# Research Papers — 2025-10 · bundle page 162 of 217

> Full-text markdown of papers #8051–8100 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/162
[← Previous bundle](https://aipod.dev/papers/archive/2025-10/page/161.md)
[Next bundle →](https://aipod.dev/papers/archive/2025-10/page/163.md)

### A Denoising Framework for Real-World Ultra-Low-Dose Lung CT Images Based on an Image Purification Strategy

Authors: Guoliang Gong, Man Yu
Published: 2025-10-08
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.07492v3

Computed Tomography (CT) is a vital diagnostic tool in clinical practice, yet the health risks associated with ionizing radiation cannot be overlooked. Low-dose CT (LDCT) helps mitigate radiation exposure but simultaneously leads to reduced image quality. Consequently, researchers have sought to reconstruct clear images from LDCT scans using artificial intelligence-based image enhancement techniques. However, these studies typically rely on synthetic LDCT images for algorithm training, which introduces significant domain-shift issues and limits the practical effectiveness of these algorithms in real-world scenarios. To address this challenge, we constructed a real-world paired lung dataset, referred to as Patient-uLDCT (ultra-low-dose CT), by performing multiple scans on volunteers. The radiation dose for the low-dose images in this dataset is only 2% of the normal dose, substantially lower than the conventional 25% low-dose and 10% ultra-low-dose levels. Furthermore, to resolve the anatomical misalignment between normal-dose and uLDCT images caused by respiratory motion during acquisition, we propose a novel purification strategy to construct corresponding aligned image pairs. Finally, we introduce a Frequency-domain Flow Matching model (FFM) that achieves excellent image reconstruction performance. Code is available at https://github.com/MonkeyDadLufy/flow-matching.

---

### Optimizing Ethical Risk Reduction for Medical Intelligent Systems with Constraint Programming

Authors: Clotilde Brayé, Aurélien Bricout, Arnaud Gotlieb, Nadjib Lazaar, Quentin Vallet
Published: 2025-10-08
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.07491v1

Medical Intelligent Systems (MIS) are increasingly integrated into healthcare workflows, offering significant benefits but also raising critical safety and ethical concerns. According to the European Union AI Act, most MIS will be classified as high-risk systems, requiring a formal risk management process to ensure compliance with the ethical requirements of trustworthy AI. In this context, we focus on risk reduction optimization problems, which aim to reduce risks with ethical considerations by finding the best balanced assignment of risk assessment values according to their coverage of trustworthy AI ethical requirements. We formalize this problem as a constrained optimization task and investigate three resolution paradigms: Mixed Integer Programming (MIP), Satisfiability (SAT), and Constraint Programming(CP).Our contributions include the mathematical formulation of this optimization problem, its modeling with the Minizinc constraint modeling language, and a comparative experimental study that analyzes the performance, expressiveness, and scalability of each approach to solving. From the identified limits of the methodology, we draw some perspectives of this work regarding the integration of the Minizinc model into a complete trustworthy AI ethical risk management process for MIS.

---

### Evaluation of LLMs for Process Model Analysis and Optimization

Authors: Akhil Kumar, Jianliang Leon Zhao, Om Dobariya
Published: 2025-10-08
Categories: cs.AI, cs.CL, cs.CY, cs.IR, cs.LG
arXiv: https://arxiv.org/abs/2510.07489v1

In this paper, we report our experience with several LLMs for their ability to understand a process model in an interactive, conversational style, find syntactical and logical errors in it, and reason with it in depth through a natural language (NL) interface. Our findings show that a vanilla, untrained LLM like ChatGPT (model o3) in a zero-shot setting is effective in understanding BPMN process models from images and answering queries about them intelligently at syntactic, logic, and semantic levels of depth. Further, different LLMs vary in performance in terms of their accuracy and effectiveness. Nevertheless, our empirical analysis shows that LLMs can play a valuable role as assistants for business process designers and users. We also study the LLM's "thought process" and ability to perform deeper reasoning in the context of process analysis and optimization. We find that the LLMs seem to exhibit anthropomorphic properties.

---

### Can Lessons From Human Teams Be Applied to Multi-Agent Systems? The Role of Structure, Diversity, and Interaction Dynamics

Authors: Rasika Muralidharan, Haewoon Kwak, Jisun An
Published: 2025-10-08
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.07488v2

Multi-Agent Systems (MAS) with Large Language Model (LLM)-powered agents are gaining attention, yet fewer studies explore their team dynamics. Inspired by human team science, we propose a multi-agent framework to examine core aspects of team science: structure, diversity, and interaction dynamics. We evaluate team performance across four tasks: CommonsenseQA, StrategyQA, Social IQa, and Latent Implicit Hate, spanning commonsense and social reasoning. Our results show that flat teams tend to perform better than hierarchical ones, while diversity has a nuanced impact. Interviews suggest agents are overconfident about their team performance, yet post-task reflections reveal both appreciation for collaboration and challenges in integration, including limited conversational coordination.

---

### Reinforcement Learning-based Task Offloading in the Internet of Wearable Things

Authors: Waleed Bin Qaim, Aleksandr Ometov, Claudia Campolo, Antonella Molinaro, Elena Simona Lohan, Jari Nurmi
Published: 2025-10-08
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.07487v2

Over the years, significant contributions have been made by the research and industrial sectors to improve wearable devices towards the Internet of Wearable Things (IoWT) paradigm. However, wearables are still facing several challenges. Many stem from the limited battery power and insufficient computation resources available on wearable devices. On the other hand, with the popularity of smart wearables, there is a consistent increase in the development of new computationally intensive and latency-critical applications. In such a context, task offloading allows wearables to leverage the resources available on nearby edge devices to enhance the overall user experience. This paper proposes a framework for Reinforcement Learning (RL)-based task offloading in the IoWT. We formulate the task offloading process considering the tradeoff between energy consumption and task accomplishment time. Moreover, we model the task offloading problem as a Markov Decision Process (MDP) and utilize the Q-learning technique to enable the wearable device to make optimal task offloading decisions without prior knowledge. We evaluate the performance of the proposed framework through extensive simulations for various applications and system configurations conducted in the ns-3 network simulator. We also show how varying the main system parameters of the Q-learning algorithm affects the overall performance in terms of average task accomplishment time, average energy consumption, and percentage of tasks offloaded.

---

### AsyncSpade: Efficient Test-Time Scaling with Asynchronous Sparse Decoding

Authors: Shuqing Luo, Yilin Guan, Pingzhi Li, Hanrui Wang, Tianlong Chen
Published: 2025-10-08
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.07486v1

Test-time scaling (TTS) boosts LLM reasoning via long chain-of-thought (CoT), but the linear KV-cache growth amplifies the memory-bound bottleneck of LLM decoding. Query-aware page-level sparse decoding can achieve state-of-the-art performance under constrained FLOPs budgets, but is limited by both sequential-dependent page filtering and coarse-grained token selection, hampering serving efficiency and model performance on TTS tasks under high concurrency and long CoT scenarios (consuming even higher runtime than the forward pipeline itself). In this paper, we first find that the current-step query state can be accurately approximated in a unified manner from a short window of recent queries, enabling training-free query-aware sparsity without waiting in the decoding loop. We propose AsyncSpade, an asynchronous framework for efficient TTS built on two core components: (1) a novel light-weight temporal-regressive module that predicts the next-token query state; (2) an asynchronous and disaggregated framework that decouples the KV cache filtering from the auto-regressive decoding loop, overlapping the token-level KV selection with the forward inference computation through asynchronism. To our knowledge, AsyncSpade is the first to eliminate the sequential dependence without sacrificing model performance. We validate the effectiveness of AsyncSpade on common LLM serving setups with an A100 node, where AsyncSpade fully overlaps KV-cache operations with the inference pipeline, achieving theoretical optimal time-per-output-token (TPOT). Specifically, AsyncSpade delivers over 20% reduction on TPOT compared to SoTA baseline (i.e. Quest) and at least 50% TPOT reduction compared to full attention on Qwen3-8B and Qwen3-32B models, while matching or surpassing their accuracy on various TTS benchmarks (AIME-24/25, GPQA-Diamond, MATH-500).

