# Research Papers — 2025-10 · bundle page 195 of 217

> Full-text markdown of papers #9701–9750 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/195
[← Previous bundle](https://aipod.dev/papers/archive/2025-10/page/194.md)
[Next bundle →](https://aipod.dev/papers/archive/2025-10/page/196.md)

### Know Thyself? On the Incapability and Implications of AI Self-Recognition

Authors: Xiaoyan Bai, Aryan Shrivastava, Ari Holtzman, Chenhao Tan
Published: 2025-10-03
Categories: cs.AI, cs.CL, cs.CY, cs.LG
arXiv: https://arxiv.org/abs/2510.03399v1

Self-recognition is a crucial metacognitive capability for AI systems, relevant not only for psychological analysis but also for safety, particularly in evaluative scenarios. Motivated by contradictory interpretations of whether models possess self-recognition (Panickssery et al., 2024; Davidson et al., 2024), we introduce a systematic evaluation framework that can be easily applied and updated. Specifically, we measure how well 10 contemporary larger language models (LLMs) can identify their own generated text versus text from other models through two tasks: binary self-recognition and exact model prediction. Different from prior claims, our results reveal a consistent failure in self-recognition. Only 4 out of 10 models predict themselves as generators, and the performance is rarely above random chance. Additionally, models exhibit a strong bias toward predicting GPT and Claude families. We also provide the first evaluation of model awareness of their own and others' existence, as well as the reasoning behind their choices in self-recognition. We find that the model demonstrates some knowledge of its own existence and other models, but their reasoning reveals a hierarchical bias. They appear to assume that GPT, Claude, and occasionally Gemini are the top-tier models, often associating high-quality text with them. We conclude by discussing the implications of our findings on AI safety and future directions to develop appropriate AI self-awareness.

---

### Studying the Korean Word-Chain Game with RLVR: Mitigating Reward Conflicts via Curriculum Learning

Authors: Donghwan Rho
Published: 2025-10-03
Categories: cs.LG, cs.CL
arXiv: https://arxiv.org/abs/2510.03394v2

Reinforcement learning with verifiable rewards (RLVR) is a promising approach for training large language models (LLMs) with stronger reasoning abilities. It has also been applied to a variety of logic puzzles. In this work, we study the Korean word-chain game using RLVR. We show that rule-derived rewards can naturally conflict, and demonstrate through experiments that a curriculum-learning scheme mitigates these conflicts. Our findings motivate further studies of puzzle tasks in diverse languages.

---

### Quantum feature-map learning with reduced resource overhead

Authors: Jonas Jäger, Philipp Elsässer, Elham Torabian
Published: 2025-10-03
Categories: quant-ph, cs.LG
arXiv: https://arxiv.org/abs/2510.03389v2

Current quantum computers require algorithms that use limited resources economically. In quantum machine learning, success hinges on quantum feature-maps, which embed classical data into the state space of qubits. We introduce Quantum Feature-Map Learning via Analytic Iterative Reconstructions (Q-FLAIR), an algorithm that reduces quantum resource overhead in iterative feature-map circuit construction. It shifts workloads to a classical computer via partial analytic reconstructions of the quantum model, using only a few evaluations. For each probed gate addition to the ansatz, the simultaneous selection and optimization of the data feature and weight parameter is then entirely classical. Integrated into quantum neural network and quantum kernel support vector classifiers, Q-FLAIR shows state-of-the-art benchmark performance. Since resource overhead decouples from feature dimension, we train a quantum model on a real IBM device in only four hours, surpassing 90% accuracy on the full-resolution MNIST dataset (784 features, digits 3 vs 5). Such results were previously unattainable, as the feature dimension prohibitively drives hardware demands for fixed and search costs for adaptive ansätze. Furthermore, Q-FLAIR demonstrates de-quantization robustness against direct classical modeling, satisfying a benchmark rare in the literature and a necessary condition for potential quantum advantage. By rethinking feature-map learning beyond black-box optimization, this work takes a concrete step toward enabling quantum machine learning for real-world problems and near-term quantum computers.

---

### Is it Bigger than a Breadbox: Efficient Cardinality Estimation for Real World Workloads

Authors: Zixuan Yi, Sami Abu-el-Haija, Yawen Wang, Teja Vemparala, Yannis Chronis, Yu Gan, Michael Burrows, Carsten Binnig, Bryan Perozzi, Ryan Marcus, Fatma Ozcan
Published: 2025-10-03
Categories: cs.DB, cs.LG
arXiv: https://arxiv.org/abs/2510.03386v1

DB engines produce efficient query execution plans by relying on cost models. Practical implementations estimate cardinality of queries using heuristics, with magic numbers tuned to improve average performance on benchmarks. Empirically, estimation error significantly grows with query complexity. Alternatively, learning-based estimators offer improved accuracy, but add operational complexity preventing their adoption in-practice. Recognizing that query workloads contain highly repetitive subquery patterns, we learn many simple regressors online, each localized to a pattern. The regressor corresponding to a pattern can be randomly-accessed using hash of graph structure of the subquery. Our method has negligible overhead and competes with SoTA learning-based approaches on error metrics. Further, amending PostgreSQL with our method achieves notable accuracy and runtime improvements over traditional methods and drastically reduces operational costs compared to other learned cardinality estimators, thereby offering the most practical and efficient solution on the Pareto frontier. Concretely, simulating JOB-lite workload on IMDb speeds-up execution by 7.5 minutes (>30%) while incurring only 37 seconds overhead for online learning.

---

### Implicit Values Embedded in How Humans and LLMs Complete Subjective Everyday Tasks

Authors: Arjun Arunasalam, Madison Pickering, Z. Berkay Celik, Blase Ur
Published: 2025-10-03
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.03384v1

Large language models (LLMs) can underpin AI assistants that help users with everyday tasks, such as by making recommendations or performing basic computation. Despite AI assistants' promise, little is known about the implicit values these assistants display while completing subjective everyday tasks. Humans may consider values like environmentalism, charity, and diversity. To what extent do LLMs exhibit these values in completing everyday tasks? How do they compare with humans? We answer these questions by auditing how six popular LLMs complete 30 everyday tasks, comparing LLMs to each other and to 100 human crowdworkers from the US. We find LLMs often do not align with humans, nor with other LLMs, in the implicit values exhibited.

---

### Proxy Reconstruction Pre-training for Ramp Flow Prediction at Highway Interchanges

Authors: Yongchao Li, Jun Chen, Zhuoxuan Li, Chao Gao, Yang Li, Chu Zhang, Changyin Dong
Published: 2025-10-03
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.03381v3

Interchanges are crucial nodes for vehicle transfers between highways, yet the lack of real-time ramp detectors creates blind spots in traffic prediction. To address this, we propose a Spatio-Temporal Decoupled Autoencoder (STDAE), a two-stage framework that leverages cross-modal reconstruction pretraining. In the first stage, STDAE reconstructs historical ramp flows from mainline data, forcing the model to capture intrinsic spatio-temporal relations. Its decoupled architecture with parallel spatial and temporal autoencoders efficiently extracts heterogeneous features. In the prediction stage, the learned representations are integrated with models such as GWNet to enhance accuracy. Experiments on three real-world interchange datasets show that STDAE-GWNET consistently outperforms thirteen state-of-the-art baselines and achieves performance comparable to models using historical ramp data. This demonstrates its effectiveness in overcoming detector scarcity and its plug-and-play potential for diverse forecasting pipelines.

