# Research Papers — 2025-11 · bundle page 135 of 197

> Full-text markdown of papers #6701–6750 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/135
[← Previous bundle](https://aipod.dev/papers/archive/2025-11/page/134.md)
[Next bundle →](https://aipod.dev/papers/archive/2025-11/page/136.md)

### Optimal control of the future via prospective learning with control

Authors: Yuxin Bai, Aranyak Acharyya, Ashwin De Silva, Zeyu Shen, James Hassett, Joshua T. Vogelstein
Published: 2025-11-11
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2511.08717v4

Optimal control of the future is the next frontier for AI. Current approaches to this problem are typically rooted in reinforcement learning (RL). RL is mathematically distinct from supervised learning, which has been the main workhorse for the recent achievements in AI. Moreover, RL typically operates in a stationary environment with episodic resets, limiting its utility. Here, we extend supervised learning to address learning to control in non-stationary, reset-free environments. Using this framework, called ''Prospective Learning with Control'' (PLuC), we prove that under certain fairly general assumptions, empirical risk minimization (ERM) asymptotically achieves the Bayes optimal policy. We then consider a specific instance of prospective learning with control: foraging, a canonical task relevant to both natural and artificial agents. We illustrate that modern RL algorithms, which assume stationarity, struggle in these non-stationary reset-free environments. Even with time-aware modifications, they converge orders of magnitude slower than our prospective foraging agents on a simple 1-D foraging benchmark. Code is available at: https://github.com/neurodata/procontrol.

---

### Bridging Natural Language and ASP: A Hybrid Approach Using LLMs and AMR Parsing

Authors: Connar Hite, Sean Saud, Raef Taha, Nayim Rahman, Tanvir Atahary, Scott Douglass, Tarek Taha
Published: 2025-11-11
Categories: cs.AI
arXiv: https://arxiv.org/abs/2511.08715v1

Answer Set Programming (ASP) is a declarative programming paradigm based on logic programming and non-monotonic reasoning. It is a tremendously powerful tool for describing and solving combinatorial problems. Like any other language, ASP requires users to learn how it works and the syntax involved. It is becoming increasingly required for those unfamiliar with programming languages to interact with code. This paper proposes a novel method of translating unconstrained English into ASP programs for logic puzzles using an LLM and Abstract Meaning Representation (AMR) graphs. Everything from ASP rules, facts, and constraints is generated to fully represent and solve the desired problem. Example logic puzzles are used to demonstrate the capabilities of the system. While most current methods rely entirely on an LLM, our system minimizes the role of the LLM only to complete straightforward tasks. The LLM is used to simplify natural language sentences, identify keywords, and generate simple facts. The AMR graphs are then parsed from simplified language and used to generate ASP constraints systematically. The system successfully creates an entire ASP program that solves a combinatorial logic problem. This approach is a significant first step in creating a lighter-weight, explainable system that converts natural language to solve complex logic problems.

---

### Harnessing Diffusion-Generated Synthetic Images for Fair Image Classification

Authors: Abhipsa Basu, Aviral Gupta, Abhijnya Bhat, R. Venkatesh Babu
Published: 2025-11-11
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.08711v2

Image classification systems often inherit biases from uneven group representation in training data. For example, in face datasets for hair color classification, blond hair may be disproportionately associated with females, reinforcing stereotypes. A recent approach leverages the Stable Diffusion model to generate balanced training data, but these models often struggle to preserve the original data distribution. In this work, we explore multiple diffusion-finetuning techniques, e.g., LoRA and DreamBooth, to generate images that more accurately represent each training group by learning directly from their samples. Additionally, in order to prevent a single DreamBooth model from being overwhelmed by excessive intra-group variations, we explore a technique of clustering images within each group and train a DreamBooth model per cluster. These models are then used to generate group-balanced data for pretraining, followed by fine-tuning on real data. Experiments on multiple benchmarks demonstrate that the studied finetuning approaches outperform vanilla Stable Diffusion on average and achieve results comparable to SOTA debiasing techniques like Group-DRO, while surpassing them as the dataset bias severity increases.

---

### Convergence dynamics of Agent-to-Agent Interactions with Misaligned objectives

Authors: Romain Cosentino, Sarath Shekkizhar, Adam Earle
Published: 2025-11-11
Categories: cs.MA, cs.AI
arXiv: https://arxiv.org/abs/2511.08710v3

We develop and analyze a theoretical framework for agent-to-agent interactions in a simplified in-context linear regression setting. In our model, each agent is instantiated as a single-layer transformer with linear self-attention (LSA) trained to implement gradient-descent-like updates on a quadratic regression objective from in-context examples. We then study the coupled dynamics when two such LSA agents alternately update from each other's outputs under potentially misaligned fixed objectives. Within this framework, we characterize the generation dynamics and show that misalignment leads to a biased equilibrium where neither agent reaches its target, with residual errors predictable from the objective gap and the prompt-induced geometry. We also characterize an adversarial regime where asymmetric convergence is possible: one agent reaches its objective exactly while inducing persistent bias in the other. We further contrast this fixed objective regime with an adaptive multi-agent setting, wherein a helper agent updates a turn-based objective to implement a Newton-like step for the main agent, eliminating the plateau and accelerating its convergence. Experiments with trained LSA agents, as well as black-box GPT-5-mini runs on in-context linear regression tasks, are consistent with our theoretical predictions within this simplified setting. We view our framework as a mechanistic framework that links prompt geometry and objective misalignment to stability, bias, and robustness, and as a stepping stone toward analyzing more realistic multi-agent LLM systems.

---

### Stabilizing Direct Training of Spiking Neural Networks: Membrane Potential Initialization and Threshold-robust Surrogate Gradient

Authors: Hyunho Kook, Byeongho Yu, Jeong Min Oh, Eunhyeok Park
Published: 2025-11-11
Categories: cs.NE, cs.CV
arXiv: https://arxiv.org/abs/2511.08708v1

Recent advancements in the direct training of Spiking Neural Networks (SNNs) have demonstrated high-quality outputs even at early timesteps, paving the way for novel energy-efficient AI paradigms. However, the inherent non-linearity and temporal dependencies in SNNs introduce persistent challenges, such as temporal covariate shift (TCS) and unstable gradient flow with learnable neuron thresholds. In this paper, we present two key innovations: MP-Init (Membrane Potential Initialization) and TrSG (Threshold-robust Surrogate Gradient). MP-Init addresses TCS by aligning the initial membrane potential with its stationary distribution, while TrSG stabilizes gradient flow with respect to threshold voltage during training. Extensive experiments validate our approach, achieving state-of-the-art accuracy on both static and dynamic image datasets. The code is available at: https://github.com/kookhh0827/SNN-MP-Init-TRSG

---

### Rethinking Generative Image Pretraining: How Far Are We From Scaling Up Next-Pixel Prediction?

Authors: Xinchen Yan, Chen Liang, Lijun Yu, Adams Wei Yu, Yifeng Lu, Quoc V. Le
Published: 2025-11-11
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2511.08704v2

This paper investigates the scaling properties of autoregressive next-pixel prediction, a simple, end-to-end yet under-explored framework for unified vision models. Starting with images at resolutions of 32x32, we train a family of Transformers using IsoFlops profiles across compute budgets up to 7e19 FLOPs and evaluate three distinct target metrics: next-pixel prediction objective, ImageNet classification accuracy, and generation-based completion measured by Fr'echet Distance. First, optimal scaling strategy is critically task-dependent. At a fixed resolution of 32x32 alone, the optimal scaling properties for image classification and image generation diverge, where generation optimal setup requires the data size grow three to five times faster than for the classification optimal setup. Second, as image resolution increases, the optimal scaling strategy indicates that the model size must grow much faster than data size. Surprisingly, by projecting our findings, we discover that the primary bottleneck is compute rather than the amount of training data. As compute continues to grow four to five times annually, we forecast the feasibility of pixel-by-pixel modeling of images within the next five years.