---

### HEMERA: A Human-Explainable Transformer Model for Estimating Lung Cancer Risk using GWAS Data

Authors: Maria Mahbub, Robert J. Klein, Myvizhi Esai Selvan, Rowena Yip, Claudia Henschke, Providencia Morales, Ian Goethert, Olivera Kotevska, Mayanka Chandra Shekar, Sean R. Wilkinson, Eileen McAllister, Samuel M. Aguayo et al.
Published: 2025-10-08
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.07477v1

Lung cancer (LC) is the third most common cancer and the leading cause of cancer deaths in the US. Although smoking is the primary risk factor, the occurrence of LC in never-smokers and familial aggregation studies highlight a genetic component. Genetic biomarkers identified through genome-wide association studies (GWAS) are promising tools for assessing LC risk. We introduce HEMERA (Human-Explainable Transformer Model for Estimating Lung Cancer Risk using GWAS Data), a new framework that applies explainable transformer-based deep learning to GWAS data of single nucleotide polymorphisms (SNPs) for predicting LC risk. Unlike prior approaches, HEMERA directly processes raw genotype data without clinical covariates, introducing additive positional encodings, neural genotype embeddings, and refined variant filtering. A post hoc explainability module based on Layer-wise Integrated Gradients enables attribution of model predictions to specific SNPs, aligning strongly with known LC risk loci. Trained on data from 27,254 Million Veteran Program participants, HEMERA achieved >99% AUC (area under receiver characteristics) score. These findings support transparent, hypothesis-generating models for personalized LC risk assessment and early intervention.

---

### MAPRO: Recasting Multi-Agent Prompt Optimization as Maximum a Posteriori Inference

Authors: Zheyuan Zhang, Lin Ge, Hongjiang Li, Weicheng Zhu, Chuxu Zhang, Yanfang Ye
Published: 2025-10-08
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.07475v1

Large language models (LLMs) have demonstrated remarkable capabilities across diverse tasks, and LLM-based agents further extend these abilities to various practical workflows. While recent progress shows that multi-agent systems (MAS) can outperform single agents by coordinating specialized roles, designing effective MAS remains difficult due to prompt sensitivity and the compounded instability MAS creates. To cope with the challenge, recent efforts in automated prompt design have reduced manual effort. However, multi-agent prompt optimization remains largely unexplored. Challenges like exponentially expanding search space and ambiguous credit assignment together make systematic design intractable without principled methods. Therefore, we introduce M}ulti-Agent PRompt Optimization (MAPRO), a four-stage framework that first formulates MAS prompt optimization as a Maximum a Posteriori (MAP) inference problem and solves it using a language-guided variant of max-product belief propagation algorithm. To address credit assignment and updates the system iteratively, MAPRO employs a topology-aware refinement mechanism that integrates execution feedback and downstream blames to selectively update agent prompts. Through this process, MAPRO progressively converges to a coordinated set of agent-specific prompt policies. Across benchmarks in various tasks, MAPRO achieves state-of-the-art performance, consistently surpassing manually engineered baselines and recent automated alternatives. Beyond performance, our MAP-based formulation also delivers general guidelines for building more reliable and principled multi-agent systems in the future

---

### Surrogate Modeling for the Design of Optimal Lattice Structures using Tensor Completion

Authors: Shaan Pakala, Aldair E. Gongora, Brian Giera, Evangelos E. Papalexakis
Published: 2025-10-08
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.07474v2

When designing new materials, it is often necessary to design a material with specific desired properties. Unfortunately, as new design variables are added, the search space grows exponentially, which makes synthesizing and validating the properties of each material very impractical and time-consuming. In this work, we focus on the design of optimal lattice structures with regard to mechanical performance. Computational approaches, including the use of machine learning (ML) methods, have shown improved success in accelerating materials design. However, these ML methods are still lacking in scenarios when training data (i.e. experimentally validated materials) come from a non-uniformly random sampling across the design space. For example, an experimentalist might synthesize and validate certain materials more frequently because of convenience. For this reason, we suggest the use of tensor completion as a surrogate model to accelerate the design of materials in these atypical supervised learning scenarios. In our experiments, we show that tensor completion is superior to classic ML methods such as Gaussian Process and XGBoost with biased sampling of the search space, with around 5\% increased $R^2$. Furthermore, tensor completion still gives comparable performance with a uniformly random sampling of the entire search space.

---

### metabeta -- A fast neural model for Bayesian mixed-effects regression

Authors: Alex Kipnis, Marcel Binz, Eric Schulz
Published: 2025-10-08
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2510.07473v2

Hierarchical data with multiple observations per group is ubiquitous in empirical sciences and is often analyzed using mixed-effects regression. In such models, Bayesian inference gives an estimate of uncertainty but is analytically intractable and requires costly approximation using Markov Chain Monte Carlo (MCMC) methods. Neural posterior estimation shifts the bulk of computation from inference time to pre-training time, amortizing over simulated datasets with known ground truth targets. We propose metabeta, a neural network model for Bayesian mixed-effects regression. Using simulated and real data, we show that it reaches stable and comparable performance to MCMC-based parameter estimation at a fraction of the usually required time, enabling new use cases for Bayesian mixed-effects modeling.

---

### Provably Accelerated Imaging with Restarted Inertia and Score-based Image Priors

Authors: Marien Renaud, Julien Hermant, Deliang Wei, Yu Sun
Published: 2025-10-08
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.07470v1

Fast convergence and high-quality image recovery are two essential features of algorithms for solving ill-posed imaging inverse problems. Existing methods, such as regularization by denoising (RED), often focus on designing sophisticated image priors to improve reconstruction quality, while leaving convergence acceleration to heuristics. To bridge the gap, we propose Restarted Inertia with Score-based Priors (RISP) as a principled extension of RED. RISP incorporates a restarting inertia for fast convergence, while still allowing score-based image priors for high-quality reconstruction. We prove that RISP attains a faster stationary-point convergence rate than RED, without requiring the convexity of the image prior. We further derive and analyze the associated continuous-time dynamical system, offering insight into the connection between RISP and the heavy-ball ordinary differential equation (ODE). Experiments across a range of imaging inverse problems demonstrate that RISP enables fast convergence while achieving high-quality reconstructions.

---

### MoGU: Mixture-of-Gaussians with Uncertainty-based Gating for Time Series Forecasting

Authors: Gilad Aviv, Jacob Goldberger, Yoli Shavit
Published: 2025-10-08
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.07459v2

We introduce Mixture-of-Gaussians with Uncertainty-based Gating (MoGU), a novel Mixture-of-Experts (MoE) framework designed for regression tasks. MoGU replaces standard learned gating with an intrinsic routing paradigm where expert-specific uncertainty serves as the native gating signal. By modeling each prediction as a Gaussian distribution, the system utilizes predicted variance to dynamically weight expert contributions. We validate MoGU on multivariate time-series forecasting, a domain defined by high volatility and varying noise patterns. Empirical results across multiple benchmarks, horizon lengths, and backbones demonstrate that MoGU consistently improves forecasting accuracy compared to traditional MoE. Further evaluation via conformal prediction indicates that our approach yields more efficient prediction intervals than existing baselines. These findings highlight MoGU's capacity for providing both competitive performance and reliable, high-fidelity uncertainty quantification. Our code is available at: https://github.com/yolish/moe_unc_tsf

---

### Populism Meets AI: Advancing Populism Research with LLMs

Authors: Yujin J. Jung, Eduardo Ryô Tamaki, Julia Chatterley, Grant Mitchell, Semir Dzebo, Cristóbal Sandoval, Levente Littvay, Kirk A. Hawkins
Published: 2025-10-08
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.07458v3

Measuring the ideational content of populism remains a challenge. Traditional strategies based on textual analysis have been critical for building the field's foundations and providing a valid, objective indicator of populist framing. Yet these approaches are costly, time consuming, and difficult to scale across languages, contexts, and large corpora. Here we present the results from a rubric and anchor guided chain of thought (CoT) prompting approach that mirrors human coder training. By leveraging the Global Populism Database (GPD), a comprehensive dataset of global leaders' speeches annotated for degrees of populism, we replicate the process used to train human coders by prompting the LLM with an adapted version of the same documentation to guide the model's reasoning. We then test multiple proprietary and open weight models by replicating scores in the GPD. Our findings reveal that this domain specific prompting strategy enables the LLM to achieve classification accuracy on par with expert human coders, demonstrating its ability to navigate the nuanced, context sensitive aspects of populism.