---

### A Robust Clustered Federated Learning Approach for Non-IID Data with Quantity Skew

Authors: Michael Ben Ali, Imen Megdiche, André Peninou, Olivier Teste
Published: 2025-10-03
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.03380v1

Federated Learning (FL) is a decentralized paradigm that enables a client-server architecture to collaboratively train a global Artificial Intelligence model without sharing raw data, thereby preserving privacy. A key challenge in FL is Non-IID data. Quantity Skew (QS) is a particular problem of Non-IID, where clients hold highly heterogeneous data volumes. Clustered Federated Learning (CFL) is an emergent variant of FL that presents a promising solution to Non-IID problem. It improves models' performance by grouping clients with similar data distributions into clusters. CFL methods generally fall into two operating strategies. In the first strategy, clients select the cluster that minimizes the local training loss. In the second strategy, the server groups clients based on local model similarities. However, most CFL methods lack systematic evaluation under QS but present significant challenges because of it. In this paper, we present two main contributions. The first one is an evaluation of state-of-the-art CFL algorithms under various Non-IID settings, applying multiple QS scenarios to assess their robustness. Our second contribution is a novel iterative CFL algorithm, named CORNFLQS, which proposes an optimal coordination between both operating strategies of CFL. Our approach is robust against the different variations of QS settings. We conducted intensive experiments on six image classification datasets, resulting in 270 Non-IID configurations. The results show that CORNFLQS achieves the highest average ranking in both accuracy and clustering quality, as well as strong robustness to QS perturbations. Overall, our approach outperforms actual CFL algorithms.

---

### Can an AI-Powered Presentation Platform Based On The Game "Just a Minute" Be Used To Improve Students' Public Speaking Skills?

Authors: Frederic Higham, Tommy Yuan
Published: 2025-10-03
Categories: cs.CY, cs.AI
arXiv: https://arxiv.org/abs/2510.03379v1

This study explores the effectiveness of applying AI and gamification into a presentation platform aimed at University students wanting to improve their public speaking skills in their native tongue. Specifically, a platform based on the radio show, Just a Minute (JAM), is explored. In this game, players are challenged to speak fluently on a topic for 60 seconds without repeating themselves, hesitating or deviating from the topic. JAM has proposed benefits such as allowing students to improve their spontaneous speaking skills and reduce their use of speech disfluencies ("um", "uh", etc.). Previous research has highlighted the difficulties students face when speaking publicly, the main one being anxiety. AI Powered Presentation Platforms (AI-PPPs), where students can speak with an immersive AI audience and receive real-time feedback, have been explored as a method to improve student's speaking skills and confidence. So far they have shown promising results which this study aims to build upon. A group of students from the University of York are enlisted to evaluate the effectiveness of the JAM platform. They are asked to fill in a questionnaire, play through the game twice and then complete a final questionnaire to discuss their experiences playing the game. Various statistics are gathered during their gameplay such as the number of points they gained and the number of rules they broke. The results showed that students found the game promising and believed that their speaking skills could improve if they played the game for longer. More work will need to be carried out to prove the effectiveness of the game beyond the short term.

---

### Refined Iterated Pareto Greedy for Energy-aware Hybrid Flowshop Scheduling with Blocking Constraints

Authors: Ahmed Missaoui, Cemalettin Ozturk, Barry O'Sullivan
Published: 2025-10-03
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.03377v1

The scarcity of non-renewable energy sources, geopolitical problems in its supply, increasing prices, and the impact of climate change, force the global economy to develop more energy-efficient solutions for their operations. The Manufacturing sector is not excluded from this challenge as one of the largest consumers of energy. Energy-efficient scheduling is a method that attracts manufacturing companies to reduce their consumption as it can be quickly deployed and can show impact immediately. In this study, the hybrid flow shop scheduling problem with blocking constraint (BHFS) is investigated in which we seek to minimize the latest completion time (i.e. makespan) and overall energy consumption, a typical manufacturing setting across many industries from automotive to pharmaceutical. Energy consumption and the latest completion time of customer orders are usually conflicting objectives. Therefore, we first formulate the problem as a novel multi-objective mixed integer programming (MIP) model and propose an augmented epsilon-constraint method for finding the Pareto-optimal solutions. Also, an effective multi-objective metaheuristic algorithm. Refined Iterated Pareto Greedy (RIPG), is developed to solve large instances in reasonable time. Our proposed methods are benchmarked using small, medium, and large-size instances to evaluate their efficiency. Two well-known algorithms are adopted for comparing our novel approaches. The computational results show the effectiveness of our method.

---

### Visual Language Model as a Judge for Object Detection in Industrial Diagrams

Authors: Sanjukta Ghosh
Published: 2025-10-03
Categories: cs.CV, eess.IV
arXiv: https://arxiv.org/abs/2510.03376v1

Industrial diagrams such as piping and instrumentation diagrams (P&IDs) are essential for the design, operation, and maintenance of industrial plants. Converting these diagrams into digital form is an important step toward building digital twins and enabling intelligent industrial automation. A central challenge in this digitalization process is accurate object detection. Although recent advances have significantly improved object detection algorithms, there remains a lack of methods to automatically evaluate the quality of their outputs. This paper addresses this gap by introducing a framework that employs Visual Language Models (VLMs) to assess object detection results and guide their refinement. The approach exploits the multimodal capabilities of VLMs to identify missing or inconsistent detections, thereby enabling automated quality assessment and improving overall detection performance on complex industrial diagrams.

---

### Conditional Pseudo-Supervised Contrast for Data-Free Knowledge Distillation

Authors: Renrong Shao, Wei Zhang, Jun wang
Published: 2025-10-03
Categories: cs.LG, cs.CV
arXiv: https://arxiv.org/abs/2510.03375v1

Data-free knowledge distillation~(DFKD) is an effective manner to solve model compression and transmission restrictions while retaining privacy protection, which has attracted extensive attention in recent years. Currently, the majority of existing methods utilize a generator to synthesize images to support the distillation. Although the current methods have achieved great success, there are still many issues to be explored. Firstly, the outstanding performance of supervised learning in deep learning drives us to explore a pseudo-supervised paradigm on DFKD. Secondly, current synthesized methods cannot distinguish the distributions of different categories of samples, thus producing ambiguous samples that may lead to an incorrect evaluation by the teacher. Besides, current methods cannot optimize the category-wise diversity samples, which will hinder the student model learning from diverse samples and further achieving better performance. In this paper, to address the above limitations, we propose a novel learning paradigm, i.e., conditional pseudo-supervised contrast for data-free knowledge distillation~(CPSC-DFKD). The primary innovations of CPSC-DFKD are: (1) introducing a conditional generative adversarial network to synthesize category-specific diverse images for pseudo-supervised learning, (2) improving the modules of the generator to distinguish the distributions of different categories, and (3) proposing pseudo-supervised contrastive learning based on teacher and student views to enhance diversity. Comprehensive experiments on three commonly-used datasets validate the performance lift of both the student and generator brought by CPSC-DFKD. The code is available at https://github.com/RoryShao/CPSC-DFKD.git

---

### Lightweight Prompt Engineering for Cognitive Alignment in Educational AI: A OneClickQuiz Case Study

Authors: Antoun Yaacoub, Zainab Assaghir, Jérôme Da-Rugna
Published: 2025-10-03
Categories: cs.CY, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2510.03374v1

The rapid integration of Artificial Intelligence (AI) into educational technology promises to revolutionize content creation and assessment. However, the quality and pedagogical alignment of AI-generated content remain critical challenges. This paper investigates the impact of lightweight prompt engineering strategies on the cognitive alignment of AI-generated questions within OneClickQuiz, a Moodle plugin leveraging generative AI. We evaluate three prompt variants-a detailed baseline, a simpler version, and a persona-based approach-across Knowledge, Application, and Analysis levels of Bloom's Taxonomy. Utilizing an automated classification model (from prior work) and human review, our findings demonstrate that explicit, detailed prompts are crucial for precise cognitive alignment. While simpler and persona-based prompts yield clear and relevant questions, they frequently misalign with intended Bloom's levels, generating outputs that are either too complex or deviate from the desired cognitive objective. This study underscores the importance of strategic prompt engineering in fostering pedagogically sound AI-driven educational solutions and advises on optimizing AI for quality content generation in learning analytics and smart learning environments.

