# Research Papers — 2025-11 · bundle page 96 of 197 > Full-text markdown of papers #4751–4800 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/96 [← Previous bundle](https://aipod.dev/papers/archive/2025-11/page/95.md) [Next bundle →](https://aipod.dev/papers/archive/2025-11/page/97.md) ### Decoupling Scene Perception and Ego Status: A Multi-Context Fusion Approach for Enhanced Generalization in End-to-End Autonomous Driving Authors: Jiacheng Tang, Mingyue Feng, Jiachao Liu, Yaonong Wang, Jian Pu Published: 2025-11-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.13079v2 Modular design of planning-oriented autonomous driving has markedly advanced end-to-end systems. However, existing architectures remain constrained by an over-reliance on ego status, hindering generalization and robust scene understanding. We identify the root cause as an inherent design within these architectures that allows ego status to be easily leveraged as a shortcut. Specifically, the premature fusion of ego status in the upstream BEV encoder allows an information flow from this strong prior to dominate the downstream planning module. To address this challenge, we propose AdaptiveAD, an architectural-level solution based on a multi-context fusion strategy. Its core is a dual-branch structure that explicitly decouples scene perception and ego status. One branch performs scene-driven reasoning based on multi-task learning, but with ego status deliberately omitted from the BEV encoder, while the other conducts ego-driven reasoning based solely on the planning task. A scene-aware fusion module then adaptively integrates the complementary decisions from the two branches to form the final planning trajectory. To ensure this decoupling does not compromise multi-task learning, we introduce a path attention mechanism for ego-BEV interaction and add two targeted auxiliary tasks: BEV unidirectional distillation and autoregressive online mapping. Extensive evaluations on the nuScenes dataset demonstrate that AdaptiveAD achieves state-of-the-art open-loop planning performance. Crucially, it significantly mitigates the over-reliance on ego status and exhibits impressive generalization capabilities across diverse scenarios. --- ### A Smart-Glasses for Emergency Medical Services via Multimodal Multitask Learning Authors: Liuyi Jin, Pasan Gunawardena, Amran Haroon, Runzhi Wang, Sangwoo Lee, Radu Stoleru, Michael Middleton, Zepeng Huo, Jeeeun Kim, Jason Moats Published: 2025-11-17 Categories: cs.LG, eess.AS, eess.IV arXiv: https://arxiv.org/abs/2511.13078v1 Emergency Medical Technicians (EMTs) operate in high-pressure environments, making rapid, life-critical decisions under heavy cognitive and operational loads. We present EMSGlass, a smart-glasses system powered by EMSNet, the first multimodal multitask model for Emergency Medical Services (EMS), and EMSServe, a low-latency multimodal serving framework tailored to EMS scenarios. EMSNet integrates text, vital signs, and scene images to construct a unified real-time understanding of EMS incidents. Trained on real-world multimodal EMS datasets, EMSNet simultaneously supports up to five critical EMS tasks with superior accuracy compared to state-of-the-art unimodal baselines. Built on top of PyTorch, EMSServe introduces a modality-aware model splitter and a feature caching mechanism, achieving adaptive and efficient inference across heterogeneous hardware while addressing the challenge of asynchronous modality arrival in the field. By optimizing multimodal inference execution in EMS scenarios, EMSServe achieves 1.9x -- 11.7x speedup over direct PyTorch multimodal inference. A user study evaluation with six professional EMTs demonstrates that EMSGlass enhances real-time situational awareness, decision-making speed, and operational efficiency through intuitive on-glass interaction. In addition, qualitative insights from the user study provide actionable directions for extending EMSGlass toward next-generation AI-enabled EMS systems, bridging multimodal intelligence with real-world emergency response workflows. --- ### Orientation-Free Neural Network-Based Bias Estimation for Low-Cost Stationary Accelerometers Authors: Michal Levin, Itzik Klein Published: 2025-11-17 Categories: cs.RO, cs.LG arXiv: https://arxiv.org/abs/2511.13071v1 Low-cost micro-electromechanical accelerometers are widely used in navigation, robotics, and consumer devices for motion sensing and position estimation. However, their performance is often degraded by bias errors. To eliminate deterministic bias terms a calibration procedure is applied under stationary conditions. It requires accelerom- eter leveling or complex orientation-dependent calibration procedures. To overcome those requirements, in this paper we present a model-free learning-based calibration method that estimates accelerometer bias under stationary conditions, without requiring knowledge of the sensor orientation and without the need to rotate the sensors. The proposed approach provides a fast, practical, and scalable solution suitable for rapid field deployment. Experimental validation on a 13.39-hour dataset collected from six accelerometers shows that the proposed method consistently achieves error levels more than 52% lower than traditional techniques. On a broader scale, this work contributes to the advancement of accurate calibration methods in orientation-free scenarios. As a consequence, it improves the reliability of low-cost inertial sensors in diverse scientific and industrial applications and eliminates the need for leveled calibration. --- ### RobustGait: Robustness Analysis for Appearance Based Gait Recognition Authors: Reeshoon Sayera, Akash Kumar, Sirshapan Mitra, Prudvi Kamtam, Yogesh S Rawat Published: 2025-11-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.13065v2 Appearance-based gait recognition have achieved strong performance on controlled datasets, yet systematic evaluation of its robustness to real-world corruptions and silhouette variability remains lacking. We present RobustGait, a framework for fine-grained robustness evaluation of appearance-based gait recognition systems. RobustGait evaluation spans four dimensions: the type of perturbation (digital, environmental, temporal, occlusion), the silhouette extraction method (segmentation and parsing networks), the architectural capacities of gait recognition models, and various deployment scenarios. The benchmark introduces 15 corruption types at 5 severity levels across CASIA-B, CCPG, and SUSTech1K, with in-the-wild validation on MEVID, and evaluates six state-of-the-art gait systems. We came across several exciting insights. First, applying noise at the RGB level better reflects real-world degradation, and reveal how distortions propagate through silhouette extraction to the downstream gait recognition systems. Second, gait accuracy is highly sensitive to silhouette extractor biases, revealing an overlooked source of benchmark bias. Third, robustness is dependent on both the type of perturbation and the architectural design. Finally, we explore robustness-enhancing strategies, showing that noise-aware training and knowledge distillation improve performance and move toward deployment-ready systems. Code is available at https://reeshoon.github.io/robustgaitbenchmark --- ### FGNet: Leveraging Feature-Guided Attention to Refine SAM2 for 3D EM Neuron Segmentation Authors: Zhenghua Li, Hang Chen, Zihao Sun, Kai Li, Xiaolin Hu Published: 2025-11-17 Categories: cs.CV, cs.IR arXiv: https://arxiv.org/abs/2511.13063v1 Accurate segmentation of neural structures in Electron Microscopy (EM) images is paramount for neuroscience. However, this task is challenged by intricate morphologies, low signal-to-noise ratios, and scarce annotations, limiting the accuracy and generalization of existing methods. To address these challenges, we seek to leverage the priors learned by visual foundation models on a vast amount of natural images to better tackle this task. Specifically, we propose a novel framework that can effectively transfer knowledge from Segment Anything 2 (SAM2), which is pre-trained on natural images, to the EM domain. We first use SAM2 to extract powerful, general-purpose features. To bridge the domain gap, we introduce a Feature-Guided Attention module that leverages semantic cues from SAM2 to guide a lightweight encoder, the Fine-Grained Encoder (FGE), in focusing on these challenging regions. Finally, a dual-affinity decoder generates both coarse and refined affinity maps. Experimental results demonstrate that our method achieves performance comparable to state-of-the-art (SOTA) approaches with the SAM2 weights frozen. Upon further fine-tuning on EM data, our method significantly outperforms existing SOTA methods. This study validates that transferring representations pre-trained on natural images, when combined with targeted domain-adaptive guidance, can effectively address the specific challenges in neuron segmentation. --- ### Self-Adaptive Graph Mixture of Models Authors: Mohit Meena, Yash Punjabi, Abhishek A, Vishal Sharma, Mahesh Chandran Published: 2025-11-17 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2511.13062v2 Graph Neural Networks (GNNs) have emerged as powerful tools for learning over graph-structured data, yet recent studies have shown that their performance gains are beginning to plateau. In many cases, well-established models such as GCN and GAT, when appropriately tuned, can match or even exceed the performance of more complex, state-of-the-art architectures. This trend highlights a key limitation in the current landscape: the difficulty of selecting the most suitable model for a given graph task or dataset. To address this, we propose Self-Adaptive Graph Mixture of Models (SAGMM), a modular and practical framework that learns to automatically select and combine the most appropriate GNN models from a diverse pool of architectures. Unlike prior mixture-of-experts approaches that rely on variations of a single base model, SAGMM leverages architectural diversity and a topology-aware attention gating mechanism to adaptively assign experts to each node based on the structure of the input graph. To improve efficiency, SAGMM includes a pruning mechanism that reduces the number of active experts during training and inference without compromising performance. We also explore a training-efficient variant in which expert models are pretrained and frozen, and only the gating and task-specific layers are trained. We evaluate SAGMM on 16 benchmark datasets covering node classification, graph classification, regression, and link prediction tasks, and demonstrate that it consistently outperforms or matches leading GNN baselines