---

### Comparison of Fully Homomorphic Encryption and Garbled Circuit Techniques in Privacy-Preserving Machine Learning Inference

Authors: Kalyan Cheerla, Lotfi Ben Othmane, Kirill Morozov
Published: 2025-10-08
Categories: cs.CR, cs.LG
arXiv: https://arxiv.org/abs/2510.07457v1

Machine Learning (ML) is making its way into fields such as healthcare, finance, and Natural Language Processing (NLP), and concerns over data privacy and model confidentiality continue to grow. Privacy-preserving Machine Learning (PPML) addresses this challenge by enabling inference on private data without revealing sensitive inputs or proprietary models. Leveraging Secure Computation techniques from Cryptography, two widely studied approaches in this domain are Fully Homomorphic Encryption (FHE) and Garbled Circuits (GC). This work presents a comparative evaluation of FHE and GC for secure neural network inference. A two-layer neural network (NN) was implemented using the CKKS scheme from the Microsoft SEAL library (FHE) and the TinyGarble2.0 framework (GC) by IntelLabs. Both implementations are evaluated under the semi-honest threat model, measuring inference output error, round-trip time, peak memory usage, communication overhead, and communication rounds. Results reveal a trade-off: modular GC offers faster execution and lower memory consumption, while FHE supports non-interactive inference.

---

### ExpertAgent: Enhancing Personalized Education through Dynamic Planning and Retrieval-Augmented Long-Chain Reasoning

Authors: Binrong Zhu, Guiran Liu, Nina Jiang
Published: 2025-10-08
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.07456v1

The application of advanced generative artificial intelligence in education is often constrained by the lack of real-time adaptability, personalization, and reliability of the content. To address these challenges, we propose ExpertAgent - an intelligent agent framework designed for personalized education that provides reliable knowledge and enables highly adaptive learning experiences. Therefore, we developed ExpertAgent, an innovative learning agent that provides users with a proactive and personalized learning experience. ExpertAgent dynamic planning of the learning content and strategy based on a continuously updated student model. Therefore, overcoming the limitations of traditional static learning content to provide optimized teaching strategies and learning experience in real time. All instructional content is grounded in a validated curriculum repository, effectively reducing hallucination risks in large language models and improving reliability and trustworthiness.

---

### Meaningful Pose-Based Sign Language Evaluation

Authors: Zifan Jiang, Colin Leong, Amit Moryossef, Anne Göhring, Annette Rios, Oliver Cory, Maksym Ivashechkin, Neha Tarigopula, Biao Zhang, Rico Sennrich, Sarah Ebling
Published: 2025-10-08
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.07453v1

We present a comprehensive study on meaningfully evaluating sign language utterances in the form of human skeletal poses. The study covers keypoint distance-based, embedding-based, and back-translation-based metrics. We show tradeoffs between different metrics in different scenarios through automatic meta-evaluation of sign-level retrieval and a human correlation study of text-to-pose translation across different sign languages. Our findings and the open-source pose-evaluation toolkit provide a practical and reproducible way of developing and evaluating sign language translation or generation systems.

---

### PATCH: Mitigating PII Leakage in Language Models with Privacy-Aware Targeted Circuit PatcHing

Authors: Anthony Hughes, Vasisht Duddu, N. Asokan, Nikolaos Aletras, Ning Ma
Published: 2025-10-08
Categories: cs.CR, cs.CL
arXiv: https://arxiv.org/abs/2510.07452v2

Language models (LMs) may memorize personally identifiable information (PII) from training data, enabling adversaries to extract it during inference. Existing defense mechanisms such as differential privacy (DP) reduce this leakage, but incur large drops in utility. Based on a comprehensive study using circuit discovery to identify the computational circuits responsible PII leakage in LMs, we hypothesize that specific PII leakage circuits in LMs should be responsible for this behavior. Therefore, we propose PATCH (Privacy-Aware Targeted Circuit PatcHing), a novel approach that first identifies and subsequently directly edits PII circuits to reduce leakage. PATCH achieves better privacy-utility trade-off than existing defenses, e.g., reducing recall of PII leakage from LMs by up to 65%. Finally, PATCH can be combined with DP to reduce recall of residual leakage of an LM to as low as 0.01%. Our analysis shows that PII leakage circuits persist even after the application of existing defense mechanisms. In contrast, PATCH can effectively mitigate their impact.

---

### VeMo: A Lightweight Data-Driven Approach to Model Vehicle Dynamics

Authors: Girolamo Oddo, Roberto Nuca, Matteo Parsani
Published: 2025-10-08
Categories: cs.RO, cs.LG, math.DS
arXiv: https://arxiv.org/abs/2510.07447v1

Developing a dynamic model for a high-performance vehicle is a complex problem that requires extensive structural information about the system under analysis. This information is often unavailable to those who did not design the vehicle and represents a typical issue in autonomous driving applications, which are frequently developed on top of existing vehicles; therefore, vehicle models are developed under conditions of information scarcity. This paper proposes a lightweight encoder-decoder model based on Gate Recurrent Unit layers to correlate the vehicle's future state with its past states, measured onboard, and control actions the driver performs. The results demonstrate that the model achieves a maximum mean relative error below 2.6% in extreme dynamic conditions. It also shows good robustness when subject to noisy input data across the interested frequency components. Furthermore, being entirely data-driven and free from physical constraints, the model exhibits physical consistency in the output signals, such as longitudinal and lateral accelerations, yaw rate, and the vehicle's longitudinal velocity.

---

### Minimizing the Value-at-Risk of Loan Portfolio via Deep Neural Networks

Authors: Albert Di Wang, Ye Du
Published: 2025-10-08
Categories: q-fin.CP, cs.AI, cs.CE, q-fin.MF, q-fin.PM
arXiv: https://arxiv.org/abs/2510.07444v1

Risk management is a prominent issue in peer-to-peer lending. An investor may naturally reduce his risk exposure by diversifying instead of putting all his money on one loan. In that case, an investor may want to minimize the Value-at-Risk (VaR) or Conditional Value-at-Risk (CVaR) of his loan portfolio. We propose a low degree of freedom deep neural network model, DeNN, as well as a high degree of freedom model, DSNN, to tackle the problem. In particular, our models predict not only the default probability of a loan but also the time when it will default. The experiments demonstrate that both models can significantly reduce the portfolio VaRs at different confidence levels, compared to benchmarks. More interestingly, the low degree of freedom model, DeNN, outperforms DSNN in most scenarios.

---

### DynamicEval: Rethinking Evaluation for Dynamic Text-to-Video Synthesis

Authors: Nithin C. Babu, Aniruddha Mahapatra, Harsh Rangwani, Rajiv Soundararajan, Kuldeep Kulkarni
Published: 2025-10-08
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.07441v1

Existing text-to-video (T2V) evaluation benchmarks, such as VBench and EvalCrafter, suffer from two limitations. (i) While the emphasis is on subject-centric prompts or static camera scenes, camera motion essential for producing cinematic shots and existing metrics under dynamic motion are largely unexplored. (ii) These benchmarks typically aggregate video-level scores into a single model-level score for ranking generative models. Such aggregation, however, overlook video-level evaluation, which is vital to selecting the better video among the candidate videos generated for a given prompt. To address these gaps, we introduce DynamicEval, a benchmark consisting of systematically curated prompts emphasizing dynamic camera motion, paired with 45k human annotations on video pairs from 3k videos generated by ten T2V models. DynamicEval evaluates two key dimensions of video quality: background scene consistency and foreground object consistency. For background scene consistency, we obtain the interpretable error maps based on the Vbench motion smoothness metric. We observe that while the Vbench motion smoothness metric shows promising alignment with human judgments, it fails in two cases: occlusions/disocclusions arising from camera and foreground object movements. Building on this, we propose a new background consistency metric that leverages object error maps to correct two failure cases in a principled manner. Our second innovation is the introduction of a foreground consistency metric that tracks points and their neighbors within each object instance to assess object fidelity. Extensive experiments demonstrate that our proposed metrics achieve stronger correlations with human preferences at both the video level and the model level (an improvement of more than 2% points), establishing DynamicEval as a more comprehensive benchmark for evaluating T2V models under dynamic camera motion.