---

### Real-time nonlinear inversion of magnetic resonance elastography with operator learning

Authors: Juampablo E. Heras Rivera, Caitlin M. Neher, Mehmet Kurt
Published: 2025-10-03
Categories: eess.IV, cs.AI, cs.CV
arXiv: https://arxiv.org/abs/2510.03372v1

$\textbf{Purpose:}$ To develop and evaluate an operator learning framework for nonlinear inversion (NLI) of brain magnetic resonance elastography (MRE) data, which enables real-time inversion of elastograms with comparable spatial accuracy to NLI. $\textbf{Materials and Methods:}$ In this retrospective study, 3D MRE data from 61 individuals (mean age, 37.4 years; 34 female) were used for development of the framework. A predictive deep operator learning framework (oNLI) was trained using 10-fold cross-validation, with the complex curl of the measured displacement field as inputs and NLI-derived reference elastograms as outputs. A structural prior mechanism, analogous to Soft Prior Regularization in the MRE literature, was incorporated to improve spatial accuracy. Subject-level evaluation metrics included Pearson's correlation coefficient, absolute relative error, and structural similarity index measure between predicted and reference elastograms across brain regions of different sizes to understand accuracy. Statistical analyses included paired t-tests comparing the proposed oNLI variants to the convolutional neural network baselines. $\textbf{Results:}$ Whole brain absolute percent error was 8.4 $\pm$ 0.5 ($μ'$) and 10.0 $\pm$ 0.7 ($μ''$) for oNLI and 15.8 $\pm$ 0.8 ($μ'$) and 26.1 $\pm$ 1.1 ($μ''$) for CNNs. Additionally, oNLI outperformed convolutional architectures as per Pearson's correlation coefficient, $r$, in the whole brain and across all subregions for both the storage modulus and loss modulus (p < 0.05). $\textbf{Conclusion:}$ The oNLI framework enables real-time MRE inversion (30,000x speedup), outperforming CNN-based approaches and maintaining the fine-grained spatial accuracy achievable with NLI in the brain.

---

### Distributed Low-Communication Training with Decoupled Momentum Optimization

Authors: Sasho Nedelkoski, Alexander Acker, Odej Kao, Soeren Becker, Dominik Scheinert
Published: 2025-10-03
Categories: cs.LG, cs.AI, cs.DC
arXiv: https://arxiv.org/abs/2510.03371v1

The training of large models demands substantial computational resources, typically available only in data centers with high-bandwidth interconnects. However, reducing the reliance on high-bandwidth interconnects between nodes enables the use of distributed compute resources as an alternative to centralized data center training. Building on recent advances in distributed model training, we propose an approach that further reduces communication by combining infrequent synchronizations across distributed model replicas with gradient momentum compression. In particular, we treat the optimizer momentum as a signal and decompose the Nesterov momentum into high- and low-frequency components via the discrete cosine transform (DCT). Only the high-frequency components are synchronized across model replicas every $H$ steps. Empirically, our method achieves up to a $16\times$ reduction in communication compared to the baseline DiLoCo, and it generalizes across architectures, including transformer-based language models and convolutional neural networks for images. Overall, this work advances the feasibility of training large models on distributed nodes with low-bandwidth interconnects.

---

### InstructPLM-mu: 1-Hour Fine-Tuning of ESM2 Beats ESM3 in Protein Mutation Predictions

Authors: Junde Xu, Yapin Shi, Lijun Lang, Taoyong Cui, Zhiming Zhang, Guangyong Chen, Jiezhong Qiu, Pheng-Ann Heng
Published: 2025-10-03
Categories: q-bio.QM, cs.AI, cs.CE
arXiv: https://arxiv.org/abs/2510.03370v3

Multimodal protein language models deliver strong performance on mutation-effect prediction, but training such models from scratch demands substantial computational resources. In this paper, we propose a fine-tuning framework called InstructPLM-mu and try to answer a question: \textit{Can multimodal fine-tuning of a pretrained, sequence-only protein language model match the performance of models trained end-to-end? } Surprisingly, our experiments show that fine-tuning ESM2 with structural inputs can reach performance comparable to ESM3. To understand how this is achieved, we systematically compare three different feature-fusion designs and fine-tuning recipes. Our results reveal that both the fusion method and the tuning strategy strongly affect final accuracy, indicating that the fine-tuning process is not trivial. We hope this work offers practical guidance for injecting structure into pretrained protein language models and motivates further research on better fusion mechanisms and fine-tuning protocols.

---

### TriQuest:An AI Copilot-Powered Platform for Interdisciplinary Curriculum Design

Authors: Huazhen Wang, Huimin Yang, Hainbin Lin, Yan Dong, Lili Chen, Liangliang Xia, Wenwen Xu
Published: 2025-10-03
Categories: cs.CY, cs.AI
arXiv: https://arxiv.org/abs/2510.03369v2

Interdisciplinary teaching is a cornerstone of modern curriculum reform, but its implementation is hindered by challenges in knowledge integration and time-consuming lesson planning. Existing tools often lack the required pedagogical and domain-specific depth.We introduce TriQuest, an AI-copilot platform designed to solve these problems. TriQuest uses large language models and knowledge graphs via an intuitive GUI to help teachers efficiently generate high-quality interdisciplinary lesson plans. Its core features include intelligent knowledge integration from various disciplines and a human-computer collaborative review process to ensure quality and innovation.In a study with 43 teachers, TriQuest increased curriculum design efficiency and improved lesson plan quality. It also significantly lowered design barriers and cognitive load. Our work presents a new paradigm for empowering teacher professional development with intelligent technologies.

---

### An Adaptive Responsible AI Governance Framework for Decentralized Organizations

Authors: Kiana Jafari Meimandi, Anka Reuel, Gabriela Aranguiz-Dias, Hatim Rahama, Ala-Eddine Ayadi, Xavier Boullier, Jérémy Verdo, Louis Montanie, Mykel Kochenderfer
Published: 2025-10-03
Categories: cs.CY, cs.AI
arXiv: https://arxiv.org/abs/2510.03368v1

This paper examines the assessment challenges of Responsible AI (RAI) governance efforts in globally decentralized organizations through a case study collaboration between a leading research university and a multinational enterprise. While there are many proposed frameworks for RAI, their application in complex organizational settings with distributed decision-making authority remains underexplored. Our RAI assessment, conducted across multiple business units and AI use cases, reveals four key patterns that shape RAI implementation: (1) complex interplay between group-level guidance and local interpretation, (2) challenges translating abstract principles into operational practices, (3) regional and functional variation in implementation approaches, and (4) inconsistent accountability in risk oversight. Based on these findings, we propose an Adaptive RAI Governance (ARGO) Framework that balances central coordination with local autonomy through three interdependent layers: shared foundation standards, central advisory resources, and contextual local implementation. We contribute insights from academic-industry collaboration for RAI assessments, highlighting the importance of modular governance approaches that accommodate organizational complexity while maintaining alignment with responsible AI principles. These lessons offer practical guidance for organizations navigating the transition from RAI principles to operational practice within decentralized structures.

---

### Viability-Preserving Passive Torque Control

Authors: Zizhe Zhang, Yicong Wang, Zhiquan Zhang, Tianyu Li, Nadia Figueroa
Published: 2025-10-03
Categories: eess.SY, cs.LG, cs.RO
arXiv: https://arxiv.org/abs/2510.03367v2

Conventional passivity-based torque controllers for manipulators are typically unconstrained, which can lead to safety violations under external perturbations. In this paper, we employ viability theory to pre-compute safe sets in the state-space of joint positions and velocities. These viable sets, constructed via data-driven and analytical methods for self-collision avoidance, external object collision avoidance and joint-position and joint-velocity limits, provide constraints on joint accelerations and thus joint torques via the robot dynamics. A quadratic programming-based control framework enforces these constraints on a passive controller tracking a dynamical system, ensuring the robot states remain within the safe set in an infinite time horizon. We validate the proposed approach through simulations and hardware experiments on a 7-DoF Franka Emika manipulator. In comparison to a baseline constrained passive controller, our method operates at higher control-loop rates and yields smoother trajectories.

