# Research Papers — 2025-10 · bundle page 100 of 217

> Full-text markdown of papers #4951–5000 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/100
[← Previous bundle](https://aipod.dev/papers/archive/2025-10/page/99.md)
[Next bundle →](https://aipod.dev/papers/archive/2025-10/page/101.md)

### A Generalizable Rhetorical Strategy Annotation Model Using LLM-based Debate Simulation and Labelling

Authors: Shiyu Ji, Farnoosh Hashemi, Joice Chen, Juanwen Pan, Weicheng Ma, Hefan Zhang, Sophia Pan, Ming Cheng, Shubham Mohole, Saeed Hassanpour, Soroush Vosoughi, Michael Macy
Published: 2025-10-16
Categories: cs.CL, cs.SI
arXiv: https://arxiv.org/abs/2510.15081v1

Rhetorical strategies are central to persuasive communication, from political discourse and marketing to legal argumentation. However, analysis of rhetorical strategies has been limited by reliance on human annotation, which is costly, inconsistent, difficult to scale. Their associated datasets are often limited to specific topics and strategies, posing challenges for robust model development. We propose a novel framework that leverages large language models (LLMs) to automatically generate and label synthetic debate data based on a four-part rhetorical typology (causal, empirical, emotional, moral). We fine-tune transformer-based classifiers on this LLM-labeled dataset and validate its performance against human-labeled data on this dataset and on multiple external corpora. Our model achieves high performance and strong generalization across topical domains. We illustrate two applications with the fine-tuned model: (1) the improvement in persuasiveness prediction from incorporating rhetorical strategy labels, and (2) analyzing temporal and partisan shifts in rhetorical strategies in U.S. Presidential debates (1960-2020), revealing increased use of affective over cognitive argument in U.S. Presidential debates.

---

### Online Correlation Clustering: Simultaneously Optimizing All $\ell_p$-norms

Authors: Sami Davies, Benjamin Moseley, Heather Newman
Published: 2025-10-16
Categories: cs.LG, cs.DM, cs.DS
arXiv: https://arxiv.org/abs/2510.15076v2

The $\ell_p$-norm objectives for correlation clustering present a fundamental trade-off between minimizing total disagreements (the $\ell_1$-norm) and ensuring fairness to individual nodes (the $\ell_\infty$-norm). Surprisingly, in the offline setting it is possible to simultaneously approximate all $\ell_p$-norms with a single clustering. Can this powerful guarantee be achieved in an online setting? This paper provides the first affirmative answer. We present a single algorithm for the online-with-a-sample (AOS) model that, given a small constant fraction of the input as a sample, produces one clustering that is simultaneously $O(\log^4 n)$-competitive for all $\ell_p$-norms with high probability, $O(\log n)$-competitive for the $\ell_\infty$-norm with high probability, and $O(1)$-competitive for the $\ell_1$-norm in expectation. This work successfully translates the offline "all-norms" guarantee to the online world. Our setting is motivated by a new hardness result that demonstrates a fundamental separation between these objectives in the standard random-order (RO) online model. Namely, while the $\ell_1$-norm is trivially $O(1)$-approximable in the RO model, we prove that any algorithm in the RO model for the fairness-promoting $\ell_\infty$-norm must have a competitive ratio of at least $Ω(n^{1/3})$. This highlights the necessity of a different beyond-worst-case model. We complement our algorithm with lower bounds, showing our competitive ratios for the $\ell_1$- and $\ell_\infty$- norms are nearly tight in the AOS model.

---

### Physics-informed data-driven machine health monitoring for two-photon lithography

Authors: Sixian Jia, Zhiqiao Dong, Chenhui Shao
Published: 2025-10-16
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2510.15075v1

Two-photon lithography (TPL) is a sophisticated additive manufacturing technology for creating three-dimensional (3D) micro- and nano-structures. Maintaining the health of TPL systems is critical for ensuring consistent fabrication quality. Current maintenance practices often rely on experience rather than informed monitoring of machine health, resulting in either untimely maintenance that causes machine downtime and poor-quality fabrication, or unnecessary maintenance that leads to inefficiencies and avoidable downtime. To address this gap, this paper presents three methods for accurate and timely monitoring of TPL machine health. Through integrating physics-informed data-driven predictive models for structure dimensions with statistical approaches, the proposed methods are able to handle increasingly complex scenarios featuring different levels of generalizability. A comprehensive experimental dataset that encompasses six process parameter combinations and six structure dimensions under two machine health conditions was collected to evaluate the effectiveness of the proposed approaches. Across all test scenarios, the approaches are shown to achieve high accuracies, demonstrating excellent effectiveness, robustness, and generalizability. These results represent a significant step toward condition-based maintenance for TPL systems.

---

### SaLon3R: Structure-aware Long-term Generalizable 3D Reconstruction from Unposed Images

Authors: Jiaxin Guo, Tongfan Guan, Wenzhen Dong, Wenzhao Zheng, Wenting Wang, Yue Wang, Yeung Yam, Yun-Hui Liu
Published: 2025-10-16
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.15072v1

Recent advances in 3D Gaussian Splatting (3DGS) have enabled generalizable, on-the-fly reconstruction of sequential input views. However, existing methods often predict per-pixel Gaussians and combine Gaussians from all views as the scene representation, leading to substantial redundancies and geometric inconsistencies in long-duration video sequences. To address this, we propose SaLon3R, a novel framework for Structure-aware, Long-term 3DGS Reconstruction. To our best knowledge, SaLon3R is the first online generalizable GS method capable of reconstructing over 50 views in over 10 FPS, with 50% to 90% redundancy removal. Our method introduces compact anchor primitives to eliminate redundancy through differentiable saliency-aware Gaussian quantization, coupled with a 3D Point Transformer that refines anchor attributes and saliency to resolve cross-frame geometric and photometric inconsistencies. Specifically, we first leverage a 3D reconstruction backbone to predict dense per-pixel Gaussians and a saliency map encoding regional geometric complexity. Redundant Gaussians are compressed into compact anchors by prioritizing high-complexity regions. The 3D Point Transformer then learns spatial structural priors in 3D space from training data to refine anchor attributes and saliency, enabling regionally adaptive Gaussian decoding for geometric fidelity. Without known camera parameters or test-time optimization, our approach effectively resolves artifacts and prunes the redundant 3DGS in a single feed-forward pass. Experiments on multiple datasets demonstrate our state-of-the-art performance on both novel view synthesis and depth estimation, demonstrating superior efficiency, robustness, and generalization ability for long-term generalizable 3D reconstruction. Project Page: https://wrld.github.io/SaLon3R/.

---

### Sequential Comics for Jailbreaking Multimodal Large Language Models via Structured Visual Storytelling

Authors: Deyue Zhang, Dongdong Yang, Junjie Mu, Quancheng Zou, Zonghao Ying, Wenzhuo Xu, Zhao Liu, Xuan Wang, Xiangzheng Zhang
Published: 2025-10-16
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2510.15068v1

Multimodal large language models (MLLMs) exhibit remarkable capabilities but remain susceptible to jailbreak attacks exploiting cross-modal vulnerabilities. In this work, we introduce a novel method that leverages sequential comic-style visual narratives to circumvent safety alignments in state-of-the-art MLLMs. Our method decomposes malicious queries into visually innocuous storytelling elements using an auxiliary LLM, generates corresponding image sequences through diffusion models, and exploits the models' reliance on narrative coherence to elicit harmful outputs. Extensive experiments on harmful textual queries from established safety benchmarks show that our approach achieves an average attack success rate of 83.5\%, surpassing prior state-of-the-art by 46\%. Compared with existing visual jailbreak methods, our sequential narrative strategy demonstrates superior effectiveness across diverse categories of harmful content. We further analyze attack patterns, uncover key vulnerability factors in multimodal safety mechanisms, and evaluate the limitations of current defense strategies against narrative-driven attacks, revealing significant gaps in existing protections.