---

### A Rotation-Invariant Embedded Platform for (Neural) Cellular Automata

Authors: Dominik Woiwode, Jakob Marten, Bodo Rosenhahn
Published: 2025-10-08
Categories: cs.NE, cs.RO
arXiv: https://arxiv.org/abs/2510.07440v1

This paper presents a rotation-invariant embedded platform for simulating (neural) cellular automata (NCA) in modular robotic systems. Inspired by previous work on physical NCA, we introduce key innovations that overcome limitations in prior hardware designs. Our platform features a symmetric, modular structure, enabling seamless connections between cells regardless of orientation. Additionally, each cell is battery-powered, allowing it to operate independently and retain its state even when disconnected from the collective. To demonstrate the platform's applicability, we present a novel rotation-invariant NCA model for isotropic shape classification. The proposed system provides a robust foundation for exploring the physical realization of NCA, with potential applications in distributed robotic systems and self-organizing structures. Our implementation, including hardware, software code, a simulator, and a video, is openly shared at: https://github.com/dwoiwode/embedded_nca

---

### LASER: An LLM-based ASR Scoring and Evaluation Rubric

Authors: Amruta Parulekar, Preethi Jyothi
Published: 2025-10-08
Categories: cs.CL, cs.AI, cs.LG, eess.AS
arXiv: https://arxiv.org/abs/2510.07437v1

Standard ASR evaluation metrics like Word Error Rate (WER) tend to unfairly penalize morphological and syntactic nuances that do not significantly alter sentence semantics. We introduce an LLM-based scoring rubric LASER that leverages state-of-the-art LLMs' in-context learning abilities to learn from prompts with detailed examples. Hindi LASER scores using Gemini 2.5 Pro achieved a very high correlation score of 94% with human annotations. Hindi examples in the prompt were also effective in analyzing errors in other Indian languages such as Marathi, Kannada and Malayalam. We also demonstrate how a smaller LLM like Llama 3 can be finetuned on word-pair examples derived from reference and ASR predictions to predict what kind of penalty should be applied with close to 89% accuracy.

---

### Parameter-Free Federated TD Learning with Markov Noise in Heterogeneous Environments

Authors: Ankur Naskar, Gugan Thoppe, Utsav Negi, Vijay Gupta
Published: 2025-10-08
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.07436v1

Federated learning (FL) can dramatically speed up reinforcement learning by distributing exploration and training across multiple agents. It can guarantee an optimal convergence rate that scales linearly in the number of agents, i.e., a rate of $\tilde{O}(1/(NT)),$ where $T$ is the iteration index and $N$ is the number of agents. However, when the training samples arise from a Markov chain, existing results on TD learning achieving this rate require the algorithm to depend on unknown problem parameters. We close this gap by proposing a two-timescale Federated Temporal Difference (FTD) learning with Polyak-Ruppert averaging. Our method provably attains the optimal $\tilde{O}(1/NT)$ rate in both average-reward and discounted settings--offering a parameter-free FTD approach for Markovian data. Although our results are novel even in the single-agent setting, they apply to the more realistic and challenging scenario of FL with heterogeneous environments.

---

### Lemma Dilemma: On Lemma Generation Without Domain- or Language-Specific Training Data

Authors: Olia Toporkov, Alan Akbik, Rodrigo Agerri
Published: 2025-10-08
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.07434v1

Lemmatization is the task of transforming all words in a given text to their dictionary forms. While large language models (LLMs) have demonstrated their ability to achieve competitive results across a wide range of NLP tasks, there is no prior evidence of how effective they are in the contextual lemmatization task. In this paper, we empirically investigate the capacity of the latest generation of LLMs to perform in-context lemmatization, comparing it to the traditional fully supervised approach. In particular, we consider the setting in which supervised training data is not available for a target domain or language, comparing (i) encoder-only supervised approaches, fine-tuned out-of-domain, and (ii) cross-lingual methods, against direct in-context lemma generation with LLMs. Our experimental investigation across 12 languages of different morphological complexity finds that, while encoders remain competitive in out-of-domain settings when fine-tuned on gold data, current LLMs reach state-of-the-art results for most languages by directly generating lemmas in-context without prior fine-tuning, provided just with a few examples. Data and code available upon publication: https://github.com/oltoporkov/lemma-dilemma

---

### TS-Agent: Understanding and Reasoning Over Raw Time Series via Iterative Insight Gathering

Authors: Penghang Liu, Elizabeth Fons, Annita Vapsi, Mohsen Ghassemi, Svitlana Vyetrenko, Daniel Borrajo, Vamsi K. Potluru, Manuela Veloso
Published: 2025-10-08
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.07432v2

Large language models (LLMs) exhibit strong symbolic and compositional reasoning, yet they struggle with time series question answering as the data is typically transformed into an LLM-compatible modality, e.g., serialized text, plotted images, or compressed time series embeddings. Such conversions impose representation bottlenecks, often require cross-modal alignment or finetuning, and can exacerbate hallucination and knowledge leakage. To address these limitations, we propose TS-Agent, an agentic, tool-grounded framework that uses LLMs strictly for iterative evidence-based reasoning, while delegating statistical and structural extraction to time series analytical tools operating on raw sequences. Our framework solves time series tasks through an evidence-driven agentic process: (1) it alternates between thinking, tool execution, and observation in a ReAct-style loop, (2) records intermediate results in an explicit evidence log and corrects the reasoning trace via a self-refinement critic, and (3) enforces a final answer-verification step to prevent hallucinations and leakage. Across four benchmarks spanning time series understanding and reasoning, TS-Agent matches or exceeds strong text-based, vision-based, and time-series language model baselines, with the largest gains on reasoning tasks where multimodal LLMs are prone to hallucination and knowledge leakage in zero-shot settings.

---

### Learning to Route LLMs from Bandit Feedback: One Policy, Many Trade-offs

Authors: Wang Wei, Tiankai Yang, Hongjie Chen, Yue Zhao, Franck Dernoncourt, Ryan A. Rossi, Hoda Eldardiry
Published: 2025-10-08
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.07429v1

Efficient use of large language models (LLMs) is critical for deployment at scale: without adaptive routing, systems either overpay for strong models or risk poor performance from weaker ones. Selecting the right LLM for each query is fundamentally an online decision problem: models differ in strengths, prices fluctuate, and users value accuracy and cost differently. Yet most routers are trained offline with labels for all candidate models, an assumption that breaks in deployment, where only the outcome of the chosen model is observed. We bridge this gap with BaRP, a Bandit-feedback Routing with Preferences approach that trains under the same partial-feedback restriction as deployment, while supporting preference-tunable inference: operators can dial the performance/cost trade-off at test time without retraining. Framed as a contextual bandit over prompt features and a user preference vector, our method simulates an online feedback setting during training and adapts its routing decisions to each new prompt, rather than depending on full-information offline supervision. Comprehensive experiments show that our method consistently outperforms strong offline routers by at least 12.46% and the largest LLM by at least 2.45%, and generalizes robustly for unseen tasks.

---

### SEPhIA: <1 laser/neuron Spiking Electro-Photonic Integrated Multi-Tiled Architecture for Scalable Optical Neuromorphic Computing

Authors: Matěj Hejda, Aishwarya Natarajan, Chaerin Hong, Mehmet Berkay On, Sébastien d'Herbais de Thun, Raymond G. Beausoleil, Thomas Van Vaerenbergh
Published: 2025-10-08
Categories: cs.ET, cs.NE, physics.optics
arXiv: https://arxiv.org/abs/2510.07427v1

Research into optical spiking neural networks (SNNs) has primarily focused on spiking devices, networks of excitable lasers or numerical modelling of large architectures, often overlooking key constraints such as limited optical power, crosstalk and footprint. We introduce SEPhIA, a photonic-electronic, multi-tiled SNN architecture emphasizing implementation feasibility and realistic scaling. SEPhIA leverages microring resonator modulators (MRMs) and multi-wavelength sources to achieve effective sub-one-laser-per-spiking neuron efficiency. We validate SEPhIA at both device and architecture levels by time-domain co-simulating excitable CMOS-MRR coupled circuits and by devising a physics-aware, trainable optoelectronic SNN model, with both approaches utilizing experimentally derived device parameters. The multi-layer optoelectronic SNN achieves classification accuracies over 90% on a four-class spike-encoded dataset, closely comparable to software models. A design space study further quantifies how photonic device parameters impact SNN performance under constrained signal-to-noise conditions. SEPhIA offers a scalable, expressive, physically grounded solution for neuromorphic photonic computing, capable of addressing spike-encoded tasks.