---

### Disentangling Recall and Reasoning in Transformer Models through Layer-wise Attention and Activation Analysis

Authors: Harshwardhan Fartale, Ashish Kattamuri, Rahul Raja, Arpita Vats, Ishita Prasad, Akshata Kishore Moharir
Published: 2025-10-03
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.03366v2

Transformer-based language models excel at both recall (retrieving memorized facts) and reasoning (performing multi-step inference), but whether these abilities rely on distinct internal mechanisms remains unclear. Distinguishing recall from reasoning is crucial for predicting model generalization, designing targeted evaluations, and building safer interventions that affect one ability without disrupting the other.We approach this question through mechanistic interpretability, using controlled datasets of synthetic linguistic puzzles to probe transformer models at the layer, head, and neuron level. Our pipeline combines activation patching and structured ablations to causally measure component contributions to each task type. Across two model families (Qwen and LLaMA), we find that interventions on distinct layers and attention heads lead to selective impairments: disabling identified "recall circuits" reduces fact-retrieval accuracy by up to 15\% while leaving reasoning intact, whereas disabling "reasoning circuits" reduces multi-step inference by a comparable margin. At the neuron level, we observe task-specific firing patterns, though these effects are less robust, consistent with neuronal polysemanticity.Our results provide the first causal evidence that recall and reasoning rely on separable but interacting circuits in transformer models. These findings advance mechanistic interpretability by linking circuit-level structure to functional specialization and demonstrate how controlled datasets and causal interventions can yield mechanistic insights into model cognition, informing safer deployment of large language models.

---

### Bias and Coverage Properties of the WENDy-IRLS Algorithm

Authors: Abhi Chawla, David M. Bortz, Vanja Dukic
Published: 2025-10-03
Categories: stat.ME, cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2510.03365v1

The Weak form Estimation of Nonlinear Dynamics (WENDy) method is a recently proposed class of parameter estimation algorithms that exhibits notable noise robustness and computational efficiency. This work examines the coverage and bias properties of the original WENDy-IRLS algorithm's parameter and state estimators in the context of the following differential equations: Logistic, Lotka-Volterra, FitzHugh-Nagumo, Hindmarsh-Rose, and a Protein Transduction Benchmark. The estimators' performance was studied in simulated data examples, under four different noise distributions (normal, log-normal, additive censored normal, and additive truncated normal), and a wide range of noise, reaching levels much higher than previously tested for this algorithm.

---

### Diffusion-Based, Data-Assimilation-Enabled Super-Resolution of Hub-height Winds

Authors: Xiaolong Ma, Xu Dong, Ashley Tarrant, Lei Yang, Rao Kotamarthi, Jiali Wang, Feng Yan, Rajkumar Kettimuthu
Published: 2025-10-03
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.03364v1

High-quality observations of hub-height winds are valuable but sparse in space and time. Simulations are widely available on regular grids but are generally biased and too coarse to inform wind-farm siting or to assess extreme-weather-related risks (e.g., gusts) at infrastructure scales. To fully utilize both data types for generating high-quality, high-resolution hub-height wind speeds (tens to ~100m above ground), this study introduces WindSR, a diffusion model with data assimilation for super-resolution downscaling of hub-height winds. WindSR integrates sparse observational data with simulation fields during downscaling using state-of-the-art diffusion models. A dynamic-radius blending method is introduced to merge observations with simulations, providing conditioning for the diffusion process. Terrain information is incorporated during both training and inference to account for its role as a key driver of winds. Evaluated against convolutional-neural-network and generative-adversarial-network baselines, WindSR outperforms them in both downscaling efficiency and accuracy. Our data assimilation reduces WindSR's model bias by approximately 20% relative to independent observations.

---

### Unified Unsupervised Anomaly Detection via Matching Cost Filtering

Authors: Zhe Zhang, Mingxiu Cai, Gaochang Wu, Jing Zhang, Lingqiao Liu, Dacheng Tao, Tianyou Chai, Xiatian Zhu
Published: 2025-10-03
Categories: cs.CV, cs.AI, eess.IV
arXiv: https://arxiv.org/abs/2510.03363v2

Unsupervised anomaly detection (UAD) aims to identify image- and pixel-level anomalies using only normal training data, with wide applications such as industrial inspection and medical analysis, where anomalies are scarce due to privacy concerns and cold-start constraints. Existing methods, whether reconstruction-based (restoring normal counterparts) or embedding-based (pretrained representations), fundamentally conduct image- or feature-level matching to generate anomaly maps. Nonetheless, matching noise has been largely overlooked, limiting their detection ability. Beyond earlier focus on unimodal RGB-based UAD, recent advances expand to multimodal scenarios, e.g., RGB-3D and RGB-Text, enabled by point cloud sensing and vision-language models. Despite shared challenges, these lines remain largely isolated, hindering a comprehensive understanding and knowledge transfer. In this paper, we advocate unified UAD for both unimodal and multimodal settings in the matching perspective. Under this insight, we present Unified Cost Filtering (UCF), a generic post-hoc refinement framework for refining anomaly cost volume of any UAD model. The cost volume is constructed by matching a test sample against normal samples from the same or different modalities, followed by a learnable filtering module with multi-layer attention guidance from the test sample, mitigating matching noise and highlighting subtle anomalies. Comprehensive experiments on 22 diverse benchmarks demonstrate the efficacy of UCF in enhancing a variety of UAD methods, consistently achieving new state-of-the-art results in both unimodal (RGB) and multimodal (RGB-3D, RGB-Text) UAD scenarios. Code and models will be released at https://github.com/ZHE-SAPI/CostFilter-AD.

---

### Estimating link level traffic emissions: enhancing MOVES with open-source data

Authors: Lijiao Wang, Muhammad Usama, Haris N. Koutsopoulos, Zhengbing He
Published: 2025-10-03
Categories: cs.LG, stat.AP, stat.ML
arXiv: https://arxiv.org/abs/2510.03362v1

Open-source data offers a scalable and transparent foundation for estimating vehicle activity and emissions in urban regions. In this study, we propose a data-driven framework that integrates MOVES and open-source GPS trajectory data, OpenStreetMap (OSM) road networks, regional traffic datasets and satellite imagery-derived feature vectors to estimate the link level operating mode distribution and traffic emissions. A neural network model is trained to predict the distribution of MOVES-defined operating modes using only features derived from readily available data. The proposed methodology was applied using open-source data related to 45 municipalities in the Boston Metropolitan area. The "ground truth" operating mode distribution was established using OSM open-source GPS trajectories. Compared to the MOVES baseline, the proposed model reduces RMSE by over 50% for regional scale traffic emissions of key pollutants including CO, NOx, CO2, and PM2.5. This study demonstrates the feasibility of low-cost, replicable, and data-driven emissions estimation using fully open data sources.

---

### Provenance Networks: End-to-End Exemplar-Based Explainability

Authors: Ali Kayyam, Anusha Madan Gopal, M. Anthony Lewis
Published: 2025-10-03
Categories: cs.CV, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.03361v1

We introduce provenance networks, a novel class of neural models designed to provide end-to-end, training-data-driven explainability. Unlike conventional post-hoc methods, provenance networks learn to link each prediction directly to its supporting training examples as part of the model's normal operation, embedding interpretability into the architecture itself. Conceptually, the model operates similarly to a learned KNN, where each output is justified by concrete exemplars weighted by relevance in the feature space. This approach facilitates systematic investigations of the trade-off between memorization and generalization, enables verification of whether a given input was included in the training set, aids in the detection of mislabeled or anomalous data points, enhances resilience to input perturbations, and supports the identification of similar inputs contributing to the generation of a new data point. By jointly optimizing the primary task and the explainability objective, provenance networks offer insights into model behavior that traditional deep networks cannot provide. While the model introduces additional computational cost and currently scales to moderately sized datasets, it provides a complementary approach to existing explainability techniques. In particular, it addresses critical challenges in modern deep learning, including model opaqueness, hallucination, and the assignment of credit to data contributors, thereby improving transparency, robustness, and trustworthiness in neural models.

