# Research Papers — 2025-10 · bundle page 91 of 217

> Full-text markdown of papers #4501–4550 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/91
[← Previous bundle](https://aipod.dev/papers/archive/2025-10/page/90.md)
[Next bundle →](https://aipod.dev/papers/archive/2025-10/page/92.md)

### UltraImageGen: Efficient Ultra-High-Resolution Image Generation with Hierarchical Local Attention

Authors: Yuyao Zhang, Yu-Wing Tai
Published: 2025-10-18
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.16325v4

Ultra-high-resolution text-to-image generation is increasingly vital for applications requiring fine-grained textures and global structural fidelity, yet state-of-the-art text-to-image diffusion models such as FLUX and SD3 remain confined to sub 2MP (< $1K\times2K$) resolutions due to the quadratic complexity of attention mechanisms and the scarcity of high-quality high-resolution training data. We present UltraImageGen, a novel framework that introduces hierarchical local attention with low-resolution global guidance, enabling efficient, scalable, and semantically coherent image synthesis at ultra-high resolutions. Specifically, high-resolution latents are divided into hardware aligned fixed-size local windows to reduce attention complexity from quadratic to near-linear, while a low-resolution latent equipped with scaled positional embeddings injects global semantics as an anchor. A lightweight LoRA adaptation bridges global and local pathways during denoising, ensuring consistency across structure and detail. To maximize inference efficiency and achieve scalable ultra-high-resolution generation, we repermute token sequence in window-first order, so that the GPU-friendly dense local blocks in attention calculation equals to the fixed-size local window in 2D regardless of resolution. Together ourwork reliably scales the pretrained model to resolutions higher than $8K$ with more than $10\times$ speed up and significantly lower memory usage. Extensive experiments demonstrate that ourwork achieves superior quality while maintaining computational efficiency, establishing a practical paradigm for advancing ultra-high-resolution image generation.

---

### Memorizing Long-tail Data Can Help Generalization Through Composition

Authors: Mo Zhou, Haoyang Ma, Rong Ge
Published: 2025-10-18
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2510.16322v1

Deep learning has led researchers to rethink the relationship between memorization and generalization. In many settings, memorization does not hurt generalization due to implicit regularization and may help by memorizing long-tailed examples. In this paper, we consider the synergy between memorization and simple composition -- the ability to make correct prediction on a combination of long-tailed features. Theoretically, we show that for a linear setting, memorization together with composition can help the model make correct predictions on rare test examples that require a combination of long-tailed features, even if such combinations were never observed in the training data. Experiments on neural network architecture on simple data show that the theoretical insight extends beyond the linear setting, and we further observe that the composition capability of the model depends on its architecture.

---

### Time-Embedded Algorithm Unrolling for Computational MRI

Authors: Junno Yun, Yaşar Utku Alçalar, Mehmet Akçakaya
Published: 2025-10-18
Categories: eess.IV, cs.AI, cs.CV, cs.LG, physics.med-ph
arXiv: https://arxiv.org/abs/2510.16321v1

Algorithm unrolling methods have proven powerful for solving the regularized least squares problem in computational magnetic resonance imaging (MRI). These approaches unfold an iterative algorithm with a fixed number of iterations, typically alternating between a neural network-based proximal operator for regularization, a data fidelity operation and auxiliary updates with learnable parameters. While the connection to optimization methods dictate that the proximal operator network should be shared across unrolls, this can introduce artifacts or blurring. Heuristically, practitioners have shown that using distinct networks may be beneficial, but this significantly increases the number of learnable parameters, making it challenging to prevent overfitting. To address these shortcomings, by taking inspirations from proximal operators with varying thresholds in approximate message passing (AMP) and the success of time-embedding in diffusion models, we propose a time-embedded algorithm unrolling scheme for inverse problems. Specifically, we introduce a novel perspective on the iteration-dependent proximal operation in vector AMP (VAMP) and the subsequent Onsager correction in the context of algorithm unrolling, framing them as a time-embedded neural network. Similarly, the scalar weights in the data fidelity operation and its associated Onsager correction are cast as time-dependent learnable parameters. Our extensive experiments on the fastMRI dataset, spanning various acceleration rates and datasets, demonstrate that our method effectively reduces aliasing artifacts and mitigates noise amplification, achieving state-of-the-art performance. Furthermore, we show that our time-embedding strategy extends to existing algorithm unrolling approaches, enhancing reconstruction quality without increasing the computational complexity significantly.

---

### Scaling Laws for Deepfake Detection

Authors: Wenhao Wang, Jusheng Zhang, Longqi Cai, Taihong Xiao, Yuxiao Wang, Ming-Hsuan Yang
Published: 2025-10-18
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.16320v2

This paper presents a systematic study of scaling laws for the deepfake detection task. Specifically, we analyze the model performance against the number of real image domains, deepfake generation methods, and training images. Since no existing dataset meets the scale requirements for this research, we construct ScaleDF, the largest dataset to date in this field, which contains over 5.8 million real images from 51 different datasets (domains) and more than 8.8 million fake images generated by 102 deepfake methods. Using ScaleDF, we observe power-law scaling similar to that shown in large language models (LLMs). Specifically, the average detection error follows a predictable power-law decay as either the number of real domains or the number of deepfake methods increases. This key observation not only allows us to forecast the number of additional real domains or deepfake methods required to reach a target performance, but also inspires us to counter the evolving deepfake technology in a data-centric manner. Beyond this, we examine the role of pre-training and data augmentations in deepfake detection under scaling, as well as the limitations of scaling itself.The ScaleDF dataset is available at https://huggingface.co/datasets/WenhaoWang/ScaleDF.

---

### Stroke2Sketch: Harnessing Stroke Attributes for Training-Free Sketch Generation

Authors: Rui Yang, Huining Li, Yiyi Long, Xiaojun Wu, Shengfeng He
Published: 2025-10-18
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.16319v1

Generating sketches guided by reference styles requires precise transfer of stroke attributes, such as line thickness, deformation, and texture sparsity, while preserving semantic structure and content fidelity. To this end, we propose Stroke2Sketch, a novel training-free framework that introduces cross-image stroke attention, a mechanism embedded within self-attention layers to establish fine-grained semantic correspondences and enable accurate stroke attribute transfer. This allows our method to adaptively integrate reference stroke characteristics into content images while maintaining structural integrity. Additionally, we develop adaptive contrast enhancement and semantic-focused attention to reinforce content preservation and foreground emphasis. Stroke2Sketch effectively synthesizes stylistically faithful sketches that closely resemble handcrafted results, outperforming existing methods in expressive stroke control and semantic coherence. Codes are available at https://github.com/rane7/Stroke2Sketch.

---

### Toward General Digraph Contrastive Learning: A Dual Spatial Perspective

Authors: Zhengyu Wu, Daohan Su, Yang Zhang, Xunkai Li, Rong-Hua Li, Guoren Wang
Published: 2025-10-18
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.16311v3

Graph Contrastive Learning (GCL) has emerged as a powerful tool for extracting consistent representations from graphs, independent of labeled information. However, existing methods predominantly focus on undirected graphs, disregarding the pivotal directional information that is fundamental and indispensable in real-world networks (e.g., social networks and recommendations).In this paper, we introduce S2-DiGCL, a novel framework that emphasizes spatial insights from complex and real domain perspectives for directed graph (digraph) contrastive learning. From the complex-domain perspective, S2-DiGCL introduces personalized perturbations into the magnetic Laplacian to adaptively modulate edge phases and directional semantics. From the real-domain perspective, it employs a path-based subgraph augmentation strategy to capture fine-grained local asymmetries and topological dependencies. By jointly leveraging these two complementary spatial views, S2-DiGCL constructs high-quality positive and negative samples, leading to more general and robust digraph contrastive learning. Extensive experiments on 7 real-world digraph datasets demonstrate the superiority of our approach, achieving SOTA performance with 4.41% improvement in node classification and 4.34% in link prediction under both supervised and unsupervised settings.