---

### Antislop: A Comprehensive Framework for Identifying and Eliminating Repetitive Patterns in Language Models

Authors: Samuel Paech, Allen Roush, Judah Goldfeder, Ravid Shwartz-Ziv
Published: 2025-10-16
Categories: cs.LG, cs.CL
arXiv: https://arxiv.org/abs/2510.15061v2

Widespread LLM adoption has introduced characteristic repetitive phraseology, termed "slop," which degrades output quality and makes AI-generated text immediately recognizable. We present Antislop, a comprehensive framework providing tools to both detect and eliminate these overused patterns. Our approach combines three innovations: (1) The Antislop Sampler, which uses backtracking to suppress unwanted strings at inference time without destroying vocabulary; (2) An automated pipeline that profiles model-specific slop against human baselines and generates training data; (3) Final Token Preference Optimization (FTPO), a novel fine-tuning method that operates on individual tokens, surgically adjusting logits wherever a banned pattern has appeared in an inference trace. We demonstrate that some slop patterns appear over 1,000x more frequently in LLM output than human text. The Antislop Sampler successfully suppresses 8,000+ patterns while maintaining quality, whereas token banning becomes unusable at just 2,000. Most importantly, FTPO achieves 90% slop reduction while maintaining or improving performance in cross-domain evals including GSM8K, MMLU, and creative writing tasks. In contrast, DPO suffers significant degradation in writing quality and lexical diversity despite achieving weaker suppression. We release all code and results under MIT license: https://github.com/sam-paech/auto-antislop.

---

### A solution to generalized learning from small training sets found in infants repeated visual experiences of individual objects

Authors: Frangil Ramirez, Elizabeth Clerkin, David J. Crandall, Linda B. Smith
Published: 2025-10-16
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.15060v4

One-year-old infants rapidly form and generalize categories from idiosyncratic experiences of very few exemplars of those categories. Here we provide evidence on the statistics of infants daily-life visual experiences for 8 object categories. Using a corpus of infant head-camera images recorded at mealtimes (87 mealtimes,14 infants), we measure the frequency of the unique instances of each category and the variability of the visual experiences within and across instances of the same category. The frequency distributions of instances for individual infants are highly skewed, containing many images of the same few objects along with fewer images of other instances. Graph theoretic measures of individual category experiences for individual children reveal a lumpy mix of high similarity and high variability, organized into multiple but interconnected clusters of high-similarity images. In computational experiments, we show that artificially created training sets characterized by an interconnected mix of high and low similarity support generalization to novel instances after limited training. We discuss implications for category recognition, and for learning more generally, by both humans and machines.

---

### The Minimax Lower Bound of Kernel Stein Discrepancy Estimation

Authors: Jose Cribeiro-Ramallo, Agnideep Aich, Florian Kalinke, Ashit Baran Aich, Zoltán Szabó
Published: 2025-10-16
Categories: stat.ML, cs.LG, math.ST
arXiv: https://arxiv.org/abs/2510.15058v3

Kernel Stein discrepancies (KSDs) have emerged as a powerful tool for quantifying goodness-of-fit over the last decade, featuring numerous successful applications. To the best of our knowledge, all existing KSD estimators with known rate achieve $\sqrt n$-convergence. In this work, we present two complementary results (with different proof strategies), establishing that the minimax lower bound of KSD estimation is $n^{-1/2}$ and settling the optimality of these estimators. Our first result focuses on KSD estimation on $\mathbb R^d$ with the Langevin-Stein operator; our explicit constant for the Gaussian kernel indicates that the difficulty of KSD estimation may increase exponentially with the dimensionality $d$. Our second result settles the minimax lower bound for KSD estimation on general domains.

---

### Learn to Change the World: Multi-level Reinforcement Learning with Model-Changing Actions

Authors: Ziqing Lu, Babak Hassibi, Lifeng Lai, Weiyu Xu
Published: 2025-10-16
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.15056v1

Reinforcement learning usually assumes a given or sometimes even fixed environment in which an agent seeks an optimal policy to maximize its long-term discounted reward. In contrast, we consider agents that are not limited to passive adaptations: they instead have model-changing actions that actively modify the RL model of world dynamics itself. Reconfiguring the underlying transition processes can potentially increase the agents' rewards. Motivated by this setting, we introduce the multi-layer configurable time-varying Markov decision process (MCTVMDP). In an MCTVMDP, the lower-level MDP has a non-stationary transition function that is configurable through upper-level model-changing actions. The agent's objective consists of two parts: Optimize the configuration policies in the upper-level MDP and optimize the primitive action policies in the lower-level MDP to jointly improve its expected long-term reward.

---

### DRIFT: Transferring Reasoning Priors for Efficient MLLM Fine-Tuning

Authors: Chao Huang, Zeliang Zhang, Jiang Liu, Ximeng Sun, Jialian Wu, Xiaodong Yu, Ze Wang, Chenliang Xu, Emad Barsoum, Zicheng Liu
Published: 2025-10-16
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.15050v2

Multimodal large language models (MLLMs) have made rapid progress, yet their reasoning ability often lags behind strong text-only LLMs. Bridging this gap typically requires large-scale multimodal reasoning data or reinforcement learning, incurring substantial cost. An appealing alternative is parameter-space model merging between reasoning-enhanced LLMs and MLLMs, but we show that naive merging is fragile: its effectiveness varies widely across model families and can significantly degrade performance (e.g., for Qwen-based MLLMs). We propose Directional Reasoning Injection for Fine-Tuning (DRIFT), a lightweight method that transfers reasoning knowledge in the gradient space while preserving multimodal alignment. DRIFT precomputes a reasoning prior from the parameter differences between text-only reasoning experts and multimodal models, and uses it to bias gradients during supervised fine-tuning. This design retains the simplicity of standard SFT pipelines while enabling efficient and stable reasoning transfer. Experiments on multimodal reasoning benchmarks, including MathVista and MathVerse, show that DRIFT consistently outperforms naive merging and standard SFT, and matches or surpasses training-intensive methods with substantially lower data and compute.

---

### Why Do LLM Agents Fail in Exploring New Environments? A World-Modeling Perspective

Authors: Shiqi Chen, Tongyao Zhu, Zian Wang, Jinghan Zhang, Kangrui Wang, Ruochen Zhou, Siyang Gao, Teng Xiao, Yee Whye Teh, Junxian He, Manling Li
Published: 2025-10-16
Categories: cs.LG, cs.CL
arXiv: https://arxiv.org/abs/2510.15047v2

Large Language Models (LLMs) as agents often fail to improve in new environments. We identify and characterize a failure mode we call exploration collapse: under reinforcement learning (RL) in environments whose states are unfamiliar to the policy, Pass@k, the probability that at least one of k sampled trajectories succeeds, drops markedly over training even as Pass@1 edges up, revealing increasingly brittle exploration; environments closer to the pretraining distribution show no such decline. We trace this collapse to weak grounding in environment states and dynamics, and study a simple remedy: explicitly teaching the agent to estimate the current state and predict its transitions before optimizing for reward. We instantiate it as SPA, an explore-then-exploit recipe that cold-starts the policy with a Self-Experience supervised finetuning (SFT) stage, collecting the model's own interaction trajectories and supervising state and next-state prediction, and then runs standard RL. The resulting world model serves as a grounded initialization for RL rather than an inference-time planner. Across unseen environments, SPA consistently and substantially improves over vanilla RL: for example, it raises the Sokoban success rate from 25.6% to 59.8% on Qwen2.5-1.5B-Instruct, letting sub-3B models surpass a 20B baseline on these tasks. Controlled studies indicate that the gains track four factors: grounded state representations, explicit transition modeling, self-experience trajectories from a sufficiently strong exploration policy, and adequate coverage of transition data.

---

### IQNN-CS: Interpretable Quantum Neural Network for Credit Scoring

Authors: Abdul Samad Khan, Nouhaila Innan, Aeysha Khalique, Muhammad Shafique
Published: 2025-10-16
Categories: cs.LG, quant-ph
arXiv: https://arxiv.org/abs/2510.15044v1

Credit scoring is a high-stakes task in financial services, where model decisions directly impact individuals' access to credit and are subject to strict regulatory scrutiny. While Quantum Machine Learning (QML) offers new computational capabilities, its black-box nature poses challenges for adoption in domains that demand transparency and trust. In this work, we present IQNN-CS, an interpretable quantum neural network framework designed for multiclass credit risk classification. The architecture combines a variational QNN with a suite of post-hoc explanation techniques tailored for structured data. To address the lack of structured interpretability in QML, we introduce Inter-Class Attribution Alignment (ICAA), a novel metric that quantifies attribution divergence across predicted classes, revealing how the model distinguishes between credit risk categories. Evaluated on two real-world credit datasets, IQNN-CS demonstrates stable training dynamics, competitive predictive performance, and enhanced interpretability. Our results highlight a practical path toward transparent and accountable QML models for financial decision-making.