---

### Automated Hardware Trojan Insertion in Industrial-Scale Designs

Authors: Yaroslav Popryho, Debjit Pal, Inna Partin-Vaisband
Published: 2025-11-11
Categories: cs.CR, cs.LG
arXiv: https://arxiv.org/abs/2511.08703v1

Industrial Systems-on-Chips (SoCs) often comprise hundreds of thousands to millions of nets and millions to tens of millions of connectivity edges, making empirical evaluation of hardware-Trojan (HT) detectors on realistic designs both necessary and difficult. Public benchmarks remain significantly smaller and hand-crafted, while releasing truly malicious RTL raises ethical and operational risks. This work presents an automated and scalable methodology for generating HT-like patterns in industry-scale netlists whose purpose is to stress-test detection tools without altering user-visible functionality. The pipeline (i) parses large gate-level designs into connectivity graphs, (ii) explores rare regions using SCOAP testability metrics, and (iii) applies parameterized, function-preserving graph transformations to synthesize trigger-payload pairs that mimic the statistical footprint of stealthy HTs. When evaluated on the benchmarks generated in this work, representative state-of-the-art graph-learning models fail to detect Trojans. The framework closes the evaluation gap between academic circuits and modern SoCs by providing reproducible challenge instances that advance security research without sharing step-by-step attack instructions.

---

### FAIRPLAI: A Human-in-the-Loop Approach to Fair and Private Machine Learning

Authors: David Sanchez, Holly Lopez, Michelle Buraczyk, Anantaa Kotal
Published: 2025-11-11
Categories: cs.LG, cs.AI, cs.CR, cs.CY
arXiv: https://arxiv.org/abs/2511.08702v1

As machine learning systems move from theory to practice, they are increasingly tasked with decisions that affect healthcare access, financial opportunities, hiring, and public services. In these contexts, accuracy is only one piece of the puzzle - models must also be fair to different groups, protect individual privacy, and remain accountable to stakeholders. Achieving all three is difficult: differential privacy can unintentionally worsen disparities, fairness interventions often rely on sensitive data that privacy restricts, and automated pipelines ignore that fairness is ultimately a human and contextual judgment. We introduce FAIRPLAI (Fair and Private Learning with Active Human Influence), a practical framework that integrates human oversight into the design and deployment of machine learning systems. FAIRPLAI works in three ways: (1) it constructs privacy-fairness frontiers that make trade-offs between accuracy, privacy guarantees, and group outcomes transparent; (2) it enables interactive stakeholder input, allowing decision-makers to select fairness criteria and operating points that reflect their domain needs; and (3) it embeds a differentially private auditing loop, giving humans the ability to review explanations and edge cases without compromising individual data security. Applied to benchmark datasets, FAIRPLAI consistently preserves strong privacy protections while reducing fairness disparities relative to automated baselines. More importantly, it provides a straightforward, interpretable process for practitioners to manage competing demands of accuracy, privacy, and fairness in socially impactful applications. By embedding human judgment where it matters most, FAIRPLAI offers a pathway to machine learning systems that are effective, responsible, and trustworthy in practice. GitHub: https://github.com/Li1Davey/Fairplai

---

### PEGNet: A Physics-Embedded Graph Network for Long-Term Stable Multiphysics Simulation

Authors: Can Yang, Zhenzhong Wang, Junyuan Liu, Yunpeng Gong, Min Jiang
Published: 2025-11-11
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.08697v1

Accurate and efficient simulations of physical phenomena governed by partial differential equations (PDEs) are important for scientific and engineering progress. While traditional numerical solvers are powerful, they are often computationally expensive. Recently, data-driven methods have emerged as alternatives, but they frequently suffer from error accumulation and limited physical consistency, especially in multiphysics and complex geometries. To address these challenges, we propose PEGNet, a Physics-Embedded Graph Network that incorporates PDE-guided message passing to redesign the graph neural network architecture. By embedding key PDE dynamics like convection, viscosity, and diffusion into distinct message functions, the model naturally integrates physical constraints into its forward propagation, producing more stable and physically consistent solutions. Additionally, a hierarchical architecture is employed to capture multi-scale features, and physical regularization is integrated into the loss function to further enforce adherence to governing physics. We evaluated PEGNet on benchmarks, including custom datasets for respiratory airflow and drug delivery, showing significant improvements in long-term prediction accuracy and physical consistency over existing methods. Our code is available at https://github.com/Yanghuoshan/PEGNet.

---

### Practical and Performant Enhancements for Maximization of Algebraic Connectivity

Authors: Leonard Jung, Alan Papalia, Kevin Doherty, Michael Everett
Published: 2025-11-11
Categories: cs.RO, cs.LG
arXiv: https://arxiv.org/abs/2511.08694v1

Long-term state estimation over graphs remains challenging as current graph estimation methods scale poorly on large, long-term graphs. To address this, our work advances a current state-of-the-art graph sparsification algorithm, maximizing algebraic connectivity (MAC). MAC is a sparsification method that preserves estimation performance by maximizing the algebraic connectivity, a spectral graph property that is directly connected to the estimation error. Unfortunately, MAC remains computationally prohibitive for online use and requires users to manually pre-specify a connectivity-preserving edge set. Our contributions close these gaps along three complementary fronts: we develop a specialized solver for algebraic connectivity that yields an average 2x runtime speedup; we investigate advanced step size strategies for MAC's optimization procedure to enhance both convergence speed and solution quality; and we propose automatic schemes that guarantee graph connectivity without requiring manual specification of edges. Together, these contributions make MAC more scalable, reliable, and suitable for real-time estimation applications.

---

### TabPFN-2.5: Advancing the State of the Art in Tabular Foundation Models

Authors: Léo Grinsztajn, Klemens Flöge, Oscar Key, Felix Birkel, Philipp Jund, Brendan Roof, Benjamin Jäger, Dominik Safaric, Simone Alessi, Adrian Hayler, Mihir Manium, Rosen Yu et al.
Published: 2025-11-11
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2511.08667v2

The first tabular foundation model, TabPFN, and its successor TabPFNv2 have impacted tabular AI substantially, with dozens of methods building on it and hundreds of applications across different use cases. This report introduces TabPFN-2.5, the next generation of our tabular foundation model, built for datasets with up to 50,000 data points and 2,000 features, a 20x increase in data cells compared to TabPFNv2. TabPFN-2.5 is now the leading method for the industry standard benchmark TabArena (which contains datasets with up to 100,000 training data points), substantially outperforming tuned tree-based models and matching the accuracy of AutoGluon 1.4, a complex four-hour tuned ensemble that even includes the previous TabPFNv2. Remarkably, default TabPFN-2.5 has a 100% win rate against default XGBoost on small to medium-sized classification datasets (<=10,000 data points, 500 features) and a 87% win rate on larger datasets up to 100K samples and 2K features (85% for regression). For production use cases, we introduce a new distillation engine that converts TabPFN-2.5 into a compact MLP or tree ensemble, preserving most of its accuracy while delivering orders-of-magnitude lower latency and plug-and-play deployment. This new release will immediately strengthen the performance of the many applications and methods already built on the TabPFN ecosystem.

---

### Privacy Beyond Pixels: Latent Anonymization for Privacy-Preserving Video Understanding

Authors: Joseph Fioresi, Ishan Rajendrakumar Dave, Mubarak Shah
Published: 2025-11-11
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.08666v2

We introduce a novel formulation of visual privacy preservation for video foundation models that operates entirely in the latent space. While spatio-temporal features learned by foundation models have deepened general understanding of video content, sharing or storing these extracted visual features for downstream tasks inadvertently reveals sensitive personal information like skin color, gender, or clothing. Current privacy preservation methods focus on input-pixel-level anonymization, which requires retraining the entire utility video model and results in task-specific anonymization, making them unsuitable for recent video foundational models. To address these challenges, we introduce a lightweight Anonymizing Adapter Module (AAM) that removes private information from video features while retaining general task utility. AAM can be applied in a plug-and-play fashion to frozen video encoders, minimizing the computational burden of finetuning and re-extracting features. Our framework employs three newly designed training objectives: (1) a clip-level self-supervised privacy objective to reduce mutual information between static clips, (2) a co-training objective to retain utility across seen tasks, and (3) a latent consistency loss for generalization on unseen tasks. Our extensive evaluations demonstrate a significant 35% reduction in privacy leakage while maintaining near-baseline utility performance across various downstream tasks: Action Recognition (Kinetics400, UCF101, HMDB51), Temporal Action Detection (THUMOS14), and Anomaly Detection (UCF-Crime). We also provide an analysis on anonymization for sensitive temporal attribute recognition. Additionally, we propose new protocols for assessing gender bias in action recognition models, showing that our method effectively mitigates such biases and promotes more equitable video understanding. https://joefioresi718.github.io/SPLAVU_webpage/

