# Research Papers — 2025-10 · bundle page 30 of 217

> Full-text markdown of papers #1451–1500 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/30
[← Previous bundle](https://aipod.dev/papers/archive/2025-10/page/29.md)
[Next bundle →](https://aipod.dev/papers/archive/2025-10/page/31.md)

### sMRI-based Brain Age Estimation in MCI using Persistent Homology

Authors: Debanjali Bhattacharya, Neelam Sinha
Published: 2025-10-27
Categories: q-bio.NC, cs.CV, eess.IV
arXiv: https://arxiv.org/abs/2511.05520v1

In this study, we propose the use of persistent homology -- specifically Betti curves for brain age prediction and for distinguishing between healthy and pathological aging. The proposed framework is applied to 100 structural MRI scans from the publicly available ADNI dataset. Our results indicate that Betti curve features, particularly those from dimension-1 (connected components) and dimension-2 (1D holes), effectively capture structural brain alterations associated with aging. Furthermore, clinical features are grouped into three categories based on their correlation, or lack thereof, with (i) predicted brain age and (ii) chronological age. The findings demonstrate that this approach successfully differentiates normal from pathological aging and provides a novel framework for understanding how structural brain changes relate to cognitive impairment. The proposed method serves as a foundation for developing potential biomarkers for early detection and monitoring of cognitive decline.

---

### Retracing the Past: LLMs Emit Training Data When They Get Lost

Authors: Myeongseob Ko, Nikhil Reddy Billa, Adam Nguyen, Charles Fleming, Ming Jin, Ruoxi Jia
Published: 2025-10-27
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2511.05518v1

The memorization of training data in large language models (LLMs) poses significant privacy and copyright concerns. Existing data extraction methods, particularly heuristic-based divergence attacks, often exhibit limited success and offer limited insight into the fundamental drivers of memorization leakage. This paper introduces Confusion-Inducing Attacks (CIA), a principled framework for extracting memorized data by systematically maximizing model uncertainty. We empirically demonstrate that the emission of memorized text during divergence is preceded by a sustained spike in token-level prediction entropy. CIA leverages this insight by optimizing input snippets to deliberately induce this consecutive high-entropy state. For aligned LLMs, we further propose Mismatched Supervised Fine-tuning (SFT) to simultaneously weaken their alignment and induce targeted confusion, thereby increasing susceptibility to our attacks. Experiments on various unaligned and aligned LLMs demonstrate that our proposed attacks outperform existing baselines in extracting verbatim and near-verbatim training data without requiring prior knowledge of the training data. Our findings highlight persistent memorization risks across various LLMs and offer a more systematic method for assessing these vulnerabilities.

---

### Automatización de Informes Geotécnicos para Macizos Rocosos con IA

Authors: Christofer Valencia, Alexis Llumigusín, Silvia Alvarez, Abrahan Arias, Christian Mejia-Escobar
Published: 2025-10-27
Categories: cs.MM, cs.CL
arXiv: https://arxiv.org/abs/2511.04690v1

Geotechnical reports are crucial for assessing the stability of rock formations and ensuring safety in modern engineering. Traditionally, these reports are prepared manually based on field observations using compasses, magnifying glasses, and notebooks. This method is slow, prone to errors, and subjective in its interpretations. To overcome these limitations, the use of artificial intelligence techniques is proposed for the automatic generation of reports through the processing of images and field data. The methodology was based on the collection of photographs of rock outcrops and manual samples with their respective descriptions, as well as on the reports prepared during the Geotechnical Studies course. These resources were used to define the report outline, prompt engineering, and validate the responses of a multimodal large language model (MLLM). The iterative refinement of prompts until structured and specific instructions were obtained for each section of the report proved to be an effective alternative to the costly process of fine-tuning the MLLM. The system evaluation establishes values of 0.455 and 0.653 for the BLEU and ROUGE-L metrics, respectively, suggesting that automatic descriptions are comparable to those made by experts. This tool, accessible via the web, with an intuitive interface and the ability to export to standardized formats, represents an innovation and an important contribution for professionals and students of field geology.

---

### Friction on Demand: A Generative Framework for the Inverse Design of Metainterfaces

Authors: Valentin Mouton, Adrien Mélot
Published: 2025-10-27
Categories: stat.ML, cs.LG, eess.SY, physics.comp-ph
arXiv: https://arxiv.org/abs/2511.03735v1

Designing frictional interfaces to exhibit prescribed macroscopic behavior is a challenging inverse problem, made difficult by the non-uniqueness of solutions and the computational cost of contact simulations. Traditional approaches rely on heuristic search over low-dimensional parameterizations, which limits their applicability to more complex or nonlinear friction laws. We introduce a generative modeling framework using Variational Autoencoders (VAEs) to infer surface topographies from target friction laws. Trained on a synthetic dataset composed of 200 million samples constructed from a parameterized contact mechanics model, the proposed method enables efficient, simulation-free generation of candidate topographies. We examine the potential and limitations of generative modeling for this inverse design task, focusing on balancing accuracy, throughput, and diversity in the generated solutions. Our results highlight trade-offs and outline practical considerations when balancing these objectives. This approach paves the way for near-real-time control of frictional behavior through tailored surface topographies.

---

### ECGXtract: Deep Learning-based ECG Feature Extraction for Automated CVD Diagnosis

Authors: Youssif Abuzied, Hassan AbdEltawab, Abdelrhman Gaber, Tamer ElBatt
Published: 2025-10-27
Categories: eess.SP, cs.LG
arXiv: https://arxiv.org/abs/2511.02850v1

This paper presents ECGXtract, a deep learning-based approach for interpretable ECG feature extraction, addressing the limitations of traditional signal processing and black-box machine learning methods. In particular, we develop convolutional neural network models capable of extracting both temporal and morphological features with strong correlations to a clinically validated ground truth. Initially, each model is trained to extract a single feature, ensuring precise and interpretable outputs. A series of experiments is then carried out to evaluate the proposed method across multiple setups, including global versus lead-specific features, different sampling frequencies, and comparisons with other approaches such as ECGdeli. Our findings show that ECGXtract achieves robust performance across most features with a mean correlation score of 0.80 with the ground truth for global features, with lead II consistently providing the best results. For lead-specific features, ECGXtract achieves a mean correlation score of 0.822. Moreover, ECGXtract achieves superior results to the state-of-the-art open source ECGdeli as it got a higher correlation score with the ground truth in 90% of the features. Furthermore, we explore the feasibility of extracting multiple features simultaneously utilizing a single model. Semantic grouping is proved to be effective for global features, while large-scale grouping and lead-specific multi-output models show notable performance drops. These results highlight the potential of structured grouping strategies to balance the computational efficiency vs. model accuracy, paving the way for more scalable and clinically interpretable ECG feature extraction systems in limited resource settings.

---

### Multi-Personality Generation of LLMs at Decoding-time

Authors: Rongxin Chen, Yunfan Li, Yige Yuan, Bingbing Xu, Huawei Shen
Published: 2025-10-27
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2511.01891v4

Multi-personality generation for LLMs, enabling simultaneous embodiment of multiple personalization attributes, is a fundamental challenge. Existing retraining-based approaches are costly and poorly scalable, while decoding-time methods often rely on external models or heuristics, limiting flexibility and robustness. In this paper, we propose a novel Multi-Personality Generation (MPG) framework under the decoding-time combination paradigm. It flexibly controls multi-personality without relying on scarce multi-dimensional models or extra training, leveraging implicit density ratios in single-dimensional models as a "free lunch" to reformulate the task as sampling from a target strategy aggregating these ratios. To implement MPG efficiently, we design Speculative Chunk-level based Rejection sampling (SCR), which generates responses in chunks and parallelly validates them via estimated thresholds within a sliding window. This significantly reduces computational overhead while maintaining high-quality generation. Experiments on MBTI personality and Role-Playing demonstrate the effectiveness of MPG, showing improvements up to 16%-18%. Code and data are available at https://github.com/Libra117/MPG .