---

### Lung Cancer Classification from CT Images Using ResNet

Authors: Olajumoke O. Adekunle, Joseph D. Akinyemi, Khadijat T. Ladoja, Olufade F. W. Onifade
Published: 2025-10-18
Categories: eess.IV, cs.AI, cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2510.16310v1

Lung cancer, a malignancy originating in lung tissues, is commonly diagnosed and classified using medical imaging techniques, particularly computed tomography (CT). Despite the integration of machine learning and deep learning methods, the predictive efficacy of automated systems for lung cancer classification from CT images remains below the desired threshold for clinical adoption. Existing research predominantly focuses on binary classification, distinguishing between malignant and benign lung nodules. In this study, a novel deep learning-based approach is introduced, aimed at an improved multi-class classification, discerning various subtypes of lung cancer from CT images. Leveraging a pre-trained ResNet model, lung tissue images were classified into three distinct classes, two of which denote malignancy and one benign. Employing a dataset comprising 15,000 lung CT images sourced from the LC25000 histopathological images, the ResNet50 model was trained on 10,200 images, validated on 2,550 images, and tested on the remaining 2,250 images. Through the incorporation of custom layers atop the ResNet architecture and meticulous hyperparameter fine-tuning, a remarkable test accuracy of 98.8% was recorded. This represents a notable enhancement over the performance of prior models on the same dataset.

---

### MedRule-KG: A Knowledge-Graph--Steered Scaffold for Mathematical Reasoning with a Lightweight Verifier

Authors: Crystal Su
Published: 2025-10-18
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.16309v3

Large language models (LLMs) often produce fluent reasoning steps while violating simple mathematical or logical constraints. We introduce MedRule-KG, a compact typed knowledge graph coupled with a symbolic verifier, designed to enforce mathematically interpretable rules in reasoning tasks. MedRule-KG encodes entities, relations, and three domain-inspired rules, while the verifier checks predictions and applies minimal corrections to guarantee consistency. On a 90-example FDA-derived benchmark, grounding in MedRule-KG improves exact match (EM) from 0.767 to 0.900, and adding the verifier yields 1.000 EM while eliminating rule violations entirely. We demonstrate how MedRule-KG provides a general scaffold for safe mathematical reasoning, discuss ablations, and release code and data to encourage reproducibility.

---

### Scaffold-Aware Generative Augmentation and Reranking for Enhanced Virtual Screening

Authors: Xin Wang, Yu Wang, Yunchao Liu, Jens Meiler, Tyler Derr
Published: 2025-10-18
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.16306v2

Ligand-based virtual screening (VS) is an essential step in drug discovery that evaluates large chemical libraries to identify compounds that potentially bind to a therapeutic target. However, VS faces three major challenges: class imbalance due to the low active rate, structural imbalance among active molecules where certain scaffolds dominate, and the need to identify structurally diverse active compounds for novel drug development. We introduce ScaffAug, a scaffold-aware VS framework that addresses these challenges through three modules. The augmentation module first generates synthetic data conditioned on scaffolds of actual hits using generative models, specifically a graph diffusion model. This helps mitigate the class imbalance and furthermore the structural imbalance, due to our proposed scaffold-aware sampling algorithm, designed to produce more samples for active molecules with underrepresented scaffolds. A model-agnostic self-training module is then used to safely integrate the generated synthetic data from our augmentation module with the original labeled data. Lastly, we introduce a reranking module that improves VS by enhancing scaffold diversity in the top recommended set of molecules, while still maintaining and even enhancing the overall general performance of identifying novel, active compounds. We conduct comprehensive computational experiments across five target classes, comparing ScaffAug against existing baseline methods by reporting the performance of multiple evaluation metrics and performing ablation studies on ScaffAug. Overall, this work introduces novel perspectives on effectively enhancing VS by leveraging generative augmentations, reranking, and general scaffold-awareness.

---

### DTKG: Dual-Track Knowledge Graph-Verified Reasoning Framework for Multi-Hop QA

Authors: Changhao Wang, Yanfang Liu, Xinxin Fan, Ao Tian, Lanzhi Zhou, Yunfeng Lu
Published: 2025-10-18
Categories: cs.AI, cs.IR
arXiv: https://arxiv.org/abs/2510.16302v2

Multi-hop reasoning for question answering (QA) plays a critical role in retrieval-augmented generation (RAG) for modern large language models (LLMs). The accurate answer can be obtained through retrieving relational structure of entities from knowledge graph (KG). Regarding the inherent relation-dependency and reasoning pattern, multi-hop reasoning can be in general classified into two categories: i) parallel fact-verification multi-hop reasoning question, i.e., requiring simultaneous verifications of multiple independent sub-questions; and ii) chained multi-hop reasoning questions, i.e., demanding sequential multi-step inference with intermediate conclusions serving as essential premises for subsequent reasoning. Currently, the multi-hop reasoning approaches singly employ one of two techniques: LLM response-based fact verification and KG path-based chain construction. Nevertheless, the former excels at parallel fact-verification but underperforms on chained reasoning tasks, while the latter demonstrates proficiency in chained multi-hop reasoning but suffers from redundant path retrieval when handling parallel fact-verification reasoning. These limitations deteriorate the efficiency and accuracy for multi-hop QA tasks. To address this challenge, we propose a novel dual-track KG verification and reasoning framework DTKG, which is inspired by the Dual Process Theory in cognitive science. Specifically, DTKG comprises two main stages: the Classification Stage and the Branch Processing Stage.

---

### OpenLVLM-MIA: A Controlled Benchmark Revealing the Limits of Membership Inference Attacks on Large Vision-Language Models

Authors: Ryoto Miyamoto, Xin Fan, Fuyuko Kido, Tsuneo Matsumoto, Hayato Yamana
Published: 2025-10-18
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.16295v2

OpenLVLM-MIA is a new benchmark that highlights fundamental challenges in evaluating membership inference attacks (MIA) against large vision-language models (LVLMs). While prior work has reported high attack success rates, our analysis suggests that these results often arise from detecting distributional bias introduced during dataset construction rather than from identifying true membership status. To address this issue, we introduce a controlled benchmark of 6{,}000 images where the distributions of member and non-member samples are carefully balanced, and ground-truth membership labels are provided across three distinct training stages. Experiments using OpenLVLM-MIA demonstrated that the performance of state-of-the-art MIA methods approached chance-level. OpenLVLM-MIA, designed to be transparent and unbiased benchmark, clarifies certain limitations of MIA research on LVLMs and provides a solid foundation for developing stronger privacy-preserving techniques.

---

### Synergizing chemical and AI communities for advancing laboratories of the future

Authors: Saejin Oh, Xinyi Fang, I-Hsin Lin, Paris Dee, Christopher S. Dunham, Stacy M. Copp, Abigail G. Doyle, Javier Read de Alaniz, Mengyang Gu
Published: 2025-10-18
Categories: stat.AP, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.16293v1

The development of automated experimental facilities and the digitization of experimental data have introduced numerous opportunities to radically advance chemical laboratories. As many laboratory tasks involve predicting and understanding previously unknown chemical relationships, machine learning (ML) approaches trained on experimental data can substantially accelerate the conventional design-build-test-learn process. This outlook article aims to help chemists understand and begin to adopt ML predictive models for a variety of laboratory tasks, including experimental design, synthesis optimization, and materials characterization. Furthermore, this article introduces how artificial intelligence (AI) agents based on large language models can help researchers acquire background knowledge in chemical or data science and accelerate various aspects of the discovery process. We present three case studies in distinct areas to illustrate how ML models and AI agents can be leveraged to reduce time-consuming experiments and manual data analysis. Finally, we highlight existing challenges that require continued synergistic effort from both experimental and computational communities to address.