---

### Physics-informed Neural-operator Predictive Control for Drag Reduction in Turbulent Flows

Authors: Zelin Zhao, Zongyi Li, Kimia Hassibi, Kamyar Azizzadenesheli, Junchi Yan, H. Jane Bae, Di Zhou, Anima Anandkumar
Published: 2025-10-03
Categories: cs.LG, cs.AI, math.OC, physics.flu-dyn
arXiv: https://arxiv.org/abs/2510.03360v1

Assessing turbulence control effects for wall friction numerically is a significant challenge since it requires expensive simulations of turbulent fluid dynamics. We instead propose an efficient deep reinforcement learning (RL) framework for modeling and control of turbulent flows. It is model-based RL for predictive control (PC), where both the policy and the observer models for turbulence control are learned jointly using Physics Informed Neural Operators (PINO), which are discretization invariant and can capture fine scales in turbulent flows accurately. Our PINO-PC outperforms prior model-free reinforcement learning methods in various challenging scenarios where the flows are of high Reynolds numbers and unseen, i.e., not provided during model training. We find that PINO-PC achieves a drag reduction of 39.0\% under a bulk-velocity Reynolds number of 15,000, outperforming previous fluid control methods by more than 32\%.

---

### LEAML: Label-Efficient Adaptation to Out-of-Distribution Visual Tasks for Multimodal Large Language Models

Authors: Ci-Siang Lin, Min-Hung Chen, Yu-Yang Sheng, Yu-Chiang Frank Wang
Published: 2025-10-03
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.03232v1

Multimodal Large Language Models (MLLMs) have achieved strong performance on general visual benchmarks but struggle with out-of-distribution (OOD) tasks in specialized domains such as medical imaging, where labeled data is limited and expensive. We introduce LEAML, a label-efficient adaptation framework that leverages both scarce labeled VQA samples and abundant unlabeled images. Our approach generates domain-relevant pseudo question-answer pairs for unlabeled data using a QA generator regularized by caption distillation. Importantly, we selectively update only those neurons most relevant to question-answering, enabling the QA Generator to efficiently acquire domain-specific knowledge during distillation. Experiments on gastrointestinal endoscopy and sports VQA demonstrate that LEAML consistently outperforms standard fine-tuning under minimal supervision, highlighting the effectiveness of our proposed LEAML framework.

---

### Reward Models are Metrics in a Trench Coat

Authors: Sebastian Gehrmann
Published: 2025-10-03
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.03231v1

The emergence of reinforcement learning in post-training of large language models has sparked significant interest in reward models. Reward models assess the quality of sampled model outputs to generate training signals. This task is also performed by evaluation metrics that monitor the performance of an AI model. We find that the two research areas are mostly separate, leading to redundant terminology and repeated pitfalls. Common challenges include susceptibility to spurious correlations, impact on downstream reward hacking, methods to improve data quality, and approaches to meta-evaluation. Our position paper argues that a closer collaboration between the fields can help overcome these issues. To that end, we show how metrics outperform reward models on specific tasks and provide an extensive survey of the two areas. Grounded in this survey, we point to multiple research topics in which closer alignment can improve reward models and metrics in areas such as preference elicitation methods, avoidance of spurious correlations and reward hacking, and calibration-aware meta-evaluation.

---

### Improving GUI Grounding with Explicit Position-to-Coordinate Mapping

Authors: Suyuchen Wang, Tianyu Zhang, Ahmed Masry, Christopher Pal, Spandana Gella, Bang Liu, Perouz Taslakian
Published: 2025-10-03
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.03230v1

GUI grounding, the task of mapping natural-language instructions to pixel coordinates, is crucial for autonomous agents, yet remains difficult for current VLMs. The core bottleneck is reliable patch-to-pixel mapping, which breaks when extrapolating to high-resolution displays unseen during training. Current approaches generate coordinates as text tokens directly from visual features, forcing the model to infer complex position-to-pixel mappings implicitly; as a result, accuracy degrades and failures proliferate on new resolutions. We address this with two complementary innovations. First, RULER tokens serve as explicit coordinate markers, letting the model reference positions similar to gridlines on a map and adjust rather than generate coordinates from scratch. Second, Interleaved MRoPE (I-MRoPE) improves spatial encoding by ensuring that width and height dimensions are represented equally, addressing the asymmetry of standard positional schemes. Experiments on ScreenSpot, ScreenSpot-V2, and ScreenSpot-Pro show consistent gains in grounding accuracy, with the largest improvements on high-resolution interfaces. By providing explicit spatial guidance rather than relying on implicit learning, our approach enables more reliable GUI automation across diverse resolutions and platforms.

---

### MIXER: Mixed Hyperspherical Random Embedding Neural Network for Texture Recognition

Authors: Ricardo T. Fares, Lucas C. Ribas
Published: 2025-10-03
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.03228v1

Randomized neural networks for representation learning have consistently achieved prominent results in texture recognition tasks, effectively combining the advantages of both traditional techniques and learning-based approaches. However, existing approaches have so far focused mainly on improving cross-information prediction, without introducing significant advancements to the overall randomized network architecture. In this paper, we propose Mixer, a novel randomized neural network for texture representation learning. At its core, the method leverages hyperspherical random embeddings coupled with a dual-branch learning module to capture both intra- and inter-channel relationships, further enhanced by a newly formulated optimization problem for building rich texture representations. Experimental results have shown the interesting results of the proposed approach across several pure texture benchmarks, each with distinct characteristics and challenges. The source code will be available upon publication.

---

### A fast non-reversible sampler for Bayesian mixture models

Authors: Filippo Ascolani, Paolo Manildo, Giacomo Zanella
Published: 2025-10-03
Categories: stat.CO, stat.ME, stat.ML
arXiv: https://arxiv.org/abs/2510.03226v2

Mixtures models are a cornerstone of Bayesian modelling, and it is well-known that sampling from the resulting posterior distribution can be a hard task. In particular, popular reversible Markov chain Monte Carlo schemes are often slow to converge when the number of observations $n$ is large. In this paper we introduce a novel and simple non-reversible sampling scheme for Bayesian mixture models (with fixed or varying number of components), which is shown to drastically outperform classical samplers in many scenarios of interest, especially during convergence phase and when components in the mixture have non-negligible overlap. At the theoretical level, we show that the performance of the proposed non-reversible scheme cannot be worse than the standard one, in terms of asymptotic variance, by more than a factor of four; and we provide a scaling limit analysis suggesting that the non-reversible sampler can reduce the convergence time from O$(n^2)$ to O$(n)$. We also discuss why the statistical features of mixture models make them an ideal case for the use of non-reversible discrete samplers.

---

### Test-Time Defense Against Adversarial Attacks via Stochastic Resonance of Latent Ensembles

Authors: Dong Lao, Yuxiang Zhang, Haniyeh Ehsani Oskouie, Yangchao Wu, Alex Wong, Stefano Soatto
Published: 2025-10-03
Categories: cs.CV, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.03224v1

We propose a test-time defense mechanism against adversarial attacks: imperceptible image perturbations that significantly alter the predictions of a model. Unlike existing methods that rely on feature filtering or smoothing, which can lead to information loss, we propose to "combat noise with noise" by leveraging stochastic resonance to enhance robustness while minimizing information loss. Our approach introduces small translational perturbations to the input image, aligns the transformed feature embeddings, and aggregates them before mapping back to the original reference image. This can be expressed in a closed-form formula, which can be deployed on diverse existing network architectures without introducing additional network modules or fine-tuning for specific attack types. The resulting method is entirely training-free, architecture-agnostic, and attack-agnostic. Empirical results show state-of-the-art robustness on image classification and, for the first time, establish a generic test-time defense for dense prediction tasks, including stereo matching and optical flow, highlighting the method's versatility and practicality. Specifically, relative to clean (unperturbed) performance, our method recovers up to 68.1% of the accuracy loss on image classification, 71.9% on stereo matching, and 29.2% on optical flow under various types of adversarial attacks.

