# Research Papers — 2025-10 · bundle page 152 of 217 > Full-text markdown of papers #7551–7600 of 10843 published in 2025-10, newest first. AI-readable mirrors of the full 10843-paper 2025-10 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2025-10/page/152 [← Previous bundle](https://aipod.dev/papers/archive/2025-10/page/151.md) [Next bundle →](https://aipod.dev/papers/archive/2025-10/page/153.md) ### RAG4Tickets: AI-Powered Ticket Resolution via Retrieval-Augmented Generation on JIRA and GitHub Data Authors: Mohammad Baqar Published: 2025-10-09 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2510.08667v3 Modern software teams frequently encounter delays in resolving recurring or related issues due to fragmented knowledge scattered across JIRA tickets, developer discussions, and GitHub pull requests (PRs). To address this challenge, we propose a Retrieval-Augmented Generation (RAG) framework that integrates Sentence-Transformers for semantic embeddings with FAISS-based vector search to deliver context-aware ticket resolution recommendations. The approach embeds historical JIRA tickets, user comments, and linked PR metadata to retrieve semantically similar past cases, which are then synthesized by a Large Language Model (LLM) into grounded and explainable resolution suggestions. The framework contributes a unified pipeline linking JIRA and GitHub data, an embedding and FAISS indexing strategy for heterogeneous software artifacts, and a resolution generation module guided by retrieved evidence. Experimental evaluation using precision, recall, resolution time reduction, and developer acceptance metrics shows that the proposed system significantly improves resolution accuracy, fix quality, and knowledge reuse in modern DevOps environments. --- ### dInfer: An Efficient Inference Framework for Diffusion Language Models Authors: Yuxin Ma, Lun Du, Lanning Wei, Kun Chen, Qian Xu, Kangyu Wang, Guofeng Feng, Guoshan Lu, Lin Liu, Xiaojing Qi, Xinyuan Zhang, Zhen Tao et al. Published: 2025-10-09 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2510.08666v3 Diffusion-based large language models (dLLMs) have emerged as a promising alternative to autoregressive (AR) LLMs, leveraging denoising-based generation to enable inherent parallelism. Even more and more open-sourced dLLM models emerge, yet their widespread adoption remains constrained by the lack of a standardized and efficient inference framework. We present dInfer, an efficient and extensible framework for dLLM inference. dInfer decomposes the inference pipeline into four modular components--model, diffusion iteration manager, decoding strategy, and KV-cache manager--and integrates novel algorithms for each component alongside system-level optimizations. Through this combination of algorithmic innovations and system enhancements, dInfer achieves substantial efficiency gains without compromising output quality on LLaDA-MoE. At batch size 1, it surpasses 1,100 tokens per second on HumanEval and averages over 800 tokens per second across six benchmarks on $8\times$ H800 GPUs. Compared to prior systems, dInfer delivers a $10\times$ speedup over Fast-dLLM while maintaining similar model performance. Even compared to the AR model (with a comparable number of activation parameters and performance) QWen2.5-3B, which is highly optimized with the latest vLLM inference engine, dInfer still delivers a $2$-$3\times$ speedup. The implementation of dInfer is open-sourced at https://github.com/inclusionAI/dInfer. --- ### RA-Gen: A Controllable Code Generation Framework Using ReAct for Multi-Agent Task Execution Authors: Aofan Liu, Haoxuan Li, Bin Wang, Ao Yang, Hui Li Published: 2025-10-09 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2510.08665v1 Code generation models based on large language models (LLMs) have gained wide adoption, but challenges remain in ensuring safety, accuracy, and controllability, especially for complex tasks. Existing methods often lack dynamic integration of external tools, transparent reasoning, and user control over safety. To address these issues, we propose a controllable code generation framework utilizing the ReAct paradigm for multi-agent task execution. This framework is a multi-agent system designed to enable efficient, precise, and interpretable code generation through dynamic interactions between LLMs and external resources. The framework adopts a collaborative architecture comprising four specialized agents: a Planner for task decomposition, a Searcher that leverages the ReAct framework for reasoning and tool integration, a CodeGen agent for accurate code generation, and an Extractor for structured data retrieval. The ReAct-based Searcher alternates between generating reasoning traces and executing actions, facilitating seamless integration of internal knowledge with external tools (such as search engines) to enhance accuracy and user control. Experimental results show the framework's effectiveness across multiple languages, achieving a 94.8% security rate on the SVEN dataset with CodeQL, outperforming existing approaches. Its transparent reasoning process fosters user trust and improves controllability. --- ### Faver: Boosting LLM-based RTL Generation with Function Abstracted Verifiable Middleware Authors: Jianan Mu, Mingyu Shi, Yining Wang, Tianmeng Yang, Bin Sun, Xing Hu, Jing Ye, Huawei Li Published: 2025-10-09 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2510.08664v1 LLM-based RTL generation is an interesting research direction, as it holds the potential to liberate the least automated stage in the current chip design. However, due to the substantial semantic gap between high-level specifications and RTL, coupled with limited training data, existing models struggle with generation accuracy. Drawing on human experience, design with verification helps improving accuracy. However, as the RTL testbench data are even more scarce, it is not friendly for LLMs. Although LLMs excel at higher-level languages like Python/C, they have a huge semantic gap from RTL. When implementing the same functionality, Python/C code and hardware code differ significantly in the spatiotemporal granularity, requiring the LLM not only to consider high-level functional semantics but also to ensure the low-level details align with the circuit code. It is not an easy task. In this paper, we propose a function abstracted verifiable middleware (Faver) that streamlines RTL verification in LLM-based workflows. By mixing LLM-friendly code structures with a rule-based template, Faver decouples the details of circuit verification, allowing the LLM to focus on the functionality itself. In our experiments on the SFT model and open-source models, Faver improved the model's generation accuracy by up to 14%. --- ### Augmenting Rating-Scale Measures with Text-Derived Items Using the Information-Determined Scoring (IDS) Framework Authors: Joe Watson, Ivan O'Connor, Chia-Wen Chen, Luning Sun, Fang Luo, David Stillwell Published: 2025-10-09 Categories: cs.CL, cs.AI, cs.CY arXiv: https://arxiv.org/abs/2510.08663v3 Psychological assessments commonly rely on rating-scale items, which require respondents to condense complex experiences into predefined categories. Although rich, unstructured text is often captured alongside these scales, it rarely contributes to measuring the target trait because it lacks direct mapping to the latent scale. We introduce the Information-Determined Scoring (IDS) framework, where large language models (LLMs) score free-text responses with simple prompts to generate candidate items that are co-calibrated with a baseline scale and retained based on the psychometric information they provide about the target trait. This marks a conceptual departure from traditional automated text scoring by prioritising information gain over fidelity to expert rubrics or human-annotated data. Using depression as a case study, we developed and tested the method in upper-secondary students (n = 693) and a matched synthetic dataset (n = 3,000). Across held-out test sets, augmenting a 19-item rating-scale measure with LLM-derived items yielded significant improvements in measurement precision and accuracy, and stronger convergent validity with an external suicidality measure throughout the adaptive test. In adaptive simulations, LLM-derived items contributed information equivalent to adding up to 6.3 and 16.0 rating-scale items in real and synthetic data, respectively. This enabled earlier high-precision measurement: after 10 items, 46.3% of respondents reached SE <= .3 under the strongest augmented test compared with 35.5% at baseline in real data, and 60.4% versus 34.7% in synthetic data. These findings illustrate how the IDS framework leverages unstructured text to enhance existing psychological measures, with applications in clinical health and beyond. --- ### DPCformer: An Interpretable Deep Learning Model for Genomic Prediction in Crops Authors: Pengcheng Deng, Kening Liu, Mengxi Zhou, Mingxi Li, Rui Yang, Chuzhe Cao, Maojun Wang, Zeyu Zhang Published: 2025-10-09 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2510.08662v2 Genomic Selection (GS) uses whole-genome information to predict crop phenotypes and accelerate breeding. Traditional GS methods, however, struggle with prediction accuracy for complex traits and large datasets. We propose DPCformer, a deep learning model integrating convolutional neural networks with a self-attention mechanism to model complex genotype-phenotype relationships. We applied DPCformer to 13 traits across five crops (maize, cotton, tomato, rice, chickpea). Our approach uses an 8-dimensional one-hot encoding for SNP data, ordered by chromosome, and employs the PMF algorithm for feature selection. Evaluations show DPCformer outperforms existing methods. In maize datasets, accuracy for traits like days to tasseling and plant height improved by up to 2.92%. For cotton, accuracy gains for fiber traits reached 8.37%. On small-sample tomato data, the Pearson Correlation Coefficient for a key trait increased by up to 57.35%. In chickpea, the yield correlation was boosted by 16.62%. DPCformer demonstrates superior accuracy, robustness in small-sample scenarios, and enhanced interpretability, providing a powerful tool for precision breeding and addressing global food security challenges. --- ### CATS-Linear: Classification Auxiliary Linear Model for Time Series Forecasting Authors: Zipo Jibao, Yingyi Fu, Xinyang Chen, Guoting Chen Published: 