# Research Papers — 2025-11 · bundle page 171 of 197

> Full-text markdown of papers #8501–8550 of 9830 published in 2025-11, newest first. AI-readable mirrors of the full 9830-paper 2025-11 archive (50 papers per file).

Canonical page: https://aipod.dev/papers/archive/2025-11/page/171
[← Previous bundle](https://aipod.dev/papers/archive/2025-11/page/170.md)
[Next bundle →](https://aipod.dev/papers/archive/2025-11/page/172.md)

### PETRA: Pretrained Evolutionary Transformer for SARS-CoV-2 Mutation Prediction

Authors: Xu Zou
Published: 2025-11-06
Categories: cs.LG, cs.AI, q-bio.GN
arXiv: https://arxiv.org/abs/2511.03976v1

Since its emergence, SARS-CoV-2 has demonstrated a rapid and unpredictable evolutionary trajectory, characterized by the continual emergence of immune-evasive variants. This poses persistent challenges to public health and vaccine development. While large-scale generative pre-trained transformers (GPTs) have revolutionized the modeling of sequential data, their direct applications to noisy viral genomic sequences are limited. In this paper, we introduce PETRA(Pretrained Evolutionary TRAnsformer), a novel transformer approach based on evolutionary trajectories derived from phylogenetic trees rather than raw RNA sequences. This method effectively mitigates sequencing noise and captures the hierarchical structure of viral evolution. With a weighted training framework to address substantial geographical and temporal imbalances in global sequence data, PETRA excels in predicting future SARS-CoV-2 mutations, achieving a weighted recall@1 of 9.45% for nucleotide mutations and 17.10\% for spike amino-acid mutations, compared to 0.49% and 6.64% respectively for the best baseline. PETRA also demonstrates its ability to aid in the real-time mutation prediction of major clades like 24F(XEC) and 25A(LP.8.1). The code is open sourced on https://github.com/xz-keg/PETra

---

### Non-Asymptotic Optimization and Generalization Bounds for Stochastic Gauss-Newton in Overparameterized Models

Authors: Semih Cayci
Published: 2025-11-06
Categories: cs.LG, math.OC, stat.ML
arXiv: https://arxiv.org/abs/2511.03972v2

An important question in deep learning is how higher-order optimization methods affect generalization. In this work, we analyze a stochastic Gauss-Newton (SGN) method with Levenberg-Marquardt damping and mini-batch sampling for training overparameterized deep neural networks with smooth activations in a regression setting. Our theoretical contributions are twofold. First, we establish finite-time convergence bounds via a variable-metric analysis in parameter space, with explicit dependencies on the batch size, network width and depth. Second, we derive non-asymptotic generalization bounds for SGN using uniform stability in the overparameterized regime, characterizing the impact of curvature, batch size, and overparameterization on generalization performance. Our theoretical results identify a favorable generalization regime for SGN in which a larger minimum eigenvalue of the Gauss-Newton matrix along the optimization path yields tighter stability bounds.

---

### Room Envelopes: A Synthetic Dataset for Indoor Layout Reconstruction from Images

Authors: Sam Bahrami, Dylan Campbell
Published: 2025-11-06
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.03970v1

Modern scene reconstruction methods are able to accurately recover 3D surfaces that are visible in one or more images. However, this leads to incomplete reconstructions, missing all occluded surfaces. While much progress has been made on reconstructing entire objects given partial observations using generative models, the structural elements of a scene, like the walls, floors and ceilings, have received less attention. We argue that these scene elements should be relatively easy to predict, since they are typically planar, repetitive and simple, and so less costly approaches may be suitable. In this work, we present a synthetic dataset -- Room Envelopes -- that facilitates progress on this task by providing a set of RGB images and two associated pointmaps for each image: one capturing the visible surface and one capturing the first surface once fittings and fixtures are removed, that is, the structural layout. As we show, this enables direct supervision for feed-forward monocular geometry estimators that predict both the first visible surface and the first layout surface. This confers an understanding of the scene's extent, as well as the shape and location of its objects.

---

### PrivacyCD: Hierarchical Unlearning for Protecting Student Privacy in Cognitive Diagnosis

Authors: Mingliang Hou, Yinuo Wang, Teng Guo, Zitao Liu, Wenzhou Dou, Jiaqi Zheng, Renqiang Luo, Mi Tian, Weiqi Luo
Published: 2025-11-06
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.03966v1

The need to remove specific student data from cognitive diagnosis (CD) models has become a pressing requirement, driven by users' growing assertion of their "right to be forgotten". However, existing CD models are largely designed without privacy considerations and lack effective data unlearning mechanisms. Directly applying general purpose unlearning algorithms is suboptimal, as they struggle to balance unlearning completeness, model utility, and efficiency when confronted with the unique heterogeneous structure of CD models. To address this, our paper presents the first systematic study of the data unlearning problem for CD models, proposing a novel and efficient algorithm: hierarchical importanceguided forgetting (HIF). Our key insight is that parameter importance in CD models exhibits distinct layer wise characteristics. HIF leverages this via an innovative smoothing mechanism that combines individual and layer, level importance, enabling a more precise distinction of parameters associated with the data to be unlearned. Experiments on three real world datasets show that HIF significantly outperforms baselines on key metrics, offering the first effective solution for CD models to respond to user data removal requests and for deploying high-performance, privacy preserving AI systems

---

### Robust inference using density-powered Stein operators

Authors: Shinto Eguchi
Published: 2025-11-06
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2511.03963v3

We introduce a density-power weighted variant of the Stein operator, called the $γ$-Stein operator, for robust inference with unnormalized probability models. The operator is motivated by the first variation of the $γ$-divergence under infinitesimal escort transport and weights the usual Stein field by a positive power of the model density. This weighting down-weights observations in low model-density regions, providing a principled robustness mechanism while retaining the normalizing-constant-free structure of score matching. We develop the resulting $γ$-score matching estimating equations and discuss their non-integrable, generalized-method-of-moments character. We further study two extensions: a $γ$-kernelized Stein discrepancy, interpreted as a robust diagnostic or contaminated-null goodness-of-fit procedure, and $γ$-Stein variational gradient descent for robust posterior approximation. Numerical examples on directional, mixture, and quartic-potential models illustrate the robustness--efficiency trade-off: positive $γ$ can stabilize inference under targeted contamination, whereas $γ=0$ remains preferable under clean well-specified models.

---

### A Linear Fractional Transformation Model and Calibration Method for Light Field Camera

Authors: Zhong Chen, Changfeng Chen
Published: 2025-11-06
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.03962v2

Accurate intrinsic calibration is a crucial yet challenging prerequisite for 3D reconstruction using light field cameras. Existing calibration models typically analyze the main lens and micro lens array (MLA) in a coupled manner, resulting in high complexity and a large number of parameters. In this paper, we propose a linear fractional transformation (LFT) model that introduces a single parameter $α$ to decouple the imaging processes of the main lens and the MLA. A dedicated matrix $\mathbf{H}_α$ is designed to characterize the MLA projection, enabling the main lens and the MLA to be calibrated independently. The proposed calibration method consists of an analytical least-squares solution for $\mathbf{H}_α$, followed by joint nonlinear refinement of all intrinsic parameters. Experimental results on both physical datasets and simulated data demonstrate that the proposed method achieves a mean translation error of $2.1\%$, outperforming the state-of-the-art, while maintaining sub-pixel reprojection accuracy. The complete codebase, including a light field simulator based on the proposed model, is openly available to the research community.

---

### Multi-Agent Collaborative Framework For Math Problem Generation

Authors: Kia Karbasi, Kevin Hong, Mohammad Amin Samadi, Gregory Pottie
Published: 2025-11-06
Categories: cs.MA, cs.CL, cs.HC
arXiv: https://arxiv.org/abs/2511.03958v1

Automatic question generation (AQG) for mathematics education remains an elusive goal for Intelligent Tutoring Systems and educators. While pre-trained transformer-based language models have significantly advanced natural language generation, they often struggle to precisely control problem complexity and cognitive demands. In this paper, we introduce a collaborative multi-agent framework as a novel method of incorporating inference-time computation into AQG. This approach leverages multiple agents that iteratively refine generated question-answer pairs to better balance complexity and cognitive demand. We evaluate the generated questions on five meta-evaluation criteria: relevance, importance, clarity, difficulty matching, answerability, to assess the system's ability to control the required complexity and quality of the questions. Preliminary evaluations show that this collaborative multi-agent framework elevates the quality of generated educational content by fostering a more nuanced balance between cognitive challenge and clarity. These promising outcomes suggest that integrating collaborative multi-agent workflows can yield more controlled, pedagogically valuable content that can help advance automated educational content generation and adaptive learning environments.