---

### Attention-Aligned Reasoning for Large Language Models

Authors: Hongxiang Zhang, Yuan Tian, Tianyi Zhang
Published: 2025-10-03
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.03223v2

Large Language Models (LLMs) tend to generate a long reasoning chain when solving complex tasks. However, as the reasoning chain extends, critical intermediate steps and the original prompt will be buried in the context, receiving insufficient attention and leading to errors. In this work, we present ATAR, a novel reasoning method that leverages the inherent reasoning structure to steer LLM attention. Our experiments show that ATAR outperforms SOTA methods across six benchmarks, achieving up to 15.39% absolute improvement. Furthermore, with ATAR, "non-reasoning" models achieve comparable or even better performance compared to reasoning models of the same size in most benchmarks. Finally, our ablation studies show that the attention alignment component contributes significantly, and that these improvements are persist under different attentionsteering backends.

---

### Low-probability Tokens Sustain Exploration in Reinforcement Learning with Verifiable Reward

Authors: Guanhua Huang, Tingqiang Xu, Mingze Wang, Qi Yi, Xue Gong, Siheng Li, Ruibin Xiong, Kejiao Li, Yuhao Jiang, Bo Zhou
Published: 2025-10-03
Categories: cs.LG, cs.CL
arXiv: https://arxiv.org/abs/2510.03222v2

Reinforcement Learning with Verifiable Rewards (RLVR) has propelled Large Language Models in complex reasoning, yet its scalability is often hindered by a training bottleneck where performance plateaus as policy entropy collapses, signaling a loss of exploration. Previous methods typically address this by maintaining high policy entropy, yet the precise mechanisms that govern meaningful exploration have remained underexplored. Our analysis suggests that an unselective focus on entropy risks amplifying irrelevant tokens and destabilizing training. This paper investigates the exploration dynamics within RLVR and identifies a key issue: the gradual elimination of valuable low-probability exploratory tokens, which we term \textbf{\textit{reasoning sparks}}. We find that while abundant in pre-trained models, these sparks are systematically extinguished during RLVR due to over-penalization, leading to a degeneracy in exploration. To address this, we introduce Low-probability Regularization (Lp-Reg). Its core mechanism regularizes the policy towards a heuristic proxy distribution. This proxy is constructed by filtering out presumed noise tokens and re-normalizing the distribution over the remaining candidates. The result is a less-noisy proxy where the probability of \textit{reasoning sparks} is amplified, which then serves as a soft regularization target to shield these valuable tokens from elimination via KL divergence. Experiments show that Lp-Reg enables stable on-policy RL, sustaining continuous scaling across $3,000$ training steps and $81,204$ GPU-hours, where baseline entropy-control methods collapse. This sustained exploration leads to state-of-the-art performance, achieving a $60.17\%$ average accuracy on five math benchmarks, an improvement of $2.66\%$ over prior methods. Code is available at https://github.com/CarlanLark/Lp-Reg.

---

### Abstain and Validate: A Dual-LLM Policy for Reducing Noise in Agentic Program Repair

Authors: José Cambronero, Michele Tufano, Sherry Shi, Renyao Wei, Grant Uy, Runxiang Cheng, Chin-Jung Liu, Shiying Pan, Satish Chandra, Pat Rondon
Published: 2025-10-03
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2510.03217v2

Agentic Automated Program Repair (APR) is increasingly tackling complex, repository-level bugs in industry, but ultimately these patches still need to be reviewed by a human before committing them to ensure they address the bug. Showing patches unlikely to be accepted can lead to substantial noise, wasting valuable developer time and eroding trust in automated code changes. We introduce two complementary LLM-based policies to reduce such noise: bug abstention and patch validation policies. Bug abstention excludes bugs that the agentic APR system is unlikely to fix. Patch validation rejects patches that are unlikely to be a good fix for the given bug. We evaluate both policies on three sets of bugs from Google's codebase, and their candidate patches generated by an internal agentic APR system. On a set of 174 human-reported bugs, removing bugs and patches rejected by our policies can raise success rates by up to 13 percentage points and 15 percentage points, respectively, and by up to 39 percentage points in combination. On null pointer exceptions and sanitizer-reported bugs with machine-generated bug reports, patch validation also improves average single-sample success rates. This two-policy approach provides a practical path to the reliable, industrial-scale deployment of agentic APR systems.

---

### Wave-GMS: Lightweight Multi-Scale Generative Model for Medical Image Segmentation

Authors: Talha Ahmed, Nehal Ahmed Shaikh, Hassan Mohy-ud-Din
Published: 2025-10-03
Categories: eess.IV, cs.AI, cs.CV
arXiv: https://arxiv.org/abs/2510.03216v1

For equitable deployment of AI tools in hospitals and healthcare facilities, we need Deep Segmentation Networks that offer high performance and can be trained on cost-effective GPUs with limited memory and large batch sizes. In this work, we propose Wave-GMS, a lightweight and efficient multi-scale generative model for medical image segmentation. Wave-GMS has a substantially smaller number of trainable parameters, does not require loading memory-intensive pretrained vision foundation models, and supports training with large batch sizes on GPUs with limited memory. We conducted extensive experiments on four publicly available datasets (BUS, BUSI, Kvasir-Instrument, and HAM10000), demonstrating that Wave-GMS achieves state-of-the-art segmentation performance with superior cross-domain generalizability, while requiring only ~2.6M trainable parameters. Code is available at https://github.com/ATPLab-LUMS/Wave-GMS.

---

### Cache-to-Cache: Direct Semantic Communication Between Large Language Models

Authors: Tianyu Fu, Zihan Min, Hanling Zhang, Jichao Yan, Guohao Dai, Wanli Ouyang, Yu Wang
Published: 2025-10-03
Categories: cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2510.03215v2

Multi-LLM systems harness the complementary strengths of diverse Large Language Models, achieving performance and efficiency gains that are not attainable by a single model. In existing designs, LLMs communicate through text, forcing internal representations to be transformed into output token sequences. This process both loses rich semantic information and incurs token-by-token generation latency. Motivated by these limitations, we ask: Can LLMs communicate beyond text? Oracle experiments show that enriching the KV-Cache semantics can improve response quality without increasing cache size, supporting KV-Cache as an effective medium for inter-model communication. Thus, we propose Cache-to-Cache (C2C), a new paradigm for direct semantic communication between LLMs. C2C uses a neural network to project and fuse the source model's KV-cache with that of the target model to enable direct semantic transfer. A learnable gating mechanism selects the target layers that benefit from cache communication. Compared with text communication, C2C utilizes the deep, specialized semantics from both models, while avoiding explicit intermediate text generation. Experiments show that C2C achieves 6.4-14.2% higher average accuracy than individual models. It further outperforms the text communication paradigm by approximately 3.1-5.4%, while delivering an average 2.5x speedup in latency. Our code is available at https://github.com/thu-nics/C2C.

---

### Joint Bidding on Intraday and Frequency Containment Reserve Markets

Authors: Yiming Zhang, Wolfgang Ridinger, David Wozabal
Published: 2025-10-03
Categories: q-fin.CP, cs.LG, q-fin.TR
arXiv: https://arxiv.org/abs/2510.03209v1

As renewable energy integration increases supply variability, battery energy storage systems (BESS) present a viable solution for balancing supply and demand. This paper proposes a novel approach for optimizing battery BESS participation in multiple electricity markets. We develop a joint bidding strategy that combines participation in the primary frequency reserve market with continuous trading in the intraday market, addressing a gap in the extant literature which typically considers these markets in isolation or simplifies the continuous nature of intraday trading. Our approach utilizes a mixed integer linear programming implementation of the rolling intrinsic algorithm for intraday decisions and state of charge recovery, alongside a learned classifier strategy (LCS) that determines optimal capacity allocation between markets. A comprehensive out-of-sample backtest over more than one year of historical German market data validates our approach: The LCS increases overall profits by over 4% compared to the best-performing static strategy and by more than 3% over a naive dynamic benchmark. Crucially, our method closes the gap to a theoretical perfect foresight strategy to just 4%, demonstrating the effectiveness of dynamic, learning-based allocation in a complex, multi-market environment.