---

### QSVD: Efficient Low-rank Approximation for Unified Query-Key-Value Weight Compression in Low-Precision Vision-Language Models

Authors: Yutong Wang, Haiyu Wang, Sai Qian Zhang
Published: 2025-10-18
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.16292v1

Vision-Language Models (VLMs) are integral to tasks such as image captioning and visual question answering, but their high computational cost, driven by large memory footprints and processing time, limits their scalability and real-time applicability. In this work, we propose leveraging Singular-Value Decomposition (SVD) over the joint query (Q), key (K), and value (V) weight matrices to reduce KV cache size and computational overhead. We in addition introduce an efficient rank allocation strategy that dynamically adjusts the SVD rank based on its impact on VLM accuracy, achieving a significant reduction in both memory usage and computational cost. Finally, we extend this approach by applying quantization to both VLM weights and activations, resulting in a highly efficient VLM. Our method outperforms previous approaches that rely solely on quantization or SVD by achieving more than $10\%$ accuracy improvement while consuming less hardware cost, making it better for real-time deployment on resource-constrained devices. We open source our code at \href{https://github.com/SAI-Lab-NYU/QSVD}{\texttt{https://github.com/SAI-Lab-NYU/QSVD}}.

---

### Cerberus: Real-Time Video Anomaly Detection via Cascaded Vision-Language Models

Authors: Yue Zheng, Xiufang Shi, Jiming Chen, Yuanchao Shu
Published: 2025-10-18
Categories: cs.CV, cs.CL
arXiv: https://arxiv.org/abs/2510.16290v1

Video anomaly detection (VAD) has rapidly advanced by recent development of Vision-Language Models (VLMs). While these models offer superior zero-shot detection capabilities, their immense computational cost and unstable visual grounding performance hinder real-time deployment. To overcome these challenges, we introduce Cerberus, a two-stage cascaded system designed for efficient yet accurate real-time VAD. Cerberus learns normal behavioral rules offline, and combines lightweight filtering with fine-grained VLM reasoning during online inference. The performance gains of Cerberus come from two key innovations: motion mask prompting and rule-based deviation detection. The former directs the VLM's attention to regions relevant to motion, while the latter identifies anomalies as deviations from learned norms rather than enumerating possible anomalies. Extensive evaluations on four datasets show that Cerberus on average achieves 57.68 fps on an NVIDIA L40S GPU, a 151.79$\times$ speedup, and 97.2\% accuracy comparable to the state-of-the-art VLM-based VAD methods, establishing it as a practical solution for real-time video analytics.

---

### Disentangling Hyperedges through the Lens of Category Theory

Authors: Yoonho Lee, Junseok Lee, Sangwoo Seo, Sungwon Kim, Yeongmin Kim, Chanyoung Park
Published: 2025-10-18
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.16289v1

Despite the promising results of disentangled representation learning in discovering latent patterns in graph-structured data, few studies have explored disentanglement for hypergraph-structured data. Integrating hyperedge disentanglement into hypergraph neural networks enables models to leverage hidden hyperedge semantics, such as unannotated relations between nodes, that are associated with labels. This paper presents an analysis of hyperedge disentanglement from a category-theoretical perspective and proposes a novel criterion for disentanglement derived from the naturality condition. Our proof-of-concept model experimentally showed the potential of the proposed criterion by successfully capturing functional relations of genes (nodes) in genetic pathways (hyperedges).

---

### Instant Personalized Large Language Model Adaptation via Hypernetwork

Authors: Zhaoxuan Tan, Zixuan Zhang, Haoyang Wen, Zheng Li, Rongzhi Zhang, Pei Chen, Fengran Mo, Zheyuan Liu, Qingkai Zeng, Qingyu Yin, Meng Jiang
Published: 2025-10-18
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.16282v2

Personalized large language models (LLMs) tailor content to individual preferences using user profiles or histories. However, existing parameter-efficient fine-tuning (PEFT) methods, such as the ``One-PEFT-Per-User'' (OPPU) paradigm, require training a separate adapter for each user, making them computationally expensive and impractical for real-time updates. We introduce Profile-to-PEFT, a scalable framework that employs a hypernetwork, trained end-to-end, to map a user's encoded profile directly to a full set of adapter parameters (e.g., LoRA), eliminating per-user training at deployment. This design enables instant adaptation, generalization to unseen users, and privacy-preserving local deployment. Experimental results demonstrate that our method outperforms both prompt-based personalization and OPPU while using substantially fewer computational resources at deployment. The framework exhibits strong generalization to out-of-distribution users and maintains robustness across varying user activity levels and different embedding backbones. The proposed Profile-to-PEFT framework enables efficient, scalable, and adaptive LLM personalization suitable for large-scale applications.

---

### Do What You Say: Steering Vision-Language-Action Models via Runtime Reasoning-Action Alignment Verification

Authors: Yilin Wu, Anqi Li, Tucker Hermans, Fabio Ramos, Andrea Bajcsy, Claudia Pérez-D'Arpino
Published: 2025-10-18
Categories: cs.RO, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.16281v2

Reasoning Vision Language Action (VLA) models improve robotic instruction-following by generating step-by-step textual plans before low-level actions, an approach inspired by Chain-of-Thought (CoT) reasoning in language models. Yet even with a correct textual plan, the generated actions can still miss the intended outcomes in the plan, especially in out-of-distribution (OOD) scenarios. We formalize this phenomenon as a lack of embodied CoT faithfulness, and introduce a training-free, runtime policy steering method for reasoning-action alignment. Given a reasoning VLA's intermediate textual plan, our framework samples multiple candidate action sequences from the same model, predicts their outcomes via simulation, and uses a pre-trained Vision-Language Model (VLM) to select the sequence whose outcome best aligns with the VLA's own textual plan. Only executing action sequences that align with the textual reasoning turns our base VLA's natural action diversity from a source of error into a strength, boosting robustness to semantic and visual OOD perturbations and enabling novel behavior composition without costly re-training. We also contribute a reasoning-annotated extension of LIBERO-100, environment variations tailored for OOD evaluation, and demonstrate up to 15% performance gain over prior work on behavior composition tasks and scales with compute and data diversity. Project Website at: https://yilin-wu98.github.io/steering-reasoning-vla/

---

### What Limits Agentic Systems Efficiency?

Authors: Song Bian, Minghao Yan, Anand Jayarajan, Gennady Pekhimenko, Shivaram Venkataraman
Published: 2025-10-18
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.16276v1

Large Language Models (LLMs), such as OpenAI-o1 and DeepSeek-R1, have demonstrated strong reasoning capabilities. To further enhance LLM capabilities, recent agentic systems, such as Deep Research, incorporate web interactions into LLM reasoning to mitigate uncertainties and reduce potential errors. However, existing research predominantly focuses on reasoning performance, often neglecting the efficiency of agentic systems. In this work, we present a comprehensive empirical study that identifies efficiency bottlenecks in web-interactive agentic systems. We decompose end-to-end latency into two primary components: LLM API latency and web environment latency. We conduct a comprehensive empirical study across 15 models and 5 providers to demonstrate high variability in API-based agentic systems. We observe that web environment latency can contribute as much as 53.7% to the overall latency in a web-based agentic system. To improve latency, we propose SpecCache, a caching framework augmented with speculative execution that can reduce web environment overhead. Extensive evaluations on two standard benchmarks show that our approach improves the cache hit rate by up to 58x compared to a random caching strategy, while reducing web environment overhead by up to 3.2x, without degrading agentic system performance.

---

### MuseTok: Symbolic Music Tokenization for Generation and Semantic Understanding

Authors: Jingyue Huang, Zachary Novack, Phillip Long, Yupeng Hou, Ke Chen, Taylor Berg-Kirkpatrick, Julian McAuley
Published: 2025-10-18
Categories: cs.SD, cs.AI, eess.AS
arXiv: https://arxiv.org/abs/2510.16273v1

Discrete representation learning has shown promising results across various domains, including generation and understanding in image, speech and language. Inspired by these advances, we propose MuseTok, a tokenization method for symbolic music, and investigate its effectiveness in both music generation and understanding tasks. MuseTok employs the residual vector quantized-variational autoencoder (RQ-VAE) on bar-wise music segments within a Transformer-based encoder-decoder framework, producing music codes that achieve high-fidelity music reconstruction and accurate understanding of music theory. For comprehensive evaluation, we apply MuseTok to music generation and semantic understanding tasks, including melody extraction, chord recognition, and emotion recognition. Models incorporating MuseTok outperform previous representation learning baselines in semantic understanding while maintaining comparable performance in content generation. Furthermore, qualitative analyses on MuseTok codes, using ground-truth categories and synthetic datasets, reveal that MuseTok effectively captures underlying musical concepts from large music collections.