---

### Conditional Score Learning for Quickest Change Detection in Markov Transition Kernels

Authors: Wuxia Chen, Taposh Banerjee, Vahid Tarokh
Published: 2025-11-06
Categories: cs.LG, eess.SP, math.ST, stat.ME, stat.ML
arXiv: https://arxiv.org/abs/2511.03953v1

We address the problem of quickest change detection in Markov processes with unknown transition kernels. The key idea is to learn the conditional score $\nabla_{\mathbf{y}} \log p(\mathbf{y}|\mathbf{x})$ directly from sample pairs $( \mathbf{x},\mathbf{y})$, where both $\mathbf{x}$ and $\mathbf{y}$ are high-dimensional data generated by the same transition kernel. In this way, we avoid explicit likelihood evaluation and provide a practical way to learn the transition dynamics. Based on this estimation, we develop a score-based CUSUM procedure that uses conditional Hyvarinen score differences to detect changes in the kernel. To ensure bounded increments, we propose a truncated version of the statistic. With Hoeffding's inequality for uniformly ergodic Markov processes, we prove exponential lower bounds on the mean time to false alarm. We also prove asymptotic upper bounds on detection delay. These results give both theoretical guarantees and practical feasibility for score-based detection in high-dimensional Markov models.

---

### High-dimensional limit theorems for SGD: Momentum and Adaptive Step-sizes

Authors: Aukosh Jagannath, Taj Jones-McCormick, Varnan Sarangian
Published: 2025-11-06
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2511.03952v2

We develop a high-dimensional scaling limit for Stochastic Gradient Descent with Polyak Momentum (SGD-M) and adaptive step-sizes. This provides a framework to rigourously compare online SGD with some of its popular variants. We show that the scaling limits of SGD-M coincide with those of online SGD after an appropriate time rescaling and a specific choice of step-size. However, if the step-size is kept the same between the two algorithms, SGD-M will amplify high-dimensional effects, potentially degrading performance relative to online SGD. We demonstrate our framework on two popular learning problems: Spiked Tensor PCA and Single Index Models. In both cases, we also examine online SGD with an adaptive step-size based on normalized gradients. In the high-dimensional regime, this algorithm yields multiple benefits: its dynamics admit fixed points closer to the population minimum and widens the range of admissible step-sizes for which the iterates converge to such solutions. These examples provide a rigorous account, aligning with empirical motivation, of how early preconditioners can stabilize and improve dynamics in settings where online SGD fails.

---

### Improving Multi-View Reconstruction via Texture-Guided Gaussian-Mesh Joint Optimization

Authors: Zhejia Cai, Puhua Jiang, Shiwei Mao, Hongkun Cao, Ruqi Huang
Published: 2025-11-06
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2511.03950v2

Reconstructing real-world objects from multi-view images is essential for applications in 3D editing, AR/VR, and digital content creation. Existing methods typically prioritize either geometric accuracy (Multi-View Stereo) or photorealistic rendering (Novel View Synthesis), often decoupling geometry and appearance optimization, which hinders downstream editing tasks. This paper advocates an unified treatment on geometry and appearance optimization for seamless Gaussian-mesh joint optimization. More specifically, we propose a novel framework that simultaneously optimizes mesh geometry (vertex positions and faces) and vertex colors via Gaussian-guided mesh differentiable rendering, leveraging photometric consistency from input images and geometric regularization from normal and depth maps. The obtained high-quality 3D reconstruction can be further exploit in down-stream editing tasks, such as relighting and shape deformation. Our code will be released in https://github.com/zhejia01/TexGuided-GS2Mesh

---

### Extracting Causal Relations in Deep Knowledge Tracing

Authors: Kevin Hong, Kia Karbasi, Gregory Pottie
Published: 2025-11-06
Categories: cs.AI, cs.HC
arXiv: https://arxiv.org/abs/2511.03948v1

A longstanding goal in computational educational research is to develop explainable knowledge tracing (KT) models. Deep Knowledge Tracing (DKT), which leverages a Recurrent Neural Network (RNN) to predict student knowledge and performance on exercises, has been proposed as a major advancement over traditional KT methods. Several studies suggest that its performance gains stem from its ability to model bidirectional relationships between different knowledge components (KCs) within a course, enabling the inference of a student's understanding of one KC from their performance on others. In this paper, we challenge this prevailing explanation and demonstrate that DKT's strength lies in its implicit ability to model prerequisite relationships as a causal structure, rather than bidirectional relationships. By pruning exercise relation graphs into Directed Acyclic Graphs (DAGs) and training DKT on causal subsets of the Assistments dataset, we show that DKT's predictive capabilities align strongly with these causal structures. Furthermore, we propose an alternative method for extracting exercise relation DAGs using DKT's learned representations and provide empirical evidence supporting our claim. Our findings suggest that DKT's effectiveness is largely driven by its capacity to approximate causal dependencies between KCs rather than simple relational mappings.

---

### Direct Semantic Communication Between Large Language Models via Vector Translation

Authors: Fu-Chun Yang, Jason Eshraghian
Published: 2025-11-06
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2511.03945v1

In multi-agent settings, such as debate, reflection, or tool-calling, large language models (LLMs) pass messages as plain tokens, discarding most latent semantics. This constrains information transfer and adds unnecessary computational overhead. We form a latent bridge via vector translations, which use learned mappings that enable direct semantic exchange between representation spaces. A dual-encoder translator trained between Llama-2-7B and Mistral-7B-Instruct attains an average cosine alignment of 0.538. Injecting the translated vectors at 30 percent blending strength steers the target model's generation without destabilizing logits. Bidirectional evaluation shows a 2.01:1 transfer asymmetry, indicating that general-purpose models yield more transferable representations than instruction-tuned variants. This conservative injection preserves computational stability while demonstrating that cross-model latent communication is feasible, enabling collaborative AI systems that share meaning rather than tokens.

---

### Temporal Zoom Networks: Distance Regression and Continuous Depth for Efficient Action Localization

Authors: Ibne Farabi Shihab, Sanjeda Akter, Anuj Sharma
Published: 2025-11-06
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.03943v3

Temporal action localization requires both precise boundary detection and computational efficiency. Current methods apply uniform computation across all temporal positions, wasting resources on easy boundaries while struggling with ambiguous ones. We address this through two complementary innovations: Boundary Distance Regression (BDR), which replaces classification-based boundary detection with signed-distance regression achieving 3.3--16.7$\times$ lower variance; and Adaptive Temporal Refinement (ATR), which allocates transformer depth continuously ($τ\in(0,1)$) to concentrate computation near difficult boundaries. On THUMOS14, our method achieves 56.5\% mAP@0.7 and 58.2\% average mAP@(0.3:0.7) with 151G FLOPs, using 36\% fewer FLOPs than ActionFormer++ (55.7\% mAP@0.7 at 235G). Compared to uniform baselines, we achieve +2.9\% mAP@0.7 (+1.8\% avg mAP, 5.4\% relative) with 24\% fewer FLOPs and 29\% lower latency, with particularly strong gains on short actions (+4.2\%, 8.6\% relative). Training requires 1.29$\times$ baseline FLOPs, but this one-time cost is amortized over many inference runs; knowledge distillation further reduces this to 1.1$\times$ while retaining 99.5\% accuracy. Our contributions include: (i) a theoretically-grounded distance formulation with information-theoretic analysis showing optimal variance scaling; (ii) a continuous depth allocation mechanism avoiding discrete routing complexity; and (iii) consistent improvements across four datasets with gains correlating with boundary heterogeneity.