2025-10-09 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2510.08661v1 Recent research demonstrates that linear models achieve forecasting performance competitive with complex architectures, yet methodologies for enhancing linear models remain underexplored. Motivated by the hypothesis that distinct time series instances may follow heterogeneous linear mappings, we propose the Classification Auxiliary Trend-Seasonal Decoupling Linear Model CATS-Linear, employing Classification Auxiliary Channel-Independence (CACI). CACI dynamically routes instances to dedicated predictors via classification, enabling supervised channel design. We further analyze the theoretical expected risks of different channel settings. Additionally, we redesign the trend-seasonal decomposition architecture by adding a decoupling -- linear mapping -- recoupling framework for trend components and complex-domain linear projections for seasonal components. Extensive experiments validate that CATS-Linear with fixed hyperparameters achieves state-of-the-art accuracy comparable to hyperparameter-tuned baselines while delivering SOTA accuracy against fixed-hyperparameter counterparts. --- ### How Scale Breaks "Normalized Stress" and KL Divergence: Rethinking Quality Metrics Authors: Kiran Smelser, Kaviru Gunaratne, Jacob Miller, Stephen Kobourov Published: 2025-10-09 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2510.08660v1 Complex, high-dimensional data is ubiquitous across many scientific disciplines, including machine learning, biology, and the social sciences. One of the primary methods of visualizing these datasets is with two-dimensional scatter plots that visually capture some properties of the data. Because visually determining the accuracy of these plots is challenging, researchers often use quality metrics to measure the projection's accuracy and faithfulness to the original data. One of the most commonly employed metrics, normalized stress, is sensitive to uniform scaling (stretching, shrinking) of the projection, despite this act not meaningfully changing anything about the projection. Another quality metric, the Kullback--Leibler (KL) divergence used in the popular t-Distributed Stochastic Neighbor Embedding (t-SNE) technique, is also susceptible to this scale sensitivity. We investigate the effect of scaling on stress and KL divergence analytically and empirically by showing just how much the values change and how this affects dimension reduction technique evaluations. We introduce a simple technique to make both metrics scale-invariant and show that it accurately captures expected behavior on a small benchmark. --- ### Provably Robust Adaptation for Language-Empowered Foundation Models Authors: Yuni Lai, Xiaoyu Xue, Linghui Shen, Yulun Wu, Gaolei Li, Song Guo, Kai Zhou, Bin Xiao Published: 2025-10-09 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2510.08659v1 Language-empowered foundation models (LeFMs), such as CLIP and GraphCLIP, have transformed multimodal learning by aligning visual (or graph) features with textual representations, enabling powerful downstream capabilities like few-shot learning. However, the reliance on small, task-specific support datasets collected in open environments exposes these models to poisoning attacks, where adversaries manipulate the support samples to degrade performance. Existing defenses rely on empirical strategies, which lack formal guarantees and remain vulnerable to unseen and adaptive attacks. Certified robustness offers provable guarantees but has been largely unexplored for few-shot classifiers based on LeFMs. This study seeks to fill these critical gaps by proposing the first provably robust few-shot classifier that is tailored for LeFMs. We term our model Language-empowered Few-shot Certification (\textbf{LeFCert}). It integrates both textual and feature embeddings with an adaptive blending mechanism. To achieve provable robustness, we propose a twofold trimmed mean prototype and derive provable upper and lower bounds for classification scores, enabling certification under worst-case poisoning scenarios. To further enhance the performance, we extend LeFCert with two variants by considering a more realistic and tighter attack budget: LeFCert-L incorporates randomized smoothing to provide Lipschitz continuity and derive robustness under dual budget constraints, and LeFCert-C provides collective certification for scenarios where attackers distribute a shared poisoning budget across multiple samples. Experiments demonstrate that LeFCert achieves state-of-the-art performance, significantly improving both clean and certified accuracy compared to existing baselines. Despite its advanced robustness mechanisms, LeFCert is computationally efficient, making it practical for real-world applications. --- ### Inner-Instance Normalization for Time Series Forecasting Authors: Zipo Jibao, Yingyi Fu, Xinyang Chen, Guoting Chen Published: 2025-10-09 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2510.08657v1 Real-world time series are influenced by numerous factors and exhibit complex non-stationary characteristics. Non-stationarity can lead to distribution shifts, where the statistical properties of time series change over time, negatively impacting model performance. Several instance normalization techniques have been proposed to address distribution shifts in time series forecasting. However, existing methods fail to account for shifts within individual instances, leading to suboptimal performance. To tackle inner-instance distribution shifts, we propose two novel point-level methods: Learning Distribution (LD) and Learning Conditional Distribution (LCD). LD eliminates internal discrepancies by fitting the internal distribution of input and output with different parameters at different time steps, while LCD utilizes neural networks to predict scaling coefficients of the output. We evaluate the performance of the two methods with various backbone models across public benchmarks and demonstrate the effectiveness of the point-level paradigm through comparative experiments. --- ### A 3D Generation Framework from Cross Modality to Parameterized Primitive Authors: Yiming Liang, Huan Yu, Zili Wang, Shuyou Zhang, Guodong Yi, Jin Wang, Jianrong Tan Published: 2025-10-09 Categories: cs.GR, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2510.08656v1 Recent advancements in AI-driven 3D model generation have leveraged cross modality, yet generating models with smooth surfaces and minimizing storage overhead remain challenges. This paper introduces a novel multi-stage framework for generating 3D models composed of parameterized primitives, guided by textual and image inputs. In the framework, A model generation algorithm based on parameterized primitives, is proposed, which can identifies the shape features of the model constituent elements, and replace the elements with parameterized primitives with high quality surface. In addition, a corresponding model storage method is proposed, it can ensure the original surface quality of the model, while retaining only the parameters of parameterized primitives. Experiments on virtual scene dataset and real scene dataset demonstrate the effectiveness of our method, achieving a Chamfer Distance of 0.003092, a VIoU of 0.545, a F1-Score of 0.9139 and a NC of 0.8369, with primitive parameter files approximately 6KB in size. Our approach is particularly suitable for rapid prototyping of simple models. --- ### Knowledge Graph Sparsification for GNN-based Rare Disease Diagnosis Authors: Premt Cara, Kamilia Zaripova, David Bani-Harouni, Nassir Navab, Azade Farshad Published: 2025-10-09 Categories: cs.LG, cs.AI, q-bio.GN arXiv: https://arxiv.org/abs/2510.08655v1 Rare genetic disease diagnosis faces critical challenges: insufficient patient data, inaccessible full genome sequencing, and the immense number of possible causative genes. These limitations cause prolonged diagnostic journeys, inappropriate treatments, and critical delays, disproportionately affecting patients in resource-limited settings where diagnostic tools are scarce. We propose RareNet, a subgraph-based Graph Neural Network that requires only patient phenotypes to identify the most likely causal gene and retrieve focused patient subgraphs for targeted clinical investigation. RareNet can function as a standalone method or serve as a pre-processing or post-processing filter for other candidate gene prioritization methods, consistently enhancing their performance while potentially enabling explainable insights. Through comprehensive evaluation on two biomedical datasets, we demonstrate competitive and robust causal gene prediction and significant performance gains when integrated with other frameworks. By requiring only phenotypic data, which is readily available in any clinical setting, RareNet democratizes access to sophisticated genetic analysis, offering particular value for underserved populations lacking advanced genomic infrastructure. --- ### PhyDAE: Physics-Guided Degradation-Adaptive Experts for All-in-One Remote Sensing Image Restoration Authors: Zhe Dong, Yuzhe Sun, Haochen Jiang, Tianzhu Liu, Yanfeng Gu Published: 2025-10-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2510.08653v1 Remote sensing images inevitably suffer from various degradation factors during acquisition, including atmospheric interference, sensor limitations, and imaging conditions. These complex and heterogeneous degradations pose severe challenges to image quality and downstream interpretation tasks. Addressing limitations of existing all-in-one restoration methods that overly rely on implicit feature representations and lack explicit modeling of degradation physics, this paper proposes Physics-Guided Degradation-Adaptive Experts (PhyDAE). The method employs a two-stage cascaded architecture transforming degradation information from implicit features into explicit decision signals, enabling precise identification and differentiated processing of multiple heterogeneous degradations including haze, noise, blur, and low-light conditions. The model incorporates progressive degradation mining and exploitation mechanisms, where the Residual Manifold Projector (RMP) and Frequency-Aware Degradation Decomposer (FADD) comprehensively analyze degradation characteristics from manifold geometry and frequency perspectives. Physics-aware expert modules and temperature-controlled sparse activation strategies are introduced to