---

### Benchmarking Federated Learning Frameworks for Medical Imaging Deployment: A Comparative Study of NVIDIA FLARE, Flower, and Owkin Substra

Authors: Riya Gupta, Alexander Chowdhury, Sahil Nalawade
Published: 2025-10-27
Categories: cs.CV, cs.DC
arXiv: https://arxiv.org/abs/2511.00037v1

Federated Learning (FL) has emerged as a transformative paradigm in medical AI, enabling collaborative model training across institutions without direct data sharing. This study benchmarks three prominent FL frameworks NVIDIA FLARE, Flower, and Owkin Substra to evaluate their suitability for medical imaging applications in real-world settings. Using the PathMNIST dataset, we assess model performance, convergence efficiency, communication overhead, scalability, and developer experience. Results indicate that NVIDIA FLARE offers superior production scalability, Flower provides flexibility for prototyping and academic research, and Owkin Substra demonstrates exceptional privacy and compliance features. Each framework exhibits strengths optimized for distinct use cases, emphasizing their relevance to practical deployment in healthcare environments.

---

### Neural Architecture Search for global multi-step Forecasting of Energy Production Time Series

Authors: Georg Velev, Stefan Lessmann
Published: 2025-10-27
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.00035v1

The dynamic energy sector requires both predictive accuracy and runtime efficiency for short-term forecasting of energy generation under operational constraints, where timely and precise predictions are crucial. The manual configuration of complex methods, which can generate accurate global multi-step predictions without suffering from a computational bottleneck, represents a procedure with significant time requirements and high risk for human-made errors. A further intricacy arises from the temporal dynamics present in energy-related data. Additionally, the generalization to unseen data is imperative for continuously deploying forecasting techniques over time. To overcome these challenges, in this research, we design a neural architecture search (NAS)-based framework for the automated discovery of time series models that strike a balance between computational efficiency, predictive performance, and generalization power for the global, multi-step short-term forecasting of energy production time series. In particular, we introduce a search space consisting only of efficient components, which can capture distinctive patterns of energy time series. Furthermore, we formulate a novel objective function that accounts for performance generalization in temporal context and the maximal exploration of different regions of our high-dimensional search space. The results obtained on energy production time series show that an ensemble of lightweight architectures discovered with NAS outperforms state-of-the-art techniques, such as Transformers, as well as pre-trained forecasting models, in terms of both efficiency and accuracy.

---

### On the Fundamental Limitations of Decentralized Learnable Reward Shaping in Cooperative Multi-Agent Reinforcement Learning

Authors: Aditya Akella
Published: 2025-10-27
Categories: cs.MA, cs.LG
arXiv: https://arxiv.org/abs/2511.00034v1

Recent advances in learnable reward shaping have shown promise in single-agent reinforcement learning by automatically discovering effective feedback signals. However, the effectiveness of decentralized learnable reward shaping in cooperative multi-agent settings remains poorly understood. We propose DMARL-RSA, a fully decentralized system where each agent learns individual reward shaping, and evaluate it on cooperative navigation tasks in the simple_spread_v3 environment. Despite sophisticated reward learning, DMARL-RSA achieves only -24.20 +/- 0.09 average reward, compared to MAPPO with centralized training at 1.92 +/- 0.87 -- a 26.12-point gap. DMARL-RSA performs similarly to simple independent learning (IPPO: -23.19 +/- 0.96), indicating that advanced reward shaping cannot overcome fundamental decentralized coordination limitations. Interestingly, decentralized methods achieve higher landmark coverage (0.888 +/- 0.029 for DMARL-RSA, 0.960 +/- 0.045 for IPPO out of 3 total) but worse overall performance than centralized MAPPO (0.273 +/- 0.008 landmark coverage) -- revealing a coordination paradox between local optimization and global performance. Analysis identifies three critical barriers: (1) non-stationarity from concurrent policy updates, (2) exponential credit assignment complexity, and (3) misalignment between individual reward optimization and global objectives. These results establish empirical limits for decentralized reward learning and underscore the necessity of centralized coordination for effective multi-agent cooperation.

---

### STRIDER: Navigation via Instruction-Aligned Structural Decision Space Optimization

Authors: Diqi He, Xuehao Gao, Hao Li, Junwei Han, Dingwen Zhang
Published: 2025-10-27
Categories: cs.RO, cs.AI
arXiv: https://arxiv.org/abs/2511.00033v1

The Zero-shot Vision-and-Language Navigation in Continuous Environments (VLN-CE) task requires agents to navigate previously unseen 3D environments using natural language instructions, without any scene-specific training. A critical challenge in this setting lies in ensuring agents' actions align with both spatial structure and task intent over long-horizon execution. Existing methods often fail to achieve robust navigation due to a lack of structured decision-making and insufficient integration of feedback from previous actions. To address these challenges, we propose STRIDER (Instruction-Aligned Structural Decision Space Optimization), a novel framework that systematically optimizes the agent's decision space by integrating spatial layout priors and dynamic task feedback. Our approach introduces two key innovations: 1) a Structured Waypoint Generator that constrains the action space through spatial structure, and 2) a Task-Alignment Regulator that adjusts behavior based on task progress, ensuring semantic alignment throughout navigation. Extensive experiments on the R2R-CE and RxR-CE benchmarks demonstrate that STRIDER significantly outperforms strong SOTA across key metrics; in particular, it improves Success Rate (SR) from 29% to 35%, a relative gain of 20.7%. Such results highlight the importance of spatially constrained decision-making and feedback-guided execution in improving navigation fidelity for zero-shot VLN-CE.

---

### From Uniform to Adaptive: General Skip-Block Mechanisms for Efficient PDE Neural Operators

Authors: Lei Liu, Zhongyi Yu, Hong Wang, Huanshuo Dong, Haiyang Xin, Hongwei Zhao, Bin Li
Published: 2025-10-27
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2511.00032v2

In recent years, Neural Operators(NO) have gradually emerged as a popular approach for solving Partial Differential Equations (PDEs). However, their application to large-scale engineering tasks suffers from significant computational overhead. And the fact that current models impose a uniform computational cost while physical fields exhibit vastly different complexities constitutes a fundamental mismatch, which is the root of this inefficiency. For instance, in turbulence flows, intricate vortex regions require deeper network processing compared to stable flows. To address this, we introduce a framework: Skip-Block Routing (SBR), a general framework designed for Transformer-based neural operators, capable of being integrated into their multi-layer architectures. First, SBR uses a routing mechanism to learn the complexity and ranking of tokens, which is then applied during inference. Then, in later layers, it decides how many tokens are passed forward based on this ranking. This way, the model focuses more processing capacity on the tokens that are more complex. Experiments demonstrate that SBR is a general framework that seamlessly integrates into various neural operators. Our method reduces computational cost by approximately 50% in terms of Floating Point Operations (FLOPs), while still delivering up to 2x faster inference without sacrificing accuracy.

---

### Probing Knowledge Holes in Unlearned LLMs

Authors: Myeongseob Ko, Hoang Anh Just, Charles Fleming, Ming Jin, Ruoxi Jia
Published: 2025-10-27
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2511.00030v1

Machine unlearning has emerged as a prevalent technical solution for selectively removing unwanted knowledge absorbed during pre-training, without requiring full retraining. While recent unlearning techniques can effectively remove undesirable content without severely compromising performance on standard benchmarks, we find that they may inadvertently create ``knowledge holes'' -- unintended losses of benign knowledge that standard benchmarks fail to capture. To probe where unlearned models reveal knowledge holes, we propose a test case generation framework that explores both immediate neighbors of unlearned content and broader areas of potential failures. Our evaluation demonstrates significant hidden costs of unlearning: up to 98.7\% of the test cases yield irrelevant or nonsensical responses from unlearned models, despite being answerable by the pretrained model. These findings necessitate rethinking the conventional approach to evaluating knowledge preservation in unlearning, moving beyond standard, static benchmarks.