---

### MIDI-LLM: Improving Text-to-MIDI Music Generation via Adapting Large Language Models

Authors: Shih-Lun Wu, Dave Carlton, Ryan Miyakawa, Yoon Kim, Chris Donahue, Cheng-Zhi Anna Huang
Published: 2025-11-06
Categories: cs.SD, cs.CL, cs.MM
arXiv: https://arxiv.org/abs/2511.03942v2

We present MIDI-LLM, a recipe that improves multitrack text-to-MIDI generation via adapting Large Language Models (LLMs). MIDI-LLM expands an LLM's text vocabulary to include MIDI tokens and employs a two-stage training pipeline: (i) unimodal continued pretraining on music-adjacent text and standalone MIDIs, and (ii) multimodal supervised finetuning on text-MIDI pairs. Our instantiation of MIDI-LLM based on Llama 3.2 (1B) outperforms the recent Text2midi model in both text control and musical quality, and readily integrates with optimized inference ecosystems like vLLM. To align with real-world songwriting workflows, we further finetune our MIDI-LLM on the TheoryTab dataset for text-conditioned lead sheet (i.e., melody + chords) generation and infilling. A comprehensive ablation study validates the synergy between LLM text pretraining, standalone MIDI pretraining, and supervised text-to-MIDI finetuning. Finally, an in-the-wild blind user study conducted in a real-world creative workflow at scale with 58 Hookpad Aria users and 4,002 generated outputs demonstrates that our MIDI-LLM achieves the highest acceptance rate in zero-to-one lead sheet generation over baselines without text control or LLM pretraining, confirming its efficacy in human-AI music co-creation.

---

### RLHF: A comprehensive Survey for Cultural, Multimodal and Low Latency Alignment Methods

Authors: Raghav Sharma, Manan Mehta, Sai Tiger Raina
Published: 2025-11-06
Categories: cs.LG, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2511.03939v1

Reinforcement Learning from Human Feedback (RLHF) is the standard for aligning Large Language Models (LLMs), yet recent progress has moved beyond canonical text-based methods. This survey synthesizes the new frontier of alignment research by addressing critical gaps in multi-modal alignment, cultural fairness, and low-latency optimization. To systematically explore these domains, we first review foundational algo- rithms, including PPO, DPO, and GRPO, before presenting a detailed analysis of the latest innovations. By providing a comparative synthesis of these techniques and outlining open challenges, this work serves as an essential roadmap for researchers building more robust, efficient, and equitable AI systems.

---

### LogHD: Robust Compression of Hyperdimensional Classifiers via Logarithmic Class-Axis Reduction

Authors: Sanggeon Yun, Hyunwoo Oh, Ryozo Masukawa, Pietro Mercati, Nathaniel D. Bastian, Mohsen Imani
Published: 2025-11-06
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.03938v2

Hyperdimensional computing (HDC) suits memory, energy, and reliability-constrained systems, yet the standard "one prototype per class" design requires $O(CD)$ memory (with $C$ classes and dimensionality $D$). Prior compaction reduces $D$ (feature axis), improving storage/compute but weakening robustness. We introduce LogHD, a logarithmic class-axis reduction that replaces the $C$ per-class prototypes with $n\!\approx\!\lceil\log_k C\rceil$ bundle hypervectors (alphabet size $k$) and decodes in an $n$-dimensional activation space, cutting memory to $O(D\log_k C)$ while preserving $D$. LogHD uses a capacity-aware codebook and profile-based decoding, and composes with feature-axis sparsification. Across datasets and injected bit flips, LogHD attains competitive accuracy with smaller models and higher resilience at matched memory. Under equal memory, it sustains target accuracy at roughly $2.5$-$3.0\times$ higher bit-flip rates than feature-axis compression; an ASIC instantiation delivers $498\times$ energy efficiency and $62.6\times$ speedup over an AMD Ryzen 9 9950X and $24.3\times$/$6.58\times$ over an NVIDIA RTX 4090, and is $4.06\times$ more energy-efficient and $2.19\times$ faster than a feature-axis HDC ASIC baseline.

---

### PEFA-AI: Advancing Open-source LLMs for RTL generation using Progressive Error Feedback Agentic-AI

Authors: Athma Narayanan, Mahesh Subedar, Omesh Tickoo
Published: 2025-11-06
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2511.03934v1

We present an agentic flow consisting of multiple agents that combine specialized LLMs and hardware simulation tools to collaboratively complete the complex task of Register Transfer Level (RTL) generation without human intervention. A key feature of the proposed flow is the progressive error feedback system of agents (PEFA), a self-correcting mechanism that leverages iterative error feedback to progressively increase the complexity of the approach. The generated RTL includes checks for compilation, functional correctness, and synthesizable constructs. To validate this adaptive approach to code generation, benchmarking is performed using two opensource natural language-to-RTL datasets. We demonstrate the benefits of the proposed approach implemented on an open source agentic framework, using both open- and closed-source LLMs, effectively bridging the performance gap between them. Compared to previously published methods, our approach sets a new benchmark, providing state-of-the-art pass rates while being efficient in token counts.

---

### NVIDIA Nemotron Nano V2 VL

Authors: NVIDIA, :, Amala Sanjay Deshmukh, Kateryna Chumachenko, Tuomas Rintamaki, Matthieu Le, Tyler Poon, Danial Mohseni Taheri, Ilia Karmanov, Guilin Liu, Jarno Seppanen, Guo Chen et al.
Published: 2025-11-06
Categories: cs.LG, cs.AI, cs.CV
arXiv: https://arxiv.org/abs/2511.03929v2

We introduce Nemotron Nano V2 VL, the latest model of the Nemotron vision-language series designed for strong real-world document understanding, long video comprehension, and reasoning tasks. Nemotron Nano V2 VL delivers significant improvements over our previous model, Llama-3.1-Nemotron-Nano-VL-8B, across all vision and text domains through major enhancements in model architecture, datasets, and training recipes. Nemotron Nano V2 VL builds on Nemotron Nano V2, a hybrid Mamba-Transformer LLM, and innovative token reduction techniques to achieve higher inference throughput in long document and video scenarios. We are releasing model checkpoints in BF16, FP8, and FP4 formats and sharing large parts of our datasets, recipes and training code.

---

### SynQuE: Estimating Synthetic Dataset Quality Without Annotations

Authors: Arthur Chen, Victor Zhong
Published: 2025-11-06
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.03928v5

We introduce and formalize the Synthetic Dataset Quality Estimation (SynQuE) problem: ranking synthetic datasets by their expected real-world task performance using only limited unannotated real data. This addresses a critical and open challenge where data is scarce due to collection costs or privacy constraints. We establish the first comprehensive benchmarks for this problem by introducing and evaluating proxy metrics that choose synthetic data for training to maximize task performance on real data. We introduce the first proxy metrics for SynQuE by adapting distribution and diversity-based distance measures to our context via embedding models. To address the shortcomings of these metrics on complex planning tasks, we propose LENS, a novel proxy that leverages large language model reasoning. Our results show that SynQuE proxies correlate with real task performance across diverse tasks, including sentiment analysis, Text2SQL, web navigation, and image classification, with LENS consistently outperforming others on complex tasks by capturing nuanced characteristics. For instance, on text-to-SQL parsing, training on the top-3 synthetic datasets selected via SynQuE proxies can raise accuracy from 30.4% to 38.4 (+8.1)% on average compared to selecting data indiscriminately. This work establishes SynQuE as a practical framework for synthetic data selection under real-data scarcity and motivates future research on foundation model-based data characterization and fine-grained data selection. We release our code.

---

### Collaborative Agents for Automated Program Repair in Ruby

Authors: Nikta Akbarpour, Mahdieh Sadat Benis, Fatemeh Hendijani Fard, Ali Ouni, Mohamed Aymen Saied
Published: 2025-11-06
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2511.03925v1

Automated Program Repair (APR) has advanced rapidly with Large Language Models (LLMs), but most existing methods remain computationally expensive, and focused on a small set of languages. Ruby, despite its widespread use in web development and the persistent challenges faced by its developers, has received little attention in APR research. In this paper, we introduce RAMP, a novel lightweight framework that formulates program repair as a feedback-driven, iterative process for Ruby. RAMP employs a team of collaborative agents that generate targeted tests, reflect on errors, and refine candidate fixes until a correct solution is found. Unlike prior approaches, RAMP is designed to avoid reliance on large multilingual repair databases or costly fine-tuning, instead operating directly on Ruby through lightweight prompting and test-driven feedback. Evaluation on the XCodeEval benchmark shows that RAMP achieves a pass@1 of 67% on Ruby, outper-forming prior approaches. RAMP converges quickly within five iterations, and ablation studies confirm that test generation and self-reflection are key drivers of its performance. Further analysis shows that RAMP is particularly effective at repairing wrong answers, compilation errors, and runtime errors. Our approach provides new insights into multi-agent repair strategies, and establishes a foundation for extending LLM-based debugging tools to under-studied languages.