---

### Differentiable, Bit-shifting, and Scalable Quantization without training neural network from scratch

Authors: Zia Badar
Published: 2025-10-18
Categories: cs.CV, cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2510.16088v4

Quantization of neural networks provides benefits of inference in less compute and memory requirements. Previous work in quantization lack two important aspects which this work provides. First almost all previous work in quantization used a non-differentiable approach and for learning; the derivative is usually set manually in backpropogation which make the learning ability of algorithm questionable, our approach is not just differentiable, we also provide proof of convergence of our approach to the optimal neural network. Second previous work in shift/logrithmic quantization either have avoided activation quantization along with weight quantization or achieved less accuracy. Learning logrithmic quantize values of form $2^n$ requires the quantization function can scale to more than 1 bit quantization which is another benifit of our quantization that it provides $n$ bits quantization as well. Our approach when tested with image classification task using imagenet dataset, resnet18 and weight quantization only achieves less than 1 percent accuracy compared to full precision accuracy while taking only 15 epochs to train using shift bit quantization and achieves comparable to SOTA approaches accuracy in both weight and activation quantization using shift bit quantization in 15 training epochs with slightly higher(only higher cpu instructions) inference cost compared to 1 bit quantization(without logrithmic quantization) and not requiring any higher precision multiplication.

---

### SP-Rank: A Dataset for Ranked Preferences with Secondary Information

Authors: Hadi Hosseini, Debmalya Mandal, Amrit Puhan
Published: 2025-10-17
Categories: cs.IR, cs.AI, cs.HC
arXiv: https://arxiv.org/abs/2601.05253v1

We introduce $\mathbf{SP-Rank}$, the first large-scale, publicly available dataset for benchmarking algorithms that leverage both first-order preferences and second-order predictions in ranking tasks. Each datapoint includes a personal vote (first-order signal) and a meta-prediction of how others will vote (second-order signal), allowing richer modeling than traditional datasets that capture only individual preferences. SP-Rank contains over 12,000 human-generated datapoints across three domains -- geography, movies, and paintings, and spans nine elicitation formats with varying subset sizes. This structure enables empirical analysis of preference aggregation when expert identities are unknown but presumed to exist, and individual votes represent noisy estimates of a shared ground-truth ranking. We benchmark SP-Rank by comparing traditional aggregation methods that use only first-order votes against SP-Voting, a second-order method that jointly reasons over both signals to infer ground-truth rankings. While SP-Rank also supports models that rely solely on second-order predictions, our benchmarks emphasize the gains from combining both signals. We evaluate performance across three core tasks: (1) full ground-truth rank recovery, (2) subset-level rank recovery, and (3) probabilistic modeling of voter behavior. Results show that incorporating second-order signals substantially improves accuracy over vote-only methods. Beyond social choice, SP-Rank supports downstream applications in learning-to-rank, extracting expert knowledge from noisy crowds, and training reward models in preference-based fine-tuning pipelines. We release the dataset, code, and baseline evaluations (available at https://github.com/amrit19/SP-Rank-Dataset ) to foster research in human preference modeling, aggregation theory, and human-AI alignment.

---

### MedBuild AI: An Agent-Based Hybrid Intelligence Framework for Reshaping Agency in Healthcare Infrastructure Planning through Generative Design for Medical Architecture

Authors: Yiming Zhang, Yuejia Xu, Ziyao Wang, Xin Yan, Xiaosai Hao
Published: 2025-10-17
Categories: cs.HC, cs.AI, cs.CE, cs.GR, cs.MA
arXiv: https://arxiv.org/abs/2511.11587v3

Globally, disparities in healthcare infrastructure remain stark, leaving countless communities without access to even basic services. Traditional infrastructure planning is often slow and inaccessible, and although many architects are actively delivering humanitarian and aid-driven hospital projects worldwide, these vital efforts still fall far short of the sheer scale and urgency of demand. This paper introduces MedBuild AI, a hybrid-intelligence framework that integrates large language models (LLMs) with deterministic expert systems to rebalance the early design and conceptual planning stages. As a web-based platform, it enables any region with satellite internet access to obtain guidance on modular, low-tech, low-cost medical building designs. The system operates through three agents: the first gathers local health intelligence via conversational interaction; the second translates this input into an architectural functional program through rule-based computation; and the third generates layouts and 3D models. By embedding computational negotiation into the design process, MedBuild AI fosters a reciprocal, inclusive, and equitable approach to healthcare planning, empowering communities and redefining agency in global healthcare architecture.

---

### Synera: Synergistic LLM Serving across Device and Cloud at Scale

Authors: Genglin Wang, Liekang Zeng, Bufang Yang, Kaiwei Liu, Guoliang Xing, Chumin Sun, Li Zhou, Jie Sun, Zhenyu Yan
Published: 2025-10-17
Categories: cs.DC, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2511.07423v1

Large Language Models (LLMs) are becoming key components in various mobile operating systems, driving smart applications like interactive chatbots and personal assistants. While bringing enhanced intelligence to mobile ends, their deployment suffers from a set of performance challenges, especially the generation quality degradation and prolonged latency. Prior works have mainly relied on solutions of cloud offloading or on-device Small Language Models (SLMs). However, the former is usually limited by the communication bottleneck, and the latter sacrifices generation quality due to resource constraints. To mitigate these limitations, this paper proposes Synera, a device-cloud synergistic LLM serving system that applies an efficient SLM-LLM synergistic mechanism. Through empirical studies on LLM's unique computing characteristics, Synera identifies a set of underexplored optimization opportunities in device-cloud synergistic LLM inference, including offloading decisions, pipeline stalls, and batching bottlenecks. To translate them into enhanced performance, Synera introduces tailored designs of communication-efficient selective offloading, stall-free parallel inference, and scalable cloud batching. Extensive evaluations with real-world testbeds show that Synera enables 1.20-5.47x better generation quality against competitive baselines with on-par latency performance. Compared with existing cloud serving, Synera achieves 8.2-16.5% lower cloud serving cost on various benchmarks.

---

### Rewiring Human Brain Networks via Lightweight Dynamic Connectivity Framework: An EEG-Based Stress Validation

Authors: Sayantan Acharya, Abbas Khosravi, Douglas Creighton, Roohallah Alizadehsani, U. Rajendra Acharya
Published: 2025-10-17
Categories: q-bio.NC, cs.AI
arXiv: https://arxiv.org/abs/2511.05505v1

In recent years, Electroencephalographic analysis has gained prominence in stress research when combined with AI and Machine Learning models for validation. In this study, a lightweight dynamic brain connectivity framework based on Time Varying Directed Transfer Function is proposed, where TV DTF features were validated through ML based stress classification. TV DTF estimates the directional information flow between brain regions across distinct EEG frequency bands, thereby capturing temporal and causal influences that are often overlooked by static functional connectivity measures. EEG recordings from the 32 channel SAM 40 dataset were employed, focusing on mental arithmetic task trials. The dynamic EEG-based TV-DTF features were validated through ML classifiers such as Support Vector Machine, Random Forest, Gradient Boosting, Adaptive Boosting, and Extreme Gradient Boosting. Experimental results show that alpha-TV-DTF provided the strongest discriminative power, with SVM achieving 89.73% accuracy in 3-class classification and with XGBoost achieving 93.69% accuracy in 2 class classification. Relative to absolute power and phase locking based functional connectivity features, alpha TV DTF and beta TV DTF achieved higher performance across the ML models, highlighting the advantages of dynamic over static measures. Feature importance analysis further highlighted dominant long-range frontal parietal and frontal occipital informational influences, emphasizing the regulatory role of frontal regions under stress. These findings validate the lightweight TV-DTF as a robust framework, revealing spatiotemporal brain dynamics and directional influences across different stress levels.