---

### Comprehensive language-image pre-training for 3D medical image understanding

Authors: Tassilo Wald, Ibrahim Ethem Hamamci, Yuan Gao, Sam Bond-Taylor, Harshita Sharma, Maximilian Ilse, Cynthia Lo, Olesya Melnichenko, Anton Schwaighofer, Noel C. F. Codella, Maria Teodora Wetscherek, Klaus H. Maier-Hein et al.
Published: 2025-10-16
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2510.15042v3

In the 3D medical image domain, vision-language pre-training is used to create vision-language encoders (VLEs) that can support radiologists by retrieving patients with similar abnormalities, predicting likelihoods of abnormality, or, with downstream adaptation, generating radiological reports. While the methodology holds promise, three challenges limit the capabilities of current 3D VLEs: data scarcity due to privacy concerns, high computational costs resulting from the volumetric nature of the images, and a domain shift between the long reports used for training and the short prompts used during inference for, e.g., zero-shot classification. As a consequence, natural-image VLE recipes do not directly transfer to 3D medical imaging. In this paper, we overcome these challenges by injecting additional supervision via a report generation objective and combining vision-language with vision-only pre-training, allowing us to leverage both image-only and paired image-text 3D datasets. Further, we propose a novel loss that addresses the domain shift between long reports and short textual prompts. Through these additional objectives, paired with best practices of the 3D medical imaging domain, we develop the Comprehensive Language-Image Pre-training (COLIPRI) encoder family. Our COLIPRI encoders achieve state-of-the-art performance in report generation, semantic segmentation, classification probing, and zero-shot classification. The model weights and inference code are freely available at https://huggingface.co/microsoft/colipri.

---

### Generalized Dynamics Generation towards Scannable Physical World Model

Authors: Yichen Li, Zhiyi Li, Brandon Feng, Dinghuai Zhang, Antonio Torralba
Published: 2025-10-16
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.15041v1

Digital twin worlds with realistic interactive dynamics presents a new opportunity to develop generalist embodied agents in scannable environments with complex physical behaviors. To this end, we present GDGen (Generalized Representation for Generalized Dynamics Generation), a framework that takes a potential energy perspective to seamlessly integrate rigid body, articulated body, and soft body dynamics into a unified, geometry-agnostic system. GDGen operates from the governing principle that the potential energy for any stable physical system should be low. This fresh perspective allows us to treat the world as one holistic entity and infer underlying physical properties from simple motion observations. We extend classic elastodynamics by introducing directional stiffness to capture a broad spectrum of physical behaviors, covering soft elastic, articulated, and rigid body systems. We propose a specialized network to model the extended material property and employ a neural field to represent deformation in a geometry-agnostic manner. Extensive experiments demonstrate that GDGen robustly unifies diverse simulation paradigms, offering a versatile foundation for creating interactive virtual environments and training robotic agents in complex, dynamically rich scenarios.

---

### Composition-Grounded Data Synthesis for Visual Reasoning

Authors: Xinyi Gu, Jiayuan Mao, Zhang-Wei Hong, Zhuoran Yu, Pengyuan Li, Dhiraj Joshi, Rogerio Feris, Zexue He
Published: 2025-10-16
Categories: cs.CV, cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2510.15040v2

Pretrained multi-modal large language models (MLLMs) demonstrate strong performance on diverse multimodal tasks, but remain limited in reasoning capabilities for domains where annotations are difficult to collect. In this work, we focus on artificial image domains such as charts, rendered documents, and webpages, which are abundant in practice yet lack large-scale human annotated reasoning datasets. We introduce COGS (COmposition-Grounded data Synthesis), a data-efficient framework for equipping MLLMs with advanced reasoning abilities from a small set of seed questions. The key idea is to decompose each seed question into primitive perception and reasoning factors, which can then be systematically recomposed with new images to generate large collections of synthetic question-answer pairs. Each generated question is paired with subquestions and intermediate answers, enabling reinforcement learning with factor-level process rewards. Experiments on chart reasoning show that COGS substantially improves performance on unseen questions, with the largest gains on reasoning-heavy and compositional questions. Moreover, training with a factor-level mixture of different seed data yields better transfer across multiple datasets, suggesting that COGS induces generalizable capabilities rather than dataset-specific overfitting. We further demonstrate that the framework extends beyond charts to other domains such as webpages.

---

### AlignFlow: Improving Flow-based Generative Models with Semi-Discrete Optimal Transport

Authors: Lingkai Kong, Molei Tao, Yang Liu, Bryan Wang, Jinmiao Fu, Chien-Chih Wang, Huidong Liu
Published: 2025-10-16
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2510.15038v1

Flow-based Generative Models (FGMs) effectively transform noise into complex data distributions. Incorporating Optimal Transport (OT) to couple noise and data during FGM training has been shown to improve the straightness of flow trajectories, enabling more effective inference. However, existing OT-based methods estimate the OT plan using (mini-)batches of sampled noise and data points, which limits their scalability to large and high-dimensional datasets in FGMs. This paper introduces AlignFlow, a novel approach that leverages Semi-Discrete Optimal Transport (SDOT) to enhance the training of FGMs by establishing an explicit, optimal alignment between noise distribution and data points with guaranteed convergence. SDOT computes a transport map by partitioning the noise space into Laguerre cells, each mapped to a corresponding data point. During FGM training, i.i.d. noise samples are paired with data points via the SDOT map. AlignFlow scales well to large datasets and model architectures with negligible computational overhead. Experimental results show that AlignFlow improves the performance of a wide range of state-of-the-art FGM algorithms and can be integrated as a plug-and-play component. Code is available at: https://github.com/konglk1203/AlignFlow.

---

### MOBIUS: Big-to-Mobile Universal Instance Segmentation via Multi-modal Bottleneck Fusion and Calibrated Decoder Pruning

Authors: Mattia Segu, Marta Tintore Gazulla, Yongqin Xian, Luc Van Gool, Federico Tombari
Published: 2025-10-16
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.15026v1

Scaling up model size and training data has advanced foundation models for instance-level perception, achieving state-of-the-art in-domain and zero-shot performance across object detection and segmentation. However, their high computational cost limits adoption on resource-constrained platforms. We first examine the limitations of existing architectures in enabling efficient edge deployment without compromising performance. We then introduce MOBIUS, a family of foundation models for universal instance segmentation, designed for Pareto-optimal downscaling to support deployment across devices ranging from high-end accelerators to mobile hardware. To reduce training and inference demands, we propose: (i) a bottleneck pixel decoder for efficient multi-scale and multi-modal fusion, (ii) a language-guided uncertainty calibration loss for adaptive decoder pruning, and (iii) a streamlined, unified training strategy. Unlike efficient baselines that trade accuracy for reduced complexity, MOBIUS reduces pixel and transformer decoder FLOPs by up to 55% and 75%, respectively, while maintaining state-of-the-art performance in just a third of the training iterations. MOBIUS establishes a new benchmark for efficient segmentation on both high-performance computing platforms and mobile devices.

---

### LoRAverse: A Submodular Framework to Retrieve Diverse Adapters for Diffusion Models

Authors: Mert Sonmezer, Matthew Zheng, Pinar Yanardag
Published: 2025-10-16
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.15022v2

Low-rank Adaptation (LoRA) models have revolutionized the personalization of pre-trained diffusion models by enabling fine-tuning through low-rank, factorized weight matrices specifically optimized for attention layers. These models facilitate the generation of highly customized content across a variety of objects, individuals, and artistic styles without the need for extensive retraining. Despite the availability of over 100K LoRA adapters on platforms like Civit.ai, users often face challenges in navigating, selecting, and effectively utilizing the most suitable adapters due to their sheer volume, diversity, and lack of structured organization. This paper addresses the problem of selecting the most relevant and diverse LoRA models from this vast database by framing the task as a combinatorial optimization problem and proposing a novel submodular framework. Our quantitative and qualitative experiments demonstrate that our method generates diverse outputs across a wide range of domains.

---

### Constantly Improving Image Models Need Constantly Improving Benchmarks

Authors: Jiaxin Ge, Grace Luo, Heekyung Lee, Nishant Malpani, Long Lian, XuDong Wang, Aleksander Holynski, Trevor Darrell, Sewon Min, David M. Chan
Published: 2025-10-16
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.15021v1

Recent advances in image generation, often driven by proprietary systems like GPT-4o Image Gen, regularly introduce new capabilities that reshape how users interact with these models. Existing benchmarks often lag behind and fail to capture these emerging use cases, leaving a gap between community perceptions of progress and formal evaluation. To address this, we present ECHO, a framework for constructing benchmarks directly from real-world evidence of model use: social media posts that showcase novel prompts and qualitative user judgments. Applying this framework to GPT-4o Image Gen, we construct a dataset of over 31,000 prompts curated from such posts. Our analysis shows that ECHO (1) discovers creative and complex tasks absent from existing benchmarks, such as re-rendering product labels across languages or generating receipts with specified totals, (2) more clearly distinguishes state-of-the-art models from alternatives, and (3) surfaces community feedback that we use to inform the design of metrics for model quality (e.g., measuring observed shifts in color, identity, and structure). Our website is at https://echo-bench.github.io.