---

### On Predicting Sociodemographics from Mobility Signals

Authors: Ekin Uğurel, Cynthia Chen, Brian H. Y. Lee, Filipe Rodrigues
Published: 2025-11-06
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.03924v1

Inferring sociodemographic attributes from mobility data could help transportation planners better leverage passively collected datasets, but this task remains difficult due to weak and inconsistent relationships between mobility patterns and sociodemographic traits, as well as limited generalization across contexts. We address these challenges from three angles. First, to improve predictive accuracy while retaining interpretability, we introduce a behaviorally grounded set of higher-order mobility descriptors based on directed mobility graphs. These features capture structured patterns in trip sequences, travel modes, and social co-travel, and significantly improve prediction of age, gender, income, and household structure over baselines features. Second, we introduce metrics and visual diagnostic tools that encourage evenness between model confidence and accuracy, enabling planners to quantify uncertainty. Third, to improve generalization and sample efficiency, we develop a multitask learning framework that jointly predicts multiple sociodemographic attributes from a shared representation. This approach outperforms single-task models, particularly when training data are limited or when applying models across different time periods (i.e., when the test set distribution differs from the training set).

---

### EvalCards: A Framework for Standardized Evaluation Reporting

Authors: Ruchira Dhar, Danae Sanchez Villegas, Antonia Karamolegkou, Alice Schiavone, Yifei Yuan, Xinyi Chen, Jiaang Li, Stella Frank, Laura De Grazia, Monorama Swain, Stephanie Brandl, Daniel Hershcovich et al.
Published: 2025-11-05
Categories: cs.CL, cs.AI, cs.CY
arXiv: https://arxiv.org/abs/2511.21695v1

Evaluation has long been a central concern in NLP, and transparent reporting practices are more critical than ever in today's landscape of rapidly released open-access models. Drawing on a survey of recent work on evaluation and documentation, we identify three persistent shortcomings in current reporting practices: reproducibility, accessibility, and governance. We argue that existing standardization efforts remain insufficient and introduce Evaluation Disclosure Cards (EvalCards) as a path forward. EvalCards are designed to enhance transparency for both researchers and practitioners while providing a practical foundation to meet emerging governance requirements.

---

### A Genetic Algorithm for Optimizing Fantasy Football Trades with Playoff Biasing

Authors: Evan Parshall, Junaid Ali, Michael Zimmerman
Published: 2025-11-05
Categories: cs.NE
arXiv: https://arxiv.org/abs/2511.17535v1

Fantasy football leagues involve strategic player trades to optimize team performance. However, identifying optimal trades is complex due to varying player projections, positional needs, and league-specific scoring. Existing approaches focus on team selection or lineup optimization, but automated trade generation remains underexplored. In this paper, an algorithm that generates optimal trades, biasing toward improved playoff performance while maintaining apparent fairness for negotiation is explored. We introduce a genetic algorithm for fantasy football trade optimization, building on existing frameworks for team selection and lineup generation. The algorithm initializes with single-player trades, evolves through custom mutations (add/remove players, combine trades, exchange players, add from other trades, and spawn new trades), and uses team-specific elitism to preserve diversity. The cost function incorporates a playoff-weighted gain for the user's team (while maintaining apparent fairness), opponent gain, and fairness penalty. Integration with ESPN data sources enables real-time projections for all positions, including kickers and defenses. On a 12-team ESPN league (Week 8, 2025), the algorithm generated trades that upgraded the projected point totals of both the trade initiator and trade partner by nearly 3 fantasy points per week ensuring positive gains for both teams. The algorithm demonstrates effective trade optimization, with potential extensions to other fantasy sports or combinatorial problems requiring temporal biasing. Open-source implementation enables practical use and further research.

---

### Learning Interestingness in Automated Mathematical Theory Formation

Authors: George Tsoukalas, Rahul Saha, Amitayush Thakur, Sabrina Reguyal, Swarat Chaudhuri
Published: 2025-11-05
Categories: cs.AI
arXiv: https://arxiv.org/abs/2511.14778v1

We take two key steps in automating the open-ended discovery of new mathematical theories, a grand challenge in artificial intelligence. First, we introduce $\emph{FERMAT}$, a reinforcement learning (RL) environment that models concept discovery and theorem-proving using a set of symbolic actions, opening up a range of RL problems relevant to theory discovery. Second, we explore a specific problem through $\emph{FERMAT}$: automatically scoring the $\emph{interestingness}$ of mathematical objects. We investigate evolutionary algorithms for synthesizing nontrivial interestingness measures. In particular, we introduce an LLM-based evolutionary algorithm that features function abstraction, leading to notable improvements in discovering elementary number theory and finite fields over hard-coded baselines. We open-source the $\emph{FERMAT}$ environment at this URL(https://github.com/trishullab/Fermat).

---

### The Illusion of Procedural Reasoning: Measuring Long-Horizon FSM Execution in LLMs

Authors: Mahdi Samiei, Mahdi Mansouri, Mahdieh Soleymani Baghshah
Published: 2025-11-05
Categories: cs.AI
arXiv: https://arxiv.org/abs/2511.14777v1

Large language models (LLMs) have achieved remarkable results on tasks framed as reasoning problems, yet their true ability to perform procedural reasoning, executing multi-step, rule-based computations remains unclear. Unlike algorithmic systems, which can deterministically execute long-horizon symbolic procedures, LLMs often degrade under extended reasoning chains, but there is no controlled, interpretable benchmark to isolate and measure this collapse. We introduce Finite-State Machine (FSM) Execution as a minimal, fully interpretable framework for evaluating the procedural reasoning capacity of LLMs. In our setup, the model is given an explicit FSM definition and must execute it step-by-step given input actions, maintaining state consistency over multiple turns. This task requires no world knowledge, only faithful application of deterministic transition rules, making it a direct probe of the model's internal procedural fidelity. We measure both Turn Accuracy and Task Accuracy to disentangle immediate computation from cumulative state maintenance. Empirical results reveal systematic degradation as task horizon or branching complexity increases. Models perform significantly worse when rule retrieval involves high branching factors than when memory span is long. Larger models show improved local accuracy but remain brittle under multi-step reasoning unless explicitly prompted to externalize intermediate steps. FSM-based evaluation offers a transparent, complexity-controlled probe for diagnosing this failure mode and guiding the design of inductive biases that enable genuine long-horizon procedural competence. By grounding reasoning in measurable execution fidelity rather than surface correctness, this work helps establish a rigorous experimental foundation for understanding and improving the algorithmic reliability of LLMs.

---

### COMPASS: Context-Modulated PID Attention Steering System for Hallucination Mitigation

Authors: Kenji Sahay, Snigdha Pandya, Rohan Nagale, Anna Lin, Shikhar Shiromani, Kevin Zhu, Dev Sunishchal
Published: 2025-11-05
Categories: cs.CL
arXiv: https://arxiv.org/abs/2511.14776v2

Large language models (LLMs) often generate fluent but factually incorrect statements despite having access to relevant evidence, a failure mode rooted in how they allocate attention between contextual and parametric knowledge. Understanding and steering this internal behavior is key both for trustworthy deployment and for scientific interpretability of model mechanisms. We introduce COMPASS (Context-Modulated PID Attention Steering System), a lightweight, interpretable control framework that embeds a model-based feedback loop directly within decoding. COMPASS quantifies context reliance via a transparent metric, the Context Reliance Score (CRS), which serves as an online probe of how attention heads ground generation in evidence. Using this interpretable signal, a PID controller dynamically modulates attention heads to maintain factual consistency without retraining or multi-pass decoding. Across benchmarks (HotpotQA, XSum, HaluEval, RAGTruth), COMPASS consistently reduces contextual hallucination rates (2.8 to 5.8 percent absolute) while revealing how distinct attention heads contribute to evidence alignment. These results highlight feedback-driven interpretability as a pathway toward scientific understanding of LLM behavior.