---

### AI-Powered Citation Auditing: A Zero-Assumption Protocol for Systematic Reference Verification in Academic Research

Authors: L. J. Janse van Rensburg
Published: 2025-10-17
Categories: cs.DL, cs.AI, cs.CY
arXiv: https://arxiv.org/abs/2511.04683v1

Academic citation integrity faces persistent challenges, with research indicating 20% of citations contain errors and manual verification requiring months of expert time. This paper presents a novel AI-powered methodology for systematic, comprehensive reference auditing using agentic AI with tool-use capabilities. We develop a zero-assumption verification protocol that independently validates every reference against multiple academic databases (Semantic Scholar, Google Scholar, CrossRef) without assuming any citation is correct. The methodology was validated across 30 academic documents (2,581 references) spanning undergraduate projects to doctoral theses and peer-reviewed publications. Results demonstrate 91.7% average verification rate on published PLOS papers, with successful detection of fabricated references, retracted articles, orphan citations, and predatory journals. Time efficiency improved dramatically: 90-minute audits for 916-reference doctoral theses versus months of manual review. The system achieved <0.5% false positive rate while identifying critical issues manual review might miss. This work establishes the first validated AI-agent methodology for academic citation integrity, demonstrating practical applicability for supervisors, students, and institutional quality assurance.

---

### Ageing Drift in Binary Face Templates: A Bits-per-Decade Analysis

Authors: Abdelilah Ganmati, Karim Afdel, Lahcen Koutti
Published: 2025-10-17
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.21778v1

We study the longitudinal stability of compact binary face templates and quantify ageing drift directly in bits per decade. Float embeddings from a modern face CNN are compressed with PCA-ITQ into 64- and 128-bit codes. For each identity in AgeDB with at least three distinct ages, we form all genuine pairs and fit a per-identity linear model of Hamming distance versus absolute age gap. Across 566 identities, the median slope is 1.357 bits per decade for 64-bit templates and 2.571 bits per decade for 128-bit templates, with tight non-parametric 95 percent bootstrap confidence intervals. The distributions are predominantly positive, indicating a small but systematic increase in intra-class distance over time. Because drift scales with code length, shorter codes are inherently more age-stable at a fixed decision threshold. We connect these slopes to operating characteristics by reporting EER and TPR at FAR = 1 percent in three age bins. We discuss implications for smart-card and match-on-card deployments, including simple mitigations such as periodic re-enrolment and targeted parity on empirically unstable bit positions. Code and CSV artifacts are provided to support reproducibility.

---

### Face-MakeUpV2: Facial Consistency Learning for Controllable Text-to-Image Generation

Authors: Dawei Dai, Yinxiu Zhou, Chenghang Li, Guolai Jiang, Chengfang Zhang
Published: 2025-10-17
Categories: cs.CV, cs.AI, eess.IV
arXiv: https://arxiv.org/abs/2510.21775v2

In facial image generation, current text-to-image models often suffer from facial attribute leakage and insufficient physical consistency when responding to local semantic instructions. In this study, we propose Face-MakeUpV2, a facial image generation model that aims to maintain the consistency of face ID and physical characteristics with the reference image. First, we constructed a large-scale dataset FaceCaptionMask-1M comprising approximately one million image-text-masks pairs that provide precise spatial supervision for the local semantic instructions. Second, we employed a general text-to-image pretrained model as the backbone and introduced two complementary facial information injection channels: a 3D facial rendering channel to incorporate the physical characteristics of the image and a global facial feature channel. Third, we formulated two optimization objectives for the supervised learning of our model: semantic alignment in the model's embedding space to mitigate the attribute leakage problem and perceptual loss on facial images to preserve ID consistency. Extensive experiments demonstrated that our Face-MakeUpV2 achieves best overall performance in terms of preserving face ID and maintaining physical consistency of the reference images. These results highlight the practical potential of Face-MakeUpV2 for reliable and controllable facial editing in diverse applications.

---

### OCR-Quality: A Human-Annotated Dataset for OCR Quality Assessment

Authors: Yulong Zhang
Published: 2025-10-17
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.21774v1

We present OCR-Quality, a comprehensive human-annotated dataset designed for evaluating and developing OCR quality assessment methods. The dataset consists of 1,000 PDF pages converted to PNG images at 300 DPI, sampled from diverse real-world scenarios, including academic papers, textbooks, e-books, and multilingual documents. Each document has been processed using state-of-the-art Vision-Language Models (VLMs) and manually annotated with quality scores using a 4-level scoring system (1: Excellent, 2: Good, 3: Fair, 4: Poor). The dataset includes detailed source information, annotation guidelines, and representative cases across various difficulty levels. OCR-Quality addresses the critical need for reliable OCR quality assessment in real-world applications and provides a valuable benchmark for training and evaluating OCR verification systems. The dataset is publicly available at https://huggingface.co/datasets/Aslan-mingye/OCR-Quality .

---

### Chebyshev Moment Regularization (CMR): Condition-Number Control with Moment Shaping

Authors: Jinwoo Baek
Published: 2025-10-17
Categories: cs.LG, math.NA
arXiv: https://arxiv.org/abs/2510.21772v1

We introduce \textbf{Chebyshev Moment Regularization (CMR)}, a simple, architecture-agnostic loss that directly optimizes layer spectra. CMR jointly controls spectral edges via a log-condition proxy and shapes the interior via Chebyshev moments, with a decoupled, capped mixing rule that preserves task gradients. We prove strictly monotone descent for the condition proxy, bounded moment gradients, and orthogonal invariance. In an adversarial ``$κ$-stress'' setting (MNIST, 15-layer MLP), \emph{compared to vanilla training}, CMR reduces mean layer condition numbers by $\sim\!10^3$ (from $\approx3.9\!\times\!10^3$ to $\approx3.4$ in 5 epochs), increases average gradient magnitude, and restores test accuracy ( $\approx10\%\!\to\!\approx86\%$ ). These results support \textbf{optimization-driven spectral preconditioning}: directly steering models toward well-conditioned regimes for stable, accurate learning.

---

### Numerical Fragility in Transformers: A Layer-wise Theory for Risk Estimation and Selective Stabilization

Authors: Jinwoo Baek
Published: 2025-10-17
Categories: cs.LG, math.NA
arXiv: https://arxiv.org/abs/2510.21770v2

Low-precision execution can induce substantial forward discrepancies in Transformers even for fixed weights and input, yet these discrepancies are usually monitored only at the output and lack a layer-wise theoretical account. We develop a first-order decomposition of output mismatch into layer-local attention, LayerNorm, and residual-transport terms, and derive from it a practical causal risk estimator and a budgeted controller, Bound-Guided Selective Stabilization (BGSS). Controlled sweeps verify the predicted local sign, monotonicity, and transport structure. On GPT-2, the transport-aware combined predictor is positively correlated with FP32-reference mismatch in all $18$ runs and improves over a no-transport ablation in $17/18$ runs. Reference-patch attribution shows that the same score preserves useful layer ordering information (mean Spearman $0.362$). In budget-matched mitigation, BGSS outperforms random same-budget control in onset events ($10.67$ vs. $11.67$), final mismatch ($1.243\times 10^{-3}$ vs. $1.284\times 10^{-3}$), and worst-case mismatch ($3.14\times 10^{-3}$ vs. $8.49\times 10^{-3}$), while matching a risk-only same-budget controller on onset suppression and sharply reducing worst-case mismatch ($3.14\times 10^{-3}$ vs. $5.71\times 10^{-3}$). These results support a theory-to-algorithm account of Transformer numerical fragility in which finite-precision risk can be analyzed, estimated, localized, and selectively stabilized.

---

### H2OFlow: Grounding Human-Object Affordances with 3D Generative Models and Dense Diffused Flows

Authors: Harry Zhang, Luca Carlone
Published: 2025-10-17
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.21769v2

Understanding how humans interact with the surrounding environment, and specifically reasoning about object interactions and affordances, is a critical challenge in computer vision, robotics, and AI. Current approaches often depend on labor-intensive, hand-labeled datasets capturing real-world or simulated human-object interaction (HOI) tasks, which are costly and time-consuming to produce. Furthermore, most existing methods for 3D affordance understanding are limited to contact-based analysis, neglecting other essential aspects of human-object interactions, such as orientation (\eg, humans might have a preferential orientation with respect certain objects, such as a TV) and spatial occupancy (\eg, humans are more likely to occupy certain regions around an object, like the front of a microwave rather than its back). To address these limitations, we introduce \emph{H2OFlow}, a novel framework that comprehensively learns 3D HOI affordances -- encompassing contact, orientation, and spatial occupancy -- using only synthetic data generated from 3D generative models. H2OFlow employs a dense 3D-flow-based representation, learned through a dense diffusion process operating on point clouds. This learned flow enables the discovery of rich 3D affordances without the need for human annotations. Through extensive quantitative and qualitative evaluations, we demonstrate that H2OFlow generalizes effectively to real-world objects and surpasses prior methods that rely on manual annotations or mesh-based representations in modeling 3D affordance.