enhance computational efficiency while ensuring imaging physics consistency. Extensive experiments on three benchmark datasets (MD-RSID, MD-RRSHID, and MDRS-Landsat) demonstrate that PhyDAE achieves superior performance across all four restoration tasks, comprehensively outperforming state-of-the-art methods. Notably, PhyDAE substantially improves restoration quality while achieving significant reductions in parameter count and computational complexity, resulting in remarkable efficiency gains compared to mainstream approaches and achieving optimal balance between performance and efficiency. Code is available at https://github.com/HIT-SIRS/PhyDAE. --- ### QuIRK: Quantum-Inspired Re-uploading KAN Authors: Vinayak Sharma, Ashish Padhy, Lord Sen, Vijay Jagdish Karanjkar, Sourav Behera, Shyamapada Mukherjee, Aviral Shrivastava Published: 2025-10-09 Categories: quant-ph, cs.LG arXiv: https://arxiv.org/abs/2510.08650v2 Kolmogorov-Arnold Networks or KANs have shown the ability to outperform classical Deep Neural Networks, while using far fewer trainable parameters for regression problems on scientific domains. Even more powerful has been their interpretability due to their structure being composed of univariate B-Spline functions. This enables us to derive closed-form equations from trained KANs for a wide range of problems. This paper introduces a quantum-inspired variant of the KAN based on Quantum Data Re-uploading (DR) models. The Quantum-Inspired Re-uploading KAN or QuIRK model replaces B-Splines with single-qubit DR models as the univariate function approximator, allowing them to match or outperform traditional KANs while using even fewer parameters. This is especially apparent in the case of periodic functions. Additionally, since the model utilizes only single-qubit circuits, it remains classically tractable to simulate with straightforward GPU acceleration. Finally, we also demonstrate that QuIRK retains the interpretability advantages and the ability to produce closed-form solutions. --- ### Formalizing Style in Personal Narratives Authors: Gustave Cortal, Alain Finkel Published: 2025-10-09 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2510.08649v2 Personal narratives are stories authors construct to make meaning of their experiences. Style, the distinctive way authors use language to express themselves, is fundamental to how these narratives convey subjective experiences. Yet there is a lack of a formal framework for systematically analyzing these stylistic choices. We present a novel approach that formalizes style in personal narratives as patterns in the linguistic choices authors make when communicating subjective experiences. Our framework integrates three domains: functional linguistics establishes language as a system of meaningful choices, computer science provides methods for automatically extracting and analyzing sequential patterns, and these patterns are linked to psychological observations. Using language models, we automatically extract linguistic features such as processes, participants, and circumstances. We apply our framework to hundreds of dream narratives, including a case study on a war veteran with post-traumatic stress disorder. Analysis of his narratives uncovers distinctive patterns, particularly how verbal processes dominate over mental ones, illustrating the relationship between linguistic choices and psychological states. --- ### Inverse-Free Wilson Loops for Transformers: A Practical Diagnostic for Invariance and Order Sensitivity Authors: Edward Y. Chang, Ethan Y. Chang Published: 2025-10-09 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2510.08648v1 Large language models can change answers under harmless edits that matter in practice: RAG outputs flip when passages are reordered, fine-tuning erodes invariances learned at pretraining, debate or chain-of-thought prompts take path-dependent routes, and compiler fusion or reordering perturbs logits near decision boundaries. These failures violate intended invariances, break continuous integration, and force teams to trade safety for speed. The effects are small yet distributed across layers and positions, sensitive to context length and evaluation order, and costly to repair with retraining or formal verification. We present WILSON, a minimal post-hoc diagnostic suite that converts simple loop and reordering checks on internal representations into system signals. WILSON combines an inverse-free curvature map over positions and layers, computed with JVPs and Hutchinson probes, with activation-level commutators that flag reorder risk. Signals are cheap to compute, model-agnostic for standard Transformers, and exported as thresholds and CSV artifacts for orchestrators. This enables concrete actions: guard RAG against order effects, catch fine-tuning regressions, stabilize debate pathways and long multi-turn contexts, and gate fusions or reorders in deployment. In short, WILSON helps anticipate failures and approve safe optimizations so reliability and throughput can improve together without changing model architecture or training. --- ### Can Reasoning Path still be Effective as Input? Bridging Post-Reasoning to Chain-of-Thought Compression Authors: Chengzhengxu Li, Xiaoming Liu, Zhaohan Zhang, Shengchao Liu, Guoxin Ma, Yu Lan, Cong Wang, Chao Shen Published: 2025-10-09 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2510.08647v2 Recent developments have enabled advanced reasoning in Large Language Models (LLMs) via long Chain-of-Thought (CoT), trading efficiency during inference for performance. Existing works focus on compressing generated CoT in reasoning, which impairs the necessary information for deriving the correct answer. In this work, we propose post-reasoning, a reasoning paradigm that takes CoT as a part of context to simplify the reasoning task for LLMs. We find that post-reasoning significantly reduces the generation length of LLMs, but its effectiveness hinges on the efficiency and the reliability of the contextual CoT generation. Therefore, we propose Upfront CoT (UCoT), an efficient post-reasoning framework for CoT compression. UCoT trains a lightweight model (compressor) to provide contextual CoT in form of soft tokens and trains the LLM (executor) to leverage this contextual CoT for producing the final answer. Extensive experiments show that UCoT maintains the powerful reasoning ability of executor while significantly reducing the length of CoT. It is worth mentioning that when applying UCoT to the Qwen2.5-7B-Instruct model, the usage of tokens on GSM8K dataset is reduced by 50%, while the performance is 3.08% higher than that of the state-of-the-art (SOTA) method. --- ### Mitigating Over-Refusal in Aligned Large Language Models via Inference-Time Activation Energy Authors: Eric Hanchen Jiang, Weixuan Ou, Run Liu, Shengyuan Pang, Guancheng Wan, Ranjie Duan, Wei Dong, Kai-Wei Chang, XiaoFeng Wang, Ying Nian Wu, Xinfeng Li Published: 2025-10-09 Categories: cs.LG, cs.AI, cs.CL, stat.ML arXiv: https://arxiv.org/abs/2510.08646v2 Safety alignment of large language models currently faces a central challenge: existing alignment techniques often prioritize mitigating responses to harmful prompts at the expense of overcautious behavior, leading models to incorrectly refuse benign requests. A key goal of safe alignment is therefore to improve safety while simultaneously minimizing false refusals. In this work, we introduce Energy Landscape Steering (ELS), a novel, fine-tuning free framework designed to resolve this challenge through dynamic, inference-time intervention. We train a lightweight external Energy-Based Model (EBM) to assign high energy to undesirable states (false refusal or jailbreak) and low energy to desirable states (helpful response or safe reject). During inference, the EBM maps the LLM's internal activations to an energy landscape, and we use the gradient of the energy function to steer the hidden states toward low-energy regions in real time. This dynamically guides the model toward desirable behavior without modifying its parameters. By decoupling behavioral control from the model's core knowledge, ELS provides a flexible and computationally efficient solution. Extensive experiments across diverse models demonstrate its effectiveness, raising compliance on the ORB-H benchmark from 57.3 percent to 82.6 percent while maintaining baseline safety performance. Our work establishes a promising paradigm for building LLMs that simultaneously achieve high safety and low false refusal rates. --- ### Generating Sizing Fields for Mesh Generation via GCN-based Simplification of Adaptive Background Grids Authors: Xunyang Zhu, Hongfei Ye, Yifei Wang, Taoran Liu, Jianjun Chen Published: 2025-10-09 Categories: cs.GR, cs.CV arXiv: https://arxiv.org/abs/2510.08645v1 The sizing field defined on a triangular background grid is pivotal for controlling the quality and efficiency of unstructured mesh generation. However, creating an optimal background grid that is geometrically conforming, computationally lightweight, and free from artifacts like banding is a significant challenge. This paper introduces a novel, adaptive background grid simplification (ABGS) framework based on a Graph Convolutional Network (GCN). We reformulate the grid simplification task as an edge score regression problem and train a GCN model to efficiently predict optimal edge collapse candidates. The model is guided by a custom loss function that holistically considers both geometric fidelity and sizing field accuracy. This data-driven approach replaces a costly procedural evaluation, accelerating the simplification process. Experimental results demonstrate the effectiveness of our framework across diverse and complex engineering models. Compared to the initial dense grids, our simplified background grids achieve an element reduction of 74%-94%, leading to a 35%-88% decrease in sizing field query times. --- ### Interlaced dynamic XCT reconstruction with spatio-temporal implicit neural representations Authors: Mathias Boulanger, Ericmoore Jossou Published: 2025-10-09 Categories: eess.IV, cond-mat.mtrl-sci, cs.CV arXiv: https://arxiv.org/abs/2510.08641v1 In this work, we investigate the use of spatio-temporalImplicit Neural Representations (INRs) for dynamic X-ray computed tomography (XCT) reconstruction under interlaced acquisition schemes. The proposed approach combines ADMM-based optimization with INCODE, a conditioning framework incorporating prior