---

### Less is More: Strategic Expert Selection Outperforms Ensemble Complexity in Traffic Forecasting

Authors: Walid Guettala, Yufan Zhao, László Gulyás
Published: 2025-10-08
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.07426v1

Traffic forecasting is fundamental to intelligent transportation systems, enabling congestion mitigation and emission reduction in increasingly complex urban environments. While recent graph neural network approaches have advanced spatial temporal modeling, existing mixture of experts frameworks like Time Enhanced Spatio Temporal Attention Model (TESTAM) lack explicit incorporation of physical road network topology, limiting their spatial capabilities. We present TESTAM+, an enhanced spatio temporal forecasting framework that introduces a novel SpatioSemantic Expert integrating physical road topology with data driven feature similarity through hybrid graph construction. TESTAM+ achieves significant improvements over TESTAM: 1.3% MAE reduction on METR LA (3.10 vs. 3.14) and 4.1% improvement on PEMS BAY (1.65 vs. 1.72). Through comprehensive ablation studies, we discover that strategic expert selection fundamentally outperforms naive ensemble aggregation. Individual experts demonstrate remarkable effectiveness: the Adaptive Expert achieves 1.63 MAE on PEMS BAY, outperforming the original three expert TESTAM (1.72 MAE), while the SpatioSemantic Expert matches this performance with identical 1.63 MAE. The optimal Identity + Adaptive configuration achieves an 11.5% MAE reduction compared to state of the art MegaCRN on METR LA (2.99 vs. 3.38), while reducing inference latency by 53.1% compared to the full four expert TESTAM+. Our findings reveal that fewer, strategically designed experts outperform complex multi expert ensembles, establishing new state of the art performance with superior computational efficiency for real time deployment.

---

### Best-of-Both Worlds for linear contextual bandits with paid observations

Authors: Nathan Boyer, Dorian Baudry, Patrick Rebeschini
Published: 2025-10-08
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.07424v3

We study linear contextual bandits with paid observations, where at each round the learner observes a context, selects an action, and may pay a fixed cost to observe feedback from a subset of arms. We propose two Follow-the-Regularized-Leader algorithms with Best-of-Both-Worlds guarantees. The first, Agg-SPB, extends the SPB-matching framework of Tsuchiya and Ito (2024) by aggregating context-dependent stability terms, achieving the characteristic $T^{2/3}$ adversarial regret rate and logarithmic dependence on $T$ in stochastic environments. The second, CE-SPB, combines arm-dependent observation probabilities with an entropy-adaptive learning rate inspired by Kuroki et al. (2024). It achieves an entropy-adaptive $\widetilde{O}(T^{2/3})$ adversarial guarantee and polylogarithmic stochastic regret, while avoiding the minimum-context-mass dependence arising in the stochastic analysis of Agg-SPB. Both algorithms further extend to corrupted stochastic environments with explicit corruption-dependent guarantees. These results establish that logarithmic stochastic regret is compatible with the $T^{2/3}$ adversarial regime for linear contextual bandits with paid observations, while highlighting a tradeoff between sharper horizon dependence in stochastic settings and path-dependent matching without explicit minimum-context-mass dependence.

---

### ProSEA: Problem Solving via Exploration Agents

Authors: William Nguyen, Vinh Luong, Christopher Nguyen
Published: 2025-10-08
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.07423v2

Large language models (LLMs) have empowered AI agents to tackle increasingly complex tasks. However, most existing agents remain limited to static planning and brittle interactions, falling short of true collaboration or adaptive reasoning. We introduce ProSEA, a modular, general-purpose multi-agent framework designed for iterative problem solving through exploration and plan evolution. ProSEA features a hierarchical architecture in which a Manager Agent orchestrates domain-specialized Expert Agents, decomposes tasks, and adaptively replans based on structured feedback from failed attempts. Unlike prior systems, ProSEA agents report not only success or failure but also detailed reasons for failure and newly discovered constraints, enabling dynamic plan refinement informed by exploratory traces. The framework operates autonomously but supports seamless integration with human collaborators when needed. Experiments on the challenging FinanceBench benchmark demonstrate that ProSEA, even without human feedback, outperforms state-of-the-art baselines and achieves robust performance across reasoning-heavy tasks. These results underscore ProSEA's potential as a foundation for more transparent, adaptive, and human-aligned AI agents.

---

### Bayesian Optimization of Multi-Bit Pulse Encoding in In2O3/Al2O3 Thin-film Transistors for Temporal Data Processing

Authors: Javier Meza-Arroyo, Benius Dunn, Weijie Xu, Yu-Chieh Chen, Jen-Sue Chen, Julia W. P. Hsu
Published: 2025-10-08
Categories: cond-mat.dis-nn, cond-mat.mtrl-sci, cs.LG
arXiv: https://arxiv.org/abs/2510.07421v1

Utilizing the intrinsic history-dependence and nonlinearity of hardware, physical reservoir computing is a promising neuromorphic approach to encode time-series data for in-sensor computing. The accuracy of this encoding critically depends on the distinguishability of multi-state outputs, which is often limited by suboptimal and empirically chosen reservoir operation conditions. In this work, we demonstrate a machine learning approach, Bayesian optimization, to improve the encoding fidelity of solution-processed Al2O3/In2O3 thin-film transistors (TFTs). We show high-fidelity 6-bit temporal encoding by exploring five key pulse parameters and using the normalized degree of separation (nDoS) as the metric of output state separability. Additionally, we show that a model trained on simpler 4-bit data can effectively guide optimization of more complex 6-bit encoding tasks, reducing experimental cost. Specifically, for the encoding and reconstruction of binary-patterned images of a moving car across 6 sequential frames, we demonstrate that the encoding is more accurate when operating the TFT using optimized pulse parameters and the 4-bit optimized operating condition performs almost as well as the 6-bit optimized condition. Finally, interpretability analysis via Shapley Additive Explanations (SHAP) reveals that gate pulse amplitude and drain voltage are the most influential parameters in achieving higher state separation. This work presents the first systematic method to identify optimal operating conditions for reservoir devices, and the approach can be extended to other physical reservoir implementations across different material platforms.

---

### Haystack Engineering: Context Engineering for Heterogeneous and Agentic Long-Context Evaluation

Authors: Mufei Li, Dongqi Fu, Limei Wang, Si Zhang, Hanqing Zeng, Kaan Sancak, Ruizhong Qiu, Haoyu Wang, Xiaoxin He, Xavier Bresson, Yinglong Xia, Chonglin Sun et al.
Published: 2025-10-08
Categories: cs.CL, cs.AI, cs.IR
arXiv: https://arxiv.org/abs/2510.07414v2

Modern long-context large language models (LLMs) perform well on synthetic "needle-in-a-haystack" (NIAH) benchmarks, but such tests overlook how noisy contexts arise from biased retrieval and agentic workflows. We argue that haystack engineering is necessary to construct noisy long contexts that faithfully capture key real-world factors -- distraction from heterogeneous biased retrievers and cascading errors in agentic workflows -- to test models' long-context robustness. We instantiate it through HaystackCraft, a new NIAH benchmark built on the full English Wikipedia hyperlink network with multi-hop questions. HaystackCraft evaluates how heterogeneous retrieval strategies (e.g., sparse, dense, hybrid, and graph-based) affect distractor composition, haystack ordering, and downstream LLM performance. HaystackCraft further extends NIAH to dynamic, LLM-dependent settings that simulate agentic operations, where models refine queries, reflect on their past reasonings, and decide when to stop. Experiments with 15 long-context models show that (1) while stronger dense retrievers can introduce more challenging distractors, graph-based reranking simultaneously improves retrieval effectiveness and mitigates more harmful distractors; (2) in agentic tests, even advanced models like Gemini 2.5 Pro and GPT-5 suffer cascading failures from self-generated distractors or struggle to perform early stops. These results highlight persistent challenges in agentic long-context reasoning and establish HaystackCraft as a valuable testbed for future progress.

---

### Quantum Grid Path Planning Using Parallel QAOA Circuits Based on Minimum Energy Principle

Authors: Jun Liu
Published: 2025-10-08
Categories: quant-ph, cs.AI, math-ph, math.OC, physics.comp-ph
arXiv: https://arxiv.org/abs/2510.07413v1

To overcome the bottleneck of classical path planning schemes in solving NP problems and address the predicament faced by current mainstream quantum path planning frameworks in the Noisy Intermediate-Scale Quantum (NISQ) era, this study attempts to construct a quantum path planning solution based on parallel Quantum Approximate Optimization Algorithm (QAOA) architecture. Specifically, the grid path planning problem is mapped to the problem of finding the minimum quantum energy state. Two parallel QAOA circuits are built to simultaneously execute two solution processes, namely connectivity energy calculation and path energy calculation. A classical algorithm is employed to filter out unreasonable solutions of connectivity energy, and finally, the approximate optimal solution to the path planning problem is obtained by merging the calculation results of the two parallel circuits. The research findings indicate that by setting appropriate filter parameters, quantum states corresponding to position points with extremely low occurrence probabilities can be effectively filtered out, thereby increasing the probability of obtaining the target quantum state. Even when the circuit layer number p is only 1, the theoretical solution of the optimal path coding combination can still be found by leveraging the critical role of the filter. Compared with serial circuits, parallel circuits exhibit a significant advantage, as they can find the optimal feasible path coding combination with the highest probability.