---

### The Coverage Principle: How Pre-Training Enables Post-Training

Authors: Fan Chen, Audrey Huang, Noah Golowich, Sadhika Malladi, Adam Block, Jordan T. Ash, Akshay Krishnamurthy, Dylan J. Foster
Published: 2025-10-16
Categories: stat.ML, cs.AI, cs.CL, cs.LG, math.ST
arXiv: https://arxiv.org/abs/2510.15020v2

Language models demonstrate remarkable abilities when pre-trained on large text corpora and fine-tuned for specific tasks, but how and why pre-training shapes the success of the final model remains poorly understood. Notably, although pre-training success is often quantified by cross-entropy loss, cross-entropy can be a poor predictor of downstream performance. Instead, we provide a theoretical perspective on this relationship through the lens of \emph{coverage}, which quantifies the probability mass the pre-trained model places on high-quality responses and which is necessary and sufficient for post-training and test-time scaling methods such as Best-of-N to succeed. Our main results develop an understanding of \emph{the coverage principle}, a phenomenon whereby next-token prediction (more generally, maximum likelihood) implicitly optimizes toward a model with good coverage. In particular, we uncover a mechanism that explains the power of coverage in predicting downstream performance: \emph{coverage generalizes faster than cross-entropy}, avoiding spurious dependence on problem-dependent parameters such as the sequence length. We also study practical algorithmic interventions with provable benefits for improving coverage, including (i) model/checkpoint selection procedures, (ii) gradient normalization schemes, and (iii) test-time decoding strategies.

---

### NANO3D: A Training-Free Approach for Efficient 3D Editing Without Masks

Authors: Junliang Ye, Shenghao Xie, Ruowen Zhao, Zhengyi Wang, Hongyu Yan, Wenqiang Zu, Lei Ma, Jun Zhu
Published: 2025-10-16
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.15019v1

3D object editing is essential for interactive content creation in gaming, animation, and robotics, yet current approaches remain inefficient, inconsistent, and often fail to preserve unedited regions. Most methods rely on editing multi-view renderings followed by reconstruction, which introduces artifacts and limits practicality. To address these challenges, we propose Nano3D, a training-free framework for precise and coherent 3D object editing without masks. Nano3D integrates FlowEdit into TRELLIS to perform localized edits guided by front-view renderings, and further introduces region-aware merging strategies, Voxel/Slat-Merge, which adaptively preserve structural fidelity by ensuring consistency between edited and unedited areas. Experiments demonstrate that Nano3D achieves superior 3D consistency and visual quality compared with existing methods. Based on this framework, we construct the first large-scale 3D editing datasets Nano3D-Edit-100k, which contains over 100,000 high-quality 3D editing pairs. This work addresses long-standing challenges in both algorithm design and data availability, significantly improving the generality and reliability of 3D editing, and laying the groundwork for the development of feed-forward 3D editing models. Project Page:https://jamesyjl.github.io/Nano3D

---

### UrbanVerse: Scaling Urban Simulation by Watching City-Tour Videos

Authors: Mingxuan Liu, Honglin He, Elisa Ricci, Wayne Wu, Bolei Zhou
Published: 2025-10-16
Categories: cs.CV, cs.AI, cs.RO
arXiv: https://arxiv.org/abs/2510.15018v2

Urban embodied AI agents, ranging from delivery robots to quadrupeds, are increasingly populating our cities, navigating chaotic streets to provide last-mile connectivity. Training such agents requires diverse, high-fidelity urban environments to scale, yet existing human-crafted or procedurally generated simulation scenes either lack scalability or fail to capture real-world complexity. We introduce UrbanVerse, a data-driven real-to-sim system that converts crowd-sourced city-tour videos into physics-aware, interactive simulation scenes. UrbanVerse consists of: (i) UrbanVerse-100K, a repository of 100k+ annotated urban 3D assets with semantic and physical attributes, and (ii) UrbanVerse-Gen, an automatic pipeline that extracts scene layouts from video and instantiates metric-scale 3D simulations using retrieved assets. Running in IsaacSim, UrbanVerse offers 160 high-quality constructed scenes from 24 countries, along with a curated benchmark of 10 artist-designed test scenes. Experiments show that UrbanVerse scenes preserve real-world semantics and layouts, achieving human-evaluated realism comparable to manually crafted scenes. In urban navigation, policies trained in UrbanVerse exhibit scaling power laws and strong generalization, improving success by +6.3% in simulation and +30.1% in zero-shot sim-to-real transfer comparing to prior methods, accomplishing a 300 m real-world mission with only two interventions.

---

### Active Honeypot Guardrail System: Probing and Confirming Multi-Turn LLM Jailbreaks

Authors: ChenYu Wu, Yi Wang, Yang Liao
Published: 2025-10-16
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2510.15017v1

Large language models (LLMs) are increasingly vulnerable to multi-turn jailbreak attacks, where adversaries iteratively elicit harmful behaviors that bypass single-turn safety filters. Existing defenses predominantly rely on passive rejection, which either fails against adaptive attackers or overly restricts benign users. We propose a honeypot-based proactive guardrail system that transforms risk avoidance into risk utilization. Our framework fine-tunes a bait model to generate ambiguous, non-actionable but semantically relevant responses, which serve as lures to probe user intent. Combined with the protected LLM's safe reply, the system inserts proactive bait questions that gradually expose malicious intent through multi-turn interactions. We further introduce the Honeypot Utility Score (HUS), measuring both the attractiveness and feasibility of bait responses, and use a Defense Efficacy Rate (DER) for balancing safety and usability. Initial experiment on MHJ Datasets with recent attack method across GPT-4o show that our system significantly disrupts jailbreak success while preserving benign user experience.

---

### DeLeaker: Dynamic Inference-Time Reweighting For Semantic Leakage Mitigation in Text-to-Image Models

Authors: Mor Ventura, Michael Toker, Or Patashnik, Yonatan Belinkov, Roi Reichart
Published: 2025-10-16
Categories: cs.CV, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2510.15015v1

Text-to-Image (T2I) models have advanced rapidly, yet they remain vulnerable to semantic leakage, the unintended transfer of semantically related features between distinct entities. Existing mitigation strategies are often optimization-based or dependent on external inputs. We introduce DeLeaker, a lightweight, optimization-free inference-time approach that mitigates leakage by directly intervening on the model's attention maps. Throughout the diffusion process, DeLeaker dynamically reweights attention maps to suppress excessive cross-entity interactions while strengthening the identity of each entity. To support systematic evaluation, we introduce SLIM (Semantic Leakage in IMages), the first dataset dedicated to semantic leakage, comprising 1,130 human-verified samples spanning diverse scenarios, together with a novel automatic evaluation framework. Experiments demonstrate that DeLeaker consistently outperforms all baselines, even when they are provided with external information, achieving effective leakage mitigation without compromising fidelity or quality. These results underscore the value of attention control and pave the way for more semantically precise T2I models.

---

### The Tree-SNE Tree Exists

Authors: Jack Kendrick
Published: 2025-10-16
Categories: stat.ML, cs.LG, math.OC
arXiv: https://arxiv.org/abs/2510.15014v1

The clustering and visualisation of high-dimensional data is a ubiquitous task in modern data science. Popular techniques include nonlinear dimensionality reduction methods like t-SNE or UMAP. These methods face the `scale-problem' of clustering: when dealing with the MNIST dataset, do we want to distinguish different digits or do we want to distinguish different ways of writing the digits? The answer is task dependent and depends on scale. We revisit an idea of Robinson & Pierce-Hoffman that exploits an underlying scaling symmetry in t-SNE to replace 2-dimensional with (2+1)-dimensional embeddings where the additional parameter accounts for scale. This gives rise to the t-SNE tree (short: tree-SNE). We prove that the optimal embedding depends continuously on the scaling parameter for all initial conditions outside a set of measure 0: the tree-SNE tree exists. This idea conceivably extends to other attraction-repulsion methods and is illustrated on several examples.