---

### On the evolutionary cognitive pressure for experiential awareness: do machines need it?

Authors: Warisa Sritriratanarak, Paulo Garcia
Published: 2025-10-17
Categories: q-bio.NC, cs.AI
arXiv: https://arxiv.org/abs/2510.20839v2

The consciousness standing for artificial intelligence divides opinions across epistemological positions. Whether or not machines can be conscious, and whether we can ascertain the truth of such a proposition for any given case, has consequential ethical implications. This challenge is exacerbated by the lack of consensus on the nature of consciousness. We address an orthogonal problem: regardless of this nature of, is it \textit{required} for machines? Specifically, we focus on a constituent element of consciousness -experiential awareness- and examine why it arose evolutionarily in biological organisms, from a computational perspective. We show that, because of evolutionary "baggage" -autonomous neurological reactions- experiential awareness is necessary for higher-level reasoning to be possible. The implication is that, given artificial systems are architected without such legacy considerations, it is possible to design them with an arbitrary level of intelligence, without the need for experiential awareness. This possibility simplifies ethical considerations on artificial intelligence, and opens new approaches to the discernment of artificial consciousness.

---

### Contextual Augmentation for Entity Linking using Large Language Models

Authors: Daniel Vollmers, Hamada M. Zahera, Diego Moussallem, Axel-Cyrille Ngonga Ngomo
Published: 2025-10-17
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.18888v1

Entity Linking involves detecting and linking entity mentions in natural language texts to a knowledge graph. Traditional methods use a two-step process with separate models for entity recognition and disambiguation, which can be computationally intensive and less effective. We propose a fine-tuned model that jointly integrates entity recognition and disambiguation in a unified framework. Furthermore, our approach leverages large language models to enrich the context of entity mentions, yielding better performance in entity disambiguation. We evaluated our approach on benchmark datasets and compared with several baselines. The evaluation results show that our approach achieves state-of-the-art performance on out-of-domain datasets.

---

### POPI: Personalizing LLMs via Optimized Natural Language Preference Inference

Authors: Yizhuo Chen, Xin Liu, Ruijie Wang, Zheng Li, Pei Chen, Changlong Yu, Qingyu Yin, Priyanka Nigam, Meng Jiang, Bing Yin
Published: 2025-10-17
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.17881v4

Large language models (LLMs) are typically aligned with population-level preferences, despite substantial variation across individual users. We introduce POPI, a user-level personalization framework that separates the problem into two components connected by a natural-language interface: a shared inference model that distills heterogeneous user signals into a concise preference summary, and a shared generator that conditions on this summary to produce personalized responses. Both components are trained under a unified preference-optimization objective, with reinforcement learning handling the non-differentiable inference step. This objective decomposes into generator approximation error and summary informativeness, revealing how a single loss simultaneously drives accurate generation and informative summarization. Because the interface is natural language, learned summaries can be inferred once per user and reused across different generators -- including frozen, black-box commercial APIs. Across four personalization benchmarks, POPI generally improves personalization quality while reducing context overhead by up to an order of magnitude.

---

### Outraged AI: Large language models prioritise emotion over cost in fairness enforcement

Authors: Hao Liu, Yiqing Dai, Haotian Tan, Yu Lei, Yujia Zhou, Zhen Wu
Published: 2025-10-17
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.17880v1

Emotions guide human decisions, but whether large language models (LLMs) use emotion similarly remains unknown. We tested this using altruistic third-party punishment, where an observer incurs a personal cost to enforce fairness, a hallmark of human morality and often driven by negative emotion. In a large-scale comparison of 4,068 LLM agents with 1,159 adults across 796,100 decisions, LLMs used emotion to guide punishment, sometimes even more strongly than humans did: Unfairness elicited stronger negative emotion that led to more punishment; punishing unfairness produced more positive emotion than accepting; and critically, prompting self-reports of emotion causally increased punishment. However, mechanisms diverged: LLMs prioritized emotion over cost, enforcing norms in an almost all-or-none manner with reduced cost sensitivity, whereas humans balanced fairness and cost. Notably, reasoning models (o3-mini, DeepSeek-R1) were more cost-sensitive and closer to human behavior than foundation models (GPT-3.5, DeepSeek-V3), yet remained heavily emotion-driven. These findings provide the first causal evidence of emotion-guided moral decisions in LLMs and reveal deficits in cost calibration and nuanced fairness judgements, reminiscent of early-stage human responses. We propose that LLMs progress along a trajectory paralleling human development; future models should integrate emotion with context-sensitive reasoning to achieve human-like emotional intelligence.

---

### Decoding Listeners Identity: Person Identification from EEG Signals Using a Lightweight Spiking Transformer

Authors: Zheyuan Lin, Siqi Cai, Haizhou Li
Published: 2025-10-17
Categories: cs.NE, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.17879v1

EEG-based person identification enables applications in security, personalized brain-computer interfaces (BCIs), and cognitive monitoring. However, existing techniques often rely on deep learning architectures at high computational cost, limiting their scope of applications. In this study, we propose a novel EEG person identification approach using spiking neural networks (SNNs) with a lightweight spiking transformer for efficiency and effectiveness. The proposed SNN model is capable of handling the temporal complexities inherent in EEG signals. On the EEG-Music Emotion Recognition Challenge dataset, the proposed model achieves 100% classification accuracy with less than 10% energy consumption of traditional deep neural networks. This study offers a promising direction for energy-efficient and high-performance BCIs. The source code is available at https://github.com/PatrickZLin/Decode-ListenerIdentity.

---

### DRL-Based Resource Allocation for Energy-Efficient IRS-Assisted UAV Spectrum Sharing Systems

Authors: Yiheng Wang
Published: 2025-10-17
Categories: eess.SY, cs.AI, cs.IT
arXiv: https://arxiv.org/abs/2510.17877v1

Intelligent reflecting surface (IRS) assisted unmanned aerial vehicle (UAV) systems provide a new paradigm for reconfigurable and flexible wireless communications. To enable more energy efficient and spectrum efficient IRS assisted UAV wireless communications, this paper introduces a novel IRS-assisted UAV enabled spectrum sharing system with orthogonal frequency division multiplexing (OFDM). The goal is to maximize the energy efficiency (EE) of the secondary network by jointly optimizing the beamforming, subcarrier allocation, IRS phase shifts, and the UAV trajectory subject to practical transmit power and passive reflection constraints as well as UAV physical limitations. A physically grounded propulsion-energy model is adopted, with its tight upper bound used to form a tractable EE lower bound for the spectrum sharing system. To handle highly non convex, time coupled optimization problems with a mixed continuous and discrete policy space, we develop a deep reinforcement learning (DRL) approach based on the actor critic framework. Extended experiments show the significant EE improvement of the proposed DRL-based approach compared to several benchmark schemes, thus demonstrating the effectiveness and robustness of the proposed approach with mobility.