knowledge, to enable efficient convergence. We evaluate our method under diverse acquisition scenarios, varying the severity of global undersampling, spatial complexity (quantified via spatial information), and noise levels. Across all settings, our model achieves strong performance and outperforms Time-Interlaced Model-Based Iterative Reconstruction (TIMBIR), a state-of-the-art model-based iterative method. In particular, we show that the inductive bias of the INR provides good robustness to moderate noise levels, and that introducing explicit noise modeling through a weighted least squares data fidelity term significantly improves performance in more challenging regimes. The final part of this work explores extensions toward a practical reconstruction framework. We demonstrate the modularity of our approach by explicitly modeling detector non-idealities, incorporating ring artifact correction directly within the reconstruction process. Additionally, we present a proof-of-concept 4D volumetric reconstruction by jointly optimizing over batched axial slices, an approach which opens up the possibilities for massive parallelization, a critical feature for processing large-scale datasets. --- ### Automating Android Build Repair: Bridging the Reasoning-Execution Gap in LLM Agents with Domain-Specific Tools Authors: Ha Min Son, Huan Ren, Xin Liu, Zhe Zhao Published: 2025-10-09 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2510.08640v3 Android is the largest mobile platform, yet automatically building applications remains a practical challenge. While Large Language Models (LLMs) show promise for code repair, their use for fixing Android build errors remains underexplored. To address this gap, we first introduce AndroidBuildBench, a benchmark of 1,019 build failures curated from the commit histories of 43 open-source Android projects. Each problem is paired with a verified solution from a subsequent commit, ensuring that fixes are feasible. Second, we propose GradleFixer, an LLM agent with domain-specific tools for inspecting and manipulating the Gradle build environment. GradleFixer achieves a resolve rate of 81.4% (pass@1), significantly outperforming a state-of-the-art coding agent that relies on a general-purpose shell. GradleFixer's success suggests that while LLMs possess the high-level knowledge to solve these failures, they struggle to translate this knowledge into effective low-level actions using a general-purpose shell. We demonstrate the effectiveness of a strategy we term Tool Bridging, which replaces general-purpose shell commands with domain-aware abstractions. We hypothesize this approach works through two mechanisms: 1) it provides tools in an API-like format that LLMs use more reliably, and 2) it constrains the action space to relevant operations. This approach bridges the gap between the model's high-level reasoning and effective low-level execution. --- ### ReSplat: Learning Recurrent Gaussian Splatting Authors: Haofei Xu, Daniel Barath, Andreas Geiger, Marc Pollefeys Published: 2025-10-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2510.08575v4 While existing feed-forward Gaussian splatting models offer computational efficiency and can generalize to sparse view settings, their performance is fundamentally constrained by relying on a single forward pass for inference. We propose ReSplat, a feed-forward recurrent Gaussian splatting model that iteratively refines 3D Gaussians without explicitly computing gradients. Our key insight is that the Gaussian splatting rendering error serves as a rich feedback signal, guiding the recurrent network to learn effective Gaussian updates. This feedback signal naturally adapts to unseen data distributions at test time, enabling robust generalization across datasets, view counts, and image resolutions. To initialize the recurrent process, we introduce a compact reconstruction model that operates in a $16 \times$ subsampled space, producing $16 \times$ fewer Gaussians than previous per-pixel Gaussian models. This substantially reduces computational overhead and allows for efficient Gaussian updates. Extensive experiments across varying number of input views (2, 8, 16, 32), resolutions ($256 \times 256$ to $540 \times 960$), and datasets (DL3DV, RealEstate10K, and ACID) demonstrate that our method achieves state-of-the-art performance while significantly reducing the number of Gaussians and improving the rendering speed. Our project page is at https://haofeixu.github.io/resplat/. --- ### Reconstructing the local density field with combined convolutional and point cloud architecture Authors: Baptiste Barthe-Gold, Nhat-Minh Nguyen, Leander Thiele Published: 2025-10-09 Categories: astro-ph.CO, cs.LG, stat.ML arXiv: https://arxiv.org/abs/2510.08573v2 We construct a neural network to perform regression on the local dark-matter density field given line-of-sight peculiar velocities of dark-matter halos, biased tracers of the dark matter field. Our architecture combines a convolutional U-Net with a point-cloud DeepSets. This combination enables efficient use of small-scale information and improves reconstruction quality relative to a U-Net-only approach. Specifically, our hybrid network recovers both clustering amplitudes and phases better than the U-Net on small scales. --- ### BLAZER: Bootstrapping LLM-based Manipulation Agents with Zero-Shot Data Generation Authors: Rocktim Jyoti Das, Harsh Singh, Diana Turmakhan, Muhammad Abdullah Sohail, Mingfei Han, Preslav Nakov, Fabio Pizzati, Ivan Laptev Published: 2025-10-09 Categories: cs.RO, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2510.08572v1 Scaling data and models has played a pivotal role in the remarkable progress of computer vision and language. Inspired by these domains, recent efforts in robotics have similarly focused on scaling both data and model size to develop more generalizable and robust policies. However, unlike vision and language, robotics lacks access to internet-scale demonstrations across diverse robotic tasks and environments. As a result, the scale of existing datasets typically suffers from the need for manual data collection and curation. To address this problem, here we propose BLAZER, a framework that learns manipulation policies from automatically generated training data. We build on the zero-shot capabilities of LLM planners and automatically generate demonstrations for diverse manipulation tasks in simulation. Successful examples are then used to finetune an LLM and to improve its planning capabilities without human supervision. Notably, while BLAZER training requires access to the simulator's state, we demonstrate direct transfer of acquired skills to sensor-based manipulation. Through extensive experiments, we show BLAZER to significantly improve zero-shot manipulation in both simulated and real environments. Moreover, BLAZER improves on tasks outside of its training pool and enables downscaling of LLM models. Our code and data will be made publicly available on the project page. --- ### Scalable Offline Metrics for Autonomous Driving Authors: Animikh Aich, Adwait Kulkarni, Eshed Ohn-Bar Published: 2025-10-09 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2510.08571v2 Real-world evaluation of perception-based planning models for robotic systems, such as autonomous vehicles, can be safely and inexpensively conducted offline, i.e. by computing model prediction error over a pre-collected validation dataset with ground-truth annotations. However, extrapolating from offline model performance to online settings remains a challenge. In these settings, seemingly minor errors can compound and result in test-time infractions or collisions. This relationship is understudied, particularly across diverse closed-loop metrics and complex urban maneuvers. In this work, we revisit this undervalued question in policy evaluation through an extensive set of experiments across diverse conditions and metrics. Based on analysis in simulation, we find an even worse correlation between offline and online settings than reported by prior studies, casting doubts on the validity of current evaluation practices and metrics for driving policies. Next, we bridge the gap between offline and online evaluation. We investigate an offline metric based on epistemic uncertainty, which aims to capture events that are likely to cause errors in closed-loop settings. The resulting metric achieves over 13% improvement in correlation compared to previous offline metrics. We further validate the generalization of our findings beyond the simulation environment in real-world settings, where even greater gains are observed. --- ### Who Said Neural Networks Aren't Linear? Authors: Nimrod Berman, Assaf Hallak, Assaf Shocher Published: 2025-10-09 Categories: cs.LG arXiv: https://arxiv.org/abs/2510.08570v2 Neural networks are famously nonlinear. However, linearity is defined relative to a pair of vector spaces, $f:X \to Y$. Leveraging the algebraic concept of transport of structure, we propose a method to explicitly identify non-standard vector spaces where a neural network acts as a linear operator. When sandwiching a linear operator $A$ between two invertible neural networks, $f(x)=g_y^{-1}(A g_x(x))$, the corresponding vector spaces $X$ and $Y$ are induced by newly defined addition and scaling actions derived from $g_x$ and $g_y$. We term this kind of architecture a Linearizer. This framework makes the entire arsenal of linear algebra, including SVD, pseudo-inverse, orthogonal projection and more, applicable to nonlinear mappings. Furthermore, we show that the composition of two Linearizers that share a neural network is also a Linearizer. We leverage this property and demonstrate that training diffusion models using our architecture makes the hundreds of sampling steps collapse into a single step. We further utilize our framework to enforce idempotency (i.e. $f(f(x))=f(x)$) on networks leading to a globally projective generative model and to demonstrate modular style transfer. --- ### ArenaBencher: Automatic Benchmark Evolution via Multi-Model Competitive Evaluation Authors: Qin Liu, Jacob Dineen, Yuxi Huang, Sheng Zhang, Hoifung Poon, Ben Zhou, Muhao Chen Published: 2025-10-09 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2510.08569v1 Benchmarks are central to measuring the capabilities of large language models and guiding model development, yet widespread data leakage from pretraining corpora undermines their