and prior mixture-based methods, offering a robust and adaptive solution for real-world graph learning. --- ### MACKO: Sparse Matrix-Vector Multiplication for Low Sparsity Authors: Vladimír Macko, Vladimír Boža Published: 2025-11-17 Categories: cs.LG, cs.AI, cs.DC, cs.DS arXiv: https://arxiv.org/abs/2511.13061v1 Sparse Matrix-Vector Multiplication (SpMV) is a fundamental operation in the inference of sparse Large Language Models (LLMs). Because existing SpMV methods perform poorly under the low and unstructured sparsity (30-90%) commonly observed in pruned LLMs, unstructured pruning provided only limited memory reduction and speedup. We propose MACKO-SpMV, a GPU-optimized format and kernel co-designed to reduce storage overhead while preserving compatibility with the GPU's execution model. This enables efficient SpMV for unstructured sparsity without specialized hardware units (e.g., tensor cores) or format-specific precomputation. Empirical results show that at sparsity 50%, MACKO is the first approach with significant 1.5x memory reduction and 1.2-1.5x speedup over dense representation. Speedups over other SpMV baselines: 2.8-13.0x over cuSPARSE, 1.9-2.6x over Sputnik, and 2.2-2.5x over DASP. Applied to Llama2-7B pruned with Wanda to sparsity 50%, it delivers 1.5x memory reduction and 1.5x faster inference at fp16 precision. Thanks to MACKO, unstructured pruning at 50% sparsity is now justified in real-world LLM workloads. --- ### Latency and Ordering Effects in Online Decisions Authors: Duo Yi Published: 2025-11-17 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2511.13060v1 Online decision systems routinely operate under delayed feedback and order-sensitive (noncommutative) dynamics: actions affect which observations arrive, and in what sequence. Taking a Bregman divergence $D_Φ$ as the loss benchmark, we prove that the excess benchmark loss admits a structured lower bound $L \ge L_{\mathrm{ideal}} + g_1(λ) + g_2(\varepsilon_\star) + g_{12}(λ,\varepsilon_\star) - D_{\mathrm{ncx}}$, where $g_1$ and $g_2$ are calibrated penalties for latency and order-sensitivity, $g_{12}$ captures their geometric interaction, and $D_{\mathrm{ncx}}\ge 0$ is a nonconvexity/approximation penalty that vanishes under convex Legendre assumptions. We extend this inequality to prox-regular and weakly convex settings, obtaining robust guarantees beyond the convex case. We also give an operational recipe for estimating and monitoring the four terms via simple $2\times 2$ randomized experiments and streaming diagnostics (effective sample size, clipping rate, interaction heatmaps). The framework packages heterogeneous latency, noncommutativity, and implementation-gap effects into a single interpretable lower-bound statement that can be stress-tested and tuned in real-world systems. --- ### Dimension vs. Precision: A Comparative Analysis of Autoencoders and Quantization for Efficient Vector Retrieval on BEIR SciFact Authors: Satyanarayan Pati Published: 2025-11-17 Categories: cs.IR, cs.AI arXiv: https://arxiv.org/abs/2511.13057v2 Dense retrieval models have become a standard for state-of-the-art information retrieval. However, their high-dimensional, high-precision (float32) vector embeddings create significant storage and memory challenges for real-world deployment. To address this, we conduct a rigorous empirical study on the BEIR SciFact benchmark, evaluating the trade-offs between two primary compression strategies: (1) Dimensionality Reduction via deep Autoencoders (AE), reducing original 384-dim vectors to latent spaces from 384 down to 12, and (2) Precision Reduction via Quantization (float16, int8, and binary). We systematically compare each method by measuring the "performance loss" (or gain) relative to a float32 baseline across a full suite of retrieval metrics (NDCG, MAP, MRR, Recall, Precision) at various k cutoffs. Our results show that int8 scalar quantization provides the most effective "sweet spot," achieving a 4x compression with a negligible (~1-2%) drop in nDCG@10. In contrast, Autoencoders show a graceful degradation but suffer a more significant performance loss at equivalent 4x compression ratios (AE-96). binary quantization was found to be unsuitable for this task due to catastrophic performance drops. This work provides a practical guide for deploying efficient, high-performance retrieval systems. --- ### Monocular 3D Lane Detection via Structure Uncertainty-Aware Network with Curve-Point Queries Authors: Ruixin Liu, Zejian Yuan Published: 2025-11-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.13055v1 Monocular 3D lane detection is challenged by aleatoric uncertainty arising from inherent observation noise. Existing methods rely on simplified geometric assumptions, such as independent point predictions or global planar modeling, failing to capture structural variations and aleatoric uncertainty in real-world scenarios. In this paper, we propose MonoUnc, a bird's-eye view (BEV)-free 3D lane detector that explicitly models aleatoric uncertainty informed by local lane structures. Specifically, 3D lanes are projected onto the front-view (FV) space and approximated by parametric curves. Guided by curve predictions, curve-point query embeddings are dynamically generated for lane point predictions in 3D space. Each segment formed by two adjacent points is modeled as a 3D Gaussian, parameterized by the local structure and uncertainty estimations. Accordingly, a novel 3D Gaussian matching loss is designed to constrain these parameters jointly. Experiments on the ONCE-3DLanes and OpenLane datasets demonstrate that MonoUnc outperforms previous state-of-the-art (SoTA) methods across all benchmarks under stricter evaluation criteria. Additionally, we propose two comprehensive evaluation metrics for ONCE-3DLanes, calculating the average and maximum bidirectional Chamfer distances to quantify global and local errors. Codes are released at https://github.com/lrx02/MonoUnc. --- ### ViSS-R1: Self-Supervised Reinforcement Video Reasoning Authors: Bo Fang, Yuxin Song, Qiangqiang Wu, Haoyuan Sun, Wenhao Wu, Antoni B. Chan Published: 2025-11-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.13054v1 Complex video reasoning remains a significant challenge for Multimodal Large Language Models (MLLMs), as current R1-based methodologies often prioritize text-centric reasoning derived from text-based and image-based developments. In video tasks, such strategies frequently underutilize rich visual information, leading to potential shortcut learning and increased susceptibility to hallucination. To foster a more robust, visual-centric video understanding, we start by introducing a novel self-supervised reinforcement learning GRPO algorithm (Pretext-GRPO) within the standard R1 pipeline, in which positive rewards are assigned for correctly solving pretext tasks on transformed visual inputs, which makes the model to non-trivially process the visual information. Building on the effectiveness of Pretext-GRPO, we further propose the ViSS-R1 framework, which streamlines and integrates pretext-task-based self-supervised learning directly into the MLLM's R1 post-training paradigm. Instead of relying solely on sparse visual cues, our framework compels models to reason about transformed visual input by simultaneously processing both pretext questions (concerning transformations) and true user queries. This necessitates identifying the applied transformation and reconstructing the original video to formulate accurate final answers. Comprehensive evaluations on six widely-used video reasoning and understanding benchmarks demonstrate the effectiveness and superiority of our Pretext-GRPO and ViSS-R1 for complex video reasoning. Our codes and models will be publicly available. --- ### Self-Organization and Spectral Mechanism of Attractor Landscapes in High-Capacity Kernel Hopfield Networks Authors: Akira Tamamori Published: 2025-11-17 Categories: cs.LG, cs.NE arXiv: https://arxiv.org/abs/2511.13053v9 Kernel-based learning methods can dramatically increase the storage capacity of Hopfield networks, yet the dynamical mechanisms behind this enhancement remain poorly understood. We address this gap by combining a geometric characterization of the attractor landscape with the spectral theory of kernel machines. Using a novel metric, Pinnacle Sharpness, we empirically uncover a rich phase diagram of attractor stability, identifying a Ridge of Optimization where the network achieves maximal robustness under high-load conditions. Phenomenologically, this ridge is characterized by a Force Antagonism, in which a strong driving force is counterbalanced by a collective feedback force. We theoretically interpret this behavior as a consequence of a specific reorganization of the weight spectrum, which we term Spectral Concentration. Unlike a simple rank-1 collapse, our analysis shows that the network on the ridge self-organizes into a critical regime: the leading eigenvalue is amplified to enhance global stability (Direct Force), while the trailing eigenvalues remain finite to sustain high memory capacity (Indirect Force). Together, these results suggest a spectral mechanism by which learning reconciles stability and capacity in high-dimensional associative memory models. --- ### Learning from the Undesirable: Robust Adaptation of Language Models without Forgetting Authors: Yunhun Nam, Jaehyung Kim, Jongheon Jeong Published: 2025-11-17 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2511.13052v1 Language models (LMs) are often adapted through supervised fine-tuning (SFT) to specialize their capabilities for downstream tasks. However, in typical scenarios where the fine-tuning data is limited, e.g., compared to pre-training, SFT can lead LMs to overfit, causing them to rely on spurious patterns within the target task or to compromise other broadly useful capabilities as a side effect of narrow specialization. In this paper, we propose Learning-from-the-Undesirable (LfU), a simple yet effective regularization scheme for SFT to mitigate overfitting issues when fine-tuning LMs with limited data. Specifically, we aim to regularize the fine-tuning process to favor solutions that are resilient to "undesirable" model updates, e.g., gradient ascent steps that steer the model toward undesirable behaviors. To this end, we propose a novel form of consistency regularization that directly aligns internal representations of the model with those after an undesirable update. By leveraging representation-level data augmentation through undesirable updates, LfU effectively promotes generalization under limited data. Our experiments on diverse LM downstream tasks show that LfU serves as an effective prior that enhances