---

### MS2Edge: Towards Energy-Efficient and Crisp Edge Detection with Multi-Scale Residual Learning in SNNs

Authors: Yimeng Fan, Changsong Liu, Mingyang Li, Yuzhou Dai, Yanyan Liu, Wei Zhang
Published: 2025-11-05
Categories: cs.NE, eess.IV
arXiv: https://arxiv.org/abs/2511.13735v1

Edge detection with Artificial Neural Networks (ANNs) has achieved remarkable prog\-ress but faces two major challenges. First, it requires pre-training on large-scale extra data and complex designs for prior knowledge, leading to high energy consumption. Second, the predicted edges perform poorly in crispness and heavily rely on post-processing. Spiking Neural Networks (SNNs), as third generation neural networks, feature quantization and spike-driven computation mechanisms. They inherently provide a strong prior for edge detection in an energy-efficient manner, while its quantization mechanism helps suppress texture artifact interference around true edges, improving prediction crispness. However, the resulting quantization error inevitably introduces sparse edge discontinuities, compromising further enhancement of crispness. To address these challenges, we propose MS2Edge, the first SNN-based model for edge detection. At its core, we build a novel spiking backbone named MS2ResNet that integrates multi-scale residual learning to recover missing boundary lines and generate crisp edges, while combining I-LIF neurons with Membrane-based Deformed Shortcut (MDS) to mitigate quantization errors. The model is complemented by a Spiking Multi-Scale Upsample Block (SMSUB) for detail reconstruction during upsampling and a Membrane Average Decoding (MAD) method for effective integration of edge maps across multiple time steps. Experimental results demonstrate that MS2Edge outperforms ANN-based methods and achieves state-of-the-art performance on the BSDS500, NYUDv2, BIPED, PLDU, and PLDM datasets without pre-trained backbones, while maintaining ultralow energy consumption and generating crisp edge maps without post-processing.

---

### Extended Physics Informed Neural Network for Hyperbolic Two-Phase Flow in Porous Media

Authors: Saif Ur Rehman, Wajid Yousuf
Published: 2025-11-05
Categories: cs.LG, math.NA, physics.comp-ph, physics.flu-dyn
arXiv: https://arxiv.org/abs/2511.13734v2

The accurate solution of nonlinear hyperbolic partial differential equations (PDEs) remains challenging due to steep gradients, discontinuities, and multiscale structures that make conventional solvers computationally demanding. Physics-Informed Neural Networks (PINNs) embed the governing equations into the learning process, enabling mesh-free solution of PDEs, yet they often struggle to capture steep gradients, discontinuities, and complex nonlinear wave interactions. To address these limitations, we employ the Extended Physics-Informed Neural Network (XPINN) framework to solve the nonlinear Buckley-Leverett equation with a nonconvex flux, modeling immiscible two-phase flow in porous media. The computational domain is dynamically decomposed in space and time into evolving pre-shock and post-shock subdomains, allowing localized subnetworks to efficiently learn distinct flow behaviors, with coupling enforced via the Rankine-Hugoniot jump condition to ensure physically consistent flux continuity. We compare XPINN with standard PINNs and its variants, including PINN with artificial viscosity, PINN with Welge construction, and PINN with the Oleinik entropy condition, and across all cases, XPINN consistently outperforms the other methods, accurately resolving sharp fronts and capturing the correct physical behavior. Importantly, XPINN achieves this using the simpler Adam optimizer, whereas some PINN variants require more complex or higher-order strategies such as L-BFGS to reach comparable accuracy, demonstrating that XPINN is a robust and scalable approach for challenging hyperbolic PDEs without artificial diffusion or entropy corrections. The code is available at github.com/saifkhanengr/XPINN-for-Buckley-Leverett.

---

### THD-BAR: Topology Hierarchical Derived Brain Autoregressive Modeling for EEG Generic Representations

Authors: Wenchao Yang, Weidong Yan, Wenkang Liu, Yulan Ma, Yang Li
Published: 2025-11-05
Categories: eess.SP, cs.LG, q-bio.NC
arXiv: https://arxiv.org/abs/2511.13733v1

Large-scale pre-trained models hold significant potential for learning universal EEG representations. However, most existing methods, particularly autoregressive (AR) frameworks, primarily rely on straightforward temporal sequencing of multi-channel EEG data, which fails to capture the rich physiological characteristics inherent to EEG signals. Moreover, their time-centered modeling approach also limits the effective representation of the dynamic spatial topology of brain activity. To address these challenges and fully exploit the potential of large-scale EEG models, we propose a novel Topology Hierarchical Derived Brain Autoregressive Modeling (THD-BAR) for EEG generic representations. The core innovation of THD-BAR lies in the introduction of the Brain Topology Hierarchy (BTH), which establishes a multi-scale spatial order for EEG channels. This hierarchical structure enables a redefinition of autoregressive learning as a "next-scale-time prediction" problem, effectively capturing both spatial and temporal dynamics. Based on BTH, we design a Topology-Hierarchical Vector Quantized-Variational Autoencoder (THVQ-VAE) for multi-scale tokenization and develop an enhanced Brain Autoregressive (BAR) module with specialized masking strategies for prediction. Through extensive large-scale pre-training on 17 datasets, followed by rigorous validation on 10 downstream datasets spanning 5 distinct tasks, THD-BAR consistently outperforms existing methods. These results highlight the superior generalization and modeling capabilities of our proposed approach.

---

### Principled Coarse-Grained Acceptance for Speculative Decoding in Speech

Authors: Moran Yanuka, Paul Dixon, Eyal Finkelshtein, Daniel Rotman, Raja Giryes
Published: 2025-11-05
Categories: eess.AS, cs.LG
arXiv: https://arxiv.org/abs/2511.13732v4

Speculative decoding accelerates autoregressive speech generation by letting a fast draft model propose tokens that a larger target model verifies. However, for speech LLMs that generate acoustic tokens, exact token matching is overly restrictive: many discrete tokens are acoustically or semantically interchangeable, reducing acceptance rates and limiting speedups. We introduce Principled Coarse-Graining (PCG), which verifies proposals at the level of Acoustic Similarity Groups (ASGs) derived from the target model's embedding space. By splitting each token's probability mass across the overlapping groups that contain it, we define an overlap-aware coarse-grained distribution and perform rejection sampling on the resulting group variable. This yields an exactness guarantee at the group level while allowing the accepted draft token to stand in for any member of the group in practice. On LibriTTS, PCG increases acceptance and throughput relative to standard speculative decoding and prior speech-specific relaxations while maintaining intelligibility and speaker similarity. These results suggest acoustically aware, group-level acceptance as a simple and general way to accelerate speech token generation while maintaining speech quality.

---

### Hierarchical Federated Graph Attention Networks for Scalable and Resilient UAV Collision Avoidance

Authors: Rathin Chandra Shit, Sharmila Subudhi
Published: 2025-11-05
Categories: cs.RO, cs.AI, cs.LG, cs.MA
arXiv: https://arxiv.org/abs/2511.11616v1

The real-time performance, adversarial resiliency, and privacy preservation are the most important metrics that need to be balanced to practice collision avoidance in large-scale multi-UAV (Unmanned Aerial Vehicle) systems. Current frameworks tend to prescribe monolithic solutions that are not only prohibitively computationally complex with a scaling cost of $O(n^2)$ but simply do not offer Byzantine fault tolerance. The proposed hierarchical framework presented in this paper tries to eliminate such trade-offs by stratifying a three-layered architecture. We spread the intelligence into three layers: an immediate collision avoiding local layer running on dense graph attention with latency of $<10 ms$, a regional layer using sparse attention with $O(nk)$ computational complexity and asynchronous federated learning with coordinate-wise trimmed mean aggregation, and lastly, a global layer using a lightweight Hashgraph-inspired protocol. We have proposed an adaptive differential privacy mechanism, wherein the noise level $(ε\in (0.1, 1.0))$ is dynamically reduced based on an evaluation of the measured real-time threat that in turn maximized the privacy-utility tradeoff. Through the use of Distributed Hash Table (DHT)-based lightweight audit logging instead of heavyweight blockchain consensus, the median cost of getting a $95^{th}$ percentile decision within 50ms is observed across all tested swarm sizes. This architecture provides a scalable scenario of 500 UAVs with a collision rate of $< 2.0\%$ and the Byzantine fault tolerance of $f < n/3$.