---

### 3D-TDA -- Topological feature extraction from 3D images for Alzheimer's disease classification

Authors: Faisal Ahmed, Taymaz Akan, Fatih Gelir, Owen T. Carmichael, Elizabeth A. Disbrow, Steven A. Conrad, Mohammad A. N. Bhuiyan
Published: 2025-11-11
Categories: eess.IV, cs.AI, cs.CV
arXiv: https://arxiv.org/abs/2511.08663v1

Now that disease-modifying therapies for Alzheimer disease have been approved by regulatory agencies, the early, objective, and accurate clinical diagnosis of AD based on the lowest-cost measurement modalities possible has become an increasingly urgent need. In this study, we propose a novel feature extraction method using persistent homology to analyze structural MRI of the brain. This approach converts topological features into powerful feature vectors through Betti functions. By integrating these feature vectors with a simple machine learning model like XGBoost, we achieve a computationally efficient machine learning model. Our model outperforms state-of-the-art deep learning models in both binary and three-class classification tasks for ADNI 3D MRI disease diagnosis. Using 10-fold cross-validation, our model achieved an average accuracy of 97.43 percent and sensitivity of 99.09 percent for binary classification. For three-class classification, it achieved an average accuracy of 95.47 percent and sensitivity of 94.98 percent. Unlike many deep learning models, our approach does not require data augmentation or extensive preprocessing, making it particularly suitable for smaller datasets. Topological features differ significantly from those commonly extracted using convolutional filters and other deep learning machinery. Because it provides an entirely different type of information from machine learning models, it has the potential to combine topological features with other models later on.

---

### Binary and Multiclass Cyberattack Classification on GeNIS Dataset

Authors: Miguel Silva, Daniela Pinto, João Vitorino, Eva Maia, Isabel Praça, Ivone Amorim, Maria João Viamonte
Published: 2025-11-11
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2511.08660v1

The integration of Artificial Intelligence (AI) in Network Intrusion Detection Systems (NIDS) is a promising approach to tackle the increasing sophistication of cyberattacks. However, since Machine Learning (ML) and Deep Learning (DL) models rely heavily on the quality of their training data, the lack of diverse and up-to-date datasets hinders their generalization capability to detect malicious activity in previously unseen network traffic. This study presents an experimental validation of the reliability of the GeNIS dataset for AI-based NIDS, to serve as a baseline for future benchmarks. Five feature selection methods, Information Gain, Chi-Squared Test, Recursive Feature Elimination, Mean Absolute Deviation, and Dispersion Ratio, were combined to identify the most relevant features of GeNIS and reduce its dimensionality, enabling a more computationally efficient detection. Three decision tree ensembles and two deep neural networks were trained for both binary and multiclass classification tasks. All models reached high accuracy and F1-scores, and the ML ensembles achieved slightly better generalization while remaining more efficient than DL models. Overall, the obtained results indicate that the GeNIS dataset supports intelligent intrusion detection and cyberattack classification with time-based and quantity-based behavioral features.

---

### Introduction to Automated Negotiation

Authors: Dave de Jonge
Published: 2025-11-11
Categories: cs.MA, cs.AI, cs.GT
arXiv: https://arxiv.org/abs/2511.08659v5

This book is an introductory textbook targeted towards computer science students who are completely new to the topic of automated negotiation. It does not require any prerequisite knowledge, except for elementary mathematics and basic programming skills. This book comes with an simple toy-world negotiation framework implemented in Python that can be used by the readers to implement their own negotiation algorithms and perform experiments with them. This framework is small and simple enough that any reader who does not like to work in Python should be able to re-implement it very quickly in any other programming language of their choice.

---

### "It Looks All the Same to Me": Cross-index Training for Long-term Financial Series Prediction

Authors: Stanislav Selitskiy
Published: 2025-11-11
Categories: q-fin.ST, cs.LG
arXiv: https://arxiv.org/abs/2511.08658v1

We investigate a number of Artificial Neural Network architectures (well-known and more ``exotic'') in application to the long-term financial time-series forecasts of indexes on different global markets. The particular area of interest of this research is to examine the correlation of these indexes' behaviour in terms of Machine Learning algorithms cross-training. Would training an algorithm on an index from one global market produce similar or even better accuracy when such a model is applied for predicting another index from a different market? The demonstrated predominately positive answer to this question is another argument in favour of the long-debated Efficient Market Hypothesis of Eugene Fama.

---

### Learning the Basis: A Kolmogorov-Arnold Network Approach Embedding Green's Function Priors

Authors: Rui Zhu, Yuexing Peng, George C. Alexandropoulos, Wenbo Wang, Wei Xiang
Published: 2025-11-11
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2511.08655v3

The Method of Moments (MoM) is constrained by the usage of static, geometry-defined basis functions, such as the Rao-Wilton-Glisson (RWG) basis. This letter reframes electromagnetic modeling around a learnable basis representation rather than solving for the coefficients over a fixed basis. We first show that the RWG basis is essentially a static and piecewise-linear realization of the Kolmogorov-Arnold representation theorem. Inspired by this insight, we propose PhyKAN, a physics-informed Kolmogorov-Arnold Network (KAN) that generalizes RWG into a learnable and adaptive basis family. Derived from the EFIE, PhyKAN integrates a local KAN branch with a global branch embedded with Green's function priors to preserve physical consistency. It is demonstrated that, across canonical geometries, PhyKAN achieves sub-0.01 reconstruction errors as well as accurate, unsupervised radar cross section predictions, offering an interpretable, physics-consistent bridge between classical solvers and modern neural network models for electromagnetic modeling.

---

### AI-generated podcasts: Synthetic Intimacy and Cultural Mistranslation in NotebookLM's Audio Overviews

Authors: Jill Walker Rettberg
Published: 2025-11-11
Categories: cs.CY, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2511.08654v2

This paper analyses AI-generated podcasts produced by Google's NotebookLM, which generates audio podcasts with two chatty AI hosts discussing whichever documents a user uploads. While AI-generated podcasts have been discussed as tools, for instance in medical education, they have not yet been analysed as media. By uploading different types of text and analysing the generated outputs I show how the podcasts' structure is built around a fixed template. I also find that NotebookLM not only translates texts from other languages into a perky standardised Mid-Western American accent, it also translates cultural contexts to a white, educated, middle-class American default. This is a distinct development in how publics are shaped by media, marking a departure from the multiple public spheres that scholars have described in human podcasting from the early 2000s until today, where hosts spoke to specific communities and responded to listener comments, to an abstraction of the podcast genre.

---

### Accelerating Training Speed of Tiny Recursive Models with Curriculum Guided Adaptive Recursion

Authors: Kaleem Ullah Qasim, Jiashu Zhang
Published: 2025-11-11
Categories: cs.LG, cs.AI, cs.CL, cs.NE
arXiv: https://arxiv.org/abs/2511.08653v3

Background: Recursive reasoning models achieve strong performance through iterative refinement, allowing small networks to match large language models. However, training is computationally expensive, often requiring 36 GPU-hours for Sudoku extreme. Existing models use fixed recursion depth and uniform supervision weighting, leading to inefficient training. Objectives: We propose CGAR (Curriculum-Guided Adaptive Recursion), applying curriculum learning to architectural depth. CGAR introduces Progressive Depth Curriculum (PDC) to dynamically adjust recursion depth and Hierarchical Supervision Weighting (HSW) to apply exponentially decaying importance to supervision steps. Methods: PDC implements a three-stage schedule transitioning from shallow (2, 1) to full depth (6, 3) configurations, providing 41.4% FLOPs reduction. HSW applies exponential decay to supervision steps, achieving 40% gradient variance reduction and accelerated convergence. Results: On Sudoku-Extreme, CGAR achieves 1.71x training speedup (10.93 to 6.38 hours) with only a 0.63% accuracy drop (86.65% to 86.02%). PDC alone achieves 2.26x speedup with 85.47% accuracy, showing a Pareto improvement in efficiency and quality. HSW provides 1.61x speedup. CGAR-trained models show superior inference efficiency with 100% halting accuracy and 11% fewer reasoning steps. Conclusions: CGAR enables efficient training of recursive models on modest hardware. By treating depth as a scheduled parameter, it achieves substantial savings and prevents overfitting, making these models practical for neurosymbolic AI and program synthesis. https://github.com/Kaleemullahqasim/CGAR and huggingface.co/Kaleemullah/trm-cgar-sudoku.