adaptability while preserving pretrained knowledge. For example, our LM from LfU achieves a 16.8% average improvement on math tasks compared to vanilla SFT on the same dataset, where the latter even leads to degraded performance on those tasks. Furthermore, LfU exhibits improved robustness to prompt variations, e.g., yielding a 92.1% lower standard deviation in output performances compared to SFT, highlighting its versatile effects. --- ### DS-ATGO: Dual-Stage Synergistic Learning via Forward Adaptive Threshold and Backward Gradient Optimization for Spiking Neural Networks Authors: Jiaqiang Jiang, Wenfeng Xu, Jing Fan, Rui Yan Published: 2025-11-17 Categories: cs.NE arXiv: https://arxiv.org/abs/2511.13050v1 Brain-inspired spiking neural networks (SNNs) are recognized as a promising avenue for achieving efficient, low-energy neuromorphic computing. Direct training of SNNs typically relies on surrogate gradient (SG) learning to estimate derivatives of non-differentiable spiking activity. However, during training, the distribution of neuronal membrane potentials varies across timesteps and progressively deviates toward both sides of the firing threshold. When the firing threshold and SG remain fixed, this may lead to imbalanced spike firing and diminished gradient signals, preventing SNNs from performing well. To address these issues, we propose a novel dual-stage synergistic learning algorithm that achieves forward adaptive thresholding and backward dynamic SG. In forward propagation, we adaptively adjust thresholds based on the distribution of membrane potential dynamics (MPD) at each timestep, which enriches neuronal diversity and effectively balances firing rates across timesteps and layers. In backward propagation, drawing from the underlying association between MPD, threshold, and SG, we dynamically optimize SG to enhance gradient estimation through spatio-temporal alignment, effectively mitigating gradient information loss. Experimental results demonstrate that our method achieves significant performance improvements. Moreover, it allows neurons to fire stable proportions of spikes at each timestep and increases the proportion of neurons that obtain gradients in deeper layers. --- ### Generalization Bounds for Semi-supervised Matrix Completion with Distributional Side Information Authors: Antoine Ledent, Mun Chong Soo, Nong Minh Hieu Published: 2025-11-17 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2511.13049v2 We study a matrix completion problem where both the ground truth $R$ matrix and the unknown sampling distribution $P$ over observed entries are low-rank matrices, and \textit{share a common subspace}. We assume that a large amount $M$ of \textit{unlabeled} data drawn from the sampling distribution $P$ is available, together with a small amount $N$ of labeled data drawn from the same distribution and noisy estimates of the corresponding ground truth entries. This setting is inspired by recommender systems scenarios where the unlabeled data corresponds to `implicit feedback' (consisting in interactions such as purchase, click, etc. ) and the labeled data corresponds to the `explicit feedback', consisting of interactions where the user has given an explicit rating to the item. Leveraging powerful results from the theory of low-rank subspace recovery, together with classic generalization bounds for matrix completion models, we show error bounds consisting of a sum of two error terms scaling as $\widetilde{O}\left(\sqrt{\frac{nd}{M}}\right)$ and $\widetilde{O}\left(\sqrt{\frac{dr}{N}}\right)$ respectively, where $d$ is the rank of $P$ and $r$ is the rank of $M$. In synthetic experiments, we confirm that the true generalization error naturally splits into independent error terms corresponding to the estimations of $P$ and and the ground truth matrix $\ground$ respectively. In real-life experiments on Douban and MovieLens with most explicit ratings removed, we demonstrate that the method can outperform baselines relying only on the explicit ratings, demonstrating that our assumptions provide a valid toy theoretical setting to study the interaction between explicit and implicit feedbacks in recommender systems. --- ### DiffPixelFormer: Differential Pixel-Aware Transformer for RGB-D Indoor Scene Segmentation Authors: Yan Gong, Jianli Lu, Yongsheng Gao, Jie Zhao, Xiaojuan Zhang, Susanto Rahardja Published: 2025-11-17 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2511.13047v1 Indoor semantic segmentation is fundamental to computer vision and robotics, supporting applications such as autonomous navigation, augmented reality, and smart environments. Although RGB-D fusion leverages complementary appearance and geometric cues, existing methods often depend on computationally intensive cross-attention mechanisms and insufficiently model intra- and inter-modal feature relationships, resulting in imprecise feature alignment and limited discriminative representation. To address these challenges, we propose DiffPixelFormer, a differential pixel-aware Transformer for RGB-D indoor scene segmentation that simultaneously enhances intra-modal representations and models inter-modal interactions. At its core, the Intra-Inter Modal Interaction Block (IIMIB) captures intra-modal long-range dependencies via self-attention and models inter-modal interactions with the Differential-Shared Inter-Modal (DSIM) module to disentangle modality-specific and shared cues, enabling fine-grained, pixel-level cross-modal alignment. Furthermore, a dynamic fusion strategy balances modality contributions and fully exploits RGB-D information according to scene characteristics. Extensive experiments on the SUN RGB-D and NYUDv2 benchmarks demonstrate that DiffPixelFormer-L achieves mIoU scores of 54.28% and 59.95%, outperforming DFormer-L by 1.78% and 2.75%, respectively. Code is available at https://github.com/gongyan1/DiffPixelFormer. --- ### Bi-View Embedding Fusion: A Hybrid Learning Approach for Knowledge Graph's Nodes Classification Addressing Problems with Limited Data Authors: Rosario Napoli, Giovanni Lonia, Antonio Celesti, Massimo Villari, Maria Fazio Published: 2025-11-17 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.13044v1 Traditional Machine Learning (ML) methods require large amounts of data to perform well, limiting their applicability in sparse or incomplete scenarios and forcing the usage of additional synthetic data to improve the model training. To overcome this challenge, the research community is looking more and more at Graph Machine Learning (GML) as it offers a powerful alternative by using relationships within data. However, this method also faces limitations, particularly when dealing with Knowledge Graphs (KGs), which can hide huge information due to their semantic nature. This study introduces Bi-View, a novel hybrid approach that increases the informative content of node features in KGs to generate enhanced Graph Embeddings (GEs) that are used to improve GML models without relying on additional synthetic data. The proposed work combines two complementary GE techniques: Node2Vec, which captures structural patterns through unsupervised random walks, and GraphSAGE, which aggregates neighbourhood information in a supervised way. Node2Vec embeddings are first computed to represent the graph topology, and node features are then enriched with centrality-based metrics, which are used as input for the GraphSAGE model. Moreover, a fusion layer combines the original Node2Vec embeddings with the GraphSAGE-influenced representations, resulting in a dual-perspective embedding space. Such a fusion captures both topological and semantic properties of the graph, enabling the model to exploit informative features that may exist in the dataset but that are not explicitly represented. Our approach improves downstream task performance, especially in scenarios with poor initial features, giving the basis for more accurate and precise KG-enanched GML models. --- ### Spark-Prover-X1: Formal Theorem Proving Through Diverse Data Training Authors: Xinyuan Zhou, Yi Lei, Xiaoyu Zhou, Jingyi Sun, Yu Zhu, Zhongyi Ye, Weitai Zhang, Quan Liu, Si Wei, Cong Liu Published: 2025-11-17 Categories: cs.CL arXiv: https://arxiv.org/abs/2511.13043v3 Large Language Models (LLMs) have shown significant promise in automated theorem proving, yet progress is often constrained by the scarcity of diverse and high-quality formal language data. To address this issue, we introduce Spark-Prover-X1, a 7B parameter model trained via an three-stage framework designed to unlock the reasoning potential of more accessible and moderately-sized LLMs. The first stage infuses deep knowledge through continuous pre-training on a broad mathematical corpus, enhanced by a suite of novel data tasks. Key innovation is a "CoT-augmented state prediction" task to achieve fine-grained reasoning. The second stage employs Supervised Fine-tuning (SFT) within an expert iteration loop to specialize both the Spark-Prover-X1-7B and Spark-Formalizer-X1-7B models. Finally, a targeted round of Group Relative Policy Optimization (GRPO) is applied to sharpen the prover's capabilities on the most challenging problems. To facilitate robust evaluation, particularly on problems from real-world examinations, we also introduce ExamFormal-Bench, a new benchmark dataset of 402 formal problems. Experimental results demonstrate that Spark-Prover achieves state-of-the-art performance among similarly-sized open-source models within the "Whole-Proof Generation" paradigm. It shows exceptional performance on difficult competition benchmarks, notably solving 27 problems on PutnamBench (pass@32) and achieving 24.0\% on CombiBench (pass@32). Our work validates that this diverse training data and progressively refined training pipeline provides an effective path for enhancing the formal reasoning capabilities of lightweight LLMs. We will release both Spark-Prover-X1-7B and Spark-Formalizer-X1-7B, along with the ExamFormal-Bench dataset, in the near future. --- ### How Good is BLI as an Alignment Measure: A Study in Word Embedding Paradigm Authors: Kasun Wickramasinghe, Nisansa de Silva Published: 2025-11-17 Categories: cs.CL arXiv: https://arxiv.org/abs/2511.13040v1 Sans a dwindling number of monolingual embedding studies originating predominantly from the low-resource domains, it is evident that multilingual embedding has become the de facto choice due to its adaptability to the usage of code-mixed languages, granting the ability to process multilingual documents in a language-agnostic manner, as well as removing the difficult task of aligning monolingual embeddings. But is this victory complete? Are the multilingual models better than aligned monolingual models