---

### Position: AI Will Transform Neuropsychology Through Mental Health Digital Twins for Dynamic Mental Health Care, Especially for ADHD

Authors: Neil Natarajan, Sruthi Viswanathan, Xavier Roberts-Gaal, Michelle Marie Martel
Published: 2025-10-08
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.07409v1

Static solutions don't serve a dynamic mind. Thus, we advocate a shift from static mental health diagnostic assessments to continuous, artificial intelligence (AI)-driven assessment. Focusing on Attention-Deficit/Hyperactivity Disorder (ADHD) as a case study, we explore how generative AI has the potential to address current capacity constraints in neuropsychology, potentially enabling more personalized and longitudinal care pathways. In particular, AI can efficiently conduct frequent, low-level experience sampling from patients and facilitate diagnostic reconciliation across care pathways. We envision a future where mental health care benefits from continuous, rich, and patient-centered data sampling to dynamically adapt to individual patient needs and evolving conditions, thereby improving both accessibility and efficacy of treatment. We further propose the use of mental health digital twins (MHDTs) - continuously updated computational models that capture individual symptom dynamics and trajectories - as a transformative framework for personalized mental health care. We ground this framework in empirical evidence and map out the research agenda required to refine and operationalize it.

---

### Attention to Order: Transformers Discover Phase Transitions via Learnability

Authors: Şener Özönder
Published: 2025-10-08
Categories: cond-mat.mtrl-sci, cond-mat.dis-nn, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.07401v1

Phase transitions mark qualitative reorganizations of collective behavior, yet identifying their boundaries remains challenging whenever analytic solutions are absent and conventional simulations fail. Here we introduce learnability as a universal criterion, defined as the ability of a transformer model containing attention mechanism to extract structure from microscopic states. Using self-supervised learning and Monte Carlo generated configurations of the two-dimensional Ising model, we show that ordered phases correspond to enhanced learnability, manifested in both reduced training loss and structured attention patterns, while disordered phases remain resistant to learning. Two unsupervised diagnostics, the sharp jump in training loss and the rise in attention entropy, recover the critical temperature in excellent agreement with the exact value. Our results establish learnability as a data-driven marker of phase transitions and highlight deep parallels between long-range order in condensed matter and the emergence of structure in modern language models.

---

### Base Models Know How to Reason, Thinking Models Learn When

Authors: Constantin Venhoff, Iván Arcuschin, Philip Torr, Arthur Conmy, Neel Nanda
Published: 2025-10-08
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.07364v4

What do thinking language models learn during training that their base models lack? We first present an unsupervised method that discovers a model's reasoning behaviors by training small Sparse Autoencoders on sentence-level activations of reasoning traces, yielding interpretable reasoning taxonomies. Building on this, we introduce constructive model diffing, which aims to reconstruct the base-to-fine-tuned difference from interpretable components: reasoning mechanisms (category vectors that can induce a reasoning behavior in the base model) and reasoning heuristics (a classifier determining when a mechanism should fire). Across nine base/thinking pairs (four RL-trained, four SFT-distilled, one mixed), two independent findings agree: category vectors in the base model converge to far lower loss for taxonomies derived from purely RL-trained models, and hybrid models recover roughly 76% of the RL base-to-thinking gap but only 11% of the SFT gap. This indicates RL primarily teaches heuristics for orchestrating pre-existing base mechanisms, whereas SFT-distillation installs new ones, offering a new lens on what training paradigms teach, with implications for efficient reasoning-model development.

---

### L2M-AID: Autonomous Cyber-Physical Defense by Fusing Semantic Reasoning of Large Language Models with Multi-Agent Reinforcement Learning (Preprint)

Authors: Tianxiang Xu, Zhichao Wen, Xinyu Zhao, Jun Wang, Yan Li, Chang Liu
Published: 2025-10-08
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.07363v2

The increasing integration of Industrial IoT (IIoT) exposes critical cyber-physical systems to sophisticated, multi-stage attacks that elude traditional defenses lacking contextual awareness. This paper introduces L2M-AID, a novel framework for Autonomous Industrial Defense using LLM-empowered, Multi-agent reinforcement learning. L2M-AID orchestrates a team of collaborative agents, each driven by a Large Language Model (LLM), to achieve adaptive and resilient security. The core innovation lies in the deep fusion of two AI paradigms: we leverage an LLM as a semantic bridge to translate vast, unstructured telemetry into a rich, contextual state representation, enabling agents to reason about adversary intent rather than merely matching patterns. This semantically-aware state empowers a Multi-Agent Reinforcement Learning (MARL) algorithm, MAPPO, to learn complex cooperative strategies. The MARL reward function is uniquely engineered to balance security objectives (threat neutralization) with operational imperatives, explicitly penalizing actions that disrupt physical process stability. To validate our approach, we conduct extensive experiments on the benchmark SWaT dataset and a novel synthetic dataset generated based on the MITRE ATT&CK for ICS framework. Results demonstrate that L2M-AID significantly outperforms traditional IDS, deep learning anomaly detectors, and single-agent RL baselines across key metrics, achieving a 97.2% detection rate while reducing false positives by over 80% and improving response times by a factor of four. Crucially, it demonstrates superior performance in maintaining physical process stability, presenting a robust new paradigm for securing critical national infrastructure.

---

### Inconsistent Affective Reaction: Sentiment of Perception and Opinion in Urban Environments

Authors: Jingfei Huang, Han Tu
Published: 2025-10-08
Categories: cs.CL, cs.LG, cs.SI
arXiv: https://arxiv.org/abs/2510.07359v1

The ascension of social media platforms has transformed our understanding of urban environments, giving rise to nuanced variations in sentiment reaction embedded within human perception and opinion, and challenging existing multidimensional sentiment analysis approaches in urban studies. This study presents novel methodologies for identifying and elucidating sentiment inconsistency, constructing a dataset encompassing 140,750 Baidu and Tencent Street view images to measure perceptions, and 984,024 Weibo social media text posts to measure opinions. A reaction index is developed, integrating object detection and natural language processing techniques to classify sentiment in Beijing Second Ring for 2016 and 2022. Classified sentiment reaction is analysed and visualized using regression analysis, image segmentation, and word frequency based on land-use distribution to discern underlying factors. The perception affective reaction trend map reveals a shift toward more evenly distributed positive sentiment, while the opinion affective reaction trend map shows more extreme changes. Our mismatch map indicates significant disparities between the sentiments of human perception and opinion of urban areas over the years. Changes in sentiment reactions have significant relationships with elements such as dense buildings and pedestrian presence. Our inconsistent maps present perception and opinion sentiments before and after the pandemic and offer potential explanations and directions for environmental management, in formulating strategies for urban renewal.

---

### Encode, Think, Decode: Scaling test-time reasoning with recursive latent thoughts

Authors: Yeskendir Koishekenov, Aldo Lipani, Nicola Cancedda
Published: 2025-10-08
Categories: cs.LG, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2510.07358v1

Most efforts to improve the reasoning capabilities of large language models (LLMs) involve either scaling the number of parameters and the size of training data, or scaling inference computation by letting models generate complex chains of thought. Motivated by interpretability studies showing that the crucial computation required for reasoning tasks is concentrated in a limited range of layers, we introduce Encode-Think-Decode (ETD), a method that enhances the reasoning capabilities of a base model by training it to iterate over a small subset of reasoning-relevant layers during the mid-training stage. ETD amplifies latent reasoning while preserving the original architecture, parameter count, hyperparameters, and training data composition. When iterating on the selected layers at inference time, ETD models yield substantial gains on 17 reasoning benchmarks, including +28.4% relative accuracy improvement on GSM8K and +36% on MATH with the OLMo-2 1B Base model. We also explore an adaptive depth strategy that adjusts the computation per input token. Our results show that recursive latent reasoning offers a simple and effective path to stronger LLM reasoning.