---

### Evaluating Modern Large Language Models on Low-Resource and Morphologically Rich Languages:A Cross-Lingual Benchmark Across Cantonese, Japanese, and Turkish

Authors: Chengxuan Xia, Qianye Wu, Hongbin Guan, Sixuan Tian, Yilun Hao, Xiaoyu Wu
Published: 2025-11-05
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2511.10664v2

Large language models (LLMs) have achieved impressive results in high-resource languages like English, yet their effectiveness in low-resource and morphologically rich languages remains underexplored. In this paper, we present a comprehensive evaluation of seven cutting-edge LLMs -- including GPT-4o, GPT-4, Claude~3.5~Sonnet, LLaMA~3.1, Mistral~Large~2, LLaMA-2~Chat~13B, and Mistral~7B~Instruct -- on a new cross-lingual benchmark covering \textbf{Cantonese, Japanese, and Turkish}. Our benchmark spans four diverse tasks: open-domain question answering, document summarization, English-to-X translation, and culturally grounded dialogue. We combine \textbf{human evaluations} (rating fluency, factual accuracy, and cultural appropriateness) with automated metrics (e.g., BLEU, ROUGE) to assess model performance. Our results reveal that while the largest proprietary models (GPT-4o, GPT-4, Claude~3.5) generally lead across languages and tasks, significant gaps persist in culturally nuanced understanding and morphological generalization. Notably, GPT-4o demonstrates robust multilingual performance even on cross-lingual tasks, and Claude~3.5~Sonnet achieves competitive accuracy on knowledge and reasoning benchmarks. However, all models struggle to some extent with the unique linguistic challenges of each language, such as Turkish agglutinative morphology and Cantonese colloquialisms. Smaller open-source models (LLaMA-2~13B, Mistral~7B) lag substantially in fluency and accuracy, highlighting the resource disparity. We provide detailed quantitative results, qualitative error analysis, and discuss implications for developing more culturally aware and linguistically generalizable LLMs. Our benchmark and evaluation data are released to foster reproducibility and further research.

---

### A Super-Learner with Large Language Models for Medical Emergency Advising

Authors: Sergey K. Aityan, Abdolreza Mosaddegh, Rolando Herrero, Haitham Tayyar, Jiang Han, Vikram Sawant, Qi Chen, Rishabh Jain, Aruna Senthamaraikannan, Stephen Wood, Manuel Mersini, Rita Lazzaro et al.
Published: 2025-11-05
Categories: cs.CL
arXiv: https://arxiv.org/abs/2511.08614v2

Medical decision-support and advising systems are critical for emergency physicians to quickly and accurately assess patients' conditions and make diagnosis. Artificial Intelligence (AI) has emerged as a transformative force in healthcare in recent years and Large Language Models (LLMs) have been employed in various fields of medical decision-support systems. We studied responses of a group of different LLMs to real cases in emergency medicine. The results of our study on five most renown LLMs showed significant differences in capabilities of Large Language Models for diagnostics acute diseases in medical emergencies with accuracy ranging between 58% and 65%. This accuracy significantly exceeds the reported accuracy of human doctors. We built a super-learner MEDAS (Medical Emergency Diagnostic Advising System) of five major LLMs - Gemini, Llama, Grok, GPT, and Claude). The super-learner produces higher diagnostic accuracy, 70%, even with a quite basic meta-learner. However, at least one of the integrated LLMs in the same super-learner produces 85% correct diagnoses. The super-learner integrates a cluster of LLMs using a meta-learner capable of learning different capabilities of each LLM to leverage diagnostic accuracy of the model by collective capabilities of all LLMs in the cluster. The results of our study showed that aggregated diagnostic accuracy provided by a meta-learning approach exceeds that of any individual LLM, suggesting that the super-learner can take advantage of the combined knowledge of the medical datasets used to train the group of LLMs.

---

### Assessing Identity Leakage in Talking Face Generation: Metrics and Evaluation Framework

Authors: Dogucan Yaman, Fevziye Irem Eyiokur, Hazım Kemal Ekenel, Alexander Waibel
Published: 2025-11-05
Categories: cs.CV, eess.IV
arXiv: https://arxiv.org/abs/2511.08613v2

Video editing-based talking face generation aims to preserve video details such as pose, lighting, and gestures while modifying only lip motion, often using an identity reference image to maintain speaker consistency. However, this mechanism can introduce lip leakage, where generated lips are influenced by the reference image rather than solely by the driving audio. Such leakage is difficult to detect with standard metrics and conventional test setup. To address this, we propose a systematic evaluation methodology to analyze and quantify lip leakage. Our framework employs three complementary test setups: silent-input generation, mismatched audio-video pairing, and matched audio-video synthesis. We also introduce derived metrics including lip-sync discrepancy and silent-audio-based lip-sync scores. In addition, we study how different identity reference selections affect leakage, providing insights into reference design. The proposed methodology is model-agnostic and establishes a more reliable benchmark for future research in talking face generation.

---

### Learning based Modelling of Throttleable Engine Dynamics for Lunar Landing Mission

Authors: Suraj Kumar, Aditya Rallapalli, Bharat Kumar GVP
Published: 2025-11-05
Categories: eess.SY, cs.LG
arXiv: https://arxiv.org/abs/2511.08612v1

Typical lunar landing missions involve multiple phases of braking to achieve soft-landing. The propulsion system configuration for these missions consists of throttleable engines. This configuration involves complex interconnected hydraulic, mechanical, and pneumatic components each exhibiting non-linear dynamic characteristics. Accurate modelling of the propulsion dynamics is essential for analyzing closed-loop guidance and control schemes during descent. This paper presents a learning-based system identification approach for modelling of throttleable engine dynamics using data obtained from high-fidelity propulsion model. The developed model is validated with experimental results and used for closed-loop guidance and control simulations.

---

### MoE-GraphSAGE-Based Integrated Evaluation of Transient Rotor Angle and Voltage Stability in Power Systems

Authors: Kunyu Zhang, Guang Yang, Fashun Shi, Shaoying He, Yuchi Zhang
Published: 2025-11-05
Categories: eess.SY, cs.LG
arXiv: https://arxiv.org/abs/2511.08610v1

The large-scale integration of renewable energy and power electronic devices has increased the complexity of power system stability, making transient stability assessment more challenging. Conventional methods are limited in both accuracy and computational efficiency. To address these challenges, this paper proposes MoE-GraphSAGE, a graph neural network framework based on the MoE for unified TAS and TVS assessment. The framework leverages GraphSAGE to capture the power grid's spatiotemporal topological features and employs multi-expert networks with a gating mechanism to model distinct instability modes jointly. Experimental results on the IEEE 39-bus system demonstrate that MoE-GraphSAGE achieves superior accuracy and efficiency, offering an effective solution for online multi-task transient stability assessment in complex power systems.

---

### Case Study: Transformer-Based Solution for the Automatic Digitization of Gas Plants

Authors: I. Bailo, F. Buonora, G. Ciarfaglia, L. T. Consoli, A. Evangelista, M. Gabusi, M. Ghiani, C. Petracca Ciavarella, F. Picariello, F. Sarcina, F. Tuosto, V. Zullo et al.
Published: 2025-11-05
Categories: cs.CV, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2511.08609v1

The energy transition is a key theme of the last decades to determine a future of eco-sustainability, and an area of such importance cannot disregard digitization, innovation and the new technological tools available. This is the context in which the Generative Artificial Intelligence models described in this paper are positioned, developed by Engineering Ingegneria Informatica SpA in order to automate the plant structures acquisition of SNAM energy infrastructure, a leading gas transportation company in Italy and Europe. The digitization of a gas plant consists in registering all its relevant information through the interpretation of the related documentation. The aim of this work is therefore to design an effective solution based on Artificial Intelligence techniques to automate the extraction of the information necessary for the digitization of a plant, in order to streamline the daily work of MGM users. The solution received the P&ID of the plant as input, each one in pdf format, and uses OCR, Vision LLM, Object Detection, Relational Reasoning and optimization algorithms to return an output consisting of two sets of information: a structured overview of the relevant design data and the hierarchical framework of the plant. To achieve convincing results, we extend a state-of-the-art model for Scene Graph Generation introducing a brand new Transformer architecture with the aim of deepening the analysis of the complex relations between the plant's components. The synergistic use of the listed AI-based technologies allowed to overcome many obstacles arising from the high variety of data, due to the lack of standardization. An accuracy of 91\% has been achieved in the extraction of textual information relating to design data. Regarding the plants topology, 93\% of components are correctly identified and the hierarchical structure is extracted with an accuracy around 80\%.