validity. Models can match memorized content rather than demonstrate true generalization, which inflates scores, distorts cross-model comparisons, and misrepresents progress. We introduce ArenaBencher, a model-agnostic framework for automatic benchmark evolution that updates test cases while preserving comparability. Given an existing benchmark and a diverse pool of models to be evaluated, ArenaBencher infers the core ability of each test case, generates candidate question-answer pairs that preserve the original objective, verifies correctness and intent with an LLM as a judge, and aggregates feedback from multiple models to select candidates that expose shared weaknesses. The process runs iteratively with in-context demonstrations that steer generation toward more challenging and diagnostic cases. We apply ArenaBencher to math problem solving, commonsense reasoning, and safety domains and show that it produces verified, diverse, and fair updates that uncover new failure modes, increase difficulty while preserving test objective alignment, and improve model separability. The framework provides a scalable path to continuously evolve benchmarks in step with the rapid progress of foundation models. --- ### NovaFlow: Zero-Shot Manipulation via Actionable Flow from Generated Videos Authors: Hongyu Li, Lingfeng Sun, Yafei Hu, Duy Ta, Jennifer Barry, George Konidaris, Jiahui Fu Published: 2025-10-09 Categories: cs.RO, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2510.08568v1 Enabling robots to execute novel manipulation tasks zero-shot is a central goal in robotics. Most existing methods assume in-distribution tasks or rely on fine-tuning with embodiment-matched data, limiting transfer across platforms. We present NovaFlow, an autonomous manipulation framework that converts a task description into an actionable plan for a target robot without any demonstrations. Given a task description, NovaFlow synthesizes a video using a video generation model and distills it into 3D actionable object flow using off-the-shelf perception modules. From the object flow, it computes relative poses for rigid objects and realizes them as robot actions via grasp proposals and trajectory optimization. For deformable objects, this flow serves as a tracking objective for model-based planning with a particle-based dynamics model. By decoupling task understanding from low-level control, NovaFlow naturally transfers across embodiments. We validate on rigid, articulated, and deformable object manipulation tasks using a table-top Franka arm and a Spot quadrupedal mobile robot, and achieve effective zero-shot execution without demonstrations or embodiment-specific training. Project website: https://novaflow.lhy.xyz/. --- ### MATRIX: Multimodal Agent Tuning for Robust Tool-Use Reasoning Authors: Tajamul Ashraf, Umair Nawaz, Abdelrahman M. Shaker, Rao Anwer, Philip Torr, Fahad Shahbaz Khan, Salman Khan Published: 2025-10-09 Categories: cs.CV, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2510.08567v3 Vision language models (VLMs) are increasingly deployed as controllers with access to external tools for complex reasoning and decision-making, yet their effectiveness remains limited by the scarcity of high-quality multimodal trajectories and the cost of manual annotation. We address this challenge with a vision-centric agent tuning framework that automatically synthesizes multimodal trajectories, generates step-wise preference pairs, and trains a VLM controller for robust tool-use reasoning. Our pipeline first constructs M-TRACE, a large-scale dataset of 28.5K multimodal tasks with 177K verified trajectories, enabling imitation-based trajectory tuning. Building on this, we develop MATRIX Agent, a controller finetuned on M-TRACE for step-wise tool reasoning. To achieve finer alignment, we further introduce Pref-X, a set of 11K automatically generated preference pairs, and optimize MATRIX on it via step-wise preference learning. Across three benchmarks, Agent-X, GTA, and GAIA, MATRIX consistently surpasses both open- and closed-source VLMs, demonstrating scalable and effective multimodal tool use. Our data and code is avaliable at https://github.com/mbzuai-oryx/MATRIX. --- ### D$^2$GS: Depth-and-Density Guided Gaussian Splatting for Stable and Accurate Sparse-View Reconstruction Authors: Meixi Song, Xin Lin, Dizhe Zhang, Haodong Li, Xiangtai Li, Bo Du, Lu Qi Published: 2025-10-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2510.08566v1 Recent advances in 3D Gaussian Splatting (3DGS) enable real-time, high-fidelity novel view synthesis (NVS) with explicit 3D representations. However, performance degradation and instability remain significant under sparse-view conditions. In this work, we identify two key failure modes under sparse-view conditions: overfitting in regions with excessive Gaussian density near the camera, and underfitting in distant areas with insufficient Gaussian coverage. To address these challenges, we propose a unified framework D$^2$GS, comprising two key components: a Depth-and-Density Guided Dropout strategy that suppresses overfitting by adaptively masking redundant Gaussians based on density and depth, and a Distance-Aware Fidelity Enhancement module that improves reconstruction quality in under-fitted far-field areas through targeted supervision. Moreover, we introduce a new evaluation metric to quantify the stability of learned Gaussian distributions, providing insights into the robustness of the sparse-view 3DGS. Extensive experiments on multiple datasets demonstrate that our method significantly improves both visual quality and robustness under sparse view conditions. The project page can be found at: https://insta360-research-team.github.io/DDGS-website/. --- ### NaViL: Rethinking Scaling Properties of Native Multimodal Large Language Models under Data Constraints Authors: Changyao Tian, Hao Li, Gen Luo, Xizhou Zhu, Weijie Su, Hanming Deng, Jinguo Zhu, Jie Shao, Ziran Zhu, Yunpeng Liu, Lewei Lu, Wenhai Wang et al. Published: 2025-10-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2510.08565v1 Compositional training has been the de-facto paradigm in existing Multimodal Large Language Models (MLLMs), where pre-trained vision encoders are connected with pre-trained LLMs through continuous multimodal pre-training. However, the multimodal scaling property of this paradigm remains difficult to explore due to the separated training. In this paper, we focus on the native training of MLLMs in an end-to-end manner and systematically study its design space and scaling property under a practical setting, i.e., data constraint. Through careful study of various choices in MLLM, we obtain the optimal meta-architecture that best balances performance and training cost. After that, we further explore the scaling properties of the native MLLM and indicate the positively correlated scaling relationship between visual encoders and LLMs. Based on these findings, we propose a native MLLM called NaViL, combined with a simple and cost-effective recipe. Experimental results on 14 multimodal benchmarks confirm the competitive performance of NaViL against existing MLLMs. Besides that, our findings and results provide in-depth insights for the future study of native MLLMs. --- ### How to Teach Large Multimodal Models New Skills Authors: Zhen Zhu, Yiming Gong, Yao Xiao, Yaoyao Liu, Derek Hoiem Published: 2025-10-09 Categories: cs.AI, cs.CV, cs.LG arXiv: https://arxiv.org/abs/2510.08564v2 How can we teach large multimodal models (LMMs) new skills without erasing prior abilities? We study sequential fine-tuning on five target skills while monitoring general ability on eight held-out benchmarks across three model families. Surprisingly, we find that performance lost on held-out tasks after fine-tuning on one skill can partly recover when the model is subsequently tuned on a different skill. We trace this behavior to a measurable shift in the output token distribution, manifested through a simple counting-bias probe that shows the shift co-varies with forgetting. Guided by this insight, we identify two simple, robust tuning recipes that learn strongly while limiting drift: (i) updating only the self-attention projection layers (SA Proj., $Δ$ learning +24.9 / $Δ$ held-out forgetting -0.6), and (ii) updating only the MLP Gate&Up while freezing the Down projection (+30.5 / -2.1). Both substantially outperform full-LLM tuning (+31.8 / -23.3) in the learning-forgetting trade-off. We also compare against common forgetting mitigation methods: Learning without Forgetting (LwF), LoRA, Mixture-of-Experts, and weight-space interpolation (WiSE-FT), and find that our selective tuning recipes match or exceed their learning-stability balance while remaining simpler, requiring no replay, auxiliary parameters, or per-stage tuning. These results hold across LLaVA-OneVision, LLaVA-NeXT, and Qwen2.5-VL, confirming that the key to teaching LMMs new skills without forgetting lies in controlling output distribution shift by choosing which components to tune. Code will be made available. --- ### Where Have All the Kaczmarz Iterates Gone? Authors: El Houcine Bergou, Soumia Boucherouite, Aritra Dutta, Xin Li, Anna Ma Published: 2025-10-09 Categories: math.NA, cs.LG, math.OC arXiv: https://arxiv.org/abs/2510.08563v1 The randomized Kaczmarz (RK) algorithm is one of the most computationally and memory-efficient iterative algorithms for solving large-scale linear systems. However, practical applications often involve noisy and potentially inconsistent systems. While the convergence of RK is well understood for consistent systems, the study of RK on noisy, inconsistent linear systems is limited. This paper investigates the asymptotic behavior of RK iterates in expectation when solving noisy and inconsistent systems, addressing the locations of their limit points. We explore the roles of singular vectors of the (noisy) coefficient matrix and derive bounds on the convergence horizon, which depend on the noise levels and system characteristics. Finally, we provide extensive numerical experiments that validate our theoretical findings, offering practical insights into the algorithm's performance under realistic conditions. These results establish a deeper understanding of the RK algorithm's limitations and robustness in noisy environments, paving the way for optimized applications in real-world scientific and engineering problems. --- ### ResAD: Normalized Residual Trajectory Modeling for