---

### ConCuR: Conciseness Makes State-of-the-Art Kernel Generation

Authors: Lingcheng Kong, Jiateng Wei, Hanzhang Shen, Huan Wang
Published: 2025-10-08
Categories: cs.LG, cs.CL, cs.CV, stat.ML
arXiv: https://arxiv.org/abs/2510.07356v1

GPU kernel generation by LLMs has recently experienced rapid development, leveraging test-time scaling and reinforcement learning techniques. However, a key challenge for kernel generation is the scarcity of high-quality data, as most high-quality kernels are proprietary and not open-source. This challenge prevents us from leveraging supervised fine-tuning to align LLMs to the kernel generation task. To address this challenge, we develop a pipeline that generates and curates high-quality CUDA kernels with reasoning traces, motivated by a critical observation that concise yet informative reasoning traces result in robust generation of high-performance kernels. Using this pipeline, we construct our dataset ConCuR and introduce our model KernelCoder, which is the first model trained on a curated dataset consisting of PyTorch, reasoning, and CUDA kernel pairs, to our knowledge. In the KernelBench setup, our model achieves significant improvements over the existing top-performing model, QwQ-32B, and outperforms all open-source models fine-tuned for kernel generation, as well as frontier models such as DeepSeek-V3.1-Think and Claude-4-sonnet. Finally, we show that the average reasoning length can serve as a metric to assess the difficulty of kernel generation tasks. The observations, metrics, and our data collection and curation pipeline can help obtain better data in the kernel generation task in the future.

---

### Out-of-Distribution Generalization in Climate-Aware Yield Prediction with Earth Observation Data

Authors: Aditya Chakravarty
Published: 2025-10-08
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.07350v1

Climate change is increasingly disrupting agricultural systems, making accurate crop yield forecasting essential for food security. While deep learning models have shown promise in yield prediction using satellite and weather data, their ability to generalize across geographic regions and years - critical for real-world deployment - remains largely untested. We benchmark two state-of-the-art models, GNN-RNN and MMST-ViT, under realistic out-of-distribution (OOD) conditions using the large-scale CropNet dataset spanning 1,200+ U.S. counties from 2017-2022. Through leave-one-cluster-out cross-validation across seven USDA Farm Resource Regions and year-ahead prediction scenarios, we identify substantial variability in cross-region transferability. GNN-RNN demonstrates superior generalization with positive correlations under geographic shifts, while MMST-ViT performs well in-domain but degrades sharply under OOD conditions. Regions like Heartland and Northern Great Plains show stable transfer dynamics (RMSE less than 10 bu/acre for soybean), whereas Prairie Gateway exhibits persistent underperformance (RMSE greater than 20 bu/acre) across both models and crops, revealing structural dissimilarities likely driven by semi-arid climate, irrigation patterns, and incomplete spectral coverage. Beyond accuracy differences, GNN-RNN achieves 135x faster training than MMST-ViT (14 minutes vs. 31.5 hours), making it more viable for sustainable deployment. Our findings underscore that spatial-temporal alignment - not merely model complexity or data scale - is key to robust generalization, and highlight the need for transparent OOD evaluation protocols to ensure equitable and reliable climate-aware agricultural forecasting.

---

### Temporal Prompting Matters: Rethinking Referring Video Object Segmentation

Authors: Ci-Siang Lin, Min-Hung Chen, I-Jieh Liu, Chien-Yi Wang, Sifei Liu, Yu-Chiang Frank Wang
Published: 2025-10-08
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.07319v1

Referring Video Object Segmentation (RVOS) aims to segment the object referred to by the query sentence in the video. Most existing methods require end-to-end training with dense mask annotations, which could be computation-consuming and less scalable. In this work, we rethink the RVOS problem and aim to investigate the key to this task. Based on existing foundation segmentation models, we decompose the RVOS task into referring, video, and segmentation factors, and propose a Temporal Prompt Generation and Selection (Tenet) framework to address the referring and video factors while leaving the segmentation problem to foundation models. To efficiently adapt image-based foundation segmentation models to referring video object segmentation, we leverage off-the-shelf object detectors and trackers to produce temporal prompts associated with the referring sentence. While high-quality temporal prompts could be produced, they can not be easily identified from confidence scores. To tackle this issue, we propose Prompt Preference Learning to evaluate the quality of the produced temporal prompts. By taking such prompts to instruct image-based foundation segmentation models, we would be able to produce high-quality masks for the referred object, enabling efficient model adaptation to referring video object segmentation. Experiments on RVOS benchmarks demonstrate the effectiveness of the Tenet framework.

---

### Artificial Hippocampus Networks for Efficient Long-Context Modeling

Authors: Yunhao Fang, Weihao Yu, Shu Zhong, Qinghao Ye, Xuehan Xiong, Lai Wei
Published: 2025-10-08
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.07318v2

Long-sequence modeling faces a fundamental trade-off between the efficiency of compressive fixed-size memory in RNN-like models and the fidelity of lossless growing memory in attention-based Transformers. Inspired by the Multi-Store Model in cognitive science, we introduce a memory framework of artificial neural networks. Our method maintains a sliding window of the Transformer's KV cache as lossless short-term memory, while a learnable module termed Artificial Hippocampus Network (AHN) recurrently compresses out-of-window information into a fixed-size compact long-term memory. To validate this framework, we instantiate AHNs using modern RNN-like architectures, including Mamba2, DeltaNet, and GatedDeltaNet to augment open-weight LLMs. We also propose an efficient self-distillation training method where the base model's all parameters are frozen and only the parameters from AHNs are optimized. For inference, our method sets a default large sliding window size of 32k for attention, and AHNs activate only when the sequence length exceeds the 32k window, addressing the quadratic-complexity issue of attention that emerges at that scale. Extensive experiments on long-context benchmarks LV-Eval and InfiniteBench demonstrate that AHN-augmented models consistently outperform sliding window baselines and achieve performance comparable or even superior to full-attention models, while substantially reducing computational and memory requirements. For instance, augmenting the Qwen2.5-3B-Instruct with AHNs reduces inference FLOPs by 40.5% and memory cache by 74.0%, while improving its average score on LV-Eval (128k sequence length) from 4.41 to 5.88. Code is available at: https://github.com/ByteDance-Seed/AHN.

---

### Quantum-enhanced Computer Vision: Going Beyond Classical Algorithms

Authors: Natacha Kuete Meli, Shuteng Wang, Marcel Seelbach Benkner, Michele Sasdelli, Tat-Jun Chin, Tolga Birdal, Michael Moeller, Vladislav Golyanik
Published: 2025-10-08
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.07317v1

Quantum-enhanced Computer Vision (QeCV) is a new research field at the intersection of computer vision, optimisation theory, machine learning and quantum computing. It has high potential to transform how visual signals are processed and interpreted with the help of quantum computing that leverages quantum-mechanical effects in computations inaccessible to classical (i.e. non-quantum) computers. In scenarios where existing non-quantum methods cannot find a solution in a reasonable time or compute only approximate solutions, quantum computers can provide, among others, advantages in terms of better time scalability for multiple problem classes. Parametrised quantum circuits can also become, in the long term, a considerable alternative to classical neural networks in computer vision. However, specialised and fundamentally new algorithms must be developed to enable compatibility with quantum hardware and unveil the potential of quantum computational paradigms in computer vision. This survey contributes to the existing literature on QeCV with a holistic review of this research field. It is designed as a quantum computing reference for the computer vision community, targeting computer vision students, scientists and readers with related backgrounds who want to familiarise themselves with QeCV. We provide a comprehensive introduction to QeCV, its specifics, and methodologies for formulations compatible with quantum hardware and QeCV methods, leveraging two main quantum computational paradigms, i.e. gate-based quantum computing and quantum annealing. We elaborate on the operational principles of quantum computers and the available tools to access, program and simulate them in the context of QeCV. Finally, we review existing quantum computing tools and learning materials and discuss aspects related to publishing and reviewing QeCV papers, open challenges and potential social implications.

---

### Pixel-Perfect Depth with Semantics-Prompted Diffusion Transformers

Authors: Gangwei Xu, Haotong Lin, Hongcheng Luo, Xianqi Wang, Jingfeng Yao, Lianghui Zhu, Yuechuan Pu, Cheng Chi, Haiyang Sun, Bing Wang, Guang Chen, Hangjun Ye et al.
Published: 2025-10-08
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.07316v2

This paper presents Pixel-Perfect Depth, a monocular depth estimation model based on pixel-space diffusion generation that produces high-quality, flying-pixel-free point clouds from estimated depth maps. Current generative depth estimation models fine-tune Stable Diffusion and achieve impressive performance. However, they require a VAE to compress depth maps into latent space, which inevitably introduces \textit{flying pixels} at edges and details. Our model addresses this challenge by directly performing diffusion generation in the pixel space, avoiding VAE-induced artifacts. To overcome the high complexity associated with pixel-space generation, we introduce two novel designs: 1) Semantics-Prompted Diffusion Transformers (SP-DiT), which incorporate semantic representations from vision foundation models into DiT to prompt the diffusion process, thereby preserving global semantic consistency while enhancing fine-grained visual details; and 2) Cascade DiT Design that progressively increases the number of tokens to further enhance efficiency and accuracy. Our model achieves the best performance among all published generative models across five benchmarks, and significantly outperforms all other models in edge-aware point cloud evaluation.