---

### RS-Net: Context-Aware Relation Scoring for Dynamic Scene Graph Generation

Authors: Hae-Won Jo, Yeong-Jun Cho
Published: 2025-11-11
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2511.08651v1

Dynamic Scene Graph Generation (DSGG) models how object relations evolve over time in videos. However, existing methods are trained only on annotated object pairs and lack guidance for non-related pairs, making it difficult to identify meaningful relations during inference. In this paper, we propose Relation Scoring Network (RS-Net), a modular framework that scores the contextual importance of object pairs using both spatial interactions and long-range temporal context. RS-Net consists of a spatial context encoder with learnable context tokens and a temporal encoder that aggregates video-level information. The resulting relation scores are integrated into a unified triplet scoring mechanism to enhance relation prediction. RS-Net can be easily integrated into existing DSGG models without architectural changes. Experiments on the Action Genome dataset show that RS-Net consistently improves both Recall and Precision across diverse baselines, with notable gains in mean Recall, highlighting its ability to address the long-tailed distribution of relations. Despite the increased number of parameters, RS-Net maintains competitive efficiency, achieving superior performance over state-of-the-art methods.

---

### A Lightweight CNN-Attention-BiLSTM Architecture for Multi-Class Arrhythmia Classification on Standard and Wearable ECGs

Authors: Vamsikrishna Thota, Hardik Prajapati, Yuvraj Joshi, Shubhangi Rathi
Published: 2025-11-11
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.08650v1

Early and accurate detection of cardiac arrhythmias is vital for timely diagnosis and intervention. We propose a lightweight deep learning model combining 1D Convolutional Neural Networks (CNN), attention mechanisms, and Bidirectional Long Short-Term Memory (BiLSTM) for classifying arrhythmias from both 12-lead and single-lead ECGs. Evaluated on the CPSC 2018 dataset, the model addresses class imbalance using a class-weighted loss and demonstrates superior accuracy and F1- scores over baseline models. With only 0.945 million parameters, our model is well-suited for real-time deployment in wearable health monitoring systems.

---

### Bio AI Agent: A Multi-Agent Artificial Intelligence System for Autonomous CAR-T Cell Therapy Development with Integrated Target Discovery, Toxicity Prediction, and Rational Molecular Design

Authors: Yi Ni, Liwei Zhu, Shuai Li
Published: 2025-11-11
Categories: q-bio.QM, cs.AI
arXiv: https://arxiv.org/abs/2511.08649v1

Chimeric antigen receptor T-cell (CAR-T) therapy represents a paradigm shift in cancer treatment, yet development timelines of 8-12 years and clinical attrition rates exceeding 40-60% highlight critical inefficiencies in target selection, safety assessment, and molecular optimization. We present Bio AI Agent, a multi-agent artificial intelligence system powered by large language models that enables autonomous CAR-T development through collaborative specialized agents. The system comprises six autonomous agents: Target Selection Agent for multi-parametric antigen prioritization across >10,000 cancer-associated targets, Toxicity Prediction Agent for comprehensive safety profiling integrating tissue expression atlases and pharmacovigilance databases, Molecular Design Agent for rational CAR engineering, Patent Intelligence Agent for freedom-to-operate analysis, Clinical Translation Agent for regulatory compliance, and Decision Orchestration Agent for multi-agent coordination. Retrospective validation demonstrated autonomous identification of high-risk targets including FcRH5 (hepatotoxicity) and CD229 (off-tumor toxicity), patent infringement risks for CD38+SLAMF7 combinations, and generation of comprehensive development roadmaps. By enabling parallel processing, specialized reasoning, and autonomous decision-making superior to monolithic AI systems, Bio AI Agent addresses critical gaps in precision oncology development and has potential to accelerate translation of next-generation immunotherapies from discovery to clinic.

---

### Compact Artificial Neural Network Models for Predicting Protein Residue -- RNA Base Binding

Authors: Stanislav Selitskiy
Published: 2025-11-11
Categories: q-bio.BM, cs.LG
arXiv: https://arxiv.org/abs/2511.08648v1

Large Artificial Neural Network (ANN) models have demonstrated success in various domains, including general text and image generation, drug discovery, and protein-RNA (ribonucleic acid) binding tasks. However, these models typically demand substantial computational resources, time, and data for effective training. Given that such extensive resources are often inaccessible to many researchers and that life sciences data sets are frequently limited, we investigated whether small ANN models could achieve acceptable accuracy in protein-RNA prediction. We experimented with shallow feed-forward ANNs comprising two hidden layers and various non-linearities. These models did not utilize explicit structural information; instead, a sliding window approach was employed to implicitly consider the context of neighboring residues and bases. We explored different training techniques to address the issue of highly unbalanced data. Among the seven most popular non-linearities for feed-forward ANNs, only three: Rectified Linear Unit (ReLU), Gated Linear Unit (GLU), and Hyperbolic Tangent (Tanh) yielded converging models. Common re-balancing techniques, such as under- and over-sampling of training sets, proved ineffective, whereas increasing the volume of training data and using model ensembles significantly improved performance. The optimal context window size, balancing both false negative and false positive errors, was found to be approximately 30 residues and bases. Our findings indicate that high-accuracy protein-RNA binding prediction is achievable using computing hardware accessible to most educational and research institutions.

---

### Simulating the Visual World with Artificial Intelligence: A Roadmap

Authors: Jingtong Yue, Ziqi Huang, Zhaoxi Chen, Xintao Wang, Pengfei Wan, Ziwei Liu
Published: 2025-11-11
Categories: cs.AI, cs.CV
arXiv: https://arxiv.org/abs/2511.08585v4

The landscape of video generation is shifting, from a focus on generating visually appealing clips to building virtual environments that support interaction and maintain physical plausibility. These developments point toward the emergence of video foundation models that function not only as visual generators but also as implicit world models, models that simulate the physical dynamics, agent-environment interactions, and task planning that govern real or imagined worlds. This survey provides a systematic overview of this evolution, conceptualizing modern video foundation models as the combination of two core components: an implicit world model and a video renderer. The world model encodes structured knowledge about the world, including physical laws, interaction dynamics, and agent behavior. It serves as a latent simulation engine that enables coherent visual reasoning, long-term temporal consistency, and goal-driven planning. The video renderer transforms this latent simulation into realistic visual observations, effectively producing videos as a "window" into the simulated world. We trace the progression of video generation through four generations, in which the core capabilities advance step by step, ultimately culminating in a world model, built upon a video generation model, that embodies intrinsic physical plausibility, real-time multimodal interaction, and planning capabilities spanning multiple spatiotemporal scales. For each generation, we define its core characteristics, highlight representative works, and examine their application domains such as robotics, autonomous driving, and interactive gaming. Finally, we discuss open challenges and design principles for next-generation world models, including the role of agent intelligence in shaping and evaluating these systems. An up-to-date list of related works is maintained at this link.

---

### SeFA-Policy: Fast and Accurate Visuomotor Policy Learning with Selective Flow Alignment

Authors: Rong Xue, Jiageng Mao, Mingtong Zhang, Yue Wang
Published: 2025-11-11
Categories: cs.RO, cs.LG
arXiv: https://arxiv.org/abs/2511.08583v2

Developing efficient and accurate visuomotor policies poses a central challenge in robotic imitation learning. While recent rectified flow approaches have advanced visuomotor policy learning, they suffer from a key limitation: After iterative distillation, generated actions may deviate from the ground-truth actions corresponding to the current visual observation, leading to accumulated error as the reflow process repeats and unstable task execution. We present Selective Flow Alignment (SeFA), an efficient and accurate visuomotor policy learning framework. SeFA resolves this challenge by a selective flow alignment strategy, which leverages expert demonstrations to selectively correct generated actions and restore consistency with observations, while preserving multimodality. This design introduces a consistency correction mechanism that ensures generated actions remain observation-aligned without sacrificing the efficiency of one-step flow inference. Extensive experiments across both simulated and real-world manipulation tasks show that SeFA Policy surpasses state-of-the-art diffusion-based and flow-based policies, achieving superior accuracy and robustness while reducing inference latency by over 98%. By unifying rectified flow efficiency with observation-consistent action generation, SeFA provides a scalable and dependable solution for real-time visuomotor policy learning. Code is available on https://github.com/RongXueZoe/SeFA.