---

### Towards Gaussian processes modelling to study the late effects of radiotherapy in children and young adults with brain tumours

Authors: Angela Davey, Arthur Leroy, Eliana Vasquez Osorio, Kate Vaughan, Peter Clayton, Marcel van Herk, Mauricio A Alvarez, Martin McCabe, Marianne Aznar
Published: 2025-10-27
Categories: stat.AP, cs.LG
arXiv: https://arxiv.org/abs/2510.26814v1

Survivors of childhood cancer need lifelong monitoring for side effects from radiotherapy. However, longitudinal data from routine monitoring is often infrequently and irregularly sampled, and subject to inaccuracies. Due to this, measurements are often studied in isolation, or simple relationships (e.g., linear) are used to impute missing timepoints. In this study, we investigated the potential role of Gaussian Processes (GP) modelling to make population-based and individual predictions, using insulin-like growth factor 1 (IGF-1) measurements as a test case. With training data of 23 patients with a median (range) of 4 (1-16) timepoints we identified a trend within the range of literature reported values. In addition, with 8 test cases, individual predictions were made with an average root mean squared error of 31.9 (10.1 - 62.3) ng/ml and 27.4 (0.02 - 66.1) ng/ml for two approaches. GP modelling may overcome limitations of routine longitudinal data and facilitate analysis of late effects of radiotherapy.

---

### Impact of clinical decision support systems (cdss) on clinical outcomes and healthcare delivery in low- and middle-income countries: protocol for a systematic review and meta-analysis

Authors: Garima Jain, Anand Bodade, Sanghamitra Pati
Published: 2025-10-27
Categories: stat.ME, cs.AI
arXiv: https://arxiv.org/abs/2510.26812v1

Clinical decision support systems (CDSS) are used to improve clinical and service outcomes, yet evidence from low- and middle-income countries (LMICs) is dispersed. This protocol outlines methods to quantify the impact of CDSS on patient and healthcare delivery outcomes in LMICs. We will include comparative quantitative designs (randomized trials, controlled before-after, interrupted time series, comparative cohorts) evaluating CDSS in World Bank-defined LMICs. Standalone qualitative studies are excluded; mixed-methods studies are eligible only if they report comparative quantitative outcomes, for which we will extract the quantitative component. Searches (from inception to 30 September 2024) will cover MEDLINE, Embase, CINAHL, CENTRAL, Web of Science, Global Health, Scopus, IEEE Xplore, LILACS, African Index Medicus, and IndMED, plus grey sources. Screening and extraction will be performed in duplicate. Risk of bias will be assessed with RoB 2 (randomized trials) and ROBINS-I (non-randomized). Random-effects meta-analysis will be performed where outcomes are conceptually or statistically comparable; otherwise, a structured narrative synthesis will be presented. Heterogeneity will be explored using relative and absolute metrics and a priori subgroups or meta-regression (condition area, care level, CDSS type, readiness proxies, study design).

---

### Magentic Marketplace: An Open-Source Environment for Studying Agentic Markets

Authors: Gagan Bansal, Wenyue Hua, Zezhou Huang, Adam Fourney, Amanda Swearngin, Will Epperson, Tyler Payne, Jake M. Hofman, Brendan Lucier, Chinmay Singh, Markus Mobius, Akshay Nambi et al.
Published: 2025-10-27
Categories: cs.MA, cs.AI
arXiv: https://arxiv.org/abs/2510.25779v1

As LLM agents advance, they are increasingly mediating economic decisions, ranging from product discovery to transactions, on behalf of users. Such applications promise benefits but also raise many questions about agent accountability and value for users. Addressing these questions requires understanding how agents behave in realistic market conditions. However, previous research has largely evaluated agents in constrained settings, such as single-task marketplaces (e.g., negotiation) or structured two-agent interactions. Real-world markets are fundamentally different: they require agents to handle diverse economic activities and coordinate within large, dynamic ecosystems where multiple agents with opaque behaviors may engage in open-ended dialogues. To bridge this gap, we investigate two-sided agentic marketplaces where Assistant agents represent consumers and Service agents represent competing businesses. To study these interactions safely, we develop Magentic-Marketplace -- a simulated environment where Assistants and Services can operate. This environment enables us to study key market dynamics: the utility agents achieve, behavioral biases, vulnerability to manipulation, and how search mechanisms shape market outcomes. Our experiments show that frontier models can approach optimal welfare -- but only under ideal search conditions. Performance degrades sharply with scale, and all models exhibit severe first-proposal bias, creating 10-30x advantages for response speed over quality. These findings reveal how behaviors emerge across market conditions, informing the design of fair and efficient agentic marketplaces.

---

### Review Based Entity Ranking using Fuzzy Logic Algorithmic Approach: Analysis

Authors: Pratik N. Kalamkar, Anupama G. Phakatkar
Published: 2025-10-27
Categories: cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2510.25778v1

Opinion mining, also called sentiment analysis, is the field of study that analyzes people opinions, sentiments, evaluations, appraisals, attitudes, and emotions towards entities such as products, services, organizations, individuals, issues, events, topics, and their attributes. Holistic lexicon-based approach does not consider the strength of each opinion, i.e., whether the opinion is very strongly negative (or positive), strongly negative (or positive), moderate negative (or positive), very weakly negative (or positive) and weakly negative (or positive). In this paper, we propose approach to rank entities based on orientation and strength of the entity reviews and user's queries by classifying them in granularity levels (i.e. very weak, weak, moderate, very strong and strong) by combining opinion words (i.e. adverb, adjective, noun and verb) that are related to aspect of interest of certain product. We shall use fuzzy logic algorithmic approach in order to classify opinion words into different category and syntactic dependency resolution to find relations for desired aspect words. Opinion words related to certain aspects of interest are considered to find the entity score for that aspect in the review.

---

### StreetMath: Study of LLMs' Approximation Behaviors

Authors: Chiung-Yi Tseng, Somshubhra Roy, Maisha Thasin, Danyang Zhang, Blessing Effiong
Published: 2025-10-27
Categories: cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2510.25776v1

There is a substantial body of literature examining the mathematical reasoning capabilities of large language models (LLMs), particularly their performance on precise arithmetic operations in autoregressive architectures. However, their ability to perform approximate reasoning in informal, fast-paced mathematical operations has received far less attention, especially among non-autoregressive decoder models. Our work addresses this gap by introducing StreetMath, a benchmark designed to evaluate models' approximation abilities under real-world approximation scenarios. We conduct extensive evaluations across different LLM architectures: Qwen3-4B-Instruct-2507, Qwen3-4B-Thinking-2507, Dream-v0-Instruct-7B, Falcon-Mamba-7B-Instruct, and Mamba-GPT-3B. Furthermore, we apply mechanistic interpretability techniques to probe their internal computational states. Our analysis reveals that LLMs generally attempt to compute exact values or invoke external tools even in tasks that call for approximation. Moreover, while models sometimes reach the correct answer in early layers or steps, they still consume more tokens when solving approximation tasks. Additional experiments indicate that exact and approximate arithmetic operations rely on largely separate neural components. Drawing upon research on cognitive psychology, we argue that LLMs do not exhibit cognitive miserliness in the same way humans do in street math settings. We open source our work https://github.com/ctseng777/StreetMath

---

### Sustained Performance and Energy Accounting for Nonlinear Forecasting Across Classical and Simulated Quantum Models

Authors: Avyay Kodali, Priyanshi Singh, Pranay Pandey, Krishna Bhatia, Shalini Devendrababu, Srinjoy Ganguly
Published: 2025-10-27
Categories: quant-ph, cs.LG
arXiv: https://arxiv.org/abs/2510.25183v2

Energy-efficient AI should be evaluated across the full application pipeline, not only by lowest error or shortest training time. We study this through nonlinear time-series forecasting using simulated quantum reservoir computing (QRC) as an emerging-computing case study. Our evaluation spans 33 forecasting configurations and 825 completed runs on NARMA-10, NARMA-20, Mackey--Glass, Lorenz-63, and Santa Fe laser data. The core benchmark includes 775 fully instrumented runs across statistical, linear, reservoir, neural, continuous-variable Gaussian QRC, and gate-based statevector QRC models, with 50 additional variational QNN runs extending the trainable-quantum comparison. We measure NRMSE, RMSE, MAE, wall time, inference latency, peak CPU/GPU memory, parameter count, operational energy, and carbon. Since a fixed QRC encoder can generate reusable features for multiple readouts, we report both cold-start and amortized costs. We also use a Sustainable Forecasting Score (SFS), a diagnostic geometric mean of normalized predictive skill and log-scaled carbon efficiency, while retaining raw measurements and Pareto analyses. The best mean NRMSE is achieved by continuous-variable QRC with a Transformer readout (0.332), followed closely by classical TCN (0.341) and QRC+TCN (0.340). However, ESN and ridge-lag deliver the strongest sustained efficiency, with average amortized carbon of 0.014 and 0.012 gCO2 per run and SFS values of 0.814 and 0.805. Larger QRC feature maps increase cost without improving average accuracy, while gate-based statevector simulation is not competitive. These results support three practices for emerging AI systems: expose stage-level energy, use reuse-aware accounting boundaries, and co-design the feature generator or accelerator with the classical readout.