---

### Reliable data clustering with Bayesian community detection

Authors: Magnus Neuman, Jelena Smiljanić, Martin Rosvall
Published: 2025-10-16
Categories: stat.ML, cs.LG, physics.data-an, stat.ME
arXiv: https://arxiv.org/abs/2510.15013v1

From neuroscience and genomics to systems biology and ecology, researchers rely on clustering similarity data to uncover modular structure. Yet widely used clustering methods, such as hierarchical clustering, k-means, and WGCNA, lack principled model selection, leaving them susceptible to noise. A common workaround sparsifies a correlation matrix representation to remove noise before clustering, but this extra step introduces arbitrary thresholds that can distort the structure and lead to unreliable results. To detect reliable clusters, we capitalize on recent advances in network science to unite sparsification and clustering with principled model selection. We test two Bayesian community detection methods, the Degree-Corrected Stochastic Block Model and the Regularized Map Equation, both grounded in the Minimum Description Length principle for model selection. In synthetic data, they outperform traditional approaches, detecting planted clusters under high-noise conditions and with fewer samples. Compared to WGCNA on gene co-expression data, the Regularized Map Equation identifies more robust and functionally coherent gene modules. Our results establish Bayesian community detection as a principled and noise-resistant framework for uncovering modular structure in high-dimensional data across fields.

---

### From Universal Approximation Theorem to Tropical Geometry of Multi-Layer Perceptrons

Authors: Yi-Shan Chu, Yueh-Cheng Kuo
Published: 2025-10-16
Categories: stat.ML, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.15012v1

We revisit the Universal Approximation Theorem(UAT) through the lens of the tropical geometry of neural networks and introduce a constructive, geometry-aware initialization for sigmoidal multi-layer perceptrons (MLPs). Tropical geometry shows that Rectified Linear Unit (ReLU) networks admit decision functions with a combinatorial structure often described as a tropical rational, namely a difference of tropical polynomials. Focusing on planar binary classification, we design purely sigmoidal MLPs that adhere to the finite-sum format of UAT: a finite linear combination of shifted and scaled sigmoids of affine functions. The resulting models yield decision boundaries that already align with prescribed shapes at initialization and can be refined by standard training if desired. This provides a practical bridge between the tropical perspective and smooth MLPs, enabling interpretable, shape-driven initialization without resorting to ReLU architectures. We focus on the construction and empirical demonstrations in two dimensions; theoretical analysis and higher-dimensional extensions are left for future work.

---

### Data-driven Calibration Sample Selection and Forecast Combination in Electricity Price Forecasting: An Application of the ARHNN Method

Authors: Tomasz Serafin, Weronika Nitka
Published: 2025-10-16
Categories: stat.AP, stat.ML
arXiv: https://arxiv.org/abs/2510.15011v1

Calibration sample selection and forecast combination are two simple yet powerful tools used in forecasting. They can be combined with a variety of models to significantly improve prediction accuracy, at the same time offering easy implementation and low computational complexity. While their effectiveness has been repeatedly confirmed in prior scientific literature, the topic is still underexplored in the field of electricity price forecasting. In this research article we apply the Autoregressive Hybrid Nearest Neighbors (ARHNN) method to three long-term time series describing the German, Spanish and New England electricity markets. We show that it outperforms popular literature benchmarks in terms of forecast accuracy by up to 10%. We also propose two simplified variants of the method, granting a vast decrease in computation time with only minor loss of prediction accuracy. Finally, we compare the forecasts' performance in a battery storage system trading case study. We find that using a forecast-driven strategy can achieve up to 80% of theoretical maximum profits while trading, demonstrating business value in practical applications.

---

### Hybrid Autoencoder-Based Framework for Early Fault Detection in Wind Turbines

Authors: Rekha R Nair, Tina Babu, Alavikunhu Panthakkan, Balamurugan Balusamy, Wathiq Mansoor
Published: 2025-10-16
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.15010v1

Wind turbine reliability is critical to the growing renewable energy sector, where early fault detection significantly reduces downtime and maintenance costs. This paper introduces a novel ensemble-based deep learning framework for unsupervised anomaly detection in wind turbines. The method integrates Variational Autoencoders (VAE), LSTM Autoencoders, and Transformer architectures, each capturing different temporal and contextual patterns from high-dimensional SCADA data. A unique feature engineering pipeline extracts temporal, statistical, and frequency-domain indicators, which are then processed by the deep models. Ensemble scoring combines model predictions, followed by adaptive thresholding to detect operational anomalies without requiring labeled fault data. Evaluated on the CARE dataset containing 89 years of real-world turbine data across three wind farms, the proposed method achieves an AUC-ROC of 0.947 and early fault detection up to 48 hours prior to failure. This approach offers significant societal value by enabling predictive maintenance, reducing turbine failures, and enhancing operational efficiency in large-scale wind energy deployments.

---

### Can generative AI figure out figurative language? The influence of idioms on essay scoring by ChatGPT, Gemini, and Deepseek

Authors: Enis Oğuz
Published: 2025-10-16
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.15009v1

The developments in Generative AI technologies have paved the way for numerous innovations in different fields. Recently, Generative AI has been proposed as a competitor to AES systems in evaluating student essays automatically. Considering the potential limitations of AI in processing idioms, this study assessed the scoring performances of Generative AI models for essays with and without idioms by incorporating insights from Corpus Linguistics and Computational Linguistics. Two equal essay lists were created from 348 student essays taken from a corpus: one with multiple idioms present in each essay and another with no idioms in essays. Three Generative AI models (ChatGPT, Gemini, and Deepseek) were asked to score all essays in both lists three times, using the same rubric used by human raters in assigning essay scores. The results revealed excellent consistency for all models, but Gemini outperformed its competitors in interrater reliability with human raters. There was also no detectable bias for any demographic group in AI assessment. For essays with multiple idioms, Gemini followed a the most similar pattern to human raters. While the models in the study demonstrated potential for a hybrid approach, Gemini was the best candidate for the task due to its ability to handle figurative language and showed promise for handling essay-scoring tasks alone in the future.

---

### Rethinking Toxicity Evaluation in Large Language Models: A Multi-Label Perspective

Authors: Zhiqiang Kou, Junyang Chen, Xin-Qiang Cai, Ming-Kun Xie, Biao Liu, Changwei Wang, Lei Feng, Yuheng Jia, Gang Niu, Masashi Sugiyama, Xin Geng
Published: 2025-10-16
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.15007v1

Large language models (LLMs) have achieved impressive results across a range of natural language processing tasks, but their potential to generate harmful content has raised serious safety concerns. Current toxicity detectors primarily rely on single-label benchmarks, which cannot adequately capture the inherently ambiguous and multi-dimensional nature of real-world toxic prompts. This limitation results in biased evaluations, including missed toxic detections and false positives, undermining the reliability of existing detectors. Additionally, gathering comprehensive multi-label annotations across fine-grained toxicity categories is prohibitively costly, further hindering effective evaluation and development. To tackle these issues, we introduce three novel multi-label benchmarks for toxicity detection: \textbf{Q-A-MLL}, \textbf{R-A-MLL}, and \textbf{H-X-MLL}, derived from public toxicity datasets and annotated according to a detailed 15-category taxonomy. We further provide a theoretical proof that, on our released datasets, training with pseudo-labels yields better performance than directly learning from single-label supervision. In addition, we develop a pseudo-label-based toxicity detection method. Extensive experimental results show that our approach significantly surpasses advanced baselines, including GPT-4o and DeepSeek, thus enabling more accurate and reliable evaluation of multi-label toxicity in LLM-generated content.

---

### ES-C51: Expected Sarsa Based C51 Distributional Reinforcement Learning Algorithm

Authors: Rijul Tandon, Peter Vamplew, Cameron Foale
Published: 2025-10-16
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.15006v1

In most value-based reinforcement learning (RL) algorithms, the agent estimates only the expected reward for each action and selects the action with the highest reward. In contrast, Distributional Reinforcement Learning (DRL) estimates the entire probability distribution of possible rewards, providing richer information about uncertainty and variability. C51 is a popular DRL algorithm for discrete action spaces. It uses a Q-learning approach, where the distribution is learned using a greedy Bellman update. However, this can cause problems if multiple actions at a state have similar expected reward but with different distributions, as the algorithm may not learn a stable distribution. This study presents a modified version of C51 (ES-C51) that replaces the greedy Q-learning update with an Expected Sarsa update, which uses a softmax calculation to combine information from all possible actions at a state rather than relying on a single best action. This reduces instability when actions have similar expected rewards and allows the agent to learn higher-performing policies. This approach is evaluated on classic control environments from Gym, and Atari-10 games. For a fair comparison, we modify the standard C51's exploration strategy from e-greedy to softmax, which we refer to as QL-C51 (Q- Learning based C51). The results demonstrate that ES-C51 outperforms QL-C51 across many environments.