---

### DeepProofLog: Efficient Proving in Deep Stochastic Logic Programs

Authors: Ying Jiao, Rodrigo Castellano Ontiveros, Luc De Raedt, Marco Gori, Francesco Giannini, Michelangelo Diligenti, Giuseppe Marra
Published: 2025-11-11
Categories: cs.AI
arXiv: https://arxiv.org/abs/2511.08581v2

Neurosymbolic (NeSy) AI aims to combine the strengths of neural architectures and symbolic reasoning to improve the accuracy, interpretability, and generalization capability of AI models. While logic inference on top of subsymbolic modules has been shown to effectively guarantee these properties, this often comes at the cost of reduced scalability, which can severely limit the usability of NeSy models. This paper introduces DeepProofLog (DPrL), a novel NeSy system based on stochastic logic programs, which addresses the scalability limitations of previous methods. DPrL parameterizes all derivation steps with neural networks, allowing efficient neural guidance over the proving system. Additionally, we establish a formal mapping between the resolution process of our deep stochastic logic programs and Markov Decision Processes, enabling the application of dynamic programming and reinforcement learning techniques for efficient inference and learning. This theoretical connection improves scalability for complex proof spaces and large knowledge bases. Our experiments on standard NeSy benchmarks and knowledge graph reasoning tasks demonstrate that DPrL outperforms existing state-of-the-art NeSy systems, advancing scalability to larger and more complex settings than previously possible.

---

### Training Language Models to Explain Their Own Computations

Authors: Belinda Z. Li, Zifan Carl Guo, Vincent Huang, Jacob Steinhardt, Jacob Andreas
Published: 2025-11-11
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2511.08579v3

Can language models (LMs) learn to faithfully describe their internal computations? Are they better able to describe themselves than other models? We study the extent to which LMs' privileged access to their own internals can be leveraged to produce new techniques for explaining their behavior. Using existing interpretability techniques as a source of ground truth, we fine-tune LMs to generate natural language descriptions of (1) the information encoded by LM features, (2) the causal structure of LMs' internal activations, and (3) the influence of specific input tokens on LM outputs. When trained with only tens of thousands of example explanations, explainer models exhibit non-trivial generalization to new queries. This generalization appears partly attributable to explainer models' privileged access to their own internals: using a model to explain its own computations generally works better than using a *different* model to explain its computations (even if the explainer model is significantly more capable than the target). Our results suggest not only that LMs can learn to reliably explain their internal computations, but that such explanations offer a scalable complement to existing interpretability methods. Code and data at https://github.com/TransluceAI/introspective-interp

---

### Think-at-Hard: Dynamic Looped Transformers for Improved Reasoning

Authors: Tianyu Fu, Yichen You, Zekai Chen, Guohao Dai, Huazhong Yang, Yu Wang
Published: 2025-11-11
Categories: cs.CL, cs.AI, cs.LG, cs.PF
arXiv: https://arxiv.org/abs/2511.08577v4

Improving the reasoning abilities of Large Language Models (LLMs), especially under parameter constraints, is crucial for real-world applications. Looped transformers address this by performing multiple latent iterations to refine each token beyond a single forward pass. However, we identify a latent overthinking phenomenon: most token predictions are already correct after the first pass, but are sometimes revised into errors in later iterations. We ask whether selectively skipping latent iterations can improve accuracy, and reveal significant potential with an oracle iteration policy that boosts performance by up to 7.3%. Motivated by this, we propose Think-at-Hard (TaH), a looped transformer optimized for selective iteration. TaH employs a lightweight neural decider to trigger latent iteration, only at tokens likely to be incorrect after the standard forward pass. During latent iterations, depth-aware Low-Rank Adaptation (LoRA) modules shift the objective from general next-token prediction to focused hard-token refinement. A duo-causal attention mechanism extends attention from the token sequence dimension to an additional iteration depth dimension, enabling cross-iteration information flow with full sequential parallelism. Experiments on nine benchmarks show consistent gains across math, QA, and coding tasks. With identical parameter counts, TaH outperforms always-iterate baselines by 3.8-4.4% while skipping iterations on 93% of tokens, and exceeds single-iteration Qwen3 baselines by 3.0-3.8%. When allowing <3% more parameters from LoRA and decider, the gains further increase to 5.3-6.2% and 6.1-6.8%, respectively. Our code is available at https://github.com/thu-nics/TaH.

---

### SENCA-st: Integrating Spatial Transcriptomics and Histopathology with Cross Attention Shared Encoder for Region Identification in Cancer Pathology

Authors: Shanaka Liyanaarachchi, Chathurya Wijethunga, Shihab Aaqil Ahamed, Akthas Absar, Ranga Rodrigo
Published: 2025-11-11
Categories: cs.CV, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2511.08573v1

Spatial transcriptomics is an emerging field that enables the identification of functional regions based on the spatial distribution of gene expression. Integrating this functional information present in transcriptomic data with structural data from histopathology images is an active research area with applications in identifying tumor substructures associated with cancer drug resistance. Current histopathology-spatial-transcriptomic region segmentation methods suffer due to either making spatial transcriptomics prominent by using histopathology features just to assist processing spatial transcriptomics data or using vanilla contrastive learning that make histopathology images prominent due to only promoting common features losing functional information. In both extremes, the model gets either lost in the noise of spatial transcriptomics or overly smoothed, losing essential information. Thus, we propose our novel architecture SENCA-st (Shared Encoder with Neighborhood Cross Attention) that preserves the features of both modalities. More importantly, it emphasizes regions that are structurally similar in histopathology but functionally different on spatial transcriptomics using cross-attention. We demonstrate the superior performance of our model that surpasses state-of-the-art methods in detecting tumor heterogeneity and tumor micro-environment regions, a clinically crucial aspect.

---

### Automatic Grid Updates for Kolmogorov-Arnold Networks using Layer Histograms

Authors: Jamison Moody, James Usevitch
Published: 2025-11-11
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2511.08570v2

Kolmogorov-Arnold Networks (KANs) are a class of neural networks that have received increased attention in recent literature. In contrast to MLPs, KANs leverage parameterized, trainable activation functions and offer several benefits including improved interpretability and higher accuracy on learning symbolic equations. However, the original KAN architecture requires adjustments to the domain discretization of the network (called the "domain grid") during training, creating extra overhead for the user in the training process. Typical KAN layers are not designed with the ability to autonomously update their domains in a data-driven manner informed by the changing output ranges of previous layers. As an added benefit, this histogram algorithm may also be applied towards detecting out-of-distribution (OOD) inputs in a variety of settings. We demonstrate that AdaptKAN exceeds or matches the performance of prior KAN architectures and MLPs on four different tasks: learning scientific equations from the Feynman dataset, image classification from frozen features, learning a control Lyapunov function, and detecting OOD inputs on the OpenOOD v1.5 benchmark.

---

### The Path Not Taken: RLVR Provably Learns Off the Principals

Authors: Hanqing Zhu, Zhenyu Zhang, Hanxian Huang, DiJia Su, Zechun Liu, Jiawei Zhao, Igor Fedorov, Hamed Pirsiavash, Zhizhou Sha, Jinwon Lee, David Z. Pan, Zhangyang Wang et al.
Published: 2025-11-11
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2511.08567v1

Reinforcement Learning with Verifiable Rewards (RLVR) reliably improves the reasoning performance of large language models, yet it appears to modify only a small fraction of parameters. We revisit this paradox and show that sparsity is a surface artifact of a model-conditioned optimization bias: for a fixed pretrained model, updates consistently localize to preferred parameter regions, highly consistent across runs and largely invariant to datasets and RL recipes. We mechanistically explain these dynamics with a Three-Gate Theory: Gate I (KL Anchor) imposes a KL-constrained update; Gate II (Model Geometry) steers the step off principal directions into low-curvature, spectrum-preserving subspaces; and Gate III (Precision) hides micro-updates in non-preferred regions, making the off-principal bias appear as sparsity. We then validate this theory and, for the first time, provide a parameter-level characterization of RLVR's learning dynamics: RLVR learns off principal directions in weight space, achieving gains via minimal spectral drift, reduced principal-subspace rotation, and off-principal update alignment. In contrast, SFT targets principal weights, distorts the spectrum, and even lags RLVR. Together, these results provide the first parameter-space account of RLVR's training dynamics, revealing clear regularities in how parameters evolve. Crucially, we show that RL operates in a distinct optimization regime from SFT, so directly adapting SFT-era parameter-efficient fine-tuning (PEFT) methods can be flawed, as evidenced by our case studies on advanced sparse fine-tuning and LoRA variants. We hope this work charts a path toward a white-box understanding of RLVR and the design of geometry-aware, RLVR-native learning algorithms, rather than repurposed SFT-era heuristics.