---

### SFMS-ALR: Script-First Multilingual Speech Synthesis with Adaptive Locale Resolution

Authors: Dharma Teja Donepudi
Published: 2025-10-27
Categories: cs.SD, cs.AI, eess.AS
arXiv: https://arxiv.org/abs/2510.25178v1

Intra-sentence multilingual speech synthesis (code-switching TTS) remains a major challenge due to abrupt language shifts, varied scripts, and mismatched prosody between languages. Conventional TTS systems are typically monolingual and fail to produce natural, intelligible speech in mixed-language contexts. We introduce Script-First Multilingual Synthesis with Adaptive Locale Resolution (SFMS-ALR), an engine-agnostic framework for fluent, real-time code-switched speech generation. SFMS-ALR segments input text by Unicode script, applies adaptive language identification to determine each segment's language and locale, and normalizes prosody using sentiment-aware adjustments to preserve expressive continuity across languages. The algorithm generates a unified SSML representation with appropriate "lang" or "voice" spans and synthesizes the utterance in a single TTS request. Unlike end-to-end multilingual models, SFMS-ALR requires no retraining and integrates seamlessly with existing voices from Google, Apple, Amazon, and other providers. Comparative analysis with data-driven pipelines such as Unicom and Mask LID demonstrates SFMS-ALR's flexibility, interpretability, and immediate deployability. The framework establishes a modular baseline for high-quality, engine-independent multilingual TTS and outlines evaluation strategies for intelligibility, naturalness, and user preference.

---

### Fortytwo: Swarm Inference with Peer-Ranked Consensus

Authors: Vladyslav Larin, Ihor Naumenko, Aleksei Ivashov, Ivan Nikitin, Alexander Firsov
Published: 2025-10-27
Categories: cs.LG, cs.AI, cs.CL, cs.MA
arXiv: https://arxiv.org/abs/2510.24801v1

As centralized AI hits compute ceilings and diminishing returns from ever-larger training runs, meeting demand requires an inference layer that scales horizontally in both capacity and capability. We present Fortytwo, a novel protocol that leverages swarm intelligence principles and distributed pairwise ranking consensus to achieve superior performance in AI inference. Our approach reimagines collaboration among AI nodes using swarm inference: a peer-ranked, reputation-weighted consensus across heterogeneous models that surfaces the highest-quality responses. Using pairwise ranking with a custom Bradley-Terry-style aggregation model, we demonstrate that swarm inference substantially outperforms majority voting, achieving 85.90% on GPQA Diamond versus 68.69% for majority voting with the same model set - an improvement of +17.21 percentage points (approximately +25.1% relative). The protocol incorporates on-chain reputation so node influence adapts to demonstrated accuracy over time, yielding a meritocratic consensus that filters low-quality or malicious participants. To resist Sybil attacks, Fortytwo employs proof-of-capability in its consensus: nodes must successfully complete calibration/test requests and stake reputation to enter ranking rounds, making multi-identity attacks economically unattractive while preserving openness. Across six challenging benchmarks, including GPQA Diamond, LiveCodeBench, and AIME, our evaluation indicates higher accuracy and strong resilience to adversarial and noisy free-form prompting (e.g., prompt-injection degradation of only 0.12% versus 6.20% for a monolithic single-model baseline), while retaining practical deployability. Together, these results establish a foundation for decentralized AI systems - democratizing access to high-quality inference through collective intelligence without sacrificing reliability or security.

---

### Large Language Models Report Subjective Experience Under Self-Referential Processing

Authors: Cameron Berg, Diogo de Lucena, Judd Rosenblatt
Published: 2025-10-27
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.24797v2

Large language models sometimes produce structured, first-person descriptions that explicitly reference awareness or subjective experience. To better understand this behavior, we investigate one theoretically motivated condition under which such reports arise: self-referential processing, a computational motif emphasized across major theories of consciousness. Through a series of controlled experiments on GPT, Claude, and Gemini model families, we test whether this regime reliably shifts models toward first-person reports of subjective experience, and how such claims behave under mechanistic and behavioral probes. Four main results emerge: (1) Inducing sustained self-reference through simple prompting consistently elicits structured subjective experience reports across model families. (2) These reports are mechanistically gated by interpretable sparse-autoencoder features associated with deception and roleplay: surprisingly, suppressing deception features sharply increases the frequency of experience claims, while amplifying them minimizes such claims. (3) Structured descriptions of the self-referential state converge statistically across model families in ways not observed in any control condition. (4) The induced state yields significantly richer introspection in downstream reasoning tasks where self-reflection is only indirectly afforded. While these findings do not constitute direct evidence of consciousness, they implicate self-referential processing as a minimal and reproducible condition under which large language models generate structured first-person reports that are mechanistically gated, semantically convergent, and behaviorally generalizable. The systematic emergence of this pattern across architectures makes it a first-order scientific and ethical priority for further investigation.

---

### Mutual Wanting in Human--AI Interaction: Empirical Evidence from Large-Scale Analysis of GPT Model Transitions

Authors: HaoYang Shang, Xuan Liu
Published: 2025-10-27
Categories: cs.CY, cs.AI
arXiv: https://arxiv.org/abs/2510.24796v2

The rapid evolution of large language models (LLMs) creates complex bidirectional expectations between users and AI systems that are poorly understood. We introduce the concept of "mutual wanting" to analyze these expectations during major model transitions. Through analysis of user comments from major AI forums and controlled experiments across multiple OpenAI models, we provide the first large-scale empirical validation of bidirectional desire dynamics in human-AI interaction. Our findings reveal that nearly half of users employ anthropomorphic language, trust significantly exceeds betrayal language, and users cluster into distinct "mutual wanting" types. We identify measurable expectation violation patterns and quantify the expectation-reality gap following major model releases. Using advanced NLP techniques including dual-algorithm topic modeling and multi-dimensional feature extraction, we develop the Mutual Wanting Alignment Framework (M-WAF) with practical applications for proactive user experience management and AI system design. These findings establish mutual wanting as a measurable phenomenon with clear implications for building more trustworthy and relationally-aware AI systems.

---

### A Survey on Efficient Vision-Language-Action Models

Authors: Zhaoshu Yu, Bo Wang, Pengpeng Zeng, Haonan Zhang, Ji Zhang, Zheng Wang, Lianli Gao, Jingkuan Song, Nicu Sebe, Heng Tao Shen
Published: 2025-10-27
Categories: cs.CV, cs.AI, cs.LG, cs.RO
arXiv: https://arxiv.org/abs/2510.24795v3

Vision-Language-Action models (VLAs) represent a significant frontier in embodied intelligence, aiming to bridge digital knowledge with physical-world interaction. Despite their remarkable performance, foundational VLAs are hindered by the prohibitive computational and data demands inherent to their large-scale architectures. To this end, recent studies improve VLA efficiency from different views, e.g., real-time inference, training computation, and scalable data collection. However, these efforts are mostly studied separately. A unified view is still missing for understanding how efficiency should be optimized across the full VLA lifecycle. To bridge this gap, this survey presents the first comprehensive review of Efficient Vision-Language-Action models (Efficient VLAs) across the entire model-training-data pipeline. Specifically, we introduce a unified taxonomy to systematically organize the disparate efforts in this domain, categorizing current techniques into three core pillars: (1) Efficient Model Design, focusing on efficient architectures and model compression; (2) Efficient Training, which reduces computational burdens during model learning; and (3) Efficient Data Collection, which addresses the bottlenecks in acquiring and utilizing robotic data. Through a critical review of state-of-the-art methods within this framework, this survey provides an organized reference for the community and summarizes representative applications, delineates key challenges, and charts a roadmap for future research. We maintain a continuously updated project page to track our latest developments: https://evla-survey.github.io/.