---

### TangledFeatures: Robust Feature Selection in Highly Correlated Spaces

Authors: Allen Daniel Sunny
Published: 2025-10-16
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.15005v1

Feature selection is a fundamental step in model development, shaping both predictive performance and interpretability. Yet, most widely used methods focus on predictive accuracy, and their performance degrades in the presence of correlated predictors. To address this gap, we introduce TangledFeatures, a framework for feature selection in correlated feature spaces. It identifies representative features from groups of entangled predictors, reducing redundancy while retaining explanatory power. The resulting feature subset can be directly applied in downstream models, offering a more interpretable and stable basis for analysis compared to traditional selection techniques. We demonstrate the effectiveness of TangledFeatures on Alanine Dipeptide, applying it to the prediction of backbone torsional angles and show that the selected features correspond to structurally meaningful intra-atomic distances that explain variation in these angles.

---

### Automated Snippet-Alignment Data Augmentation for Code Translation

Authors: Zhiming Zhang, Qingfu Zhu, Xianzhen Luo, Yixuan Wang, Bohan Li, Wanxiang Che
Published: 2025-10-16
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2510.15004v1

Code translation aims to translate the code from its source language to the target language and is used in various software development scenarios. Recent developments in Large Language Models (LLMs) have showcased their capabilities in code translation, and parallel corpora play a crucial role in training models for code translation. Parallel corpora can be categorized into program-alignment (PA) and snippet-alignment (SA) data. Although PA data has complete context and is suitable for semantic alignment learning, it may not provide adequate fine-grained training signals due to its extended length, while the brevity of SA data enables more fine-grained alignment learning. Due to limited parallel corpora, researchers explore several augmentation methods for code translation. Previous studies mainly focus on augmenting PA data. In this paper, we propose a data augmentation method that leverages LLMs to generate SA data automatically. To fully leverage both PA data and SA data, we explore a simple yet effective two-stage training strategy, which consistently enhances model performance compared to fine-tuning solely on PA data. Experiments on TransCoder-test demonstrate that our augmented SA data combined with the two-stage training approach yields consistent improvements over the baseline, achieving a maximum gain of 3.78% on pass@k.

---

### Coupled Diffusion Sampling for Training-Free Multi-View Image Editing

Authors: Hadi Alzayer, Yunzhi Zhang, Chen Geng, Jia-Bin Huang, Jiajun Wu
Published: 2025-10-16
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.14981v1

We present an inference-time diffusion sampling method to perform multi-view consistent image editing using pre-trained 2D image editing models. These models can independently produce high-quality edits for each image in a set of multi-view images of a 3D scene or object, but they do not maintain consistency across views. Existing approaches typically address this by optimizing over explicit 3D representations, but they suffer from a lengthy optimization process and instability under sparse view settings. We propose an implicit 3D regularization approach by constraining the generated 2D image sequences to adhere to a pre-trained multi-view image distribution. This is achieved through coupled diffusion sampling, a simple diffusion sampling technique that concurrently samples two trajectories from both a multi-view image distribution and a 2D edited image distribution, using a coupling term to enforce the multi-view consistency among the generated images. We validate the effectiveness and generality of this framework on three distinct multi-view image editing tasks, demonstrating its applicability across various model architectures and highlighting its potential as a general solution for multi-view consistent editing.

---

### Compositional Machine Design as Program Synthesis with LLMs

Authors: Wenqian Zhang, Yangyi Huang, Weiyang Liu, Zhen Liu
Published: 2025-10-16
Categories: cs.AI, cs.CL, cs.CV, cs.GR, cs.LG
arXiv: https://arxiv.org/abs/2510.14980v4

Large language models (LLMs) have shown strong abilities in writing and revising programs, yet many program-synthesis benchmarks still evaluate programs in symbolic or digital environments. We introduce compositional machine design, a physically grounded form of program synthesis where machines are written as programs that compose standardized parts, and success is determined by simulated physical behavior. To study this problem, we present BesiegeField, a testbed built on the machine-building game Besiege. In BesiegeField, LLM agents generate machine programs from textual functional demands, execute the resulting machines in simulation, and receive rewards and state feedback. We benchmark LLM agents across representative machine-design tasks under single-agent generation, iterative editing, and hierarchical workflows. Strong models recover task-relevant structures and sometimes achieve nontrivial physical performance, but often struggle with spatially precise assembly, mechanism-level planning, and translating feedback into useful structural edits. We further finetune Qwen2.5-14B, an open-source LLM, with reinforcement learning from simulation-derived rewards. We find that, under a fixed generation budget, RL improves the best machine discovered. We additionally evaluate human performance to provide a reference point for task difficulty. These results establish compositional machine design as a testbed for studying LLM agents that synthesize executable machine programs and improve them through physical feedback.

---

### From Pixels to Words -- Towards Native Vision-Language Primitives at Scale

Authors: Haiwen Diao, Mingxuan Li, Silei Wu, Linjun Dai, Xiaohua Wang, Hanming Deng, Lewei Lu, Dahua Lin, Ziwei Liu
Published: 2025-10-16
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.14979v2

The edifice of native Vision-Language Models (VLMs) has emerged as a rising contender to typical modular VLMs, shaped by evolving model architectures and training paradigms. Yet, two lingering clouds cast shadows over its widespread exploration and promotion: (-) What fundamental constraints set native VLMs apart from modular ones, and to what extent can these barriers be overcome? (-) How to make research in native VLMs more accessible and democratized, thereby accelerating progress in the field. In this paper, we clarify these challenges and outline guiding principles for constructing native VLMs. Specifically, one native VLM primitive should: (i) effectively align pixel and word representations within a shared semantic space; (ii) seamlessly integrate the strengths of formerly separate vision and language modules; (iii) inherently embody various cross-modal properties that support unified vision-language encoding, aligning, and reasoning. Hence, we launch NEO, a novel family of native VLMs built from first principles, greatly narrowing the gap with top-tier modular counterparts across diverse real-world scenarios. With 390M image-text examples, NEO efficiently develops visual perception from scratch while mitigating vision-language conflicts inside a dense and monolithic model crafted from our elaborate primitives. We position NEO as a cornerstone for scalable and powerful native VLM development, paired with a rich set of reusable components that foster a cost-effective and extensible ecosystem. Our code and models are publicly available at: https://github.com/EvolvingLMMs-Lab/NEO.

---

### Learning an Image Editing Model without Image Editing Pairs

Authors: Nupur Kumari, Sheng-Yu Wang, Nanxuan Zhao, Yotam Nitzan, Yuheng Li, Krishna Kumar Singh, Richard Zhang, Eli Shechtman, Jun-Yan Zhu, Xun Huang
Published: 2025-10-16
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2510.14978v2

Recent image editing models have achieved impressive results while following natural language editing instructions, but they rely on supervised fine-tuning with large datasets of input-target pairs. This is a critical bottleneck, as such naturally occurring pairs are hard to curate at scale. Current workarounds use synthetic training pairs that leverage the zero-shot capabilities of existing models. However, this can propagate and magnify the artifacts of the pretrained model into the final trained model. In this work, we present a new training paradigm that eliminates the need for paired data entirely. Our approach directly optimizes a few-step diffusion model by unrolling it during training and leveraging feedback from vision-language models (VLMs). For each input and editing instruction, the VLM evaluates if an edit follows the instruction and preserves unchanged content, providing direct gradients for end-to-end optimization. To ensure visual fidelity, we incorporate distribution matching loss (DMD), which constrains generated images to remain within the image manifold learned by pretrained models. We evaluate our method on standard benchmarks and include an extensive ablation study. Without any paired data, our method performs on par with various image editing diffusion models trained on extensive supervised paired data, under the few-step setting. Given the same VLM as the reward model, we also outperform RL-based techniques like Flow-GRPO.

---

### Terra: Explorable Native 3D World Model with Point Latents

Authors: Yuanhui Huang, Weiliang Chen, Wenzhao Zheng, Xin Tao, Pengfei Wan, Jie Zhou, Jiwen Lu
Published: 2025-10-16
Categories: cs.CV, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.14977v1

World models have garnered increasing attention for comprehensive modeling of the real world. However, most existing methods still rely on pixel-aligned representations as the basis for world evolution, neglecting the inherent 3D nature of the physical world. This could undermine the 3D consistency and diminish the modeling efficiency of world models. In this paper, we present Terra, a native 3D world model that represents and generates explorable environments in an intrinsic 3D latent space. Specifically, we propose a novel point-to-Gaussian variational autoencoder (P2G-VAE) that encodes 3D inputs into a latent point representation, which is subsequently decoded as 3D Gaussian primitives to jointly model geometry and appearance. We then introduce a sparse point flow matching network (SPFlow) for generating the latent point representation, which simultaneously denoises the positions and features of the point latents. Our Terra enables exact multi-view consistency with native 3D representation and architecture, and supports flexible rendering from any viewpoint with only a single generation process. Furthermore, Terra achieves explorable world modeling through progressive generation in the point latent space. We conduct extensive experiments on the challenging indoor scenes from ScanNet v2. Terra achieves state-of-the-art performance in both reconstruction and generation with high 3D consistency.