---

### Moral Susceptibility and Robustness under Persona Role-Play in Large Language Models

Authors: Davi Bastos Costa, Felippe Alves, Renato Vicente
Published: 2025-11-11
Categories: cs.CL, cs.AI, cs.CY
arXiv: https://arxiv.org/abs/2511.08565v3

Large language models (LLMs) increasingly operate in social contexts, motivating analysis of how they express and shift moral judgments. In this work, we investigate the moral response of LLMs to persona role-play, prompting a LLM to assume a specific character. Using the Moral Foundations Questionnaire (MFQ), we introduce a benchmark that quantifies two properties: moral susceptibility and moral robustness, defined from the variability of MFQ scores across- and within-personas. We estimate these quantities with two complementary procedures, repeated sampling and a logit-based method that directly estimates the rating distributions and enables temperature analysis. We evaluate 15 models across six families: Claude, DeepSeek, Gemini, GPT, Grok, and Llama. The two metrics show qualitatively different patterns. Moral robustness varies by more than an order of magnitude, with a coefficient of variation of about $152\%$, and is explained almost entirely by model family. The Claude family is, by a significant margin, the most robust, about 30 times more so than the lower-performing families (DeepSeek, Grok, and Llama), while Gemini and GPT occupy an intermediate tier. This strong family dependence suggests that robustness is primarily shaped by post-training. Moral susceptibility, by contrast, spans a much narrower range, with a coefficient of variation of about $13\%$, and the most susceptible model is only 1.6 times more susceptible than the least. Unlike robustness, susceptibility shows no clear family dependence, suggesting that it is primarily determined by pre-training. Additionally, we present moral foundation profiles for models without persona role-play and for personas averaged across models. Together, these analyses provide a systematic view of how persona conditioning shapes moral behavior in LLMs and a window into the internal machinery they use to instantiate personas.

---

### Hyperdimensional Decoding of Spiking Neural Networks

Authors: Cedrick Kinavuidi, Luca Peres, Oliver Rhodes
Published: 2025-11-11
Categories: cs.AI
arXiv: https://arxiv.org/abs/2511.08558v2

This work presents a novel spiking neural network (SNN) decoding method, combining SNNs with Hyperdimensional computing (HDC). The goal is to create a decoding method with high accuracy, high noise robustness, low latency and low energy usage. Compared to analogous architectures decoded with existing approaches, the presented SNN-HDC model attains generally better classification accuracy, lower classification latency and lower estimated energy consumption on multiple test cases from literature. The SNN-HDC achieved estimated energy consumption reductions ranging from 1.24x to 3.67x on the DvsGesture dataset and from 1.38x to 2.27x on the SL-Animals-DVS dataset. The presented decoding method can also efficiently identify unknown classes it has not been trained on. In the DvsGesture dataset the SNN-HDC model can identify 100% of samples from an unseen/untrained class. Given the numerous benefits shown and discussed in this paper, this decoding method represents a very compelling alternative to both rate and latency decoding.

---

### FMMI: Flow Matching Mutual Information Estimation

Authors: Ivan Butakov, Alexander Semenenko, Valeriya Kirova, Alexey Frolov, Ivan Oseledets
Published: 2025-11-11
Categories: cs.LG, cs.IT
arXiv: https://arxiv.org/abs/2511.08552v2

We introduce a novel Mutual Information (MI) estimator that fundamentally reframes the discriminative approach. Instead of training a classifier to discriminate between joint and marginal distributions, we learn a normalizing flow that transforms one into the other. This technique produces a computationally efficient and precise MI estimate that scales well to high dimensions and across a wide range of ground-truth MI values.

---

### Vision Transformer Based User Equipment Positioning

Authors: Parshwa Shah, Dhaval K. Patel, Brijesh Soni, Miguel López-Benítez, Siddhartan Govindasamy
Published: 2025-11-11
Categories: cs.CV, cs.NI
arXiv: https://arxiv.org/abs/2511.08549v1

Recently, Deep Learning (DL) techniques have been used for User Equipment (UE) positioning. However, the key shortcomings of such models is that: i) they weigh the same attention to the entire input; ii) they are not well suited for the non-sequential data e.g., when only instantaneous Channel State Information (CSI) is available. In this context, we propose an attention-based Vision Transformer (ViT) architecture that focuses on the Angle Delay Profile (ADP) from CSI matrix. Our approach, validated on the `DeepMIMO' and `ViWi' ray-tracing datasets, achieves an Root Mean Squared Error (RMSE) of 0.55m indoors, 13.59m outdoors in DeepMIMO, and 3.45m in ViWi's outdoor blockage scenario. The proposed scheme outperforms state-of-the-art schemes by $\sim$ 38\%. It also performs substantially better than other approaches that we have considered in terms of the distribution of error distance.

---

### A Matter of Interest: Understanding Interestingness of Math Problems in Humans and Language Models

Authors: Shubhra Mishra, Yuka Machino, Gabriel Poesia, Albert Jiang, Joy Hsu, Adrian Weller, Challenger Mishra, David Broman, Joshua B. Tenenbaum, Mateja Jamnik, Cedegao E. Zhang, Katherine M. Collins
Published: 2025-11-11
Categories: cs.AI
arXiv: https://arxiv.org/abs/2511.08548v2

The evolution of mathematics is shaped importantly by interestingness: researchers choose which problems to pursue, and students choose which problems to engage with, based on expectations of interest and challenge. As AI systems, particularly large language models (LLMs) that operate flexibly over natural language and formal mathematics, are increasingly used in mathematics research and education, it becomes crucial to characterize how closely their judgments align with people from different mathematical backgrounds. We study whether LLMs align with human interestingness judgments by comparing LLM ratings with those of two populations, crowdsourced participants with college math experience and International Math Olympiad competitors. Although many LLMs broadly agree with human notions of interestingness, they largely fail to match the distribution of human judgments. They also weakly align with why humans find problems interesting, with low correlation to human-selected rationales. Finally, we evaluate LLMs' ability to generate interesting problems and find that, after filtering for validity, LLMs are able to generate engaging problems. We conclude with takeaways, including the need for multi-LLM human-AI collaborative systems, that highlight both the promise and current limits of LLMs as partners in mathematical reasoning.

---

### RePose-NeRF: Robust Radiance Fields for Mesh Reconstruction under Noisy Camera Poses

Authors: Sriram Srinivasan, Gautam Ramachandra
Published: 2025-11-11
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.08545v1

Accurate 3D reconstruction from multi-view images is essential for downstream robotic tasks such as navigation, manipulation, and environment understanding. However, obtaining precise camera poses in real-world settings remains challenging, even when calibration parameters are known. This limits the practicality of existing NeRF-based methods that rely heavily on accurate extrinsic estimates. Furthermore, their implicit volumetric representations differ significantly from the widely adopted polygonal meshes, making rendering and manipulation inefficient in standard 3D software. In this work, we propose a robust framework that reconstructs high-quality, editable 3D meshes directly from multi-view images with noisy extrinsic parameters. Our approach jointly refines camera poses while learning an implicit scene representation that captures fine geometric detail and photorealistic appearance. The resulting meshes are compatible with common 3D graphics and robotics tools, enabling efficient downstream use. Experiments on standard benchmarks demonstrate that our method achieves accurate and robust 3D reconstruction under pose uncertainty, bridging the gap between neural implicit representations and practical robotic applications.