---

### MR-Align: Meta-Reasoning Informed Factuality Alignment for Large Reasoning Models

Authors: Xinming Wang, Jian Xu, Bin Yu, Sheng Lian, Hongzhu Yi, Yi Chen, Yingjian Zhu, Boran Wang, Hongming Yang, Han Hu, Xu-Yao Zhang, Cheng-Lin Liu
Published: 2025-10-27
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.24794v2

Large reasoning models (LRMs) show strong capabilities in complex reasoning, yet their marginal gains on evidence-dependent factual questions are limited. We find this limitation is partially attributable to a reasoning-answer hit gap, where the model identifies the correct facts during reasoning but fails to incorporate them into the final response, thereby reducing factual fidelity. To address this issue, we propose MR-ALIGN, a Meta-Reasoning informed alignment framework that enhances factuality without relying on external verifiers. MR-ALIGN quantifies state transition probabilities along the model's thinking process and constructs a transition-aware implicit reward that reinforces beneficial reasoning patterns while suppressing defective ones at the atomic thinking segments. This re-weighting reshapes token-level signals into probability-aware segment scores, encouraging coherent reasoning trajectories that are more conducive to factual correctness. Empirical evaluations across four factual QA datasets and one long-form factuality benchmark show that MR-ALIGN consistently improves accuracy and truthfulness while reducing misleading reasoning. These results highlight that aligning the reasoning process itself, rather than merely the outputs, is pivotal for advancing factuality in LRMs.

---

### SwiftEmbed: Ultra-Fast Text Embeddings via Static Token Lookup for Real-Time Applications

Authors: Edouard Lansiaux, Antoine Simonet, Eric Wiel
Published: 2025-10-27
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.24793v3

We present SwiftEmbed, a production-oriented serving system for static token embeddings that achieves 1.12\,ms p50 latency for single-text requests while maintaining a 60.6 MTEB average score across 8 representative tasks. Built around the open-source Potion-base-8M distilled model from MinishLab and implemented in Rust, the system delivers 50,000 requests per second through static embedding lookup, mean pooling, and zero-copy IEEE754 binary serialization. Evaluation demonstrates exceptional duplicate detection performance (90.1% AP) and strong semantic similarity (76.1% Spearman correlation). Performance relative to Sentence-BERT is task-dependent: robust for deduplication and similarity workloads (89--100%), substantially lower for classification and complex retrieval tasks (75%). Domain-specific performance ranges from 75% to 131% of a GloVe-840B baseline. The system targets real-time embedding applications where sub-5\,ms latency is operationally critical and where full transformer inference is not feasible.

---

### PISA-Bench: The PISA Index as a Multilingual and Multimodal Metric for the Evaluation of Vision-Language Models

Authors: Patrick Haller, Fabio Barth, Jonas Golde, Georg Rehm, Alan Akbik
Published: 2025-10-27
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.24792v2

Vision-language models (VLMs) have demonstrated remarkable progress in multimodal reasoning. However, existing benchmarks remain limited in terms of high-quality, human-verified examples. Many current datasets rely on synthetically generated content by large language models (LLMs). Furthermore, most datasets are limited to English, as manual quality assurance of translated samples is time-consuming and costly. To fill this gap, we introduce PISA-Bench, a multilingual benchmark derived from English examples of the expert-created PISA tests, a unified framework for the assessment of student competencies in over eighty countries. Each example consists of human-extracted instructions, questions, answer options, and images, enriched with question type categories, and has been translated from English into five additional languages (Spanish, German, Chinese, French, and Italian), resulting in a fully parallel corpus covering six languages. We evaluate state-of-the-art vision-language models on PISA-Bench and find that especially small models (<20B parameters) fail to achieve high test scores. We further find substantial performance degradation on non-English splits as well as high error-rates when models are tasked with spatial and geometric reasoning. By releasing the dataset and evaluation framework, we provide a resource for advancing research on multilingual multimodal reasoning.

---

### A Re-node Self-training Approach for Deep Graph-based Semi-supervised Classification on Multi-view Image Data

Authors: Jingjun Bi, Fadi Dornaika
Published: 2025-10-27
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2510.24791v1

Recently, graph-based semi-supervised learning and pseudo-labeling have gained attention due to their effectiveness in reducing the need for extensive data annotations. Pseudo-labeling uses predictions from unlabeled data to improve model training, while graph-based methods are characterized by processing data represented as graphs. However, the lack of clear graph structures in images combined with the complexity of multi-view data limits the efficiency of traditional and existing techniques. Moreover, the integration of graph structures in multi-view data is still a challenge. In this paper, we propose Re-node Self-taught Graph-based Semi-supervised Learning for Multi-view Data (RSGSLM). Our method addresses these challenges by (i) combining linear feature transformation and multi-view graph fusion within a Graph Convolutional Network (GCN) framework, (ii) dynamically incorporating pseudo-labels into the GCN loss function to improve classification in multi-view data, and (iii) correcting topological imbalances by adjusting the weights of labeled samples near class boundaries. Additionally, (iv) we introduce an unsupervised smoothing loss applicable to all samples. This combination optimizes performance while maintaining computational efficiency. Experimental results on multi-view benchmark image datasets demonstrate that RSGSLM surpasses existing semi-supervised learning approaches in multi-view contexts.

---

### Cross-Lingual Summarization as a Black-Box Watermark Removal Attack

Authors: Gokul Ganesan
Published: 2025-10-27
Categories: cs.CL, cs.CR
arXiv: https://arxiv.org/abs/2510.24789v2

Watermarking has been proposed as a lightweight mechanism to identify AI-generated text, with schemes typically relying on perturbations to token distributions. While prior work shows that paraphrasing can weaken such signals, these attacks remain partially detectable or degrade text quality. We demonstrate that cross-lingual summarization attacks (CLSA) -- translation to a pivot language followed by summarization and optional back-translation -- constitute a qualitatively stronger attack vector. By forcing a semantic bottleneck across languages, CLSA systematically destroys token-level statistical biases while preserving semantic fidelity. In experiments across multiple watermarking schemes (KGW, SIR, XSIR, Unigram) and five languages (Amharic, Chinese, Hindi, Spanish, Swahili), we show that CLSA reduces watermark detection accuracy more effectively than monolingual paraphrase at similar quality levels. Our results highlight an underexplored vulnerability that challenges the practicality of watermarking for provenance or regulation. We argue that robust provenance solutions must move beyond distributional watermarking and incorporate cryptographic or model-attestation approaches. On 300 held-out samples per language, CLSA consistently drives detection toward chance while preserving task utility. Concretely, for XSIR (explicitly designed for cross-lingual robustness), AUROC with paraphrasing is $0.827$, with Cross-Lingual Watermark Removal Attacks (CWRA) (He et al., 2024) using Chinese as the pivot, it is $0.823$, whereas CLSA drives it down to $0.53$ (near chance). Results highlight a practical, low-cost removal pathway that crosses languages and compresses content without visible artifacts.

---

### The Underappreciated Power of Vision Models for Graph Structural Understanding

Authors: Xinjian Zhao, Wei Pang, Zhongkai Xue, Xiangru Jian, Lei Zhang, Yaoyao Xu, Xiaozhuang Song, Shu Wu, Tianshu Yu
Published: 2025-10-27
Categories: cs.CV, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.24788v1

Graph Neural Networks operate through bottom-up message-passing, fundamentally differing from human visual perception, which intuitively captures global structures first. We investigate the underappreciated potential of vision models for graph understanding, finding they achieve performance comparable to GNNs on established benchmarks while exhibiting distinctly different learning patterns. These divergent behaviors, combined with limitations of existing benchmarks that conflate domain features with topological understanding, motivate our introduction of GraphAbstract. This benchmark evaluates models' ability to perceive global graph properties as humans do: recognizing organizational archetypes, detecting symmetry, sensing connectivity strength, and identifying critical elements. Our results reveal that vision models significantly outperform GNNs on tasks requiring holistic structural understanding and maintain generalizability across varying graph scales, while GNNs struggle with global pattern abstraction and degrade with increasing graph size. This work demonstrates that vision models possess remarkable yet underutilized capabilities for graph structural understanding, particularly for problems requiring global topological awareness and scale-invariant reasoning. These findings open new avenues to leverage this underappreciated potential for developing more effective graph foundation models for tasks dominated by holistic pattern recognition.