---

### Ponimator: Unfolding Interactive Pose for Versatile Human-human Interaction Animation

Authors: Shaowei Liu, Chuan Guo, Bing Zhou, Jian Wang
Published: 2025-10-16
Categories: cs.CV, cs.GR, cs.RO
arXiv: https://arxiv.org/abs/2510.14976v1

Close-proximity human-human interactive poses convey rich contextual information about interaction dynamics. Given such poses, humans can intuitively infer the context and anticipate possible past and future dynamics, drawing on strong priors of human behavior. Inspired by this observation, we propose Ponimator, a simple framework anchored on proximal interactive poses for versatile interaction animation. Our training data consists of close-contact two-person poses and their surrounding temporal context from motion-capture interaction datasets. Leveraging interactive pose priors, Ponimator employs two conditional diffusion models: (1) a pose animator that uses the temporal prior to generate dynamic motion sequences from interactive poses, and (2) a pose generator that applies the spatial prior to synthesize interactive poses from a single pose, text, or both when interactive poses are unavailable. Collectively, Ponimator supports diverse tasks, including image-based interaction animation, reaction animation, and text-to-interaction synthesis, facilitating the transfer of interaction knowledge from high-quality mocap data to open-world scenarios. Empirical experiments across diverse datasets and applications demonstrate the universality of the pose prior and the effectiveness and robustness of our framework.

---

### WithAnyone: Towards Controllable and ID Consistent Image Generation

Authors: Hengyuan Xu, Wei Cheng, Peng Xing, Yixiao Fang, Shuhan Wu, Rui Wang, Xianfang Zeng, Daxin Jiang, Gang Yu, Xingjun Ma, Yu-Gang Jiang
Published: 2025-10-16
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.14975v1

Identity-consistent generation has become an important focus in text-to-image research, with recent models achieving notable success in producing images aligned with a reference identity. Yet, the scarcity of large-scale paired datasets containing multiple images of the same individual forces most approaches to adopt reconstruction-based training. This reliance often leads to a failure mode we term copy-paste, where the model directly replicates the reference face rather than preserving identity across natural variations in pose, expression, or lighting. Such over-similarity undermines controllability and limits the expressive power of generation. To address these limitations, we (1) construct a large-scale paired dataset MultiID-2M, tailored for multi-person scenarios, providing diverse references for each identity; (2) introduce a benchmark that quantifies both copy-paste artifacts and the trade-off between identity fidelity and variation; and (3) propose a novel training paradigm with a contrastive identity loss that leverages paired data to balance fidelity with diversity. These contributions culminate in WithAnyone, a diffusion-based model that effectively mitigates copy-paste while preserving high identity similarity. Extensive qualitative and quantitative experiments demonstrate that WithAnyone significantly reduces copy-paste artifacts, improves controllability over pose and expression, and maintains strong perceptual quality. User studies further validate that our method achieves high identity fidelity while enabling expressive controllable generation.

---

### pi-Flow: Policy-Based Few-Step Generation via Imitation Distillation

Authors: Hansheng Chen, Kai Zhang, Hao Tan, Leonidas Guibas, Gordon Wetzstein, Sai Bi
Published: 2025-10-16
Categories: cs.LG, cs.AI, cs.CV
arXiv: https://arxiv.org/abs/2510.14974v3

Few-step diffusion or flow-based generative models typically distill a velocity-predicting teacher into a student that predicts a shortcut towards denoised data. This format mismatch has led to complex distillation procedures that often suffer from a quality-diversity trade-off. To address this, we propose policy-based flow models ($π$-Flow). $π$-Flow modifies the output layer of a student flow model to predict a network-free policy at one timestep. The policy then produces dynamic flow velocities at future substeps with negligible overhead, enabling fast and accurate ODE integration on these substeps without extra network evaluations. To match the policy's ODE trajectory to the teacher's, we introduce a novel imitation distillation approach, which matches the policy's velocity to the teacher's along the policy's trajectory using a standard $\ell_2$ flow matching loss. By simply mimicking the teacher's behavior, $π$-Flow enables stable and scalable training and avoids the quality-diversity trade-off. On ImageNet 256$^2$, it attains a 1-NFE FID of 2.85, outperforming previous 1-NFE models of the same DiT architecture. On FLUX.1-12B and Qwen-Image-20B at 4 NFEs, $π$-Flow achieves substantially better diversity than state-of-the-art DMD models, while maintaining teacher-level quality.

---

### Attention Is All You Need for KV Cache in Diffusion LLMs

Authors: Quan Nguyen-Tri, Mukul Ranjan, Zhiqiang Shen
Published: 2025-10-16
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.14973v2

This work studies how to adaptively recompute key-value (KV) caches for diffusion large language models (DLMs) to maximize prediction accuracy while minimizing decoding latency. Prior methods' decoders recompute QKV for all tokens at every denoising step and layer, despite KV states changing little across most steps, especially in shallow layers, leading to substantial redundancy. We make three observations: (1) distant ${\bf MASK}$ tokens primarily act as a length-bias and can be cached block-wise beyond the active prediction window; (2) KV dynamics increase with depth, suggesting that selective refresh starting from deeper layers is sufficient; and (3) the most-attended token exhibits the smallest KV drift, providing a conservative lower bound on cache change for other tokens. Building on these, we propose ${\bf Elastic-Cache}$, a training-free, architecture-agnostic strategy that jointly decides ${when}$ to refresh (via an attention-aware drift test on the most-attended token) and ${where}$ to refresh (via a depth-aware schedule that recomputes from a chosen layer onward while reusing shallow-layer caches and off-window MASK caches). Unlike fixed-period schemes, Elastic-Cache performs adaptive, layer-aware cache updates for diffusion LLMs, reducing redundant computation and accelerating decoding with negligible loss in generation quality. Experiments on LLaDA-Instruct, LLaDA-1.5, and LLaDA-V across mathematical reasoning and code generation tasks demonstrate consistent speedups: $8.7\times$ on GSM8K (256 tokens), and $45.1\times$ on longer sequences, while consistently maintaining higher accuracy than the baseline. Our method achieves significantly higher throughput ($6.8\times$ on GSM8K) than existing confidence-based approaches while preserving generation quality, enabling practical deployment of diffusion LLMs.

---

### TokDrift: When LLM Speaks in Subwords but Code Speaks in Grammar

Authors: Yinxi Li, Yuntian Deng, Pengyu Nie
Published: 2025-10-16
Categories: cs.CL, cs.AI, cs.LG, cs.PL, cs.SE
arXiv: https://arxiv.org/abs/2510.14972v1

Large language models (LLMs) for code rely on subword tokenizers, such as byte-pair encoding (BPE), learned from mixed natural language text and programming language code but driven by statistics rather than grammar. As a result, semantically identical code snippets can be tokenized differently depending on superficial factors such as whitespace or identifier naming. To measure the impact of this misalignment, we introduce TokDrift, a framework that applies semantic-preserving rewrite rules to create code variants differing only in tokenization. Across nine code LLMs, including large ones with over 30B parameters, even minor formatting changes can cause substantial shifts in model behavior. Layer-wise analysis shows that the issue originates in early embeddings, where subword segmentation fails to capture grammar token boundaries. Our findings identify misaligned tokenization as a hidden obstacle to reliable code understanding and generation, highlighting the need for grammar-aware tokenization for future code LLMs.