---

### To Distill or Decide? Understanding the Algorithmic Trade-off in Partially Observable Reinforcement Learning

Authors: Yuda Song, Dhruv Rohatgi, Aarti Singh, J. Andrew Bagnell
Published: 2025-10-03
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.03207v1

Partial observability is a notorious challenge in reinforcement learning (RL), due to the need to learn complex, history-dependent policies. Recent empirical successes have used privileged expert distillation--which leverages availability of latent state information during training (e.g., from a simulator) to learn and imitate the optimal latent, Markovian policy--to disentangle the task of "learning to see" from "learning to act". While expert distillation is more computationally efficient than RL without latent state information, it also has well-documented failure modes. In this paper--through a simple but instructive theoretical model called the perturbed Block MDP, and controlled experiments on challenging simulated locomotion tasks--we investigate the algorithmic trade-off between privileged expert distillation and standard RL without privileged information. Our main findings are: (1) The trade-off empirically hinges on the stochasticity of the latent dynamics, as theoretically predicted by contrasting approximate decodability with belief contraction in the perturbed Block MDP; and (2) The optimal latent policy is not always the best latent policy to distill. Our results suggest new guidelines for effectively exploiting privileged information, potentially advancing the efficiency of policy learning across many practical partially observable domains.

---

### Coevolutionary Continuous Discrete Diffusion: Make Your Diffusion Language Model a Latent Reasoner

Authors: Cai Zhou, Chenxiao Yang, Yi Hu, Chenyu Wang, Chubin Zhang, Muhan Zhang, Lester Mackey, Tommi Jaakkola, Stephen Bates, Dinghuai Zhang
Published: 2025-10-03
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2510.03206v2

Diffusion language models, especially masked discrete diffusion models, have achieved great success recently. While there are some theoretical and primary empirical results showing the advantages of latent reasoning with looped transformers or continuous chain-of-thoughts, continuous diffusion models typically underperform their discrete counterparts. In this paper, we argue that diffusion language models do not necessarily need to be in the discrete space. In particular, we prove that continuous diffusion models have stronger expressivity than discrete diffusions and looped transformers. We attribute the contradiction between the theoretical expressiveness and empirical performance to their practical trainability: while continuous diffusion provides intermediate supervision that looped transformers lack, they introduce additional difficulty decoding tokens into the discrete token space from the continuous representation space. We therefore propose Coevolutionary Continuous Discrete Diffusion (CCDD), which defines a joint multimodal diffusion process on the union of a continuous representation space and a discrete token space, leveraging a single model to simultaneously denoise in the joint space. By combining two modalities, CCDD is expressive with rich semantics in the latent space, as well as good trainability and sample quality with the help of explicit discrete tokens. We also propose effective architectures and advanced training/sampling techniques for CCDD, which reveals strong empirical performance in extensive language modeling experiments on real-world tasks.

---

### Automatic Generation of Digital Twins for Network Testing

Authors: Shenjia Ding, David Flynn, Paul Harvey
Published: 2025-10-03
Categories: cs.NI, cs.LG
arXiv: https://arxiv.org/abs/2510.03205v1

The increased use of software in the operation and management of telecommunication networks has moved the industry one step closer to realizing autonomous network operation. One consequence of this shift is the significantly increased need for testing and validation before such software can be deployed. Complementing existing simulation or hardware-based approaches, digital twins present an environment to achieve this testing; however, they require significant time and human effort to configure and execute. This paper explores the automatic generation of digital twins to provide efficient and accurate validation tools, aligned to the ITU-T autonomous network architecture's experimentation subsystem. We present experimental results for an initial use case, demonstrating that the approach is feasible in automatically creating efficient digital twins with sufficient accuracy to be included as part of existing validation pipelines.

---

### FocusAgent: Simple Yet Effective Ways of Trimming the Large Context of Web Agents

Authors: Imene Kerboua, Sahar Omidi Shayegan, Megh Thakkar, Xing Han Lù, Léo Boisvert, Massimo Caccia, Jérémy Espinas, Alexandre Aussem, Véronique Eglin, Alexandre Lacoste
Published: 2025-10-03
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.03204v2

Web agents powered by large language models (LLMs) must process lengthy web page observations to complete user goals; these pages often exceed tens of thousands of tokens. This saturates context limits and increases computational cost processing; moreover, processing full pages exposes agents to security risks such as prompt injection. Existing pruning strategies either discard relevant content or retain irrelevant context, leading to suboptimal action prediction. We introduce FocusAgent, a simple yet effective approach that leverages a lightweight LLM retriever to extract the most relevant lines from accessibility tree (AxTree) observations, guided by task goals. By pruning noisy and irrelevant content, FocusAgent enables efficient reasoning while reducing vulnerability to injection attacks. Experiments on WorkArena and WebArena benchmarks show that FocusAgent matches the performance of strong baselines, while reducing observation size by over 50%. Furthermore, a variant of FocusAgent significantly reduces the success rate of prompt-injection attacks, including banner and pop-up attacks, while maintaining task success performance in attack-free settings. Our results highlight that targeted LLM-based retrieval is a practical and robust strategy for building web agents that are efficient, effective, and secure.

---

### Model-Based Ranking of Source Languages for Zero-Shot Cross-Lingual Transfer

Authors: Abteen Ebrahimi, Adam Wiemerslage, Katharina von der Wense
Published: 2025-10-03
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.03202v2

We present NN-Rank, an algorithm for ranking source languages for cross-lingual transfer, which leverages hidden representations from multilingual models and unlabeled target-language data. We experiment with two pretrained multilingual models and two tasks: part-of-speech tagging (POS) and named entity recognition (NER). We consider 51 source languages and evaluate on 56 and 72 target languages for POS and NER, respectively. When using in-domain data, NN-Rank beats state-of-the-art baselines that leverage lexical and linguistic features, with average improvements of up to 35.56 NDCG for POS and 18.14 NDCG for NER. As prior approaches can fall back to language-level features if target language data is not available, we show that NN-Rank remains competitive using only the Bible, an out-of-domain corpus available for a large number of languages. Ablations on the amount of unlabeled target data show that, for subsets consisting of as few as 25 examples, NN-Rank produces high-quality rankings which achieve 92.8% of the NDCG achieved using all available target data for ranking.

---

### MonSTeR: a Unified Model for Motion, Scene, Text Retrieval

Authors: Luca Collorone, Matteo Gioia, Massimiliano Pappa, Paolo Leoni, Giovanni Ficarra, Or Litany, Indro Spinelli, Fabio Galasso
Published: 2025-10-03
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.03200v1

Intention drives human movement in complex environments, but such movement can only happen if the surrounding context supports it. Despite the intuitive nature of this mechanism, existing research has not yet provided tools to evaluate the alignment between skeletal movement (motion), intention (text), and the surrounding context (scene). In this work, we introduce MonSTeR, the first MOtioN-Scene-TExt Retrieval model. Inspired by the modeling of higher-order relations, MonSTeR constructs a unified latent space by leveraging unimodal and cross-modal representations. This allows MonSTeR to capture the intricate dependencies between modalities, enabling flexible but robust retrieval across various tasks. Our results show that MonSTeR outperforms trimodal models that rely solely on unimodal representations. Furthermore, we validate the alignment of our retrieval scores with human preferences through a dedicated user study. We demonstrate the versatility of MonSTeR's latent space on zero-shot in-Scene Object Placement and Motion Captioning. Code and pre-trained models are available at github.com/colloroneluca/MonSTeR.