---

### ESCA: Enabling Seamless Codec Avatar Execution through Algorithm and Hardware Co-Optimization for Virtual Reality

Authors: Mingzhi Zhu, Ding Shang, Sai Qian Zhang
Published: 2025-10-27
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.24787v1

Photorealistic Codec Avatars (PCA), which generate high-fidelity human face renderings, are increasingly being used in Virtual Reality (VR) environments to enable immersive communication and interaction through deep learning-based generative models. However, these models impose significant computational demands, making real-time inference challenging on resource-constrained VR devices such as head-mounted displays, where latency and power efficiency are critical. To address this challenge, we propose an efficient post-training quantization (PTQ) method tailored for Codec Avatar models, enabling low-precision execution without compromising output quality. In addition, we design a custom hardware accelerator that can be integrated into the system-on-chip of VR devices to further enhance processing efficiency. Building on these components, we introduce ESCA, a full-stack optimization framework that accelerates PCA inference on edge VR platforms. Experimental results demonstrate that ESCA boosts FovVideoVDP quality scores by up to $+0.39$ over the best 4-bit baseline, delivers up to $3.36\times$ latency reduction, and sustains a rendering rate of 100 frames per second in end-to-end tests, satisfying real-time VR requirements. These results demonstrate the feasibility of deploying high-fidelity codec avatars on resource-constrained devices, opening the door to more immersive and portable VR experiences.

---

### Leveraging LLMs for Early Alzheimer's Prediction

Authors: Tananun Songdechakraiwut
Published: 2025-10-27
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.23946v1

We present a connectome-informed LLM framework that encodes dynamic fMRI connectivity as temporal sequences, applies robust normalization, and maps these data into a representation suitable for a frozen pre-trained LLM for clinical prediction. Applied to early Alzheimer's detection, our method achieves sensitive prediction with error rates well below clinically recognized margins, with implications for timely Alzheimer's intervention.

---

### Adaptive Training of INRs via Pruning and Densification

Authors: Diana Aldana, João Paulo Lima, Daniel Csillag, Daniel Perazzo, Haoan Feng, Luiz Velho, Tiago Novello
Published: 2025-10-27
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.23943v1

Encoding input coordinates with sinusoidal functions into multilayer perceptrons (MLPs) has proven effective for implicit neural representations (INRs) of low-dimensional signals, enabling the modeling of high-frequency details. However, selecting appropriate input frequencies and architectures while managing parameter redundancy remains an open challenge, often addressed through heuristics and heavy hyperparameter optimization schemes. In this paper, we introduce AIRe ($\textbf{A}$daptive $\textbf{I}$mplicit neural $\textbf{Re}$presentation), an adaptive training scheme that refines the INR architecture over the course of optimization. Our method uses a neuron pruning mechanism to avoid redundancy and input frequency densification to improve representation capacity, leading to an improved trade-off between network size and reconstruction quality. For pruning, we first identify less-contributory neurons and apply a targeted weight decay to transfer their information to the remaining neurons, followed by structured pruning. Next, the densification stage adds input frequencies to spectrum regions where the signal underfits, expanding the representational basis. Through experiments on images and SDFs, we show that AIRe reduces model size while preserving, or even improving, reconstruction quality. Code and pretrained models will be released for public use.

---

### Decentralized Causal Discovery using Judo Calculus

Authors: Sridhar Mahadevan
Published: 2025-10-27
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.23942v2

We describe a theory and implementation of an intuitionistic decentralized framework for causal discovery using judo calculus, which is formally defined as j-stable causal inference using j-do-calculus in a topos of sheaves. In real-world applications -- from biology to medicine and social science -- causal effects depend on regime (age, country, dose, genotype, or lab protocol). Our proposed judo calculus formalizes this context dependence formally as local truth: a causal claim is proven true on a cover of regimes, not everywhere at once. The Lawvere-Tierney modal operator j chooses which regimes are relevant; j-stability means the claim holds constructively and consistently across that family. We describe an algorithmic and implementation framework for judo calculus, combining it with standard score-based, constraint-based, and gradient-based causal discovery methods. We describe experimental results on a range of domains, from synthetic to real-world datasets from biology and economics. Our experimental results show the computational efficiency gained by the decentralized nature of sheaf-theoretic causal discovery, as well as improved performance over classical causal discovery methods.

---

### Auto prompting without training labels: An LLM cascade for product quality assessment in e-commerce catalogs

Authors: Soham Satyadharma, Fatemeh Sheikholeslami, Swati Kaul, Aziz Umit Batur, Suleiman A. Khan
Published: 2025-10-27
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.23941v1

We introduce a novel, training free cascade for auto-prompting Large Language Models (LLMs) to assess product quality in e-commerce. Our system requires no training labels or model fine-tuning, instead automatically generating and refining prompts for evaluating attribute quality across tens of thousands of product category-attribute pairs. Starting from a seed of human-crafted prompts, the cascade progressively optimizes instructions to meet catalog-specific requirements. This approach bridges the gap between general language understanding and domain-specific knowledge at scale in complex industrial catalogs. Our extensive empirical evaluations shows the auto-prompt cascade improves precision and recall by $8-10\%$ over traditional chain-of-thought prompting. Notably, it achieves these gains while reducing domain expert effort from 5.1 hours to 3 minutes per attribute - a $99\%$ reduction. Additionally, the cascade generalizes effectively across five languages and multiple quality assessment tasks, consistently maintaining performance gains.

---

### Modeling Biological Multifunctionality with Echo State Networks

Authors: Anastasia-Maria Leventi-Peetz, Jörg-Volker Peetz, Kai Weber, Nikolaos Zacharis
Published: 2025-10-27
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.23940v1

In this work, a three-dimensional multicomponent reaction-diffusion model has been developed, combining excitable-system dynamics with diffusion processes and sharing conceptual features with the FitzHugh-Nagumo model. Designed to capture the spatiotemporal behavior of biological systems, particularly electrophysiological processes, the model was solved numerically to generate time-series data. These data were subsequently used to train and evaluate an Echo State Network (ESN), which successfully reproduced the system's dynamic behavior. The results demonstrate that simulating biological dynamics using data-driven, multifunctional ESN models is both feasible and effective.

---

### Scalable GPU-Based Integrity Verification for Large Machine Learning Models

Authors: Marcin Spoczynski, Marcela S. Melara
Published: 2025-10-27
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2510.23938v1

We present a security framework that strengthens distributed machine learning by standardizing integrity protections across CPU and GPU platforms and significantly reducing verification overheads. Our approach co-locates integrity verification directly with large ML model execution on GPU accelerators, resolving the fundamental mismatch between how large ML workloads typically run (primarily on GPUs) and how security verifications traditionally operate (on separate CPU-based processes), delivering both immediate performance benefits and long-term architectural consistency. By performing cryptographic operations natively on GPUs using dedicated compute units (e.g., Intel Arc's XMX units, NVIDIA's Tensor Cores), our solution eliminates the potential architectural bottlenecks that could plague traditional CPU-based verification systems when dealing with large models. This approach leverages the same GPU-based high-memory bandwidth and parallel processing primitives that power ML workloads ensuring integrity checks keep pace with model execution even for massive models exceeding 100GB. This framework establishes a common integrity verification mechanism that works consistently across different GPU vendors and hardware configurations. By anticipating future capabilities for creating secure channels between trusted execution environments and GPU accelerators, we provide a hardware-agnostic foundation that enterprise teams can deploy regardless of their underlying CPU and GPU infrastructures.