---

### Biology-informed neural networks learn nonlinear representations from omics data to improve genomic prediction and interpretability

Authors: Katiana Kontolati, Rini Jasmine Gladstone, Ian Davis, Ethan Pickering
Published: 2025-10-16
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.14970v1

We extend biologically-informed neural networks (BINNs) for genomic prediction (GP) and selection (GS) in crops by integrating thousands of single-nucleotide polymorphisms (SNPs) with multi-omics measurements and prior biological knowledge. Traditional genotype-to-phenotype (G2P) models depend heavily on direct mappings that achieve only modest accuracy, forcing breeders to conduct large, costly field trials to maintain or marginally improve genetic gain. Models that incorporate intermediate molecular phenotypes such as gene expression can achieve higher predictive fit, but they remain impractical for GS since such data are unavailable at deployment or design time. BINNs overcome this limitation by encoding pathway-level inductive biases and leveraging multi-omics data only during training, while using genotype data alone during inference. Applied to maize gene-expression and multi-environment field-trial data, BINN improves rank-correlation accuracy by up to 56% within and across subpopulations under sparse-data conditions and nonlinearly identifies genes that GWAS/TWAS fail to uncover. With complete domain knowledge for a synthetic metabolomics benchmark, BINN reduces prediction error by 75% relative to conventional neural nets and correctly identifies the most important nonlinear pathway. Importantly, both cases show highly sensitive BINN latent variables correlate with the experimental quantities they represent, despite not being trained on them. This suggests BINNs learn biologically-relevant representations, nonlinear or linear, from genotype to phenotype. Together, BINNs establish a framework that leverages intermediate domain information to improve genomic prediction accuracy and reveal nonlinear biological relationships that can guide genomic selection, candidate gene selection, pathway enrichment, and gene-editing prioritization.

---

### LLMs as Scalable, General-Purpose Simulators For Evolving Digital Agent Training

Authors: Yiming Wang, Da Yin, Yuedong Cui, Ruichen Zheng, Zhiqian Li, Zongyu Lin, Di Wu, Xueqing Wu, Chenchen Ye, Yu Zhou, Kai-Wei Chang
Published: 2025-10-16
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.14969v1

Digital agents require diverse, large-scale UI trajectories to generalize across real-world tasks, yet collecting such data is prohibitively expensive in both human annotation, infra and engineering perspectives. To this end, we introduce $\textbf{UI-Simulator}$, a scalable paradigm that generates structured UI states and transitions to synthesize training trajectories at scale. Our paradigm integrates a digital world simulator for diverse UI states, a guided rollout process for coherent exploration, and a trajectory wrapper that produces high-quality and diverse trajectories for agent training. We further propose $\textbf{UI-Simulator-Grow}$, a targeted scaling strategy that enables more rapid and data-efficient scaling by prioritizing high-impact tasks and synthesizes informative trajectory variants. Experiments on WebArena and AndroidWorld show that UI-Simulator rivals or surpasses open-source agents trained on real UIs with significantly better robustness, despite using weaker teacher models. Moreover, UI-Simulator-Grow matches the performance of Llama-3-70B-Instruct using only Llama-3-8B-Instruct as the base model, highlighting the potential of targeted synthesis scaling paradigm to continuously and efficiently enhance the digital agents.

---

### RDD: Retrieval-Based Demonstration Decomposer for Planner Alignment in Long-Horizon Tasks

Authors: Mingxuan Yan, Yuping Wang, Zechun Liu, Jiachen Li
Published: 2025-10-16
Categories: cs.RO, cs.AI, cs.CV, cs.LG, eess.SY
arXiv: https://arxiv.org/abs/2510.14968v1

To tackle long-horizon tasks, recent hierarchical vision-language-action (VLAs) frameworks employ vision-language model (VLM)-based planners to decompose complex manipulation tasks into simpler sub-tasks that low-level visuomotor policies can easily handle. Typically, the VLM planner is finetuned to learn to decompose a target task. This finetuning requires target task demonstrations segmented into sub-tasks by either human annotation or heuristic rules. However, the heuristic subtasks can deviate significantly from the training data of the visuomotor policy, which degrades task performance. To address these issues, we propose a Retrieval-based Demonstration Decomposer (RDD) that automatically decomposes demonstrations into sub-tasks by aligning the visual features of the decomposed sub-task intervals with those from the training data of the low-level visuomotor policies. Our method outperforms the state-of-the-art sub-task decomposer on both simulation and real-world tasks, demonstrating robustness across diverse settings. Code and more results are available at rdd-neurips.github.io.

---

### Information Gain-based Policy Optimization: A Simple and Effective Approach for Multi-Turn Search Agents

Authors: Guoqing Wang, Sunhao Dai, Guangze Ye, Zeyu Gan, Wei Yao, Yong Deng, Xiaofeng Wu, Zhenzhe Ying
Published: 2025-10-16
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.14967v2

Large language model (LLM)-based agents are increasingly trained with reinforcement learning (RL) to enhance their ability to interact with external environments through tool use, particularly in search-based settings that require multi-turn reasoning and knowledge acquisition. However, existing approaches typically rely on outcome-based rewards that are only provided exclusively upon generating the final answer. This reward sparsity becomes particularly problematic in multi-turn settings, where long trajectories exacerbate three critical issues: (i) advantage collapse, where all rollouts receive identical rewards and provide no useful learning signals; (ii) lack of fine-grained credit assignment, where the correctness of intermediate turns is obscured, especially in long-horizon tasks; and (iii) poor sample efficiency, where each rollout yields only a single outcome signal, leading to low data utilization. In this paper, we propose Information Gain-based Policy Optimization (IGPO), a simple yet effective RL framework that provides dense and intrinsic supervision for multi-turn agent training. IGPO models each interaction turn as an incremental process of acquiring information about the ground truth, and defines turn-level rewards as the marginal increase in the policy's probability of producing the correct answer. Unlike prior process-level reward approaches that depend on external reward models or costly Monte Carlo estimation, IGPO derives intrinsic rewards directly from the model's own belief updates. These intrinsic turn-level rewards are combined with outcome-level supervision to form dense reward signals. Extensive experiments on both in-domain and out-of-domain benchmarks demonstrate that IGPO consistently outperforms strong baselines in multi-turn scenarios, achieving higher accuracy and improved data efficiency. Our code is available at https://github.com/GuoqingWang1/IGPO.

---

### Identity-Link IRT for Label-Free LLM Evaluation: Preserving Additivity in TVD-MI Scores

Authors: Zachary Robertson
Published: 2025-10-16
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2510.14966v1

Pairwise comparisons of large language models using total variation distance mutual information (TVD-MI) produce binary critic decisions per pair. We show that averaging TVD-MI's binary trials yields centered-probability scores with additive structure suitable for item-response theory (IRT) without nonlinear link functions. Maximum-likelihood approaches to IRT use logistic links, but we find empirically that these transformations introduce curvature that breaks additivity: across three domains, the identity link yields median curl on raw data of 0.080-0.150 (P95 = (0.474, 0.580)), whereas probit/logit introduce substantially higher violations (median (0.245, 0.588), P95 (0.825, 2.252)). We derive this clipped-linear model from Gini entropy maximization, yielding a box-constrained least-squares formulation that handles boundary saturation. At 33% coverage, we achieve holdout RMSE $0.117 \pm 0.008$ while preserving agent rankings (Spearman $ρ= 0.972 \pm 0.015$), three times fewer evaluations than full dense. Judge robustness analysis (GPT-4o-mini vs. Llama3-70b) shows strong agreement in agent rankings ($ρ= 0.872$) and consistent identity-link advantage. TVD-MI's geometry is best preserved by identity mapping for efficient LLM evaluation, applicable to other bounded-response domains.

---

### ChangingGrounding: 3D Visual Grounding in Changing Scenes

Authors: Miao Hu, Zhiwei Huang, Tai Wang, Jiangmiao Pang, Dahua Lin, Nanning Zheng, Runsen Xu
Published: 2025-10-16
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.14965v1

Real-world robots localize objects from natural-language instructions while scenes around them keep changing. Yet most of the existing 3D visual grounding (3DVG) method still assumes a reconstructed and up-to-date point cloud, an assumption that forces costly re-scans and hinders deployment. We argue that 3DVG should be formulated as an active, memory-driven problem, and we introduce ChangingGrounding, the first benchmark that explicitly measures how well an agent can exploit past observations, explore only where needed, and still deliver precise 3D boxes in changing scenes. To set a strong reference point, we also propose Mem-ChangingGrounder, a zero-shot method for this task that marries cross-modal retrieval with lightweight multi-view fusion: it identifies the object type implied by the query, retrieves relevant memories to guide actions, then explores the target efficiently in the scene, falls back when previous operations are invalid, performs multi-view scanning of the target, and projects the fused evidence from multi-view scans to get accurate object bounding boxes. We evaluate different baselines on ChangingGrounding, and our Mem-ChangingGrounder achieves the highest localization accuracy while greatly reducing exploration cost. We hope this benchmark and method catalyze a shift toward practical, memory-centric 3DVG research for real-world applications. Project page: https://hm123450.github.io/CGB/ .

---