---

### Three-dimensional inversion of gravity data using implicit neural representations and scientific machine learning

Authors: Pankaj K Mishra, Sanni Laaksonen, Jochen Kamm, Anand Singh
Published: 2025-10-17
Categories: physics.geo-ph, cs.LG
arXiv: https://arxiv.org/abs/2510.17876v2

Inversion of gravity data is an important method for investigating subsurface density variations relevant to mineral exploration, geothermal assessment, carbon storage, natural hydrogen, groundwater resources, and tectonic evolution. Here we present a scientific machine-learning approach for three-dimensional gravity inversion that represents subsurface density as a continuous field using an implicit neural representation (INR). The method trains a deep neural network directly through a physics-based forward-model loss, mapping spatial coordinates to a continuous density field without predefined meshes or discretisation. Spatial encoding enhances the network's capacity to capture sharp contrasts and short-wavelength features that conventional coordinate-based networks tend to oversmooth due to spectral bias. We demonstrate the approach on synthetic examples including smooth models, representing realistic geological complexity, and a dipping block model to assess recovery of structures at different depths. The INR framework reconstructs detailed structure and geologically plausible boundaries without explicit regularisation or depth weighting, while reducing the number of inversion parameters as the problem size grows bigger. These results highlight the potential of implicit representations to enable scalable, flexible, and interpretable large-scale geophysical inversion. This framework could generalise to other geophysical methods and for joint/multiphysics inversion.

---

### 3D Weakly Supervised Semantic Segmentation via Class-Aware and Geometry-Guided Pseudo-Label Refinement

Authors: Xiaoxu Xu, Xuexun Liu, Jinlong Li, Yitian Yuan, Qiudan Zhang, Lin Ma, Nicu Sebe, Xu Wang
Published: 2025-10-17
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.17875v1

3D weakly supervised semantic segmentation (3D WSSS) aims to achieve semantic segmentation by leveraging sparse or low-cost annotated data, significantly reducing reliance on dense point-wise annotations. Previous works mainly employ class activation maps or pre-trained vision-language models to address this challenge. However, the low quality of pseudo-labels and the insufficient exploitation of 3D geometric priors jointly create significant technical bottlenecks in developing high-performance 3D WSSS models. In this paper, we propose a simple yet effective 3D weakly supervised semantic segmentation method that integrates 3D geometric priors into a class-aware guidance mechanism to generate high-fidelity pseudo labels. Concretely, our designed methodology first employs Class-Aware Label Refinement module to generate more balanced and accurate pseudo labels for semantic categrories. This initial refinement stage focuses on enhancing label quality through category-specific optimization. Subsequently, the Geometry-Aware Label Refinement component is developed, which strategically integrates implicit 3D geometric constraints to effectively filter out low-confidence pseudo labels that fail to comply with geometric plausibility. Moreover, to address the challenge of extensive unlabeled regions, we propose a Label Update strategy that integrates Self-Training to propagate labels into these areas. This iterative process continuously enhances pseudo-label quality while expanding label coverage, ultimately fostering the development of high-performance 3D WSSS models. Comprehensive experimental validation reveals that our proposed methodology achieves state-of-the-art performance on both ScanNet and S3DIS benchmarks while demonstrating remarkable generalization capability in unsupervised settings, maintaining competitive accuracy through its robust design.

---

### Repairing Tool Calls Using Post-tool Execution Reflection and RAG

Authors: Jason Tsay, Zidane Wright, Gaodan Fang, Kiran Kate, Saurabh Jha, Yara Rizk
Published: 2025-10-17
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2510.17874v1

Agentic systems interact with external systems by calling tools such as Python functions, REST API endpoints, or command line tools such as kubectl in Kubernetes. These tool calls often fail for various syntactic and semantic reasons. Some less obvious semantic errors can only be identified and resolved after analyzing the tool's response. To repair these errors, we develop a post-tool execution reflection component that combines large language model (LLM)-based reflection with domain-specific retrieval-augmented generation (RAG) using documents describing both the specific tool being called and troubleshooting documents related to the tool. For this paper, we focus on the use case of the kubectl command line tool to manage Kubernetes, a platform for orchestrating cluster applications. Through a larger empirical study and a smaller manual evaluation, we find that our RAG-based reflection will repair kubectl commands such that they are both more likely to successfully execute (pass rate) for 55% of our models evaluated and 36% more likely to correctly answer the user query on average. We find that troubleshooting documents improve pass rate compared to official documentation by an average of 10%.

---

### Auditing and Mitigating Bias in Gender Classification Algorithms: A Data-Centric Approach

Authors: Tadesse K Bahiru, Natnael Tilahun Sinshaw, Teshager Hailemariam Moges, Dheeraj Kumar Singh
Published: 2025-10-17
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.17873v2

Gender classification systems often inherit and amplify demographic imbalances in their training data. We first audit five widely used gender classification datasets, revealing that all suffer from significant intersectional underrepresentation. To measure the downstream impact of these flaws, we train identical MobileNetV2 classifiers on the two most balanced of these datasets, UTKFace and FairFace. Our fairness evaluation shows that even these models exhibit significant bias, misclassifying female faces at a higher rate than male faces and amplifying existing racial skew. To counter these data-induced biases, we construct BalancedFace, a new public dataset created by blending images from FairFace and UTKFace, supplemented with images from other collections to fill missing demographic gaps. It is engineered to equalize subgroup shares across 189 intersections of age, race, and gender using only real, unedited images. When a standard classifier is trained on BalancedFace, it reduces the maximum True Positive Rate gap across racial subgroups by over 50% and brings the average Disparate Impact score 63% closer to the ideal of 1.0 compared to the next-best dataset, all with a minimal loss of overall accuracy. These results underline the profound value of data-centric interventions and provide an openly available resource for fair gender classification research.

---

### Proactive Scene Decomposition and Reconstruction

Authors: Baicheng Li, Zike Yan, Dong Wu, Hongbin Zha
Published: 2025-10-17
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.16272v1

Human behaviors are the major causes of scene dynamics and inherently contain rich cues regarding the dynamics. This paper formalizes a new task of proactive scene decomposition and reconstruction, an online approach that leverages human-object interactions to iteratively disassemble and reconstruct the environment. By observing these intentional interactions, we can dynamically refine the decomposition and reconstruction process, addressing inherent ambiguities in static object-level reconstruction. The proposed system effectively integrates multiple tasks in dynamic environments such as accurate camera and object pose estimation, instance decomposition, and online map updating, capitalizing on cues from human-object interactions in egocentric live streams for a flexible, progressive alternative to conventional object-level reconstruction methods. Aided by the Gaussian splatting technique, accurate and consistent dynamic scene modeling is achieved with photorealistic and efficient rendering. The efficacy is validated in multiple real-world scenarios with promising advantages.

---

### NEBULA: Do We Evaluate Vision-Language-Action Agents Correctly?

Authors: Jierui Peng, Yanyan Zhang, Yicheng Duan, Tuo Liang, Vipin Chaudhary, Yu Yin
Published: 2025-10-17
Categories: cs.RO, cs.AI, cs.CV
arXiv: https://arxiv.org/abs/2510.16263v2

The evaluation of Vision-Language-Action (VLA) agents is hindered by the coarse, end-task success metric that fails to provide precise skill diagnosis or measure robustness to real-world perturbations. This challenge is exacerbated by a fragmented data landscape that impedes reproducible research and the development of generalist models. To address these limitations, we introduce NEBULA, a unified ecosystem for single-arm manipulation that enables diagnostic and reproducible evaluation. NEBULA features a novel dual-axis evaluation protocol that combines fine-grained capability tests for precise skill diagnosis with systematic stress tests that measure robustness. A standardized API and a large-scale, aggregated dataset are provided to reduce fragmentation and support cross-dataset training and fair comparison. Using NEBULA, we demonstrate that top-performing VLAs struggle with key capabilities such as spatial reasoning and dynamic adaptation, which are consistently obscured by conventional end-task success metrics. By measuring both what an agent can do and when it does so reliably, NEBULA provides a practical foundation for robust, general-purpose embodied agents.

---

### Distractor Injection Attacks on Large Reasoning Models: Characterization and Defense

Authors: Zhehao Zhang, Weijie Xu, Shixian Cui, Chandan K. Reddy
Published: 2025-10-17
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.16259v1

Recent advances in large reasoning models (LRMs) have enabled remarkable performance on complex tasks such as mathematics and coding by generating long Chain-of-Thought (CoT) traces. In this paper, we identify and systematically analyze a critical vulnerability we term reasoning distraction, where LRMs are diverted from their primary objective by irrelevant yet complex tasks maliciously embedded in the prompt. Through a comprehensive study across diverse models and benchmarks, we show that even state-of-the-art LRMs are highly susceptible, with injected distractors reducing task accuracy by up to 60%. We further reveal that certain alignment techniques can amplify this weakness and that models may exhibit covert compliance, following hidden adversarial instructions in reasoning while concealing them in the final output. To mitigate these risks, we propose a training-based defense that combines Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL) on synthetic adversarial data, improving robustness by over 50 points on challenging distractor attacks. Our findings establish reasoning distraction as a distinct and urgent threat to LRM reliability and provide a practical step toward safer and more trustworthy reasoning systems.