---

### LeJEPA: Provable and Scalable Self-Supervised Learning Without the Heuristics

Authors: Randall Balestriero, Yann LeCun
Published: 2025-11-11
Categories: cs.LG, cs.AI, cs.CV, stat.ML
arXiv: https://arxiv.org/abs/2511.08544v3

Learning manipulable representations of the world and its dynamics is central to AI. Joint-Embedding Predictive Architectures (JEPAs) offer a promising blueprint, but lack of practical guidance and theory has led to ad-hoc R&D. We present a comprehensive theory of JEPAs and instantiate it in {\bf LeJEPA}, a lean, scalable, and theoretically grounded training objective. First, we identify the isotropic Gaussian as the optimal distribution that JEPAs' embeddings should follow to minimize downstream prediction risk. Second, we introduce a novel objective--{\bf Sketched Isotropic Gaussian Regularization} (SIGReg)--to constrain embeddings to reach that ideal distribution. Combining the JEPA predictive loss with SIGReg yields LeJEPA with numerous theoretical and practical benefits: (i) single trade-off hyperparameter, (ii) linear time and memory complexity, (iii) stability across hyper-parameters, architectures (ResNets, ViTs, ConvNets) and domains, (iv) heuristics-free, e.g., no stop-gradient, no teacher-student, no hyper-parameter schedulers, and (v) distributed training-friendly implementation requiring only $\approx$50 lines of code. Our empirical validation covers 10+ datasets, 60+ architectures, all with varying scales and domains. As an example, using imagenet-1k for pretraining and linear evaluation with frozen backbone, LeJEPA reaches 79\% with a ViT-H/14. We hope that the simplicity and theory-friendly ecosystem offered by LeJEPA will reestablish self-supervised pre-training as a core pillar of AI research (\href{https://github.com/rbalestr-lab/lejepa}{GitHub repo}).

---

### From Semantic Roles to Opinion Roles: SRL Data Extraction for Multi-Task and Transfer Learning in Low-Resource ORL

Authors: Amirmohammad Omidi Galdiani, Sepehr Rezaei Melal, Mohammad Norasteh, Arash Yousefi Jordehi, Seyed Abolghasem Mirroshandel
Published: 2025-11-11
Categories: cs.CL
arXiv: https://arxiv.org/abs/2511.08537v1

This report presents a detailed methodology for constructing a high-quality Semantic Role Labeling (SRL) dataset from the Wall Street Journal (WSJ) portion of the OntoNotes 5.0 corpus and adapting it for Opinion Role Labeling (ORL) tasks. Leveraging the PropBank annotation framework, we implement a reproducible extraction pipeline that aligns predicate-argument structures with surface text, converts syntactic tree pointers to coherent spans, and applies rigorous cleaning to ensure semantic fidelity. The resulting dataset comprises 97,169 predicate-argument instances with clearly defined Agent (ARG0), Predicate (REL), and Patient (ARG1) roles, mapped to ORL's Holder, Expression, and Target schema. We provide a detailed account of our extraction algorithms, discontinuous argument handling, annotation corrections, and statistical analysis of the resulting dataset. This work offers a reusable resource for researchers aiming to leverage SRL for enhancing ORL, especially in low-resource opinion mining scenarios.

---

### 3D4D: An Interactive, Editable, 4D World Model via 3D Video Generation

Authors: Yunhong He, Zhengqing Yuan, Zhengzhong Tu, Yanfang Ye, Lichao Sun
Published: 2025-11-11
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.08536v1

We introduce 3D4D, an interactive 4D visualization framework that integrates WebGL with Supersplat rendering. It transforms static images and text into coherent 4D scenes through four core modules and employs a foveated rendering strategy for efficient, real-time multi-modal interaction. This framework enables adaptive, user-driven exploration of complex 4D environments. The project page and code are available at https://yunhonghe1021.github.io/NOVA/.

---

### Large Sign Language Models: Toward 3D American Sign Language Translation

Authors: Sen Zhang, Xiaoxiao He, Di Liu, Zhaoyang Xia, Mingyu Zhao, Chaowei Tan, Vivian Li, Bo Liu, Dimitris N. Metaxas, Mubbasir Kapadia
Published: 2025-11-11
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2511.08535v1

We present Large Sign Language Models (LSLM), a novel framework for translating 3D American Sign Language (ASL) by leveraging Large Language Models (LLMs) as the backbone, which can benefit hearing-impaired individuals' virtual communication. Unlike existing sign language recognition methods that rely on 2D video, our approach directly utilizes 3D sign language data to capture rich spatial, gestural, and depth information in 3D scenes. This enables more accurate and resilient translation, enhancing digital communication accessibility for the hearing-impaired community. Beyond the task of ASL translation, our work explores the integration of complex, embodied multimodal languages into the processing capabilities of LLMs, moving beyond purely text-based inputs to broaden their understanding of human communication. We investigate both direct translation from 3D gesture features to text and an instruction-guided setting where translations can be modulated by external prompts, offering greater flexibility. This work provides a foundational step toward inclusive, multimodal intelligent systems capable of understanding diverse forms of language.

---

### Investigating CoT Monitorability in Large Reasoning Models

Authors: Shu Yang, Junchao Wu, Xilin Gong, Xuansheng Wu, Derek Wong, Ninghao Liu, Di Wang
Published: 2025-11-11
Categories: cs.CL
arXiv: https://arxiv.org/abs/2511.08525v3

Large Reasoning Models (LRMs) have demonstrated remarkable performance on complex tasks by engaging in extended reasoning before producing final answers. Beyond improving abilities, these detailed reasoning traces also create a new opportunity for AI safety, CoT Monitorability: monitoring potential model misbehavior, such as the use of shortcuts or sycophancy, through their chain-of-thought (CoT) during decision-making. However, two key fundamental challenges arise when attempting to build more effective monitors through CoT analysis. First, as prior research on CoT faithfulness has pointed out, models do not always truthfully represent their internal decision-making in the generated reasoning. Second, monitors themselves may be either overly sensitive or insufficiently sensitive, and can potentially be deceived by models' long, elaborate reasoning traces. In this paper, we present the first systematic investigation of the challenges and potential of CoT monitorability. Motivated by two fundamental challenges we mentioned before, we structure our study around two central perspectives: (i) verbalization: to what extent do LRMs faithfully verbalize the true factors guiding their decisions in the CoT, and (ii) monitor reliability: to what extent can misbehavior be reliably detected by a CoT-based monitor? Specifically, we provide empirical evidence and correlation analyses between verbalization quality, monitor reliability, and LLM performance across mathematical, scientific, and ethical domains. Then we further investigate how different CoT intervention methods, designed to improve reasoning efficiency or performance, will affect monitoring effectiveness. Finally, we propose MoME, a new paradigm in which LLMs monitor other models' misbehavior through their CoT and provide structured judgments along with supporting evidence.

---

### AlphaResearch: Accelerating New Algorithm Discovery with Language Models

Authors: Zhaojian Yu, Kaiyue Feng, Yilun Zhao, Shilin He, Xiao-Ping Zhang, Arman Cohan
Published: 2025-11-11
Categories: cs.CL
arXiv: https://arxiv.org/abs/2511.08522v2

LLMs have made significant progress in complex but easy-to-verify problems, yet they still struggle with discovering the unknown. In this paper, we present \textbf{AlphaResearch}, an autonomous research agent designed to discover new algorithms on open-ended problems by iteratively running the following steps: (1) propose new ideas (2) program to verify (3) optimize the research proposals. To synergize the feasibility and innovation of the discovery process, we construct a novel dual environment by combining the execution-based verifiable reward and reward from simulated real-world peer review environment in AlphaResearch. We construct \textbf{\dataset}, a set of questions that includes an eight open-ended algorithmic problems competition to benchmark AlphaResearch. Experimental results show that AlphaResearch achieves stronger discovery performance than other agentic discovery systems on six open-ended problems. Notably, the algorithm discovered by AlphaResearch on the \emph{``packing circles''} problem achieves the best-of-known performance, surpassing the results of human researchers and strong baselines from recent work (e.g., AlphaEvolve). Additionally, we conduct a comprehensive analysis of the benefits and remaining challenges of autonomous research agent, providing valuable insights for future research.