in every aspect? Can the higher computational cost of multilingual models always be justified? Or is there a compromise between the two extremes? Bilingual Lexicon Induction is one of the most widely used metrics in terms of evaluating the degree of alignment between two embedding spaces. In this study, we explore the strengths and limitations of BLI as a measure to evaluate the degree of alignment of two embedding spaces. Further, we evaluate how well traditional embedding alignment techniques, novel multilingual models, and combined alignment techniques perform BLI tasks in the contexts of both high-resource and low-resource languages. In addition to that, we investigate the impact of the language families to which the pairs of languages belong. We identify that BLI does not measure the true degree of alignment in some cases and we propose solutions for them. We propose a novel stem-based BLI approach to evaluate two aligned embedding spaces that take into account the inflected nature of languages as opposed to the prevalent word-based BLI techniques. Further, we introduce a vocabulary pruning technique that is more informative in showing the degree of the alignment, especially performing BLI on multilingual embedding models. Often, combined embedding alignment techniques perform better while in certain cases multilingual embeddings perform better (mainly low-resource language cases). --- ### MGCA-Net: Multi-Grained Category-Aware Network for Open-Vocabulary Temporal Action Localization Authors: Zhenying Fang, Richang Hong Published: 2025-11-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.13039v2 Open-Vocabulary Temporal Action Localization (OV-TAL) aims to recognize and localize instances of any desired action categories in videos without explicitly curating training data for all categories. Existing methods mostly recognize action categories at a single granularity, which degrades the recognition accuracy of both base and novel action categories. To address these issues, we propose a Multi-Grained Category-Aware Network (MGCA-Net) comprising a localizer, an action presence predictor, a conventional classifier, and a coarse-to-fine classifier. Specifically, the localizer localizes category-agnostic action proposals. For these action proposals, the action presence predictor estimates the probability that they belong to an action instance. At the same time, the conventional classifier predicts the probability of each action proposal over base action categories at the snippet granularity. Novel action categories are recognized by the coarse-to-fine classifier, which first identifies action presence at the video granularity. Finally, it assigns each action proposal to one category from the coarse categories at the proposal granularity. Through coarse-to-fine category awareness for novel actions and the conventional classifier's awareness of base actions, multi-grained category awareness is achieved, effectively enhancing localization performance. Comprehensive evaluations on the THUMOS'14 and ActivityNet-1.3 benchmarks demonstrate that our method achieves state-of-the-art performance. Furthermore, our MGCA-Net achieves state-of-the-art results under the Zero-Shot Temporal Action Localization setting. --- ### uCLIP: Parameter-Efficient Multilingual Extension of Vision-Language Models with Unpaired Data Authors: Dahyun Chung, Donghyun Shin, Yujin Sung, Seunggi Moon, Jinwoo Jeon, Byung-Jun Lee Published: 2025-11-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.13036v2 Contrastive Language-Image Pre-training (CLIP) has demonstrated strong generalization across a wide range of visual tasks by leveraging large-scale English-image pairs. However, its extension to low-resource languages remains limited due to the scarcity of high-quality multilingual image-text data. Existing multilingual vision-language models exhibit consistently low retrieval performance in underrepresented languages including Czech, Finnish, Croatian, Hungarian, and Romanian on the Crossmodal-3600 (XM3600) benchmark. To address this, we propose a lightweight and data-efficient framework for multilingual vision-language alignment. Our approach requires no image-text pairs or text-text pairs and freezes both the pretrained image encoder and multilingual text encoder during training. Only a compact 1.7M-parameter projection module is trained, using a contrastive loss over English representations as semantic anchors. This minimal training setup enables robust multilingual alignment even for languages with limited supervision. Extensive evaluation across multiple multilingual retrieval benchmarks confirms the effectiveness of our method, showing significant gains in five underrepresented languages where existing models typically underperform. These findings highlight the effectiveness of our pivot-based, parameter-efficient alignment strategy for inclusive multimodal learning. --- ### One-Step Generative Policies with Q-Learning: A Reformulation of MeanFlow Authors: Zeyuan Wang, Da Li, Yulin Chen, Ye Shi, Liang Bai, Tianyuan Yu, Yanwei Fu Published: 2025-11-17 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2511.13035v1 We introduce a one-step generative policy for offline reinforcement learning that maps noise directly to actions via a residual reformulation of MeanFlow, making it compatible with Q-learning. While one-step Gaussian policies enable fast inference, they struggle to capture complex, multimodal action distributions. Existing flow-based methods improve expressivity but typically rely on distillation and two-stage training when trained with Q-learning. To overcome these limitations, we propose to reformulate MeanFlow to enable direct noise-to-action generation by integrating the velocity field and noise-to-action transformation into a single policy network-eliminating the need for separate velocity estimation. We explore several reformulation variants and identify an effective residual formulation that supports expressive and stable policy learning. Our method offers three key advantages: 1) efficient one-step noise-to-action generation, 2) expressive modelling of multimodal action distributions, and 3) efficient and stable policy learning via Q-learning in a single-stage training setup. Extensive experiments on 73 tasks across the OGBench and D4RL benchmarks demonstrate that our method achieves strong performance in both offline and offline-to-online reinforcement learning settings. Code is available at https://github.com/HiccupRL/MeanFlowQL. --- ### Uni-Inter: Unifying 3D Human Motion Synthesis Across Diverse Interaction Contexts Authors: Sheng Liu, Yuanzhi Liang, Jiepeng Wang, Sidan Du, Chi Zhang, Xuelong Li Published: 2025-11-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.13032v2 We present Uni-Inter, a unified framework for human motion generation that supports a wide range of interaction scenarios: including human-human, human-object, and human-scene-within a single, task-agnostic architecture. In contrast to existing methods that rely on task-specific designs and exhibit limited generalization, Uni-Inter introduces the Unified Interactive Volume (UIV), a volumetric representation that encodes heterogeneous interactive entities into a shared spatial field. This enables consistent relational reasoning and compound interaction modeling. Motion generation is formulated as joint-wise probabilistic prediction over the UIV, allowing the model to capture fine-grained spatial dependencies and produce coherent, context-aware behaviors. Experiments across three representative interaction tasks demonstrate that Uni-Inter achieves competitive performance and generalizes well to novel combinations of entities. These results suggest that unified modeling of compound interactions offers a promising direction for scalable motion synthesis in complex environments. --- ### Towards 3D Object-Centric Feature Learning for Semantic Scene Completion Authors: Weihua Wang, Yubo Cui, Xiangru Lin, Zhiheng Li, Zheng Fang Published: 2025-11-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.13031v3 Vision-based 3D Semantic Scene Completion (SSC) has received growing attention due to its potential in autonomous driving. While most existing approaches follow an ego-centric paradigm by aggregating and diffusing features over the entire scene, they often overlook fine-grained object-level details, leading to semantic and geometric ambiguities, especially in complex environments. To address this limitation, we propose Ocean, an object-centric prediction framework that decomposes the scene into individual object instances to enable more accurate semantic occupancy prediction. Specifically, we first employ a lightweight segmentation model, MobileSAM, to extract instance masks from the input image. Then, we introduce a 3D Semantic Group Attention module that leverages linear attention to aggregate object-centric features in 3D space. To handle segmentation errors and missing instances, we further design a Global Similarity-Guided Attention module that leverages segmentation features for global interaction. Finally, we propose an Instance-aware Local Diffusion module that improves instance features through a generative process and subsequently refines the scene representation in the BEV space. Extensive experiments on the SemanticKITTI and SSCBench-KITTI360 benchmarks demonstrate that Ocean achieves state-of-the-art performance, with mIoU scores of 17.40 and 20.28, respectively. --- ### AA-Omniscience: Evaluating Cross-Domain Knowledge Reliability in Large Language Models Authors: Declan Jackson, William Keating, George Cameron, Micah Hill-Smith Published: 2025-11-17 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2511.13029v1 Existing language model evaluations primarily measure general capabilities, yet reliable use of these models across a range of domains demands factual accuracy and recognition of knowledge gaps. We introduce AA-Omniscience, a benchmark designed to measure both factual recall and knowledge calibration across 6,000 questions. Questions are derived from authoritative academic and industry sources, and cover 42 economically relevant topics within six different domains. The evaluation measures a model's Omniscience Index, a bounded metric (-100 to 100) measuring factual recall that jointly penalizes hallucinations and rewards abstention when uncertain, with 0 equating to a model that answers questions correctly as much as it does incorrectly. Among evaluated models, Claude 4.1 Opus attains the highest score (4.8), making it one of only three models to score above zero. These results reveal persistent factuality and calibration weaknesses across frontier models. Performance also