---

### SWE-IF: Aligning Code Evaluation with Human Preference

Authors: Ming Zhong, Xiang Zhou, Ting-Yun Chang, Qingze Wang, Nan Xu, Xiance Si, Dan Garrette, Shyam Upadhyay, Jeremiah Liu, Jiawei Han, Benoit Schillings, Jiao Sun
Published: 2025-10-08
Categories: cs.CL, cs.AI, cs.LG, cs.SE
arXiv: https://arxiv.org/abs/2510.07315v2

Large Language Models (LLMs) have catalyzed vibe coding, where users leverage LLMs to generate and iteratively refine code through natural language interactions until it passes their vibe check. Vibe check reflects human preference and goes beyond functionality: the solution should feel right, read cleanly, preserve intent, and remain correct. However, current code evaluation remains anchored to pass@k and captures only functional correctness, overlooking non-functional instructions that users routinely apply. In this paper, we hypothesize that instruction following is the missing piece underlying vibe check besides functional correctness. To quantify models' code instruction-following capabilities with measurable signals, we present VeriCode, a taxonomy of 30 verifiable code instructions together with deterministic verifiers. We use the taxonomy to augment established evaluation suites, resulting in SWE-IF, a testbed to assess both instruction following and functional correctness. Evaluating 31 LLMs, we show that even the strongest models struggle to comply with multiple instructions and exhibit functional regression. Most importantly, a composite score of functional correctness and instruction following correlates best with human preference, with instruction following emerging as the primary differentiator among LLMs. Our code, data, and taxonomy are available at https://github.com/maszhongming/SWE-IF.

---

### GyroSwin: 5D Surrogates for Gyrokinetic Plasma Turbulence Simulations

Authors: Fabian Paischer, Gianluca Galletti, William Hornsby, Paul Setinek, Lorenzo Zanisi, Naomi Carey, Stanislas Pamela, Johannes Brandstetter
Published: 2025-10-08
Categories: physics.plasm-ph, cs.AI, stat.ML
arXiv: https://arxiv.org/abs/2510.07314v4

Nuclear fusion plays a pivotal role in the quest for reliable and sustainable energy production. A major roadblock to viable fusion power is understanding plasma turbulence, which significantly impairs plasma confinement, and is vital for next-generation reactor design. Plasma turbulence is governed by the nonlinear gyrokinetic equation, which evolves a 5D distribution function over time. Due to its high computational cost, reduced-order models are often employed in practice to approximate turbulent transport of energy. However, they omit nonlinear effects unique to the full 5D dynamics. To tackle this, we introduce GyroSwin, the first scalable 5D neural surrogate that can model 5D nonlinear gyrokinetic simulations, thereby capturing the physical phenomena neglected by reduced models, while providing accurate estimates of turbulent heat transport. GyroSwin (i) extends hierarchical Vision Transformers to 5D, (ii) introduces cross-attention and integration modules for latent 3D$\leftrightarrow$5D interactions between electrostatic potential fields and the distribution function, and (iii) performs channelwise mode separation inspired by nonlinear physics. We demonstrate that GyroSwin outperforms widely used reduced numerics on heat flux prediction, captures the turbulent energy cascade, and reduces the cost of fully resolved nonlinear gyrokinetics by three orders of magnitude while remaining physically verifiable. GyroSwin shows promising scaling laws, tested up to one billion parameters, paving the way for scalable neural surrogates for gyrokinetic simulations of plasma turbulence.

---

### WristWorld: Generating Wrist-Views via 4D World Models for Robotic Manipulation

Authors: Zezhong Qian, Xiaowei Chi, Yuming Li, Shizun Wang, Zhiyuan Qin, Xiaozhu Ju, Sirui Han, Shanghang Zhang
Published: 2025-10-08
Categories: cs.CV, cs.RO
arXiv: https://arxiv.org/abs/2510.07313v1

Wrist-view observations are crucial for VLA models as they capture fine-grained hand-object interactions that directly enhance manipulation performance. Yet large-scale datasets rarely include such recordings, resulting in a substantial gap between abundant anchor views and scarce wrist views. Existing world models cannot bridge this gap, as they require a wrist-view first frame and thus fail to generate wrist-view videos from anchor views alone. Amid this gap, recent visual geometry models such as VGGT emerge with geometric and cross-view priors that make it possible to address extreme viewpoint shifts. Inspired by these insights, we propose WristWorld, the first 4D world model that generates wrist-view videos solely from anchor views. WristWorld operates in two stages: (i) Reconstruction, which extends VGGT and incorporates our Spatial Projection Consistency (SPC) Loss to estimate geometrically consistent wrist-view poses and 4D point clouds; (ii) Generation, which employs our video generation model to synthesize temporally coherent wrist-view videos from the reconstructed perspective. Experiments on Droid, Calvin, and Franka Panda demonstrate state-of-the-art video generation with superior spatial consistency, while also improving VLA performance, raising the average task completion length on Calvin by 3.81% and closing 42.4% of the anchor-wrist view gap.

---

### h1: Bootstrapping LLMs to Reason over Longer Horizons via Reinforcement Learning

Authors: Sumeet Ramesh Motwani, Alesia Ivanova, Ziyang Cai, Philip Torr, Riashat Islam, Shital Shah, Christian Schroeder de Witt, Charles London
Published: 2025-10-08
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.07312v2

Large language models excel at short-horizon reasoning tasks, but performance drops as reasoning horizon lengths increase. Existing approaches to combat this rely on inference-time scaffolding or costly step-level supervision, neither of which scales easily. In this work, we introduce a scalable method to bootstrap long-horizon reasoning capabilities using only existing, abundant short-horizon data. Our approach synthetically composes simple problems into complex, multi-step dependency chains of arbitrary length. We train models on this data using outcome-only rewards under a curriculum that automatically increases in complexity, allowing RL training to be scaled much further without saturating. Empirically, our method generalizes remarkably well: curriculum training on composed 6th-grade level math problems (GSM8K) boosts accuracy on longer, competition-level benchmarks (GSM-Symbolic, MATH-500, AIME) by up to 2.06x. It also transfers significantly to diverse out-of-distribution ReasoningGym domains and long-context benchmarks, indicating broader generalization. Importantly, our long-horizon improvements are significantly higher than baselines even at high pass@k, showing that models can learn new reasoning paths under RL. Theoretically, we show that curriculum RL with outcome rewards achieves an exponential improvement in sample complexity over full-horizon training, providing training signal comparable to dense supervision. h1 therefore introduces an efficient path towards scaling RL for long-horizon problems using only existing data.

---

### MATRIX: Mask Track Alignment for Interaction-aware Video Generation

Authors: Siyoon Jin, Seongchan Kim, Dahyun Chung, Jaeho Lee, Hyunwook Choi, Jisu Nam, Jiyoung Kim, Seungryong Kim
Published: 2025-10-08
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.07310v2

Video DiTs have advanced video generation, yet they still struggle to model multi-instance or subject-object interactions. This raises a key question: How do these models internally represent interactions? To answer this, we curate MATRIX-11K, a video dataset with interaction-aware captions and multi-instance mask tracks. Using this dataset, we conduct a systematic analysis that formalizes two perspectives of video DiTs: semantic grounding, via video-to-text attention, which evaluates whether noun and verb tokens capture instances and their relations; and semantic propagation, via video-to-video attention, which assesses whether instance bindings persist across frames. We find both effects concentrate in a small subset of interaction-dominant layers. Motivated by this, we introduce MATRIX, a simple and effective regularization that aligns attention in specific layers of video DiTs with multi-instance mask tracks from the MATRIX-11K dataset, enhancing both grounding and propagation. We further propose InterGenEval, an evaluation protocol for interaction-aware video generation. In experiments, MATRIX improves both interaction fidelity and semantic alignment while reducing drift and hallucination. Extensive ablations validate our design choices. Codes and weights will be released.

---