End-to-End Autonomous Driving Authors: Zhiyu Zheng, Shaoyu Chen, Haoran Yin, Xinbang Zhang, Jialv Zou, Xinggang Wang, Qian Zhang, Lefei Zhang Published: 2025-10-09 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2510.08562v2 End-to-end autonomous driving (E2EAD) systems, which learn to predict future trajectories directly from sensor data, are fundamentally challenged by the inherent spatio-temporal imbalance of trajectory data. This imbalance creates a significant optimization burden, causing models to learn spurious correlations instead of robust driving logic, while also prioritizing uncertain, distant predictions, thereby compromising immediate safety. To address these issues, we propose ResAD, a novel Normalized Residual Trajectory Modeling framework. Instead of predicting the future trajectory directly, our approach reframes and simplifies the learning task by predicting the residual deviation from a deterministic inertial reference. This inertial reference serves as a strong physical prior, compelling the model to move beyond simple pattern-matching and instead focus its capacity on learning the necessary, context-driven deviations (e.g., traffic rules, obstacles) from this default, inertially-guided path. To mitigate the optimization imbalance caused by uncertain, long-term horizons, ResAD further incorporates Point-wise Normalization of the predicted residual. This technique re-weights the optimization objective, preventing large-magnitude errors associated with distant, uncertain waypoints from dominating the learning signal. On the NAVSIM v1 and v2 benchmarks, ResAD achieves state-of-the-art results of 88.8 PDMS and 85.5 EPDMS with only two denoising steps, demonstrating that ResAD significantly simplifies the learning task and improves planning performance. The code will be released to facilitate further research. --- ### MultiCOIN: Multi-Modal COntrollable Video INbetweening Authors: Maham Tanveer, Yang Zhou, Simon Niklaus, Ali Mahdavi Amiri, Hao Zhang, Krishna Kumar Singh, Nanxuan Zhao Published: 2025-10-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2510.08561v2 Video inbetweening creates smooth and natural transitions between two image frames, making it an indispensable tool for video editing and long-form video synthesis. Existing works in this domain are unable to generate large, complex, or intricate motions. In particular, they cannot accommodate the versatility of user intents and generally lack fine control over the details of intermediate frames, leading to misalignment with the creative mind. To fill these gaps, we introduce MultiCOIN, a video inbetweening framework that allows multi-modal controls, including depth transition and layering, motion trajectories, text prompts, and target regions for movement localization, while achieving a balance between flexibility, ease of use, and precision for fine-grained video interpolation. To achieve this, we adopt the Diffusion Transformer (DiT) architecture as our video generative model, due to its proven capability to generate high-quality long videos. To ensure compatibility between DiT and our multi-modal controls, we map all motion controls into a common sparse and user-friendly point-based representation as the video/noise input. Further, to respect the variety of controls which operate at varying levels of granularity and influence, we separate content controls and motion controls into two branches to encode the required features before guiding the denoising process, resulting in two generators, one for motion and the other for content. Finally, we propose a stage-wise training strategy to ensure that our model learns the multi-modal controls smoothly. Extensive qualitative and quantitative experiments demonstrate that multi-modal controls enable a more dynamic, customizable, and contextually accurate visual narrative. --- ### SciVideoBench: Benchmarking Scientific Video Reasoning in Large Multimodal Models Authors: Andong Deng, Taojiannan Yang, Shoubin Yu, Lincoln Spencer, Mohit Bansal, Chen Chen, Serena Yeung-Levy, Xiaohan Wang Published: 2025-10-09 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2510.08559v1 Large Multimodal Models (LMMs) have achieved remarkable progress across various capabilities; however, complex video reasoning in the scientific domain remains a significant and challenging frontier. Current video benchmarks predominantly target general scenarios where perception/recognition is heavily relied on, while with relatively simple reasoning tasks, leading to saturation and thus failing to effectively evaluate advanced multimodal cognitive skills. To address this critical gap, we introduce SciVideoBench, a rigorous benchmark specifically designed to assess advanced video reasoning in scientific contexts. SciVideoBench consists of 1,000 carefully crafted multiple-choice questions derived from cutting-edge scientific experimental videos spanning over 25 specialized academic subjects and verified by a semi-automatic system. Each question demands sophisticated domain-specific knowledge, precise spatiotemporal perception, and intricate logical reasoning, effectively challenging models' higher-order cognitive abilities. Our evaluation highlights significant performance deficits in state-of-the-art proprietary and open-source LMMs, including Gemini 2.5 Pro and Qwen2.5-VL, indicating substantial room for advancement in video reasoning capabilities. Detailed analyses of critical factors such as reasoning complexity and visual grounding provide valuable insights and clear direction for future developments in LMMs, driving the evolution of truly capable multimodal AI co-scientists. We hope SciVideoBench could fit the interests of the community and help to push the boundary of cutting-edge AI for border science. --- ### Agent Learning via Early Experience Authors: Kai Zhang, Xiangchao Chen, Bo Liu, Tianci Xue, Zeyi Liao, Zhihan Liu, Xiyao Wang, Yuting Ning, Zhaorun Chen, Xiaohan Fu, Jian Xie, Yuxuan Sun et al. Published: 2025-10-09 Categories: cs.AI, cs.CL, cs.IR, cs.LG arXiv: https://arxiv.org/abs/2510.08558v3 A long-term goal of language agents is to learn and improve through their own experience, ultimately outperforming humans in complex, real-world tasks. However, training agents from experience data with reinforcement learning remains difficult in many environments, which either lack verifiable rewards (e.g., websites) or require inefficient long-horizon rollouts (e.g., multi-turn tool use). As a result, most current agents rely on supervised fine-tuning on expert data, which is challenging to scale and generalizes poorly. This limitation stems from the nature of expert demonstrations: they capture only a narrow range of scenarios, and expose the agent to limited environment diversity. We address this limitation with a middle-ground paradigm we call early experience: interaction data generated by the agent's own actions, where the resulting future states serve as supervision without reward signals. Within this paradigm, we study two strategies of using such data: (1) implicit world modeling, which uses collected states to ground the policy in environment dynamics; and (2) self-reflection, where the agent learns from its suboptimal actions to improve reasoning and decision-making. Evaluation across eight diverse environments and multiple model families shows that our approaches consistently improve effectiveness and out-of-domain generalization, highlighting the value of early experience. Moreover, in environments with verifiable rewards, our results provide promising signals that early experience offers a strong foundation for subsequent reinforcement learning, making it a practical bridge between imitation learning and fully experience-driven agents. --- ### DexNDM: Closing the Reality Gap for Dexterous In-Hand Rotation via Joint-Wise Neural Dynamics Model Authors: Xueyi Liu, He Wang, Li Yi Published: 2025-10-09 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2510.08556v1 Achieving generalized in-hand object rotation remains a significant challenge in robotics, largely due to the difficulty of transferring policies from simulation to the real world. The complex, contact-rich dynamics of dexterous manipulation create a "reality gap" that has limited prior work to constrained scenarios involving simple geometries, limited object sizes and aspect ratios, constrained wrist poses, or customized hands. We address this sim-to-real challenge with a novel framework that enables a single policy, trained in simulation, to generalize to a wide variety of objects and conditions in the real world. The core of our method is a joint-wise dynamics model that learns to bridge the reality gap by effectively fitting limited amount of real-world collected data and then adapting the sim policy's actions accordingly. The model is highly data-efficient and generalizable across different whole-hand interaction distributions by factorizing dynamics across joints, compressing system-wide influences into low-dimensional variables, and learning each joint's evolution from its own dynamic profile, implicitly capturing these net effects. We pair this with a fully autonomous data collection strategy that gathers diverse, real-world interaction data with minimal human intervention. Our complete pipeline demonstrates unprecedented generality: a single policy successfully rotates challenging objects with complex shapes (e.g., animals), high aspect ratios (up to 5.33), and small sizes, all while handling diverse wrist orientations and rotation axes. Comprehensive real-world evaluations and a teleoperation application for complex tasks validate the effectiveness and robustness of our approach. Website: https://meowuu7.github.io/DexNDM/ --- ### VideoCanvas: Unified Video Completion from Arbitrary Spatiotemporal Patches via In-Context Conditioning Authors: Minghong Cai, Qiulin Wang, Zongli Ye, Wenze Liu, Quande Liu, Weicai Ye, Xintao Wang, Pengfei Wan, Kun Gai, Xiangyu Yue Published: 2025-10-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2510.08555v2 Existing controllable video generation methods are typically designed for rigid, task-specific settings, such as first-frame image-to-video, inpainting, or interpolation, treating spatio-temporal control as a set of isolated problems. We formalize a unified task, arbitrary spatio-temporal video completion, where a model generates a coherent video from user-specified patches placed at any spatial location