varies by domain, with the models from three different research labs leading across the six domains. This performance variability suggests models should be chosen according to the demands of the use case rather than general performance for tasks where knowledge is important. --- ### Scaling Generative Verifiers For Natural Language Mathematical Proof Verification And Selection Authors: Sadegh Mahdavi, Branislav Kisacanin, Shubham Toshniwal, Wei Du, Ivan Moshkov, George Armstrong, Renjie Liao, Christos Thrampoulidis, Igor Gitman Published: 2025-11-17 Categories: cs.AI arXiv: https://arxiv.org/abs/2511.13027v1 Large language models have achieved remarkable success on final-answer mathematical problems, largely due to the ease of applying reinforcement learning with verifiable rewards. However, the reasoning underlying these solutions is often flawed. Advancing to rigorous proof-based mathematics requires reliable proof verification capabilities. We begin by analyzing multiple evaluation setups and show that focusing on a single benchmark can lead to brittle or misleading conclusions. To address this, we evaluate both proof-based and final-answer reasoning to obtain a more reliable measure of model performance. We then scale two major generative verification methods (GenSelect and LLM-as-a-Judge) to millions of tokens and identify their combination as the most effective framework for solution verification and selection. We further show that the choice of prompt for LLM-as-a-Judge significantly affects the model's performance, but reinforcement learning can reduce this sensitivity. However, despite improving proof-level metrics, reinforcement learning does not enhance final-answer precision, indicating that current models often reward stylistic or procedural correctness rather than mathematical validity. Our results establish practical guidelines for designing and evaluating scalable proof-verification and selection systems. --- ### REVISOR: Beyond Textual Reflection, Towards Multimodal Introspective Reasoning in Long-Form Video Understanding Authors: Jiaze Li, Hao Yin, Wenhui Tan, Jingyang Chen, Boshen Xu, Yuxun Qu, Yijing Chen, Jianzhong Ju, Zhenbo Luo, Jian Luan Published: 2025-11-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.13026v3 Self-reflection mechanisms that rely on purely text-based rethinking processes perform well in most multimodal tasks. However, when directly applied to long-form video understanding scenarios, they exhibit clear limitations. The fundamental reasons for this lie in two points: (1)long-form video understanding involves richer and more dynamic visual input, meaning rethinking only the text information is insufficient and necessitates a further rethinking process specifically targeting visual information; (2) purely text-based reflection mechanisms lack cross-modal interaction capabilities, preventing them from fully integrating visual information during reflection. Motivated by these insights, we propose REVISOR (REflective VIsual Segment Oriented Reasoning), a novel framework for tool-augmented multimodal reflection. REVISOR enables MLLMs to collaboratively construct introspective reflection processes across textual and visual modalities, significantly enhancing their reasoning capability for long-form video understanding. To ensure that REVISOR can learn to accurately review video segments highly relevant to the question during reinforcement learning, we designed the Dual Attribution Decoupled Reward (DADR) mechanism. Integrated into the GRPO training strategy, this mechanism enforces causal alignment between the model's reasoning and the selected video evidence. Notably, the REVISOR framework significantly enhances long-form video understanding capability of MLLMs without requiring supplementary supervised fine-tuning or external models, achieving impressive results on four benchmarks including VideoMME, LongVideoBench, MLVU, and LVBench. --- ### Reconstruction of Manifold Distances from Noisy Observations Authors: Charles Fefferman, Jonathan Marty, Kevin Ren Published: 2025-11-17 Categories: stat.ML, cs.LG, math.DG, math.PR arXiv: https://arxiv.org/abs/2511.13025v1 We consider the problem of reconstructing the intrinsic geometry of a manifold from noisy pairwise distance observations. Specifically, let $M$ denote a diameter 1 d-dimensional manifold and $μ$ a probability measure on $M$ that is mutually absolutely continuous with the volume measure. Suppose $X_1,\dots,X_N$ are i.i.d. samples of $μ$ and we observe noisy-distance random variables $d'(X_j, X_k)$ that are related to the true geodesic distances $d(X_j,X_k)$. With mild assumptions on the distributions and independence of the noisy distances, we develop a new framework for recovering all distances between points in a sufficiently dense subsample of $M$. Our framework improves on previous work which assumed i.i.d. additive noise with known moments. Our method is based on a new way to estimate $L_2$-norms of certain expectation-functions $f_x(y)=\mathbb{E}d'(x,y)$ and use them to build robust clusters centered at points of our sample. Using a new geometric argument, we establish that, under mild geometric assumptions--bounded curvature and positive injectivity radius--these clusters allow one to recover the true distances between points in the sample up to an additive error of $O(\varepsilon \log \varepsilon^{-1})$. We develop two distinct algorithms for producing these clusters. The first achieves a sample complexity $N \asymp \varepsilon^{-2d-2}\log(1/\varepsilon)$ and runtime $o(N^3)$. The second introduces novel geometric ideas that warrant further investigation. In the presence of missing observations, we show that a quantitative lower bound on sampling probabilities suffices to modify the cluster construction in the first algorithm and extend all recovery guarantees. Our main technical result also elucidates which properties of a manifold are necessary for the distance recovery, which suggests further extension of our techniques to a broader class of metric probability spaces. --- ### SLMQuant:Benchmarking Small Language Model Quantization for Practical Deployment Authors: Jiacheng Wang, Yejun Zeng, Jinyang Guo, Yuqing Ma, Aishan Liu, Xianglong Liu Published: 2025-11-17 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2511.13023v1 Despite the growing interest in Small Language Models (SLMs) as resource-efficient alternatives to Large Language Models (LLMs), their deployment on edge devices remains challenging due to unresolved efficiency gaps in model compression. While quantization has proven effective for LLMs, its applicability to SLMs is significantly underexplored, with critical questions about differing quantization bottlenecks and efficiency profiles. This paper introduces SLMQuant, the first systematic benchmark for evaluating LLM compression techniques when applied to SLMs. Through comprehensive multi-track evaluations across diverse architectures and tasks, we analyze how state-of-the-art quantization methods perform on SLMs. Our findings reveal fundamental disparities between SLMs and LLMs in quantization sensitivity, demonstrating that direct transfer of LLM-optimized techniques leads to suboptimal results due to SLMs' unique architectural characteristics and training dynamics. We identify key factors governing effective SLM quantization and propose actionable design principles for SLM-tailored compression. SLMQuant establishes a foundational framework for advancing efficient SLM deployment on low-end devices in edge applications, and provides critical insights for deploying lightweight language models in resource-constrained scenarios. --- ### Learning Time-Scale Invariant Population-Level Neural Representations Authors: Eshani Patel, Yisong Yue, Geeling Chau Published: 2025-11-17 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.13022v1 General-purpose foundation models for neural time series can help accelerate neuroscientific discoveries and enable applications such as brain computer interfaces (BCIs). A key component in scaling these models is population-level representation learning, which leverages information across channels to capture spatial as well as temporal structure. Population-level approaches have recently shown that such representations can be both efficient to learn on top of pretrained temporal encoders and produce useful representations for decoding a variety of downstream tasks. However, these models remain sensitive to mismatches in preprocessing, particularly on time-scales, between pretraining and downstream settings. We systematically examine how time-scale mismatches affects generalization and find that existing representations lack invariance. To address this, we introduce Time-scale Augmented Pretraining (TSAP), which consistently improves robustness to different time-scales across decoding tasks and builds invariance in the representation space. These results highlight handling preprocessing diversity as a key step toward building generalizable neural foundation models. --- ### PragWorld: A Benchmark Evaluating LLMs' Local World Model under Minimal Linguistic Alterations and Conversational Dynamics Authors: Sachin Vashistha, Aryan Bibhuti, Atharva Naik, Martin Tutek, Somak Aditya Published: 2025-11-17 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2511.13021v1 Real-world conversations are rich with pragmatic elements, such as entity mentions, references, and implicatures. Understanding such nuances is a requirement for successful natural communication, and often requires building a local world model which encodes such elements and captures the dynamics of their evolving states. However, it is not well-understood whether language models (LMs) construct or maintain a robust implicit representation of conversations. In this work, we evaluate the ability of LMs to encode and update their internal world model in dyadic conversations and test their malleability under linguistic alterations. To facilitate this, we apply seven minimal linguistic alterations to conversations sourced from popular datasets and construct two benchmarks comprising yes-no questions. We evaluate a wide range of open and closed source LMs and observe that they struggle to maintain robust accuracy. Our analysis unveils that LMs struggle to memorize crucial details, such as tracking entities under linguistic alterations to conversations. We then propose a dual-perspective interpretability framework which identifies transformer layers that are useful or harmful and highlights linguistic alterations most influenced by harmful layers, typically due to encoding spurious signals or relying on shortcuts. Inspired by these insights, we propose two