---

### Best-of-Majority: Minimax-Optimal Strategy for Pass@$k$ Inference Scaling

Authors: Qiwei Di, Kaixuan Ji, Xuheng Li, Heyang Zhao, Quanquan Gu
Published: 2025-10-03
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2510.03199v1

LLM inference often generates a batch of candidates for a prompt and selects one via strategies like majority voting or Best-of- N (BoN). For difficult tasks, this single-shot selection often underperforms. Consequently, evaluations commonly report Pass@$k$: the agent may submit up to $k$ responses, and only the best of them is used when computing regret. Motivated by this, we study inference scaling in the more general Pass@$k$ inference setting, and prove that neither majority voting nor BoN exhibits the desirable scaling with $k$ and the sampling budget $N$. Combining the advantages of majority voting and BoN, we propose a new inference strategy called Best-of-Majority (BoM), with a pivotal step that restricts the candidates to the responses with high frequency in the $N$ samples before selecting the top-$k$ rewards. We prove that when the sampling budget is $N=\tildeΩ(C^*)$, the regret of BoM is $O(ε_{\mathrm{opt}}+\sqrt{ε_{\mathrm{RM}}^2C^*/k})$, where $C^*$ is the coverage coefficient, $ε_{\mathrm{RM}}$ is the estimation error of the reward model, and $ε_{\mathrm{opt}}$ is the estimation error of reward at the optimal response. We further establish a matching lower bound, certifying that our algorithm is minimax optimal. Beyond optimality, BoM has a key advantage: unlike majority voting and BoN, its performance does not degrade when increasing $N$. Experimental results of inference on math problems show BoM outperforming both majority voting and BoN.

---

### Memory Forcing: Spatio-Temporal Memory for Consistent Scene Generation on Minecraft

Authors: Junchao Huang, Xinting Hu, Boyao Han, Shaoshuai Shi, Zhuotao Tian, Tianyu He, Li Jiang
Published: 2025-10-03
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.03198v1

Autoregressive video diffusion models have proved effective for world modeling and interactive scene generation, with Minecraft gameplay as a representative application. To faithfully simulate play, a model must generate natural content while exploring new scenes and preserve spatial consistency when revisiting explored areas. Under limited computation budgets, it must compress and exploit historical cues within a finite context window, which exposes a trade-off: Temporal-only memory lacks long-term spatial consistency, whereas adding spatial memory strengthens consistency but may degrade new scene generation quality when the model over-relies on insufficient spatial context. We present Memory Forcing, a learning framework that pairs training protocols with a geometry-indexed spatial memory. Hybrid Training exposes distinct gameplay regimes, guiding the model to rely on temporal memory during exploration and incorporate spatial memory for revisits. Chained Forward Training extends autoregressive training with model rollouts, where chained predictions create larger pose variations and encourage reliance on spatial memory for maintaining consistency. Point-to-Frame Retrieval efficiently retrieves history by mapping currently visible points to their source frames, while Incremental 3D Reconstruction maintains and updates an explicit 3D cache. Extensive experiments demonstrate that Memory Forcing achieves superior long-term spatial consistency and generative quality across diverse environments, while maintaining computational efficiency for extended sequences.

---

### Estimation of Resistance Training RPE using Inertial Sensors and Electromyography

Authors: James Thomas, Johan Wahlström
Published: 2025-10-03
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.03197v1

Accurate estimation of rating of perceived exertion (RPE) can enhance resistance training through personalized feedback and injury prevention. This study investigates the application of machine learning models to estimate RPE during single-arm dumbbell bicep curls, using data from wearable inertial and electromyography (EMG) sensors. A custom dataset of 69 sets and over 1000 repetitions was collected, with statistical features extracted for model training. Among the models evaluated, a random forest classifier achieved the highest performance, with 41.4% exact accuracy and 85.9% $\pm1$ RPE accuracy. While the inclusion of EMG data slightly improved model accuracy over inertial sensors alone, its utility may have been limited by factors such as data quality and placement sensitivity. Feature analysis highlighted eccentric repetition time as the strongest RPE predictor. The results demonstrate the feasibility of wearable-sensor-based RPE estimation and identify key challenges for improving model generalizability.

---

### CoDA: Agentic Systems for Collaborative Data Visualization

Authors: Zichen Chen, Jiefeng Chen, Sercan Ö. Arik, Misha Sra, Tomas Pfister, Jinsung Yoon
Published: 2025-10-03
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.03194v1

Deep research has revolutionized data analysis, yet data scientists still devote substantial time to manually crafting visualizations, highlighting the need for robust automation from natural language queries. However, current systems struggle with complex datasets containing multiple files and iterative refinement. Existing approaches, including simple single- or multi-agent systems, often oversimplify the task, focusing on initial query parsing while failing to robustly manage data complexity, code errors, or final visualization quality. In this paper, we reframe this challenge as a collaborative multi-agent problem. We introduce CoDA, a multi-agent system that employs specialized LLM agents for metadata analysis, task planning, code generation, and self-reflection. We formalize this pipeline, demonstrating how metadata-focused analysis bypasses token limits and quality-driven refinement ensures robustness. Extensive evaluations show CoDA achieves substantial gains in the overall score, outperforming competitive baselines by up to 41.5%. This work demonstrates that the future of visualization automation lies not in isolated code generation but in integrated, collaborative agentic workflows.

---

### Product-Quantised Image Representation for High-Quality Image Synthesis

Authors: Denis Zavadski, Nikita Philip Tatsch, Carsten Rother
Published: 2025-10-03
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.03191v1

Product quantisation (PQ) is a classical method for scalable vector encoding, yet it has seen limited usage for latent representations in high-fidelity image generation. In this work, we introduce PQGAN, a quantised image autoencoder that integrates PQ into the well-known vector quantisation (VQ) framework of VQGAN. PQGAN achieves a noticeable improvement over state-of-the-art methods in terms of reconstruction performance, including both quantisation methods and their continuous counterparts. We achieve a PSNR score of 37dB, where prior work achieves 27dB, and are able to reduce the FID, LPIPS, and CMMD score by up to 96%. Our key to success is a thorough analysis of the interaction between codebook size, embedding dimensionality, and subspace factorisation, with vector and scalar quantisation as special cases. We obtain novel findings, such that the performance of VQ and PQ behaves in opposite ways when scaling the embedding dimension. Furthermore, our analysis shows performance trends for PQ that help guide optimal hyperparameter selection. Finally, we demonstrate that PQGAN can be seamlessly integrated into pre-trained diffusion models. This enables either a significantly faster and more compute-efficient generation, or a doubling of the output resolution at no additional cost, positioning PQ as a strong extension for discrete latent representation in image synthesis.

---

### Dynamic Prompt Generation for Interactive 3D Medical Image Segmentation Training

Authors: Tidiane Camaret Ndir, Alexander Pfefferle, Robin Tibor Schirrmeister
Published: 2025-10-03
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.03189v3

Interactive 3D biomedical image segmentation requires efficient models that can iteratively refine predictions based on user prompts. Current foundation models either lack volumetric awareness or suffer from limited interactive capabilities. We propose a training strategy that combines dynamic volumetric prompt generation with content-aware adaptive cropping to optimize the use of the image encoder. Our method simulates realistic user interaction patterns during training while addressing the computational challenges of learning from sequential refinement feedback on a single GPU. For efficient training, we initialize our network using the publicly available weights from the nnInteractive segmentation model. Evaluation on the \textbf{Foundation Models for Interactive 3D Biomedical Image Segmentation} competition demonstrates strong performance with an average final Dice score of 0.6385, normalized surface distance of 0.6614, and area-under-the-curve metrics of 2.4799 (Dice) and 2.5671 (NSD).

---

### Superposition disentanglement of neural representations reveals hidden alignment

Authors: André Longon, David Klindt, Meenakshi Khosla
Published: 2025-10-03
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.03186v2

The superposition hypothesis states that single neurons may participate in representing multiple features in order for the neural network to represent more features than it has neurons. In neuroscience and AI, representational alignment metrics measure the extent to which different deep neural networks (DNNs) or brains represent similar information. In this work, we explore a critical question: does superposition interact with alignment metrics in any undesirable way? We hypothesize that models which represent the same features in different superposition arrangements, i.e., their neurons have different linear combinations of the features, will interfere with predictive mapping metrics (semi-matching, soft-matching, linear regression), producing lower alignment than expected. We develop a theory for how permutation metrics are dependent on superposition arrangements. This is tested by training sparse autoencoders (SAEs) to disentangle superposition in toy models, where alignment scores are shown to typically increase when a model's base neurons are replaced with its sparse overcomplete latent codes. We find similar increases for DNN-DNN and DNN-brain linear regression alignment in the visual domain. Our results suggest that superposition disentanglement is necessary for mapping metrics to uncover the true representational alignment between neural networks.

---