and timestamp. However, realizing such a unified framework within modern latent video diffusion models is non-trivial: causal video VAEs compress multiple frames into a single latent slot, making frame-level conditioning fundamentally ill-posed, and directly feeding sparsely populated, zero-padded video inputs into the VAE leads to severe out-of-distribution artifacts. To address these challenges, we propose VideoCanvas, a simple yet effective framework that adapts the In-Context Conditioning paradigm to arbitrary spatio-temporal completion without modifying or retraining the VAE. Our key idea is a hybrid conditioning strategy that decouples spatial and temporal control: spatially, we encode zero-padded full-frame canvases in image mode to keep VAE inputs in-distribution, and temporally we use Temporal RoPE Interpolation to assign each condition a continuous fractional index in the latent sequence for precise frame-level alignment. To evaluate this capability, we develop VideoCanvasBench, the first benchmark for arbitrary spatio-temporal video completion, covering both intra-scene fidelity and inter-scene creativity. Extensive experiments demonstrate that VideoCanvas achieves state-of-the-art performance across a diverse range of video generation tasks under a single, unified framework. --- ### Improving Reasoning for Diffusion Language Models via Group Diffusion Policy Optimization Authors: Kevin Rojas, Jiahe Lin, Kashif Rasul, Anderson Schneider, Yuriy Nevmyvaka, Molei Tao, Wei Deng Published: 2025-10-09 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2510.08554v3 Diffusion language models (DLMs) enable parallel, order-agnostic generation with iterative refinement, offering a flexible alternative to autoregressive large language models (LLMs). However, adapting reinforcement learning (RL) fine-tuning to DLMs remains an open challenge because of the intractable likelihood. Pioneering work such as diffu-GRPO estimated token-level likelihoods via one-step unmasking. While computationally efficient, this approach is severely biased. A more principled foundation lies in sequence-level likelihoods, where the evidence lower bound (ELBO) serves as a surrogate. Yet, despite this clean mathematical connection, ELBO-based methods have seen limited adoption due to the prohibitive cost of likelihood evaluation. In this work, we revisit ELBO estimation and disentangle its sources of variance. This decomposition motivates reducing variance through fast, deterministic integral approximations along a few pivotal dimensions. Building on this insight, we introduce Group Diffusion Policy Optimization (GDPO), a new RL algorithm tailored for DLMs. GDPO leverages simple yet effective Semi-deterministic Monte Carlo schemes to mitigate the variance explosion of ELBO estimators under vanilla double Monte Carlo sampling, yielding a provably lower-variance estimator under tight evaluation budgets. Empirically, GDPO achieves consistent gains over pretrained checkpoints and outperforms diffu-GRPO, one of the state-of-the-art baselines, on the majority of math, reasoning, and coding benchmarks. --- ### Dream to Recall: Imagination-Guided Experience Retrieval for Memory-Persistent Vision-and-Language Navigation Authors: Yunzhe Xu, Yiyuan Pan, Zhe Liu Published: 2025-10-09 Categories: cs.CV, cs.AI, cs.RO arXiv: https://arxiv.org/abs/2510.08553v2 Vision-and-Language Navigation (VLN) requires agents to follow natural language instructions through environments, with memory-persistent variants demanding progressive improvement through accumulated experience. Existing approaches for memory-persistent VLN face critical limitations: they lack effective memory access mechanisms, instead relying on entire memory incorporation or fixed-horizon lookup, and predominantly store only environmental observations while neglecting navigation behavioral patterns that encode valuable decision-making strategies. We present Memoir, which employs imagination as a retrieval mechanism grounded by explicit memory: a world model imagines future navigation states as queries to selectively retrieve relevant environmental observations and behavioral histories. The approach comprises: 1) a language-conditioned world model that imagines future states serving dual purposes: encoding experiences for storage and generating retrieval queries; 2) Hybrid Viewpoint-Level Memory that anchors both observations and behavioral patterns to viewpoints, enabling hybrid retrieval; and 3) an experience-augmented navigation model that integrates retrieved knowledge through specialized encoders. Extensive evaluation across diverse memory-persistent VLN benchmarks with 10 distinct testing scenarios demonstrates Memoir's effectiveness: significant improvements across all scenarios, with 5.4% SPL gains on IR2R over the best memory-persistent baseline, accompanied by 8.3x training speedup and 74% inference memory reduction. The results validate that predictive retrieval of both environmental and behavioral memories enables more effective navigation, with analysis indicating substantial headroom (73.3% vs 93.4% upper bound) for this imagination-guided paradigm. --- ### ARTDECO: Towards Efficient and High-Fidelity On-the-Fly 3D Reconstruction with Structured Scene Representation Authors: Guanghao Li, Kerui Ren, Linning Xu, Zhewen Zheng, Changjian Jiang, Xin Gao, Bo Dai, Jian Pu, Mulin Yu, Jiangmiao Pang Published: 2025-10-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2510.08551v1 On-the-fly 3D reconstruction from monocular image sequences is a long-standing challenge in computer vision, critical for applications such as real-to-sim, AR/VR, and robotics. Existing methods face a major tradeoff: per-scene optimization yields high fidelity but is computationally expensive, whereas feed-forward foundation models enable real-time inference but struggle with accuracy and robustness. In this work, we propose ARTDECO, a unified framework that combines the efficiency of feed-forward models with the reliability of SLAM-based pipelines. ARTDECO uses 3D foundation models for pose estimation and point prediction, coupled with a Gaussian decoder that transforms multi-scale features into structured 3D Gaussians. To sustain both fidelity and efficiency at scale, we design a hierarchical Gaussian representation with a LoD-aware rendering strategy, which improves rendering fidelity while reducing redundancy. Experiments on eight diverse indoor and outdoor benchmarks show that ARTDECO delivers interactive performance comparable to SLAM, robustness similar to feed-forward systems, and reconstruction quality close to per-scene optimization, providing a practical path toward on-the-fly digitization of real-world environments with both accurate geometry and high visual fidelity. Explore more demos on our project page: https://city-super.github.io/artdeco/. --- ### Entropy Regularizing Activation: Boosting Continuous Control, Large Language Models, and Image Classification with Activation as Entropy Constraints Authors: Zilin Kang, Chonghua Liao, Tingqiang Xu, Huazhe Xu Published: 2025-10-09 Categories: cs.LG arXiv: https://arxiv.org/abs/2510.08549v2 We propose ERA, a new paradigm that constrains the sampling entropy above given thresholds by applying specially designed activations to the outputs of models. Our approach demonstrates broad effectiveness across different domains: 1) for large language models(LLMs), boosting the AIME 2025 score for Qwen2.5-Math-7B by 37.4%; 2) for continuous control reinforcement learning agents, improving performance by more than 30% over strong baselines such as SAC on the challenging HumanoidBench; 3) for image classification, enhancing ImageNet top-1 accuracy by 0.69% for ResNet-50. These gains are achieved with a computational overhead of less than 7%. Our work validates output activation as a powerful tool for entropy control, opening a new direction for designing simpler and more robust algorithms. --- ### R2RGEN: Real-to-Real 3D Data Generation for Spatially Generalized Manipulation Authors: Xiuwei Xu, Angyuan Ma, Hankun Li, Bingyao Yu, Zheng Zhu, Jie Zhou, Jiwen Lu Published: 2025-10-09 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2510.08547v2 Towards the aim of generalized robotic manipulation, spatial generalization is the most fundamental capability that requires the policy to work robustly under different spatial distribution of objects, environment and agent itself. To achieve this, substantial human demonstrations need to be collected to cover different spatial configurations for training a generalized visuomotor policy via imitation learning. Prior works explore a promising direction that leverages data generation to acquire abundant spatially diverse data from minimal source demonstrations. However, most approaches face significant sim-to-real gap and are often limited to constrained settings, such as fixed-base scenarios and predefined camera viewpoints. In this paper, we propose a real-to-real 3D data generation framework (R2RGen) that directly augments the pointcloud observation-action pairs to generate real-world data. R2RGen is simulator- and rendering-free, thus being efficient and plug-and-play. Specifically, we propose a unified three-stage framework, which (1) pre-processes source demonstrations under different camera setups in a shared 3D space with scene / trajectory parsing; (2) augments objects and robot's position with a group-wise backtracking strategy; (3) aligns the distribution of generated data with real-world 3D sensor using camera-aware post-processing. Empirically, R2RGen substantially enhances data efficiency on extensive experiments and demonstrates strong potential for scaling and application on mobile manipulation. --- ### SPAD: Specialized Prefill and Decode Hardware for Disaggregated LLM Inference Authors: Hengrui Zhang, Pratyush Patel, August Ning, David Wentzlaff Published: 2025-10-09 Categories: cs.AR, cs.DC, cs.LG arXiv: https://arxiv.org/abs/2510.08544v1 Large Language Models (LLMs) have gained popularity in recent years, driving up the demand for inference. LLM inference is composed of two phases with distinct characteristics: a compute-bound prefill phase followed by a memory-bound decode phase. To efficiently serve LLMs, prior work proposes prefill-decode disaggregation to run each phase on separate hardware. However, existing hardware poorly matches the different requirements of each phase. Current datacenter GPUs and TPUs follow