layer-regularization based fine-tuning strategies that suppress the effect of the harmful layers. --- ### PHASE: Physiology-Aware Hyperspectral Reconstruction via Object-to-Human Domain Adaptation Authors: Yufei Wen, Shuxing Zhong, Jingdan Kang, Yuting Zhang, Jintai Chen, Kaishun Wu Published: 2025-11-17 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2511.13020v2 Although hyperspectral imaging offers unparalleled non-invasive physiological insight, its bulky hardware, slow acquisition, and regulatory burden severely limit its clinical availability. A natural workaround is to reconstruct hyperspectral information from ubiquitous RGB or CASSI measurements. However, existing paradigms, developed for object-centric scenes, rely on reflectance-based feature alignment, assuming that spectral similarity preserves semantic meaning. This assumption breaks down in physiological imaging, where visually similar RGB responses may arise from distinct and entangled physiological states. This mismatch motivates a shift from reflectance alignment to physiology-aware representation learning, grounded in shared light-matter interaction principles -- a shift that introduces fundamental challenges from cross-channel semantic shifts (C1) and irreversible information loss in RGB-based acquisition (C2). We therefore design PHASE, a physiology-aware hyperspectral reconstruction paradigm that fundamentally redefines object-to-human transfer by disentangling cross-channel physiological semantics via Physiological Channel Reinterpretation and restricting reconstruction to physiologically plausible solutions through Physiologically Constrained Alignment. Under two source-to-target transfer protocols, PHASE consistently outperforms state-of-the-art methods by up to +2.20 SSIM and -3.06 in SAM with merely 1.5% labeled supervision. --- ### MeanFlow Transformers with Representation Autoencoders Authors: Zheyuan Hu, Chieh-Hsin Lai, Ge Wu, Yuki Mitsufuji, Stefano Ermon Published: 2025-11-17 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2511.13019v1 MeanFlow (MF) is a diffusion-motivated generative model that enables efficient few-step generation by learning long jumps directly from noise to data. In practice, it is often used as a latent MF by leveraging the pre-trained Stable Diffusion variational autoencoder (SD-VAE) for high-dimensional data modeling. However, MF training remains computationally demanding and is often unstable. During inference, the SD-VAE decoder dominates the generation cost, and MF depends on complex guidance hyperparameters for class-conditional generation. In this work, we develop an efficient training and sampling scheme for MF in the latent space of a Representation Autoencoder (RAE), where a pre-trained vision encoder (e.g., DINO) provides semantically rich latents paired with a lightweight decoder. We observe that naive MF training in the RAE latent space suffers from severe gradient explosion. To stabilize and accelerate training, we adopt Consistency Mid-Training for trajectory-aware initialization and use a two-stage scheme: distillation from a pre-trained flow matching teacher to speed convergence and reduce variance, followed by an optional bootstrapping stage with a one-point velocity estimator to further reduce deviation from the oracle mean flow. This design removes the need for guidance, simplifies training configurations, and reduces computation in both training and sampling. Empirically, our method achieves a 1-step FID of 2.03, outperforming vanilla MF's 3.43, while reducing sampling GFLOPS by 38% and total training cost by 83% on ImageNet 256. We further scale our approach to ImageNet 512, achieving a competitive 1-step FID of 3.23 with the lowest GFLOPS among all baselines. Code is available at https://github.com/sony/mf-rae. --- ### The Final-Stage Bottleneck: A Systematic Dissection of the R-Learner for Network Causal Inference Authors: S Sairam, Sara Girdhar, Shivam Soni Published: 2025-11-17 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.13018v3 The R-Learner is a powerful, theoretically-grounded framework for estimating heterogeneous treatment effects, prized for its robustness to nuisance model errors. However, its application to network data, where causal heterogeneity is often graph-dependent, presents a critical challenge to its core assumption of a well-specified final-stage model. In this paper, we conduct a large-scale empirical study to systematically dissect the R-Learner framework on graphs. We provide the first rigorous evidence that the primary driver of performance is the inductive bias of the final-stage CATE estimator, an effect that dominates the choice of nuisance models. Our central finding is the quantification of a catastrophic "representation bottleneck": we prove with overwhelming statistical significance (p < 0.001) that R-Learners with a graph-blind final stage fail completely (MSE > 4.0), even when paired with powerful GNN nuisance models. Conversely, our proposed end-to-end Graph R-Learner succeeds and significantly outperforms a strong, non-DML GNN T-Learner baseline. Furthermore, we identify and provide a mechanistic explanation for a subtle, topology-dependent "nuisance bottleneck," linking it to GNN over-squashing via a targeted "Hub-Periphery Trade-off" analysis. Our findings are validated across diverse synthetic and semi-synthetic benchmarks. We release our code as a reproducible benchmark to facilitate future research on this critical "final-stage bottleneck." --- ### The Good, The Bad, and The Hybrid: A Reward Structure Showdown in Reasoning Models Training Authors: Subramanyam Sahoo Published: 2025-11-17 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.13016v1 Reward design is central to reinforcement learning from human feedback (RLHF) and alignment research. In this work, we propose a unified framework to study hard, continuous, and hybrid reward structures for fine-tuning large language models (LLMs) on mathematical reasoning tasks. Using Qwen3-4B with LoRA fine-tuning on the GSM8K dataset, we formalize and empirically evaluate reward formulations that incorporate correctness, perplexity, reasoning quality, and consistency. We introduce an adaptive hybrid reward scheduler that transitions between discrete and continuous signals, balancing exploration and stability. Our results show that hybrid reward structures improve convergence speed and training stability over purely hard or continuous approaches, offering insights for alignment via adaptive reward modeling. --- ### Geometry Meets Light: Leveraging Geometric Priors for Universal Photometric Stereo under Limited Multi-Illumination Cues Authors: King-Man Tam, Satoshi Ikehata, Yuta Asano, Zhaoyi An, Rei Kawakami Published: 2025-11-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.13015v2 Universal Photometric Stereo is a promising approach for recovering surface normals without strict lighting assumptions. However, it struggles when multi-illumination cues are unreliable, such as under biased lighting or in shadows or self-occluded regions of complex in-the-wild scenes. We propose GeoUniPS, a universal photometric stereo network that integrates synthetic supervision with high-level geometric priors from large-scale 3D reconstruction models pretrained on massive in-the-wild data. Our key insight is that these 3D reconstruction models serve as visual-geometry foundation models, inherently encoding rich geometric knowledge of real scenes. To leverage this, we design a Light-Geometry Dual-Branch Encoder that extracts both multi-illumination cues and geometric priors from the frozen 3D reconstruction model. We also address the limitations of the conventional orthographic projection assumption by introducing the PS-Perp dataset with realistic perspective projection to enable learning of spatially varying view directions. Extensive experiments demonstrate that GeoUniPS delivers state-of-the-arts performance across multiple datasets, both quantitatively and qualitatively, especially in the complex in-the-wild scenes. --- ### You Only Look Omni Gradient Backpropagation for Moving Infrared Small Target Detection Authors: Guoyi Zhang, Guangsheng Xu, Siyang Chen, Han Wang, Xiaohu Zhang Published: 2025-11-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.13013v2 Moving infrared small target detection is a key component of infrared search and tracking systems, yet it remains extremely challenging due to low signal-to-clutter ratios, severe target-background imbalance, and weak discriminative features. Existing deep learning methods primarily focus on spatio-temporal feature aggregation, but their gains are limited, revealing that the fundamental bottleneck lies in ambiguous per-frame feature representations rather than spatio-temporal modeling itself. Motivated by this insight, we propose BP-FPN, a backpropagation-driven feature pyramid architecture that fundamentally rethinks feature learning for small target. BP-FPN introduces Gradient-Isolated Low-Level Shortcut (GILS) to efficiently incorporate fine-grained target details without inducing shortcut learning, and Directional Gradient Regularization (DGR) to enforce hierarchical feature consistency during backpropagation. The design is theoretically grounded, introduces negligible computational overhead, and can be seamlessly integrated into existing frameworks. Extensive experiments on multiple public datasets show that BP-FPN consistently establishes new state-of-the-art performance. To the best of our knowledge, it is the first FPN designed for this task entirely from the backpropagation perspective. --- ### Beyond Darkness: Thermal-Supervised 3D Gaussian Splatting for Low-Light Novel View Synthesis Authors: Qingsen Ma, Chen Zou, Dianyun Wang, Jia Wang, Liuyu Xiang, Zhaofeng He Published: 2025-11-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.13011v1 Under extremely low-light conditions, novel view synthesis (NVS) faces severe degradation in terms of geometry, color consistency, and radiometric stability. Standard 3D Gaussian Splatting (3DGS) pipelines fail when applied directly to underexposed inputs, as independent enhancement across views causes illumination inconsistencies and geometric distortion. To address this, we present DTGS, a unified framework that tightly couples Retinex-inspired illumination decomposition with thermal-guided 3D Gaussian Splatting for illumination-invariant reconstruction. Unlike prior approaches that treat enhancement as a pre-processing step, DTGS performs joint optimization across enhancement, geometry, and thermal supervision through a cyclic enhancement-reconstruction mechanism. A thermal supervisory branch stabilizes both color restoration and geometry