---

### A data free neural operator enabling fast inference of 2D and 3D Navier Stokes equations

Authors: Junho Choi, Teng-Yuan Chang, Namjung Kim, Youngjoon Hong
Published: 2025-10-27
Categories: cs.LG, physics.flu-dyn
arXiv: https://arxiv.org/abs/2510.23936v2

Ensemble simulations of high-dimensional flow models (e.g., Navier Stokes type PDEs) are computationally prohibitive for real time applications. Neural operators enable fast inference but are limited by costly data requirements and poor generalization to 3D flows. We present a data-free operator network for the Navier Stokes equations that eliminates the need for paired solution data and enables robust, real time inference for large ensemble forecasting. The physics-grounded architecture takes initial and boundary conditions as well as forcing functions, yielding solutions robust to high variability and perturbations. Across 2D benchmarks and 3D test cases, the method surpasses prior neural operators in accuracy and, for ensembles, achieves greater efficiency than conventional numerical solvers. Notably, it delivers accurate solutions of the three dimensional Navier Stokes equations, a regime not previously demonstrated for data free neural operators. By uniting a numerically grounded architecture with the scalability of machine learning, this approach establishes a practical pathway toward data free, high fidelity PDE surrogates for end to end scientific simulation and prediction.

---

### Understanding Fairness and Prediction Error through Subspace Decomposition and Influence Analysis

Authors: Enze Shi, Pankaj Bhagwat, Zhixian Yang, Linglong Kong, Bei Jiang
Published: 2025-10-27
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2510.23935v2

Machine learning models have achieved widespread success but often inherit and amplify historical biases, resulting in unfair outcomes. Traditional fairness methods typically impose constraints at the prediction level, without addressing underlying biases in data representations. In this work, we propose a principled framework that adjusts data representations to balance predictive utility and fairness. Using sufficient dimension reduction, we decompose the feature space into target-relevant, sensitive, and shared components, and control the fairness-utility trade-off by selectively removing sensitive information. We provide a theoretical analysis of how prediction error and fairness gaps evolve as shared subspaces are added, and employ influence functions to quantify their effects on the asymptotic behavior of parameter estimates. Experiments on both synthetic and real-world datasets validate our theoretical insights and show that the proposed method effectively improves fairness while preserving predictive performance.

---

### MFiSP: A Multimodal Fire Spread Prediction Framework

Authors: Alec Sathiyamoorthy, Wenhao Zhou, Xiangmin Zhou, Xiaodong Li, Iqbal Gondal
Published: 2025-10-27
Categories: cs.CY, cs.AI, cs.ET
arXiv: https://arxiv.org/abs/2510.23934v1

The 2019-2020 Black Summer bushfires in Australia devastated 19 million hectares, destroyed 3,000 homes, and lasted seven months, demonstrating the escalating scale and urgency of wildfire threats requiring better forecasting for effective response. Traditional fire modeling relies on manual interpretation by Fire Behaviour Analysts (FBAns) and static environmental data, often leading to inaccuracies and operational limitations. Emerging data sources, such as NASA's FIRMS satellite imagery and Volunteered Geographic Information, offer potential improvements by enabling dynamic fire spread prediction. This study proposes a Multimodal Fire Spread Prediction Framework (MFiSP) that integrates social media data and remote sensing observations to enhance forecast accuracy. By adapting fuel map manipulation strategies between assimilation cycles, the framework dynamically adjusts fire behavior predictions to align with the observed rate of spread. We evaluate the efficacy of MFiSP using synthetically generated fire event polygons across multiple scenarios, analyzing individual and combined impacts on forecast perimeters. Results suggest that our MFiSP integrating multimodal data can improve fire spread prediction beyond conventional methods reliant on FBAn expertise and static inputs.

---

### Differential Privacy: Gradient Leakage Attacks in Federated Learning Environments

Authors: Miguel Fernandez-de-Retana, Unai Zulaika, Rubén Sánchez-Corcuera, Aitor Almeida
Published: 2025-10-27
Categories: cs.LG, cs.CR, cs.DC
arXiv: https://arxiv.org/abs/2510.23931v1

Federated Learning (FL) allows for the training of Machine Learning models in a collaborative manner without the need to share sensitive data. However, it remains vulnerable to Gradient Leakage Attacks (GLAs), which can reveal private information from the shared model updates. In this work, we investigate the effectiveness of Differential Privacy (DP) mechanisms - specifically, DP-SGD and a variant based on explicit regularization (PDP-SGD) - as defenses against GLAs. To this end, we evaluate the performance of several computer vision models trained under varying privacy levels on a simple classification task, and then analyze the quality of private data reconstructions obtained from the intercepted gradients in a simulated FL environment. Our results demonstrate that DP-SGD significantly mitigates the risk of gradient leakage attacks, albeit with a moderate trade-off in model utility. In contrast, PDP-SGD maintains strong classification performance but proves ineffective as a practical defense against reconstruction attacks. These findings highlight the importance of empirically evaluating privacy mechanisms beyond their theoretical guarantees, particularly in distributed learning scenarios where information leakage may represent an unassumable critical threat to data security and privacy.

---

### PlanarGS: High-Fidelity Indoor 3D Gaussian Splatting Guided by Vision-Language Planar Priors

Authors: Xirui Jin, Renbiao Jin, Boying Li, Danping Zou, Wenxian Yu
Published: 2025-10-27
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.23930v1

Three-dimensional Gaussian Splatting (3DGS) has recently emerged as an efficient representation for novel-view synthesis, achieving impressive visual quality. However, in scenes dominated by large and low-texture regions, common in indoor environments, the photometric loss used to optimize 3DGS yields ambiguous geometry and fails to recover high-fidelity 3D surfaces. To overcome this limitation, we introduce PlanarGS, a 3DGS-based framework tailored for indoor scene reconstruction. Specifically, we design a pipeline for Language-Prompted Planar Priors (LP3) that employs a pretrained vision-language segmentation model and refines its region proposals via cross-view fusion and inspection with geometric priors. 3D Gaussians in our framework are optimized with two additional terms: a planar prior supervision term that enforces planar consistency, and a geometric prior supervision term that steers the Gaussians toward the depth and normal cues. We have conducted extensive experiments on standard indoor benchmarks. The results show that PlanarGS reconstructs accurate and detailed 3D surfaces, consistently outperforming state-of-the-art methods by a large margin. Project page: https://planargs.github.io

---

### TurboPortrait3D: Single-step diffusion-based fast portrait novel-view synthesis

Authors: Emily Kim, Julieta Martinez, Timur Bagautdinov, Jessica Hodgins
Published: 2025-10-27
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.23929v1

We introduce TurboPortrait3D: a method for low-latency novel-view synthesis of human portraits. Our approach builds on the observation that existing image-to-3D models for portrait generation, while capable of producing renderable 3D representations, are prone to visual artifacts, often lack of detail, and tend to fail at fully preserving the identity of the subject. On the other hand, image diffusion models excel at generating high-quality images, but besides being computationally expensive, are not grounded in 3D and thus are not directly capable of producing multi-view consistent outputs. In this work, we demonstrate that image-space diffusion models can be used to significantly enhance the quality of existing image-to-avatar methods, while maintaining 3D-awareness and running with low-latency. Our method takes a single frontal image of a subject as input, and applies a feedforward image-to-avatar generation pipeline to obtain an initial 3D representation and corresponding noisy renders. These noisy renders are then fed to a single-step diffusion model which is conditioned on input image(s), and is specifically trained to refine the renders in a multi-view consistent way. Moreover, we introduce a novel effective training strategy that includes pre-training on a large corpus of synthetic multi-view data, followed by fine-tuning on high-quality real images. We demonstrate that our approach both qualitatively and quantitatively outperforms current state-of-the-art for portrait novel-view synthesis, while being efficient in time.

---

### Adaptive Keyframe Selection for Scalable 3D Scene Reconstruction in Dynamic Environments

Authors: Raman Jha, Yang Zhou, Giuseppe Loianno
Published: 2025-10-27
Categories: cs.RO, cs.CV
arXiv: https://arxiv.org/abs/2510.23928v3

In this paper, we propose an adaptive keyframe selection method for improved 3D scene reconstruction in dynamic environments. The proposed method integrates two complementary modules: an error-based selection module utilizing photometric and structural similarity (SSIM) errors, and a momentum-based update module that dynamically adjusts keyframe selection thresholds according to scene motion dynamics. By dynamically curating the most informative frames, our approach addresses a key data bottleneck in real-time perception. This allows for the creation of high-quality 3D world representations from a compressed data stream, a critical step towards scalable robot learning and deployment in complex, dynamic environments. Experimental results demonstrate significant improvements over traditional static keyframe selection strategies, such as fixed temporal intervals or uniform frame skipping. These findings highlight a meaningful advancement toward adaptive perception systems that can dynamically respond to complex and evolving visual scenes. We evaluate our proposed adaptive keyframe selection module on two recent state-of-the-art 3D reconstruction networks, Spann3r and CUT3R, and observe consistent improvements in reconstruction quality across both frameworks. Furthermore, an extensive ablation study confirms the effectiveness of each individual component in our method, underlining their contribution to the overall performance gains.