a more-is-better design philosophy that maximizes compute and memory resources, causing memory bandwidth underutilization in the prefill phase and compute underutilization in the decode phase. Such underutilization directly translates into increased serving costs. This paper proposes SPAD (Specialized Prefill and Decode hardware), adopting a less-is-more methodology to design specialized chips tailored to the distinct characteristics of prefill and decode phases. The proposed Prefill Chips have larger systolic arrays and use cost-effective GDDR memory, whereas the proposed Decode Chips retain high memory bandwidth but reduce compute capacity. Compared to modeled H100s, simulations show that the proposed Prefill Chips deliver 8% higher prefill performance on average at 52% lower hardware cost, while the proposed Decode Chips achieve 97% of the decode performance with 28% lower TDP. End-to-end simulations on production traces show that SPAD reduces hardware cost by 19%-41% and TDP by 2%-17% compared to modeled baseline clusters while offering the same performance. Even when models and workloads change, SPAD can reallocate either type of chip to run either phase and still achieve 11%-43% lower hardware costs, demonstrating the longevity of the SPAD design. --- ### VideoNorms: Benchmarking Cultural Awareness of Video Language Models Authors: Nikhil Reddy Varimalla, Yunfei Xu, Meng Fan Wang, Arkadiy Saakyan, Smaranda Muresan Published: 2025-10-09 Categories: cs.CV, cs.AI, cs.CL, cs.CY arXiv: https://arxiv.org/abs/2510.08543v2 As Video Large Language Models (VideoLLMs) are deployed globally, it is important to assess their ability to reason across cultural contexts. To advance cultural norm awareness evaluation in VideoLLMs, we introduce VideoNorms, a dataset of cultural norm annotations from popular US and Chinese TV shows annotated with adherence or violation labels and (non-)verbal evidence. Through a human-AI collaboration framework, each item was first annotated by a large VideoLLM, and then reviewed by at least three trained monocultural annotators with significant lived experience in the target culture, resulting in a dataset of over 3,000 human judgments. Human verification showed disparity in US and Chinese norm extraction performance, cautioning against fully automatic approaches cultures under-represented in training data. Hierarchical linear modeling analysis of $7$ open-weight VideoLLMs' performance revealed that: 1) models perform worse in Chinese compared to US, particularly for norm adherence prediction; 2) models have more difficulty in providing non-verbal evidence compared to verbal evidence for norm adherence/violation predictions. Ablation studies confirm video modality is indeed necessary for accurate performance, and scaling model size does not yield classification score improvements. Our findings and data contribute to culturally grounded video model training and evaluation. --- ### Computational and statistical lower bounds for low-rank estimation under general inhomogeneous noise Authors: Debsurya De, Dmitriy Kunisky Published: 2025-10-09 Categories: math.ST, cs.DS, cs.LG, math.PR arXiv: https://arxiv.org/abs/2510.08541v1 Recent work has generalized several results concerning the well-understood spiked Wigner matrix model of a low-rank signal matrix corrupted by additive i.i.d. Gaussian noise to the inhomogeneous case, where the noise has a variance profile. In particular, for the special case where the variance profile has a block structure, a series of results identified an effective spectral algorithm for detecting and estimating the signal, identified the threshold signal strength required for that algorithm to succeed, and proved information-theoretic lower bounds that, for some special signal distributions, match the above threshold. We complement these results by studying the computational optimality of this spectral algorithm. Namely, we show that, for a much broader range of signal distributions, whenever the spectral algorithm cannot detect a low-rank signal, then neither can any low-degree polynomial algorithm. This gives the first evidence for a computational hardness conjecture of Guionnet, Ko, Krzakala, and Zdeborová (2023). With similar techniques, we also prove sharp information-theoretic lower bounds for a class of signal distributions not treated by prior work. Unlike all of the above results on inhomogeneous models, our results do not assume that the variance profile has a block structure, and suggest that the same spectral algorithm might remain optimal for quite general profiles. We include a numerical study of this claim for an example of a smoothly-varying rather than piecewise-constant profile. Our proofs involve analyzing the graph sums of a matrix, which also appear in free and traffic probability, but we require new bounds on these quantities that are tighter than existing ones for non-negative matrices, which may be of independent interest. --- ### MM-HELIX: Boosting Multimodal Long-Chain Reflective Reasoning with Holistic Platform and Adaptive Hybrid Policy Optimization Authors: Xiangyu Zhao, Junming Lin, Tianhao Liang, Yifan Zhou, Wenhao Chai, Yuzhe Gu, Weiyun Wang, Kai Chen, Gen Luo, Wenwei Zhang, Junchi Yan, Hua Yang et al. Published: 2025-10-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2510.08540v2 While current Multimodal Large Language Models (MLLMs) have demonstrated proficiency in reasoning tasks such as mathematics and logic, their capacity for long-chain reflective reasoning, a prerequisite for solving complex real-world problems, remains largely underexplored. In this work, we first conduct an extensive empirical investigation to evaluate this capability. Leveraging a carefully designed data synthesis engine, we construct MM-HELIX, a multimodal benchmark consisting 1,260 samples of 42 challenging synthetic tasks that require iterative thinking and backtracking. Empirical results on this benchmark reveal that existing MLLMs exhibit significant performance deficits in long-chain reflective reasoning. To address this limitation, we generate post-training data and further explore learning paradigms for exploiting such data. We first develop the Step-Elicited Response Generation pipeline to create MM-HELIX-100K, a large-scale dataset of 100k high-quality, reflective reasoning traces for instruction-tuning stage. Given that standard Reinforcement Learning fails on complex tasks due to sparse reward signals and catastrophic forgetting after Supervised Fine-Tuning, we propose Adaptive Hybrid Policy Optimization (AHPO), a novel training strategy that dynamically unifies offline supervision and online optimization into a single stage. This strategy enables the model to learn from expert data when rewards are sparse and conduct independent exploration once proficient. When applied to the Qwen2.5-VL-7B baseline, our method achieves a +18.6\% accuracy improvement on MM-HELIX benchmark and demonstrates strong generalization with a +5.7\% average performance gain on general mathematic and logic tasks. Our work demonstrate that reflective reasoning in MLLMs can be effectively learned and generalized, paving the way for developing more capable MLLMs. --- ### On the optimization dynamics of RLVR: Gradient gap and step size thresholds Authors: Joe Suk, Yaqi Duan Published: 2025-10-09 Categories: cs.LG, cs.AI, cs.IT, math.OC, stat.ML arXiv: https://arxiv.org/abs/2510.08539v4 Reinforcement Learning with Verifiable Rewards (RLVR), which uses simple binary feedback to post-train large language models, has found significant empirical success. However, a principled understanding of why it works is lacking. This paper builds a theoretical foundation for RLVR by analyzing its training process at both the full-response (trajectory) and token levels. Central to our analysis is a new quantity called the Gradient Gap, which formalizes the direction of improvement from low-reward to high-reward regions of the response space. We prove that convergence critically depends on aligning the update direction with this Gradient Gap. Moreover, we derive a sharp step-size threshold based on the magnitude of the Gradient Gap: below it, learning converges, whereas above it, performance collapses. Our theory further predicts how the critical step size must scale with response length and the success rate, thereby explaining why practical heuristics such as length normalization improve stability and showing that, with a fixed learning rate, the success rate can stagnate strictly below $100\%$. Importantly, our theory holds flexibly for any policy-gradient algorithm and so characterizes the dynamics of popular approaches such as REINFORCE and GRPO. We validate these predictions through controlled bandit simulations and language model experiments on post-training Qwen2.5-Math-7B with GRPO. --- ### Permutation-Invariant Spectral Learning via Dyson Diffusion Authors: Tassilo Schwarz, Cai Dieball, Constantin Kogler, Renaud Lambiotte, Arnaud Doucet, Aljaž Godec, George Deligiannidis Published: 2025-10-09 Categories: stat.ML, cs.LG, math.PR arXiv: https://arxiv.org/abs/2510.08535v2 Diffusion models are central to generative modeling and have been adapted to graphs by diffusing adjacency matrix representations. The challenge of having up to $n!$ such representations for graphs with $n$ nodes is only partially mitigated by using permutation-equivariant learning architectures. Despite their computational efficiency, existing graph diffusion models struggle to distinguish certain graph families and their spectra, unless graph data are augmented with ad hoc features. This shortcoming stems from enforcing the inductive bias within the learning architecture. In this work, we leverage random matrix theory to analytically extract the spectral properties of the diffusion process, allowing us to push most of the inductive bias from the architecture into the dynamics. Building on this, we introduce the Dyson Diffusion Model, which employs Dyson's Brownian motion to capture the spectral dynamics of an Ornstein-Uhlenbeck process on the adjacency matrix. Furthermore, conditioned on the spectral dynamics, we formulate a Lie group diffusion, appropriately modeling the remaining degrees of freedom. Strikingly, the resulting learning problem becomes permutation invariant at the Lie algebra level. We demonstrate that the Dyson Diffusion Model learns graph spectra accurately and outperforms existing graph diffusion models. ---