---

### Data-driven Feynman-Kac Discovery with Applications to Prediction and Data Generation

Authors: Qi Feng, Guang Lin, Purav Matlia, Denny Serdarevic
Published: 2025-11-05
Categories: q-fin.MF, cs.AI, q-fin.CP
arXiv: https://arxiv.org/abs/2511.08606v1

In this paper, we propose a novel data-driven framework for discovering probabilistic laws underlying the Feynman-Kac formula. Specifically, we introduce the first stochastic SINDy method formulated under the risk-neutral probability measure to recover the backward stochastic differential equation (BSDE) from a single pair of stock and option trajectories. Unlike existing approaches to identifying stochastic differential equations-which typically require ergodicity-our framework leverages the risk-neutral measure, thereby eliminating the ergodicity assumption and enabling BSDE recovery from limited financial time series data. Using this algorithm, we are able not only to make forward-looking predictions but also to generate new synthetic data paths consistent with the underlying probabilistic law.

---

### Exploring the Psychometric Validity of AI-Generated Student Responses: A Study on Virtual Personas' Learning Motivation

Authors: Huanxiao Wang
Published: 2025-11-05
Categories: cs.CY, cs.AI
arXiv: https://arxiv.org/abs/2511.07451v1

This study explores whether large language models (LLMs) can simulate valid student responses for educational measurement. Using GPT -4o, 2000 virtual student personas were generated. Each persona completed the Academic Motivation Scale (AMS). Factor analyses(EFA and CFA) and clustering showed GPT -4o reproduced the AMS structure and distinct motivational subgroups.

---

### Large Language Models for Scientific Idea Generation: A Creativity-Centered Survey

Authors: Fatemeh Shahhosseini, Arash Marioriyad, Ali Momen, Mahdieh Soleymani Baghshah, Mohammad Hossein Rohban, Shaghayegh Haghjooy Javanmard
Published: 2025-11-05
Categories: cs.CL
arXiv: https://arxiv.org/abs/2511.07448v2

Scientific idea generation is central to discovery, requiring the joint satisfaction of novelty and scientific soundness. Unlike standard reasoning or general creative generation, scientific ideation is inherently open-ended and multi-objective, making its automation particularly challenging. Recent advances in large language models (LLMs) have enabled the generation of coherent and plausible scientific ideas, yet the nature and limits of their creative capabilities remain poorly understood. This survey provides a structured synthesis of methods for LLM-driven scientific ideation, focusing on how different approaches trade off novelty and scientific validity. We organize existing methods into five complementary families: External knowledge augmentation, Prompt-based distributional steering, Inference-time scaling, Multi-agent collaboration, and Parameter-level adaptation. To interpret their contributions, we adopt two complementary creativity frameworks: Boden taxonomy to characterize the expected level of creative novelty, and Rhodes 4Ps framework to analyze the aspects or sources of creativity emphasized by each method. By aligning methodological developments with cognitive creativity frameworks, this survey clarifies the evaluation landscape and identifies key challenges and directions for reliable and systematic LLM-based scientific discovery.

---

### From Prompts to Power: Measuring the Energy Footprint of LLM Inference

Authors: Francisco Caravaca, Ángel Cuevas, Rubén Cuevas
Published: 2025-11-05
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2511.05597v1

The rapid expansion of Large Language Models (LLMs) has introduced unprecedented energy demands, extending beyond training to large-scale inference workloads that often dominate total lifecycle consumption. Deploying these models requires energy-intensive GPU infrastructure, and in some cases has even prompted plans to power data centers with nuclear energy. Despite this growing relevance, systematic analyses of inference energy consumption remain limited. In this work, we present a large-scale measurement-based study comprising over 32,500 measurements across 21 GPU configurations and 155 model architectures, from small open-source models to frontier systems. Using the vLLM inference engine, we quantify energy usage at the prompt level and identify how architectural and operational factors shape energy demand. Building on these insights, we develop a predictive model that accurately estimates inference energy consumption across unseen architectures and hardware, and implement it as a browser extension to raise awareness of the environmental impact of generative AI.

---

### AutoHood3D: A Multi-Modal Benchmark for Automotive Hood Design and Fluid-Structure Interaction

Authors: Vansh Sharma, Harish Jai Ganesh, Maryam Akram, Wanjiao Liu, Venkat Raman
Published: 2025-11-05
Categories: cs.LG, physics.comp-ph, physics.flu-dyn
arXiv: https://arxiv.org/abs/2511.05596v1

This study presents a new high-fidelity multi-modal dataset containing 16000+ geometric variants of automotive hoods useful for machine learning (ML) applications such as engineering component design and process optimization, and multiphysics system surrogates. The dataset is centered on a practical multiphysics problem-hood deformation from fluid entrapment and inertial loading during rotary-dip painting. Each hood is numerically modeled with a coupled Large-Eddy Simulation (LES)-Finite Element Analysis (FEA), using 1.2M cells in total to ensure spatial and temporal accuracy. The dataset provides time-resolved physical fields, along with STL meshes and structured natural language prompts for text-to-geometry synthesis. Existing datasets are either confined to 2D cases, exhibit limited geometric variations, or lack the multi-modal annotations and data structures - shortcomings we address with AutoHood3D. We validate our numerical methodology, establish quantitative baselines across five neural architectures, and demonstrate systematic surrogate errors in displacement and force predictions. These findings motivate the design of novel approaches and multiphysics loss functions that enforce fluid-solid coupling during model training. By providing fully reproducible workflows, AutoHood3D enables physics-aware ML development, accelerates generative-design iteration, and facilitates the creation of new FSI benchmarks. Dataset and code URLs in Appendix.

---

### FlowNet: Modeling Dynamic Spatio-Temporal Systems via Flow Propagation

Authors: Yutong Feng, Xu Liu, Yutong Xia, Yuxuan Liang
Published: 2025-11-05
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2511.05595v1

Accurately modeling complex dynamic spatio-temporal systems requires capturing flow-mediated interdependencies and context-sensitive interaction dynamics. Existing methods, predominantly graph-based or attention-driven, rely on similarity-driven connectivity assumptions, neglecting asymmetric flow exchanges that govern system evolution. We propose Spatio-Temporal Flow, a physics-inspired paradigm that explicitly models dynamic node couplings through quantifiable flow transfers governed by conservation principles. Building on this, we design FlowNet, a novel architecture leveraging flow tokens as information carriers to simulate source-to-destination transfers via Flow Allocation Modules, ensuring state redistribution aligns with conservation laws. FlowNet dynamically adjusts the interaction radius through an Adaptive Spatial Masking module, suppressing irrelevant noise while enabling context-aware propagation. A cascaded architecture enhances scalability and nonlinear representation capacity. Experiments demonstrate that FlowNet significantly outperforms existing state-of-the-art approaches on seven metrics in the modeling of three real-world systems, validating its efficiency and physical interpretability. We establish a principled methodology for modeling complex systems through spatio-temporal flow interactions.

---

### Optimizing Predictive Maintenance in Intelligent Manufacturing: An Integrated FNO-DAE-GNN-PPO MDP Framework

Authors: Shiqing Qiu
Published: 2025-11-05
Categories: cs.LG, cs.CE
arXiv: https://arxiv.org/abs/2511.05594v1

In the era of smart manufacturing, predictive maintenance (PdM) plays a pivotal role in improving equipment reliability and reducing operating costs. In this paper, we propose a novel Markov Decision Process (MDP) framework that integrates advanced soft computing techniques - Fourier Neural Operator (FNO), Denoising Autoencoder (DAE), Graph Neural Network (GNN), and Proximal Policy Optimisation (PPO) - to address the multidimensional challenges of predictive maintenance in complex manufacturing systems. Specifically, the proposed framework innovatively combines the powerful frequency-domain representation capability of FNOs to capture high-dimensional temporal patterns; DAEs to achieve robust, noise-resistant latent state embedding from complex non-Gaussian sensor data; and GNNs to accurately represent inter-device dependencies for coordinated system-wide maintenance decisions. Furthermore, by exploiting PPO, the framework ensures stable and efficient optimisation of long-term maintenance strategies to effectively handle uncertainty and non-stationary dynamics. Experimental validation demonstrates that the approach significantly outperforms multiple deep learning baseline models with up to 13% cost reduction, as well as strong convergence and inter-module synergy. The framework has considerable industrial potential to effectively reduce downtime and operating expenses through data-driven strategies.