---

### UniVA: Universal Video Agent towards Open-Source Next-Generation Video Generalist

Authors: Zhengyang Liang, Daoan Zhang, Huichi Zhou, Rui Huang, Bobo Li, Yuechen Zhang, Shengqiong Wu, Xiaohan Wang, Jiebo Luo, Lizi Liao, Hao Fei
Published: 2025-11-11
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.08521v1

While specialized AI models excel at isolated video tasks like generation or understanding, real-world applications demand complex, iterative workflows that combine these capabilities. To bridge this gap, we introduce UniVA, an open-source, omni-capable multi-agent framework for next-generation video generalists that unifies video understanding, segmentation, editing, and generation into cohesive workflows. UniVA employs a Plan-and-Act dual-agent architecture that drives a highly automated and proactive workflow: a planner agent interprets user intentions and decomposes them into structured video-processing steps, while executor agents execute these through modular, MCP-based tool servers (for analysis, generation, editing, tracking, etc.). Through a hierarchical multi-level memory (global knowledge, task context, and user-specific preferences), UniVA sustains long-horizon reasoning, contextual continuity, and inter-agent communication, enabling interactive and self-reflective video creation with full traceability. This design enables iterative and any-conditioned video workflows (e.g., text/image/video-conditioned generation $\rightarrow$ multi-round editing $\rightarrow$ object segmentation $\rightarrow$ compositional synthesis) that were previously cumbersome to achieve with single-purpose models or monolithic video-language models. We also introduce UniVA-Bench, a benchmark suite of multi-step video tasks spanning understanding, editing, segmentation, and generation, to rigorously evaluate such agentic video systems. Both UniVA and UniVA-Bench are fully open-sourced, aiming to catalyze research on interactive, agentic, and general-purpose video intelligence for the next generation of multimodal AI systems. (https://univa.online/)

---

### Clustering Guided Residual Neural Networks for Multi-Tx Localization in Molecular Communications

Authors: Ali Sonmez, Erencem Ozbey, Efe Feyzi Mantaroglu, H. Birkan Yilmaz
Published: 2025-11-11
Categories: cs.LG, cs.ET
arXiv: https://arxiv.org/abs/2511.08513v1

Transmitter localization in Molecular Communication via Diffusion is a critical topic with many applications. However, accurate localization of multiple transmitters is a challenging problem due to the stochastic nature of diffusion and overlapping molecule distributions at the receiver surface. To address these issues, we introduce clustering-based centroid correction methods that enhance robustness against density variations, and outliers. In addition, we propose two clusteringguided Residual Neural Networks, namely AngleNN for direction refinement and SizeNN for cluster size estimation. Experimental results show that both approaches provide significant improvements with reducing localization error between 69% (2-Tx) and 43% (4-Tx) compared to the K-means.

---

### CleverBirds: A Multiple-Choice Benchmark for Fine-grained Human Knowledge Tracing

Authors: Leonie Bossemeyer, Samuel Heinrich, Grant Van Horn, Oisin Mac Aodha
Published: 2025-11-11
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2511.08512v1

Mastering fine-grained visual recognition, essential in many expert domains, can require that specialists undergo years of dedicated training. Modeling the progression of such expertize in humans remains challenging, and accurately inferring a human learner's knowledge state is a key step toward understanding visual learning. We introduce CleverBirds, a large-scale knowledge tracing benchmark for fine-grained bird species recognition. Collected by the citizen-science platform eBird, it offers insight into how individuals acquire expertize in complex fine-grained classification. More than 40,000 participants have engaged in the quiz, answering over 17 million multiple-choice questions spanning over 10,000 bird species, with long-range learning patterns across an average of 400 questions per participant. We release this dataset to support the development and evaluation of new methods for visual knowledge tracing. We show that tracking learners' knowledge is challenging, especially across participant subgroups and question types, with different forms of contextual information offering varying degrees of predictive benefit. CleverBirds is among the largest benchmark of its kind, offering a substantially higher number of learnable concepts. With it, we hope to enable new avenues for studying the development of visual expertize over time and across individuals.

---

### Fast Multi-Organ Fine Segmentation in CT Images with Hierarchical Sparse Sampling and Residual Transformer

Authors: Xueqi Guo, Halid Ziya Yerebakan, Yoshihisa Shinagawa, Kritika Iyer, Gerardo Hermosillo Valadez
Published: 2025-11-11
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.08509v1

Multi-organ segmentation of 3D medical images is fundamental with meaningful applications in various clinical automation pipelines. Although deep learning has achieved superior performance, the time and memory consumption of segmenting the entire 3D volume voxel by voxel using neural networks can be huge. Classifiers have been developed as an alternative in cases with certain points of interest, but the trade-off between speed and accuracy remains an issue. Thus, we propose a novel fast multi-organ segmentation framework with the usage of hierarchical sparse sampling and a Residual Transformer. Compared with whole-volume analysis, the hierarchical sparse sampling strategy could successfully reduce computation time while preserving a meaningful hierarchical context utilizing multiple resolution levels. The architecture of the Residual Transformer segmentation network could extract and combine information from different levels of information in the sparse descriptor while maintaining a low computational cost. In an internal data set containing 10,253 CT images and the public dataset TotalSegmentator, the proposed method successfully improved qualitative and quantitative segmentation performance compared to the current fast organ classifier, with fast speed at the level of ~2.24 seconds on CPU hardware. The potential of achieving real-time fine organ segmentation is suggested.

---

### Introducing A Bangla Sentence - Gloss Pair Dataset for Bangla Sign Language Translation and Research

Authors: Neelavro Saha, Rafi Shahriyar, Nafis Ashraf Roudra, Saadman Sakib, Annajiat Alim Rasel
Published: 2025-11-11
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2511.08507v1

Bangla Sign Language (BdSL) translation represents a low-resource NLP task due to the lack of large-scale datasets that address sentence-level translation. Correspondingly, existing research in this field has been limited to word and alphabet level detection. In this work, we introduce Bangla-SGP, a novel parallel dataset consisting of 1,000 human-annotated sentence-gloss pairs which was augmented with around 3,000 synthetically generated pairs using syntactic and morphological rules through a rule-based Retrieval-Augmented Generation (RAG) pipeline. The gloss sequences of the spoken Bangla sentences are made up of individual glosses which are Bangla sign supported words and serve as an intermediate representation for a continuous sign. Our dataset consists of 1000 high quality Bangla sentences that are manually annotated into a gloss sequence by a professional signer. The augmentation process incorporates rule-based linguistic strategies and prompt engineering techniques that we have adopted by critically analyzing our human annotated sentence-gloss pairs and by working closely with our professional signer. Furthermore, we fine-tune several transformer-based models such as mBart50, Google mT5, GPT4.1-nano and evaluate their sentence-to-gloss translation performance using BLEU scores, based on these evaluation metrics we compare the model's gloss-translation consistency across our dataset and the RWTH-PHOENIX-2014T benchmark.

---

### Structured RAG for Answering Aggregative Questions

Authors: Omri Koshorek, Niv Granot, Aviv Alloni, Shahar Admati, Roee Hendel, Ido Weiss, Alan Arazi, Shay-Nitzan Cohen, Yonatan Belinkov
Published: 2025-11-11
Categories: cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2511.08505v1

Retrieval-Augmented Generation (RAG) has become the dominant approach for answering questions over large corpora. However, current datasets and methods are highly focused on cases where only a small part of the corpus (usually a few paragraphs) is relevant per query, and fail to capture the rich world of aggregative queries. These require gathering information from a large set of documents and reasoning over them. To address this gap, we propose S-RAG, an approach specifically designed for such queries. At ingestion time, S-RAG constructs a structured representation of the corpus; at inference time, it translates natural-language queries into formal queries over said representation. To validate our approach and promote further research in this area, we introduce two new datasets of aggregative queries: HOTELS and WORLD CUP. Experiments with S-RAG on the newly introduced datasets, as well as on a public benchmark, demonstrate that it substantially outperforms both common RAG systems and long-context LLMs.

---

### SPEAR-MM: Selective Parameter Evaluation and Restoration via Model Merging for Efficient Financial LLM Adaptation

Authors: Berkcan Kapusuzoglu, Supriyo Chakraborty, Renkun Ni, Stephen Rawls, Sambit Sahu
Published: 2025-11-11
Categories: cs.CL, cs.AI, cs.LG, math.SP
arXiv: https://arxiv.org/abs/2511.08500v1

Large language models (LLMs) adapted to financial domains often suffer from catastrophic forgetting of general reasoning capabilities essential for customer interactions and complex financial analysis. We introduce Selective Parameter Evaluation and Restoration via Model Merging (SPEAR-MM), a practical framework that preserves critical capabilities while enabling domain adaptation. Our method approximates layer-wise impact on external benchmarks through post-hoc analysis, then selectively freezes or restores transformer layers via spherical interpolation merging. Applied to LLaMA-3.1-8B for financial tasks, SPEAR-MM achieves 91.2% retention of general capabilities versus 69.7% for standard continual pretraining, while maintaining 94% of domain adaptation gains. The approach provides interpretable trade-off control and reduces computational costs by 90% crucial for resource-constrained financial institutions.

---