieves over 1.7x end-to-end RL training speedup over state-of-the-art systems, preserves the model accuracy, and yields a high-quality draft model as a free byproduct suitable for efficient deployment. Code is released at https://github.com/mit-han-lab/fastrl. --- ### Taming the Long-Tail: Efficient Reasoning RL Training with Adaptive Drafter Authors: Qinghao Hu, Shang Yang, Junxian Guo, Xiaozhe Yao, Yujun Lin, Yuxian Gu, Han Cai, Chuang Gan, Ana Klimovic, Song Han Published: 2025-11-20 Categories: cs.LG, cs.AI, cs.DC arXiv: https://arxiv.org/abs/2511.16665v1 The emergence of Large Language Models (LLMs) with strong reasoning capabilities marks a significant milestone, unlocking new frontiers in complex problem-solving. However, training these reasoning models, typically using Reinforcement Learning (RL), encounters critical efficiency bottlenecks: response generation during RL training exhibits a persistent long-tail distribution, where a few very long responses dominate execution time, wasting resources and inflating costs. To address this, we propose TLT, a system that accelerates reasoning RL training losslessly by integrating adaptive speculative decoding. Applying speculative decoding in RL is challenging due to the dynamic workloads, evolving target model, and draft model training overhead. TLT overcomes these obstacles with two synergistic components: (1) Adaptive Drafter, a lightweight draft model trained continuously on idle GPUs during long-tail generation to maintain alignment with the target model at no extra cost; and (2) Adaptive Rollout Engine, which maintains a memory-efficient pool of pre-captured CUDAGraphs and adaptively select suitable SD strategies for each input batch. Evaluations demonstrate that TLT achieves over 1.7x end-to-end RL training speedup over state-of-the-art systems, preserves the model accuracy, and yields a high-quality draft model as a free byproduct suitable for efficient deployment. Code is released at https://github.com/mit-han-lab/fastrl. --- ### Nemotron Elastic: Towards Efficient Many-in-One Reasoning LLMs Authors: Ali Taghibakhshi, Sharath Turuvekere Sreenivas, Saurav Muralidharan, Ruisi Cai, Marcin Chochowski, Ameya Sunil Mahabaleshwarkar, Yoshi Suhara, Oluwatobi Olabiyi, Daniel Korzekwa, Mostofa Patwary, Mohammad Shoeybi, Jan Kautz et al. Published: 2025-11-20 Categories: cs.CL arXiv: https://arxiv.org/abs/2511.16664v1 Training a family of large language models targeting multiple scales and deployment objectives is prohibitively expensive, requiring separate training runs for each different size. Recent work on model compression through pruning and knowledge distillation has reduced this cost; however, this process still incurs hundreds of billions of tokens worth of training cost per compressed model. In this paper, we present Nemotron Elastic, a framework for building reasoning-oriented LLMs, including hybrid Mamba-Attention architectures, that embed multiple nested submodels within a single parent model, each optimized for different deployment configurations and budgets. Each of these submodels shares weights with the parent model and can be extracted zero-shot during deployment without additional training or fine-tuning. We enable this functionality through an end-to-end trained router, tightly coupled to a two-stage training curriculum designed specifically for reasoning models. We additionally introduce group-aware SSM elastification that preserves Mamba's structural constraints, heterogeneous MLP elastification, normalized MSE-based layer importance for improved depth selection, and knowledge distillation enabling simultaneous multi-budget optimization. We apply Nemotron Elastic to the Nemotron Nano V2 12B model, simultaneously producing a 9B and a 6B model using only 110B training tokens; this results in over 360x cost reduction compared to training model families from scratch, and around 7x compared to SoTA compression techniques. Each of the nested models performs on par or better than the SoTA in accuracy. Moreover, unlike other compression methods, the nested capability of our approach allows having a many-in-one reasoning model that has constant deployment memory against the number of models in the family. --- ### TriDiff-4D: Fast 4D Generation through Diffusion-based Triplane Re-posing Authors: Eddie Pokming Sheung, Qihao Liu, Wufei Ma, Prakhar Kaushik, Jianwen Xie, Alan Yuille Published: 2025-11-20 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.16662v1 With the increasing demand for 3D animation, generating high-fidelity, controllable 4D avatars from textual descriptions remains a significant challenge. Despite notable efforts in 4D generative modeling, existing methods exhibit fundamental limitations that impede their broader applicability, including temporal and geometric inconsistencies, perceptual artifacts, motion irregularities, high computational costs, and limited control over dynamics. To address these challenges, we propose TriDiff-4D, a novel 4D generative pipeline that employs diffusion-based triplane re-posing to produce high-quality, temporally coherent 4D avatars. Our model adopts an auto-regressive strategy to generate 4D sequences of arbitrary length, synthesizing each 3D frame with a single diffusion process. By explicitly learning 3D structure and motion priors from large-scale 3D and motion datasets, TriDiff-4D enables skeleton-driven 4D generation that excels in temporal consistency, motion accuracy, computational efficiency, and visual fidelity. Specifically, TriDiff-4D first generates a canonical 3D avatar and a corresponding motion sequence from a text prompt, then uses a second diffusion model to animate the avatar according to the motion sequence, supporting arbitrarily long 4D generation. Experimental results demonstrate that TriDiff-4D significantly outperforms existing methods, reducing generation time from hours to seconds by eliminating the optimization process, while substantially improving the generation of complex motions with high-fidelity appearance and accurate 3D geometry. --- ### Dexterity from Smart Lenses: Multi-Fingered Robot Manipulation with In-the-Wild Human Demonstrations Authors: Irmak Guzey, Haozhi Qi, Julen Urain, Changhao Wang, Jessica Yin, Krishna Bodduluri, Mike Lambeta, Lerrel Pinto, Akshara Rai, Jitendra Malik, Tingfan Wu, Akash Sharma et al. Published: 2025-11-20 Categories: cs.RO, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2511.16661v1 Learning multi-fingered robot policies from humans performing daily tasks in natural environments has long been a grand goal in the robotics community. Achieving this would mark significant progress toward generalizable robot manipulation in human environments, as it would reduce the reliance on labor-intensive robot data collection. Despite substantial efforts, progress toward this goal has been bottle-necked by the embodiment gap between humans and robots, as well as by difficulties in extracting relevant contextual and motion cues that enable learning of autonomous policies from in-the-wild human videos. We claim that with simple yet sufficiently powerful hardware for obtaining human data and our proposed framework AINA, we are now one significant step closer to achieving this dream. AINA enables learning multi-fingered policies from data collected by anyone, anywhere, and in any environment using Aria Gen 2 glasses. These glasses are lightweight and portable, feature a high-resolution RGB camera, provide accurate on-board 3D head and hand poses, and offer a wide stereo view that can be leveraged for depth estimation of the scene. This setup enables the learning of 3D point-based policies for multi-fingered hands that are robust to background changes and can be deployed directly without requiring any robot data (including online corrections, reinforcement learning, or simulation). We compare our framework against prior human-to-robot policy learning approaches, ablate our design choices, and demonstrate results across nine everyday manipulation tasks. Robot rollouts are best viewed on our website: https://aina-robot.github.io. ---