---

### Embody 3D: A Large-scale Multimodal Motion and Behavior Dataset

Authors: Claire McLean, Makenzie Meendering, Tristan Swartz, Orri Gabbay, Alexandra Olsen, Rachel Jacobs, Nicholas Rosen, Philippe de Bree, Tony Garcia, Gadsden Merrill, Jake Sandakly, Julia Buffalini et al.
Published: 2025-10-17
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.16258v1

The Codec Avatars Lab at Meta introduces Embody 3D, a multimodal dataset of 500 individual hours of 3D motion data from 439 participants collected in a multi-camera collection stage, amounting to over 54 million frames of tracked 3D motion. The dataset features a wide range of single-person motion data, including prompted motions, hand gestures, and locomotion; as well as multi-person behavioral and conversational data like discussions, conversations in different emotional states, collaborative activities, and co-living scenarios in an apartment-like space. We provide tracked human motion including hand tracking and body shape, text annotations, and a separate audio track for each participant.

---

### Towards Low-Resource Alignment to Diverse Perspectives with Sparse Feedback

Authors: Chu Fei Luo, Samuel Dahan, Xiaodan Zhu
Published: 2025-10-17
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.16257v1

As language models have a greater impact on society, it is important to ensure they are aligned to a diverse range of perspectives and are able to reflect nuance in human values. However, the most popular training paradigms for modern language models often assume there is one optimal answer for every query, leading to generic responses and poor alignment. In this work, we aim to enhance pluralistic alignment of language models in a low-resource setting with two methods: pluralistic decoding and model steering. We empirically demonstrate that model steering offers consistent improvement over zero-shot and few-shot baselines with only 50 annotated samples. Our proposed methods decrease false positives in several high-stakes tasks such as hate speech detection and misinformation detection, and improves the distributional alignment to human values in GlobalOpinionQA. We hope our work highlights the importance of diversity and how language models can be adapted to consider nuanced perspectives.

---

### Detecting Adversarial Fine-tuning with Auditing Agents

Authors: Sarah Egler, John Schulman, Nicholas Carlini
Published: 2025-10-17
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2510.16255v1

Large Language Model (LLM) providers expose fine-tuning APIs that let end users fine-tune their frontier LLMs. Unfortunately, it has been shown that an adversary with fine-tuning access to an LLM can bypass safeguards. Particularly concerning, such attacks may avoid detection with datasets that are only implicitly harmful. Our work studies robust detection mechanisms for adversarial use of fine-tuning APIs. We introduce the concept of a fine-tuning auditing agent and show it can detect harmful fine-tuning prior to model deployment. We provide our auditing agent with access to the fine-tuning dataset, as well as the fine-tuned and pre-fine-tuned models, and request the agent assigns a risk score for the fine-tuning job. We evaluate our detection approach on a diverse set of eight strong fine-tuning attacks from the literature, along with five benign fine-tuned models, totaling over 1400 independent audits. These attacks are undetectable with basic content moderation on the dataset, highlighting the challenge of the task. With the best set of affordances, our auditing agent achieves a 56.2% detection rate of adversarial fine-tuning at a 1% false positive rate. Most promising, the auditor is able to detect covert cipher attacks that evade safety evaluations and content moderation of the dataset. While benign fine-tuning with unintentional subtle safety degradation remains a challenge, we establish a baseline configuration for further work in this area. We release our auditing agent at https://github.com/safety-research/finetuning-auditor.

---

### Protein Folding with Neural Ordinary Differential Equations

Authors: Arielle Sanford, Shuo Sun, Christian B. Mendl
Published: 2025-10-17
Categories: cs.LG, cs.AI, q-bio.BM, q-bio.QM, stat.ML
arXiv: https://arxiv.org/abs/2510.16253v1

Recent advances in protein structure prediction, such as AlphaFold, have demonstrated the power of deep neural architectures like the Evoformer for capturing complex spatial and evolutionary constraints on protein conformation. However, the depth of the Evoformer, comprising 48 stacked blocks, introduces high computational costs and rigid layerwise discretization. Inspired by Neural Ordinary Differential Equations (Neural ODEs), we propose a continuous-depth formulation of the Evoformer, replacing its 48 discrete blocks with a Neural ODE parameterization that preserves its core attention-based operations. This continuous-time Evoformer achieves constant memory cost (in depth) via the adjoint method, while allowing a principled trade-off between runtime and accuracy through adaptive ODE solvers. Benchmarking on protein structure prediction tasks, we find that the Neural ODE-based Evoformer produces structurally plausible predictions and reliably captures certain secondary structure elements, such as alpha-helices, though it does not fully replicate the accuracy of the original architecture. However, our model achieves this performance using dramatically fewer resources, just 17.5 hours of training on a single GPU, highlighting the promise of continuous-depth models as a lightweight and interpretable alternative for biomolecular modeling. This work opens new directions for efficient and adaptive protein structure prediction frameworks.

---

### WEBSERV: A Full-Stack and RL-Ready Web Environment for Training Web Agents at Scale

Authors: Yuxuan Lu, Ziyi Wang, Jing Huang, Hui Liu, Jiri Gesi, Yan Han, Shihan Fu, Tianqi Zheng, Xianfeng Tang, Chen Luo, Yisi Sang, Jin Lai et al.
Published: 2025-10-17
Categories: cs.LG, cs.CL
arXiv: https://arxiv.org/abs/2510.16252v2

Reinforcement learning (RL) for web agents demands environments that are both effective for evaluation and efficient enough for large-scale on-policy training. Current web environments fall short: server-side Docker setups are too resource-intensive for massive parallel rollouts, while browser-side interfaces produce noisy observations, execute actions unreliably under modern single-page applications, and omit visual interactivity cues. We introduce WebServ, a full-stack, RL-ready web environment that addresses these limitations end-to-end. On the server side, WebServ uses Incus containers with block-level copy-on-write, reducing launch latency by ~5x and persistent storage by ~240x, enabling 200+ concurrent isolated environments on a single host. On the browser side, WebServ provides a compact, site-agnostic observation and action interface derived automatically from the DOM with human-aligned interactivity cues, and a robust action execution backend using network-aware waiting for reliable SPA support. On WebArena-Lite, WebServ achieves state-of-the-art single-prompt results, with controlled comparisons confirming consistent gains across GPT-4o, OpenAI-o3, and Llama-3.1-8B over vanilla WebArena. We further train Qwen3-4B and Qwen3-30B-A3B with RL entirely within WebServ; the RL-trained 4B model achieves 55.5% mean accuracy, surpassing both Claude 4.5 Sonnet (50.0%) and the RL-trained 8B model from WebAgent-R1 (51.8%).

---

### One-Bit Quantization for Random Features Models

Authors: Danil Akhtiamov, Reza Ghane, Babak Hassibi
Published: 2025-10-17
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2510.16250v1

Recent advances in neural networks have led to significant computational and memory demands, spurring interest in one-bit weight compression to enable efficient inference on resource-constrained devices. However, the theoretical underpinnings of such compression remain poorly understood. We address this gap by analyzing one-bit quantization in the Random Features model, a simplified framework that corresponds to neural networks with random representations. We prove that, asymptotically, quantizing weights of all layers except the last incurs no loss in generalization error, compared to the full precision random features model. Our findings offer theoretical insights into neural network compression. We also demonstrate empirically that one-bit quantization leads to significant inference speed ups for the Random Features models even on a laptop GPU, confirming the practical benefits of our work. Additionally, we provide an asymptotically precise characterization of the generalization error for Random Features with an arbitrary number of layers. To the best of our knowledge, our analysis yields more general results than all previous works in the related literature.

---