learning by dynamically balancing enhancement, structural, and thermal losses. Moreover, a Retinex-based decomposition module embedded within the 3DGS loop provides physically interpretable reflectance-illumination separation, ensuring consistent color and texture across viewpoints. To evaluate our method, we construct RGBT-LOW, a new multi-view low-light thermal dataset capturing severe illumination degradation. Extensive experiments show that DTGS significantly outperforms existing low-light enhancement and 3D reconstruction baselines, achieving superior radiometric consistency, geometric fidelity, and color stability under extreme illumination. --- ### Are Graph Transformers Necessary? Efficient Long-Range Message Passing with Fractal Nodes in MPNNs Authors: Jeongwhan Choi, Seungjun Park, Sumin Park, Sung-Bae Cho, Noseong Park Published: 2025-11-17 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2511.13010v1 Graph Neural Networks (GNNs) have emerged as powerful tools for learning on graph-structured data, but often struggle to balance local and global information. While graph Transformers aim to address this by enabling long-range interactions, they often overlook the inherent locality and efficiency of Message Passing Neural Networks (MPNNs). We propose a new concept called fractal nodes, inspired by the fractal structure observed in real-world networks. Our approach is based on the intuition that graph partitioning naturally induces fractal structure, where subgraphs often reflect the connectivity patterns of the full graph. Fractal nodes are designed to coexist with the original nodes and adaptively aggregate subgraph-level feature representations, thereby enforcing feature similarity within each subgraph. We show that fractal nodes alleviate the over-squashing problem by providing direct shortcut connections that enable long-range propagation of subgraph-level representations. Experiment results show that our method improves the expressive power of MPNNs and achieves comparable or better performance to graph Transformers while maintaining the computational efficiency of MPNN by improving the long-range dependencies of MPNN. --- ### TR-Gaussians: High-fidelity Real-time Rendering of Planar Transmission and Reflection with 3D Gaussian Splatting Authors: Yong Liu, Keyang Ye, Tianjia Shao, Kun Zhou Published: 2025-11-17 Categories: cs.GR, cs.CV arXiv: https://arxiv.org/abs/2511.13009v1 We propose Transmission-Reflection Gaussians (TR-Gaussians), a novel 3D-Gaussian-based representation for high-fidelity rendering of planar transmission and reflection, which are ubiquitous in indoor scenes. Our method combines 3D Gaussians with learnable reflection planes that explicitly model the glass planes with view-dependent reflectance strengths. Real scenes and transmission components are modeled by 3D Gaussians and the reflection components are modeled by the mirrored Gaussians with respect to the reflection plane. The transmission and reflection components are blended according to a Fresnel-based, view-dependent weighting scheme, allowing for faithful synthesis of complex appearance effects under varying viewpoints. To effectively optimize TR-Gaussians, we develop a multi-stage optimization framework incorporating color and geometry constraints and an opacity perturbation mechanism. Experiments on different datasets demonstrate that TR-Gaussians achieve real-time, high-fidelity novel view synthesis in scenes with planar transmission and reflection, and outperform state-of-the-art approaches both quantitatively and qualitatively. --- ### GEM: Generative Entropy-Guided Preference Modeling for Few-shot Alignment of LLMs Authors: Yiyang Zhao, Huiyu Bai, Xuejiao Zhao Published: 2025-11-17 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2511.13007v1 Alignment of large language models (LLMs) with human preferences typically relies on supervised reward models or external judges that demand abundant annotations. However, in fields that rely on professional knowledge, such as medicine and law, such large-scale preference labels are often unachievable. In this paper, we propose a generative entropy-guided preference modeling approach named GEM for LLMs aligment at low-resource and domain-specific scenarios. Instead of training a discriminative reward model on preference data, we directly train the LLM to internalize a closed-loop optimization architecture that can extract and exploit the multi-dimensional, fine-grained cognitive signals implicit in human preferences. Specifically, our Cognitive Filtering module, based on entropy theory in decision making, first leverages Chain-of-Thought (CoT) prompting to generate diverse candidate reasoning chains (CoTs) from preference data. Subsequently, it introduces a token scoring mechanism to rank and weight the sampled CoTs, boosting the importance of high-confidence answers and strategically high-entropy tokens. Building on these filtered preferences, we fine-tune the LLM using a novel self-evaluated group advantage algorithm, SEGA, which effectively aggregates group-level cognitive signals and transforms the entropy-based scores into implicit rewards for policy optimization. In these ways, GEM empowers the LLM to rely on its own judgments and establishes an entropy-guided closed-loop cognitive optimization framework, enabling highly efficient few-shot alignment of LLMs. Experiments on general benchmarks and domain-specific tasks (such as mathematical reasoning and medical dialogues) demonstrate that our GEM achieves significant improvements with few-shot preference data. --- ### SAGE: Spuriousness-Aware Guided Prompt Exploration for Mitigating Multimodal Bias Authors: Wenqian Ye, Di Wang, Guangtao Zheng, Bohan Liu, Aidong Zhang Published: 2025-11-17 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2511.13005v1 Large vision-language models, such as CLIP, have shown strong zero-shot classification performance by aligning images and text in a shared embedding space. However, CLIP models often develop multimodal spurious biases, which is the undesirable tendency to rely on spurious features. For example, CLIP may infer object types in images based on frequently co-occurring backgrounds rather than the object's core features. This bias significantly impairs the robustness of pre-trained CLIP models on out-of-distribution data, where such cross-modal associations no longer hold. Existing methods for mitigating multimodal spurious bias typically require fine-tuning on downstream data or prior knowledge of the bias, which undermines the out-of-the-box usability of CLIP. In this paper, we first theoretically analyze the impact of multimodal spurious bias in zero-shot classification. Based on this insight, we propose Spuriousness-Aware Guided Exploration (SAGE), a simple and effective method that mitigates spurious bias through guided prompt selection. SAGE requires no training, fine-tuning, or external annotations. It explores a space of prompt templates and selects the prompts that induce the largest semantic separation between classes, thereby improving worst-group robustness. Extensive experiments on four real-world benchmark datasets and five popular backbone models demonstrate that SAGE consistently improves zero-shot performance and generalization, outperforming previous zero-shot approaches without any external knowledge or model updates. --- ### Infinite-Story: A Training-Free Consistent Text-to-Image Generation Authors: Jihun Park, Kyoungmin Lee, Jongmin Gim, Hyeonseo Jo, Minseok Oh, Wonhyeok Choi, Kyumin Hwang, Jaeyeul Kim, Minwoo Choi, Sunghoon Im Published: 2025-11-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.13002v1 We present Infinite-Story, a training-free framework for consistent text-to-image (T2I) generation tailored for multi-prompt storytelling scenarios. Built upon a scale-wise autoregressive model, our method addresses two key challenges in consistent T2I generation: identity inconsistency and style inconsistency. To overcome these issues, we introduce three complementary techniques: Identity Prompt Replacement, which mitigates context bias in text encoders to align identity attributes across prompts; and a unified attention guidance mechanism comprising Adaptive Style Injection and Synchronized Guidance Adaptation, which jointly enforce global style and identity appearance consistency while preserving prompt fidelity. Unlike prior diffusion-based approaches that require fine-tuning or suffer from slow inference, Infinite-Story operates entirely at test time, delivering high identity and style consistency across diverse prompts. Extensive experiments demonstrate that our method achieves state-of-the-art generation performance, while offering over 6X faster inference (1.72 seconds per image) than the existing fastest consistent T2I models, highlighting its effectiveness and practicality for real-world visual storytelling. --- ### Medal S: Spatio-Textual Prompt Model for Medical Segmentation Authors: Pengcheng Shi, Jiawei Chen, Jiaqi Liu, Xinglin Zhang, Tao Chen, Lei Li Published: 2025-11-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.13001v1 We introduce Medal S, a medical segmentation foundation model that supports native-resolution spatial and textual prompts within an end-to-end trainable framework. Unlike text-only methods lacking spatial awareness, Medal S achieves channel-wise alignment between volumetric prompts and text embeddings, mitigating inaccuracies from resolution mismatches. By preserving full 3D context, it efficiently processes multiple native-resolution masks in parallel, enhancing multi-class segmentation performance. A lightweight 3D convolutional module enables precise voxel-space refinement guided by both prompt types, supporting up to 243 classes across CT, MRI, PET, ultrasound, and microscopy modalities in the BiomedSegFM dataset. Medal S offers two prompting modes: a text-only mode, where model predictions serve as spatial prompts for self-refinement without human input, and a hybrid mode, incorporating manual annotations for enhanced flexibility. For 24-class segmentation, parallel spatial prompting reduces inference time by more than 90% compared to sequential prompting. We propose dynamic resampling to address target-patch ratio imbalance, extending SAT and nnU-Net for data augmentation. Furthermore, we develop optimized text preprocessing, a two-stage inference strategy, and post-processing techniques to improve memory efficiency, precision, and inference speed. On the five-modality average on the validation set, Medal S outperforms SAT with a DSC of 75.44 (vs. 69.83), NSD of 77.34 (vs. 71.06), F1 of 38.24 (vs. 24.88), and DSC TP of 65.46 (vs. 46.97). Medal S achieves