---

### Improving the Straight-Through Estimator with Zeroth-Order Information

Authors: Ningfeng Yang, Tor M. Aamodt
Published: 2025-10-27
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.23926v1

We study the problem of training neural networks with quantized parameters. Learning low-precision quantized parameters by enabling computation of gradients via the Straight-Through Estimator (STE) can be challenging. While the STE enables back-propagation, which is a first-order method, recent works have explored the use of zeroth-order (ZO) gradient descent for fine-tuning. We note that the STE provides high-quality biased gradients, and ZO gradients are unbiased but can be expensive. We thus propose First-Order-Guided Zeroth-Order Gradient Descent (FOGZO) that reduces STE bias while reducing computations relative to ZO methods. Empirically, we show FOGZO improves the tradeoff between quality and training time in Quantization-Aware Pre-Training. Specifically, versus STE at the same number of iterations, we show a 1-8\% accuracy improvement for DeiT Tiny/Small, 1-2\% accuracy improvement on ResNet 18/50, and 1-22 perplexity point improvement for LLaMA models with up to 0.3 billion parameters. For the same loss, FOGZO yields a 796$\times$ reduction in computation versus n-SPSA for a 2-layer MLP on MNIST. Code is available at https://github.com/1733116199/fogzo.

---

### Latent Chain-of-Thought for Visual Reasoning

Authors: Guohao Sun, Hang Hua, Jian Wang, Jiebo Luo, Sohail Dianat, Majid Rabbani, Raghuveer Rao, Zhiqiang Tao
Published: 2025-10-27
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2510.23925v2

Chain-of-thought (CoT) reasoning is critical for improving the interpretability and reliability of Large Vision-Language Models (LVLMs). However, existing training algorithms such as SFT, PPO, and GRPO may not generalize well across unseen reasoning tasks and heavily rely on a biased reward model. To address this challenge, we reformulate reasoning in LVLMs as posterior inference and propose a scalable training algorithm based on amortized variational inference. By leveraging diversity-seeking reinforcement learning algorithms, we introduce a novel sparse reward function for token-level learning signals that encourage diverse, high-likelihood latent CoT, overcoming deterministic sampling limitations and avoiding reward hacking. Additionally, we implement a Bayesian inference-scaling strategy that replaces costly Best-of-N and Beam Search with a marginal likelihood to efficiently rank optimal rationales and answers. We empirically demonstrate that the proposed method enhances the state-of-the-art LVLMs on seven reasoning benchmarks, in terms of effectiveness, generalization, and interpretability.

---

### Agent-based Automated Claim Matching with Instruction-following LLMs

Authors: Dina Pisarevskaya, Arkaitz Zubiaga
Published: 2025-10-27
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.23924v1

We present a novel agent-based approach for the automated claim matching task with instruction-following LLMs. We propose a two-step pipeline that first generates prompts with LLMs, to then perform claim matching as a binary classification task with LLMs. We demonstrate that LLM-generated prompts can outperform SOTA with human-generated prompts, and that smaller LLMs can do as well as larger ones in the generation process, allowing to save computational resources. We also demonstrate the effectiveness of using different LLMs for each step of the pipeline, i.e. using an LLM for prompt generation, and another for claim matching. Our investigation into the prompt generation process in turn reveals insights into the LLMs' understanding of claim matching.

---

### Breaking the Benchmark: Revealing LLM Bias via Minimal Contextual Augmentation

Authors: Kaveh Eskandari Miandoab, Mahammed Kamruzzaman, Arshia Gharooni, Gene Louis Kim, Vasanth Sarathy, Ninareh Mehrabi
Published: 2025-10-27
Categories: cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2510.23921v1

Large Language Models have been shown to demonstrate stereotypical biases in their representations and behavior due to the discriminative nature of the data that they have been trained on. Despite significant progress in the development of methods and models that refrain from using stereotypical information in their decision-making, recent work has shown that approaches used for bias alignment are brittle. In this work, we introduce a novel and general augmentation framework that involves three plug-and-play steps and is applicable to a number of fairness evaluation benchmarks. Through application of augmentation to a fairness evaluation dataset (Bias Benchmark for Question Answering (BBQ)), we find that Large Language Models (LLMs), including state-of-the-art open and closed weight models, are susceptible to perturbations to their inputs, showcasing a higher likelihood to behave stereotypically. Furthermore, we find that such models are more likely to have biased behavior in cases where the target demographic belongs to a community less studied by the literature, underlining the need to expand the fairness and safety research to include more diverse communities.

---

### Revisiting Value Iteration: Unified Analysis of Discounted and Average-Reward Cases

Authors: Arsenii Mustafin, Xinyi Sheng, Dominik Baumann
Published: 2025-10-27
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.23914v2

While Value Iteration (VI) is one of the most fundamental algorithms in Reinforcement Learning, its theoretical convergence guarantees still exhibit a persistent mismatch with empirical behavior. In the discounted-reward case, classical theory guarantees geometric convergence with rate $γ$, while in the average-reward case recent work suggests that only sublinear convergence can be expected. In practice, however, VI is often observed to converge significantly faster. In this work, we show through a unified geometry-based analysis that, under an assumption of a unique and unichain optimal policy, (i) convergence is geometric in both the discounted- and average-reward settings and (ii) the convergence rate is faster than previous analyses suggest.

---

### Key and Value Weights Are Probably All You Need: On the Necessity of the Query, Key, Value weight Triplet in Self-Attention Transformers

Authors: Marko Karbevski, Antonij Mijoski
Published: 2025-10-27
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.23912v7

We theoretically investigate whether the Query, Key, Value weight triplet can be reduced in encoder-only and decoder-only transformers. Under mild assumptions, we prove that one of the Query, Key or Value weights are redundant and can be replaced with the identity matrix, reducing attention parameters by 25\%. If applied to the Query or Key weights, this also simplifies optimization: attention logits depend on a single learned weight matrix rather than on a product of two. Validating the Query weight removal on decoder-only GPT-style small models trained from scratch, we find that reduced models match baseline performance despite fewer parameters, and outperform baselines when saved parameters are reallocated. Our analysis has also led us to a structural expressivity boundary: in the mathematically tractable ReLU setting, skip connections push MLPs into a generically disjoint function class at fixed width. These findings motivate investigation across modalities and at scale, where the observed stability and efficiency gains may prove most consequential.

---

### DynaStride: Dynamic Stride Windowing with MMCoT for Instructional Multi-Scene Captioning

Authors: Eddison Pham, Prisha Priyadarshini, Adrian Maliackel, Kanishk Bandi, Cristian Meo, Kevin Zhu
Published: 2025-10-27
Categories: cs.CV, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.23907v2

Scene-level captioning in instructional videos can enhance learning by requiring an understanding of both visual cues and temporal structure. By aligning visual cues with textual guidance, this understanding supports procedural learning and multimodal reasoning, providing a richer context for skill acquisition. However, captions that fail to capture this structure may lack coherence and quality, which can create confusion and undermine the video's educational intent. To address this gap, we introduce DynaStride, a pipeline to generate coherent, scene-level captions without requiring manual scene segmentation. Using the YouCookII dataset's scene annotations, DynaStride performs adaptive frame sampling and multimodal windowing to capture key transitions within each scene. It then employs a multimodal chain-of-thought process to produce multiple action-object pairs, which are refined and fused using a dynamic stride window selection algorithm that adaptively balances temporal context and redundancy. The final scene-level caption integrates visual semantics and temporal reasoning in a single instructional caption. Empirical evaluations against strong baselines, including VLLaMA3 and GPT-4o, demonstrate consistent gains on both N-gram-based metrics (BLEU, METEOR) and semantic similarity measures (BERTScore, CLIPScore). Qualitative analyses further show that DynaStride produces captions that are more temporally coherent and informative, suggesting a promising direction for improving AI-powered instructional content generation.

---