---

### Gradient Projection onto Historical Descent Directions for Communication-Efficient Federated Learning

Authors: Arnaud Descours, Léonard Deroose, Jan Ramon
Published: 2025-11-05
Categories: cs.LG, cs.NE, math.OC, math.ST
arXiv: https://arxiv.org/abs/2511.05593v1

Federated Learning (FL) enables decentralized model training across multiple clients while optionally preserving data privacy. However, communication efficiency remains a critical bottleneck, particularly for large-scale models. In this work, we introduce two complementary algorithms: ProjFL, designed for unbiased compressors, and ProjFL+EF, tailored for biased compressors through an Error Feedback mechanism. Both methods rely on projecting local gradients onto a shared client-server subspace spanned by historical descent directions, enabling efficient information exchange with minimal communication overhead. We establish convergence guarantees for both algorithms under strongly convex, convex, and non-convex settings. Empirical evaluations on standard FL classification benchmarks with deep neural networks show that ProjFL and ProjFL+EF achieve accuracy comparable to existing baselines while substantially reducing communication costs.

---

### GRAVER: Generative Graph Vocabularies for Robust Graph Foundation Models Fine-tuning

Authors: Haonan Yuan, Qingyun Sun, Junhua Shi, Xingcheng Fu, Bryan Hooi, Jianxin Li, Philip S. Yu
Published: 2025-11-05
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.05592v1

Inspired by the remarkable success of foundation models in language and vision, Graph Foundation Models (GFMs) hold significant promise for broad applicability across diverse graph tasks and domains. However, existing GFMs struggle with unstable few-shot fine-tuning, where both performance and adaptation efficiency exhibit significant fluctuations caused by the randomness in the support sample selection and structural discrepancies between the pre-trained and target graphs. How to fine-tune GFMs robustly and efficiently to enable trustworthy knowledge transfer across domains and tasks is the major challenge. In this paper, we propose GRAVER, a novel Generative gRAph VocabulariEs for Robust GFM fine-tuning framework that tackles the aforementioned instability via generative augmentations. Specifically, to identify transferable units, we analyze and extract key class-specific subgraph patterns by ego-graph disentanglement and validate their transferability both theoretically and empirically. To enable effective pre-training across diverse domains, we leverage a universal task template based on ego-graph similarity and construct graph vocabularies via graphon-based generative experts. To facilitate robust and efficient prompt fine-tuning, we grave the support samples with in-context vocabularies, where the lightweight MoE-CoE network attentively routes knowledge from source domains. Extensive experiments demonstrate the superiority of GRAVER over effectiveness, robustness, and efficiency on downstream few-shot node and graph classification tasks compared with 15 state-of-the-art baselines.

---

### FedSparQ: Adaptive Sparse Quantization with Error Feedback for Robust & Efficient Federated Learning

Authors: Chaimaa Medjadji, Sadi Alawadi, Feras M. Awaysheh, Guilain Leduc, Sylvain Kubler, Yves Le Traon
Published: 2025-11-05
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.05591v1

Federated Learning (FL) enables collaborative model training across decentralized clients while preserving data privacy by keeping raw data local. However, FL suffers from significant communication overhead due to the frequent exchange of high-dimensional model updates over constrained networks. In this paper, we present FedSparQ, a lightweight compression framework that dynamically sparsifies the gradient of each client through an adaptive threshold, applies half-precision quantization to retained entries and integrates residuals from error feedback to prevent loss of information. FedSparQ requires no manual tuning of sparsity rates or quantization schedules, adapts seamlessly to both homogeneous and heterogeneous data distributions, and is agnostic to model architecture. Through extensive empirical evaluation on vision benchmarks under independent and identically distributed (IID) and non-IID data, we show that FedSparQ substantially reduces communication overhead (reducing by 90% of bytes sent compared to FedAvg) while preserving or improving model accuracy (improving by 6% compared to FedAvg non-compressed solution or to state-of-the-art compression models) and enhancing convergence robustness (by 50%, compared to the other baselines). Our approach provides a practical, easy-to-deploy solution for bandwidth-constrained federated deployments and lays the groundwork for future extensions in adaptive precision and privacy-preserving protocols.

---

### Beyond Softmax: Dual-Branch Sigmoid Architecture for Accurate Class Activation Maps

Authors: Yoojin Oh, Junhyug Noh
Published: 2025-11-05
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2511.05590v1

Class Activation Mapping (CAM) and its extensions have become indispensable tools for visualizing the evidence behind deep network predictions. However, by relying on a final softmax classifier, these methods suffer from two fundamental distortions: additive logit shifts that arbitrarily bias importance scores, and sign collapse that conflates excitatory and inhibitory features. We propose a simple, architecture-agnostic dual-branch sigmoid head that decouples localization from classification. Given any pretrained model, we clone its classification head into a parallel branch ending in per-class sigmoid outputs, freeze the original softmax head, and fine-tune only the sigmoid branch with class-balanced binary supervision. At inference, softmax retains recognition accuracy, while class evidence maps are generated from the sigmoid branch -- preserving both magnitude and sign of feature contributions. Our method integrates seamlessly with most CAM variants and incurs negligible overhead. Extensive evaluations on fine-grained tasks (CUB-200-2011, Stanford Cars) and WSOL benchmarks (ImageNet-1K, OpenImages30K) show improved explanation fidelity and consistent Top-1 Localization gains -- without any drop in classification accuracy. Code is available at https://github.com/finallyupper/beyond-softmax.

---

### CoPRIS: Efficient and Stable Reinforcement Learning via Concurrency-Controlled Partial Rollout with Importance Sampling

Authors: Zekai Qu, Yinxu Pan, Ao Sun, Chaojun Xiao, Xu Han
Published: 2025-11-05
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2511.05589v1

Reinforcement learning (RL) post-training has become a trending paradigm for enhancing the capabilities of large language models (LLMs). Most existing RL systems for LLMs operate in a fully synchronous manner, where training must wait for the rollout of an entire batch to complete. This design leads to severe inefficiencies, as extremely long trajectories can stall the entire rollout process and leave many GPUs idle. To address this issue, we propose Concurrency- Controlled Partial Rollout with Importance Sampling (CoPRIS), which mitigates long-tail inefficiencies by maintaining a fixed number of concurrent rollouts, early-terminating once sufficient samples are collected, and reusing unfinished trajectories in subsequent rollouts. To mitigate the impact of off-policy trajectories, we introduce Cross-stage Importance Sampling Correction, which concatenates buffered log probabilities from the previous policy with those recomputed under the current policy for importance sampling correction. Experiments on challenging mathematical reasoning benchmarks show that CoPRIS achieves up to 1.94x faster training while maintaining comparable or superior performance to synchronous RL systems. The code of CoPRIS is available at https://github.com/777pomingzi/CoPRIS.

---

### Prompting Neural-Guided Equation Discovery Based on Residuals

Authors: Jannis Brugger, Viktor Pfanschilling, David Richter, Mira Mezini, Stefan Kramer
Published: 2025-11-05
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.05586v1

Neural-guided equation discovery systems use a data set as prompt and predict an equation that describes the data set without extensive search. However, if the equation does not meet the user's expectations, there are few options for getting other equation suggestions without intensive work with the system. To fill this gap, we propose Residuals for Equation Discovery (RED), a post-processing method that improves a given equation in a targeted manner, based on its residuals. By parsing the initial equation to a syntax tree, we can use node-based calculation rules to compute the residual for each subequation of the initial equation. It is then possible to use this residual as new target variable in the original data set and generate a new prompt. If, with the new prompt, the equation discovery system suggests a subequation better than the old subequation on a validation set, we replace the latter by the former. RED is usable with any equation discovery system, is fast to calculate, and is easy to extend for new mathematical operations. In experiments on 53 equations from the Feynman benchmark, we show that it not only helps to improve all tested neural-guided systems, but also all tested classical genetic programming systems.

---