excellent performance by harmonizing spatial precision with semantic textual guidance, demonstrating superior efficiency and accuracy in multi-class medical segmentation tasks compared to sequential prompt-based approaches. Medal S will be publicly available at https://github.com/yinghemedical/Medal-S. --- ### Scalable Vision-Guided Crop Yield Estimation Authors: Harrison H. Li, Medhanie Irgau, Nabil Janmohamed, Karen Solveig Rieckmann, David B. Lobell Published: 2025-11-17 Categories: stat.AP, cs.CV arXiv: https://arxiv.org/abs/2511.12999v1 Precise estimation and uncertainty quantification for average crop yields are critical for agricultural monitoring and decision making. Existing data collection methods, such as crop cuts in randomly sampled fields at harvest time, are relatively time-consuming. Thus, we propose an approach based on prediction-powered inference (PPI) to supplement these crop cuts with less time-consuming field photos. After training a computer vision model to predict the ground truth crop cut yields from the photos, we learn a ``control function" that recalibrates these predictions with the spatial coordinates of each field. This enables fields with photos but not crop cuts to be leveraged to improve the precision of zone-wide average yield estimates. Our control function is learned by training on a dataset of nearly 20,000 real crop cuts and photos of rice and maize fields in sub-Saharan Africa. To improve precision, we pool training observations across different zones within the same first-level subdivision of each country. Our final PPI-based point estimates of the average yield are provably asymptotically unbiased and cannot increase the asymptotic variance beyond that of the natural baseline estimator -- the sample average of the crop cuts -- as the number of fields grows. We also propose a novel bias-corrected and accelerated (BCa) bootstrap to construct accompanying confidence intervals. Even in zones with as few as 20 fields, the point estimates show significant empirical improvement over the baseline, increasing the effective sample size by as much as 73% for rice and by 12-23% for maize. The confidence intervals are accordingly shorter at minimal cost to empirical finite-sample coverage. This demonstrates the potential for relatively low-cost images to make area-based crop insurance more affordable and thus spur investment into sustainable agricultural practices. --- ### PerTouch: VLM-Driven Agent for Personalized and Semantic Image Retouching Authors: Zewei Chang, Zheng-Peng Duan, Jianxing Zhang, Chun-Le Guo, Siyu Liu, Hyungju Chun, Hyunhee Park, Zikun Liu, Chongyi Li Published: 2025-11-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.12998v3 Image retouching aims to enhance visual quality while aligning with users' personalized aesthetic preferences. To address the challenge of balancing controllability and subjectivity, we propose a unified diffusion-based image retouching framework called PerTouch. Our method supports semantic-level image retouching while maintaining global aesthetics. Using parameter maps containing attribute values in specific semantic regions as input, PerTouch constructs an explicit parameter-to-image mapping for fine-grained image retouching. To improve semantic boundary perception, we introduce semantic replacement and parameter perturbation mechanisms during training. To connect natural language instructions with visual control, we develop a VLM-driven agent to handle both strong and weak user instructions. Equipped with mechanisms of feedback-driven rethinking and scene-aware memory, PerTouch better aligns with user intent and captures long-term preferences. Extensive experiments demonstrate each component's effectiveness and the superior performance of PerTouch in personalized image retouching. Code Pages: https://github.com/Auroral703/PerTouch. --- ### WebCoach: Self-Evolving Web Agents with Cross-Session Memory Guidance Authors: Genglin Liu, Shijie Geng, Sha Li, Hejie Cui, Sarah Zhang, Xin Liu, Tianyi Liu Published: 2025-11-17 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2511.12997v2 Multimodal LLM-powered agents have recently demonstrated impressive capabilities in web navigation, enabling agents to complete complex browsing tasks across diverse domains. However, current agents struggle with repetitive errors and lack the ability to learn from past experiences across sessions, limiting their long-term robustness and sample efficiency. We introduce WebCoach, a model-agnostic self-evolving framework that equips web browsing agents with persistent cross-session memory, enabling improved long-term planning, reflection, and continual learning without retraining. WebCoach consists of three key components: (1) a WebCondenser, which standardizes raw navigation logs into concise summaries; (2) an External Memory Store, which organizes complete trajectories as episodic experiences; and (3) a Coach, which retrieves relevant experiences based on similarity and recency, and decides whether to inject task-specific advice into the agent via runtime hooks. This design empowers web agents to access long-term memory beyond their native context window, improving robustness in complex browsing tasks. Moreover, WebCoach achieves self-evolution by continuously curating episodic memory from new navigation trajectories, enabling agents to improve over time without retraining. Evaluations on the WebVoyager benchmark demonstrate that WebCoach consistently improves the performance of browser-use agents across three different LLM backbones. With a 38B model, it increases task success rates from 47% to 61% while reducing or maintaining the average number of steps. Notably, smaller base models with WebCoach achieve performance comparable to the same web agent using GPT-4o. --- ### Revealing the dynamic responses of Pb under shock loading based on DFT-accuracy machine learning potential Authors: Enze Hou, Xiaoyang Wang, Han Wang Published: 2025-11-17 Categories: cond-mat.mtrl-sci, cs.LG arXiv: https://arxiv.org/abs/2511.12995v1 Lead (Pb) is a typical low-melting-point ductile metal and serves as an important model material in the study of dynamic responses. Under shock-wave loading, its dynamic mechanical behavior comprises two key phenomena: plastic deformation and shock induced phase transitions. The underlying mechanisms of these processes are still poorly understood. Revealing these mechanisms remains challenging for experimental approaches. Non-equilibrium molecular dynamics (NEMD) simulations are an alternative theoretical tool for studying dynamic responses, as they capture atomic-scale mechanisms such as defect evolution and deformation pathways. However, due to the limited accuracy of empirical interatomic potentials, the reliability of previous NEMD studies is questioned. Using our newly developed machine learning potential for Pb-Sn alloys, we revisited the microstructure evolution in response to shock loading under various shock orientations. The results reveal that shock loading along the (001) orientation of Pb exhibits a fast, reversible, and massive phase transition and stacking fault evolution. The behavior of Pb differs from previous studies by the absence of twinning during plastic deformation. Loading along the (011) orientation leads to slow, irreversible plastic deformation, and a localized FCC-BCC phase transition in the Pitsch orientation relationship. This study provides crucial theoretical insights into the dynamic mechanical response of Pb, offering a theoretical input for understanding the microstructure-performance relationship under extreme conditions. --- ### Semantic Prioritization in Visual Counterfactual Explanations with Weighted Segmentation and Auto-Adaptive Region Selection Authors: Lintong Zhang, Kang Yin, Seong-Whan Lee Published: 2025-11-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.12992v1 In the domain of non-generative visual counterfactual explanations (CE), traditional techniques frequently involve the substitution of sections within a query image with corresponding sections from distractor images. Such methods have historically overlooked the semantic relevance of the replacement regions to the target object, thereby impairing the model's interpretability and hindering the editing workflow. Addressing these challenges, the present study introduces an innovative methodology named as Weighted Semantic Map with Auto-adaptive Candidate Editing Network (WSAE-Net). Characterized by two significant advancements: the determination of an weighted semantic map and the auto-adaptive candidate editing sequence. First, the generation of the weighted semantic map is designed to maximize the reduction of non-semantic feature units that need to be computed, thereby optimizing computational efficiency. Second, the auto-adaptive candidate editing sequences are designed to determine the optimal computational order among the feature units to be processed, thereby ensuring the efficient generation of counterfactuals while maintaining the semantic relevance of the replacement feature units to the target object. Through comprehensive experimentation, our methodology demonstrates superior performance, contributing to a more lucid and in-depth understanding of visual counterfactual explanations. --- ### Fine-Tuned LLMs Know They Don't Know: A Parameter-Efficient Approach to Recovering Honesty Authors: Zeyu Shi, Ziming Wang, Tianyu Chen, Shiqi Gao, Haoyi Zhou, Qingyun Sun, Jianxin Li Published: 2025-11-17 Categories: cs.CL arXiv: https://arxiv.org/abs/2511.12991v1 The honesty of Large Language Models (LLMs) is increasingly important for safe deployment in high-stakes domains. However, this crucial trait is severely undermined by supervised fine-tuning (SFT), a common technique for model specialization. Existing recovery methods rely on data-intensive global parameter adjustments, implicitly assuming that SFT deeply corrupts the models' ability to recognize their knowledge boundaries. However, we observe that fine-tuned LLMs still preserve this ability; what is damaged is their capacity to faithfully express that awareness. Building on this, we propose Honesty-Critical Neurons Restoration (HCNR) to surgically repair this suppressed capacity. HCNR identifies and restores key expression-governing neurons to their pre-trained state while harmonizing them with task-oriented neurons via Hessian-guided compensation. Experiments on four QA tasks and five LLM families demonstrate that HCNR effectively recovers 33.25% of the compromised honesty while achieving at least 2.23x speedup with over 10x less data compared to baseline methods, offering a practical solution for trustworthy LLM deployment. ---