# Research Papers — 2025-11 · bundle page 134 of 197

> Full-text markdown of papers #6651–6700 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/134
[← Previous bundle](https://aipod.dev/papers/archive/2025-11/page/133.md)
[Next bundle →](https://aipod.dev/papers/archive/2025-11/page/135.md)

### Beyond Superficial Forgetting: Thorough Unlearning through Knowledge Density Estimation and Block Re-insertion

Authors: Feng Guo, Yuntao Wen, Shen Gao, Junshuo Zhang, Shuo Shang
Published: 2025-11-11
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2511.11667v2

Machine unlearning, which selectively removes harmful knowledge from a pre-trained model without retraining from scratch, is crucial for addressing privacy, regulatory compliance, and ethical concerns in Large Language Models (LLMs). However, existing unlearning methods often struggle to thoroughly remove harmful knowledge, leaving residual harmful knowledge that can be easily recovered. To address these limitations, we propose Knowledge Density-Guided Unlearning via Blocks Reinsertion (KUnBR), a novel approach that first identifies layers with rich harmful knowledge and then thoroughly eliminates the harmful knowledge via re-insertion strategy. Our method introduces knowledge density estimation to quantify and locate layers containing the most harmful knowledge, enabling precise unlearning. Additionally, we design a layer re-insertion strategy that extracts and re-inserts harmful knowledge-rich layers into the original LLM, bypassing gradient obstruction caused by cover layers and ensuring effective gradient propagation during unlearning. Extensive experiments conducted on several unlearning and general capability benchmarks demonstrate that KUnBR achieves state-of-the-art forgetting performance while maintaining model utility.

---

### Adaptive Stepsizing for Stochastic Gradient Langevin Dynamics in Bayesian Neural Networks

Authors: Rajit Rajpal, Benedict Leimkuhler, Yuanhao Jiang
Published: 2025-11-11
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2511.11666v3

Bayesian neural networks (BNNs) require scalable sampling algorithms to approximate posterior distributions over parameters. Existing stochastic gradient Markov Chain Monte Carlo (SGMCMC) methods are highly sensitive to the choice of stepsize and adaptive variants such as pSGLD typically fail to sample the correct invariant measure without addition of a costly divergence correction term. In this work, we build on the recently proposed `SamAdams' framework for timestep adaptation (Leimkuhler, Lohmann, and Whalley 2025), introducing an adaptive scheme: SA-SGLD, which employs time rescaling to modulate the stepsize according to a monitored quantity (typically the local gradient norm). SA-SGLD can automatically shrink stepsizes in regions of high curvature and expand them in flatter regions, improving both stability and mixing without introducing bias. We show that our method can achieve more accurate posterior sampling than SGLD on high-curvature 2D toy examples and in image classification with BNNs using sharp priors.

---

### Clifford Algebraic Rotor Embeddings : Maybe embeddings should start to CARE

Authors: Sameeksha Sriram, Ayush Paliwal, Alexander S. Ecker, Chase van de Geijn
Published: 2025-11-11
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2511.11665v1

Rotary Positional Embeddings (RoPE) have demonstrated exceptional performance as a positional encoding method, consistently outperforming their baselines. While recent work has sought to extend RoPE to higher-dimensional inputs, many such extensions are non-commutative, thereby forfeiting RoPE's shift-equivariance property. Spherical RoPE is one such non-commutative variant, motivated by the idea of rotating embedding vectors on spheres rather than circles. However, spherical rotations are inherently non-commutative, making the choice of rotation sequence ambiguous. In this work, we explore a quaternion-based approach -- Quaternion Rotary Embeddings (QuatRo) -- in place of Euler angles, leveraging quaternions' ability to represent 3D rotations to parameterize the axes of rotation. We show Mixed RoPE and Spherical RoPE to be special cases of QuatRo. Further, we propose a generalization of QuatRo to Clifford Algebraic Rotary Embeddings (CARE) using geometric algebra. Viewing quaternions as the even subalgebra of Cl(3,0,0), we extend the notion of rotary embeddings from quaternions to Clifford rotors acting on multivectors. This formulation enables two key generalizations: (1) extending rotary embeddings to arbitrary dimensions, and (2) encoding positional information in multivectors of multiple grades, not just vectors. We present preliminary experiments comparing spherical, quaternion, and Clifford-based rotary embeddings.

---

### Range Asymmetric Numeral Systems-Based Lightweight Intermediate Feature Compression for Split Computing of Deep Neural Networks

Authors: Mingyu Sung, Suhwan Im, Vikas Palakonda, Jae-Mo Kang
Published: 2025-11-11
Categories: cs.DC, cs.AI, cs.CV
arXiv: https://arxiv.org/abs/2511.11664v1

Split computing distributes deep neural network inference between resource-constrained edge devices and cloud servers but faces significant communication bottlenecks when transmitting intermediate features. To this end, in this paper, we propose a novel lightweight compression framework that leverages Range Asymmetric Numeral Systems (rANS) encoding with asymmetric integer quantization and sparse tensor representation to reduce transmission overhead dramatically. Specifically, our approach combines asymmetric integer quantization with a sparse representation technique, eliminating the need for complex probability modeling or network modifications. The key contributions include: (1) a distribution-agnostic compression pipeline that exploits inherent tensor sparsity to achieve bandwidth reduction with minimal computational overhead; (2) an approximate theoretical model that optimizes tensor reshaping dimensions to maximize compression efficiency; and (3) a GPU-accelerated implementation with sub-millisecond encoding/decoding latency. Extensive evaluations across diverse neural architectures (ResNet, VGG16, MobileNetV2, SwinT, DenseNet121, EfficientNetB0) demonstrate that the proposed framework consistently maintains near-baseline accuracy across CIFAR100 and ImageNet benchmarks. Moreover, we validated the framework's effectiveness on advanced natural language processing tasks by employing Llama2 7B and 13B on standard benchmarks such as MMLU, HellaSwag, ARC, PIQA, Winogrande, BoolQ, and OpenBookQA, demonstrating its broad applicability beyond computer vision. Furthermore, this method addresses a fundamental bottleneck in deploying sophisticated artificial intelligence systems in bandwidth-constrained environments without compromising model performance.

---

### SpecQuant: Spectral Decomposition and Adaptive Truncation for Ultra-Low-Bit LLMs Quantization

Authors: Zhixiong Zhao, Fangxin Liu, Junjie Wang, Chenyang Guan, Zongwu Wang, Li Jiang, Haibing Guan
Published: 2025-11-11
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2511.11663v2

The emergence of accurate open large language models (LLMs) has sparked a push for advanced quantization techniques to enable efficient deployment on end-user devices. In this paper, we revisit the challenge of extreme LLM compression -- targeting ultra-low-bit quantization for both activations and weights -- from a Fourier frequency domain perspective. We propose SpecQuant, a two-stage framework that tackles activation outliers and cross-channel variance. In the first stage, activation outliers are smoothed and transferred into the weight matrix to simplify downstream quantization. In the second stage, we apply channel-wise low-frequency Fourier truncation to suppress high-frequency components while preserving essential signal energy, improving quantization robustness. Our method builds on the principle that most of the weight energy is concentrated in low-frequency components, which can be retained with minimal impact on model accuracy. To enable runtime adaptability, we introduce a lightweight truncation module during inference that adjusts truncation thresholds based on channel characteristics. On LLaMA-3 8B, SpecQuant achieves 4-bit quantization for both weights and activations, narrowing the zero-shot accuracy gap to only 1.5% compared to full precision, while delivering 2 times faster inference and 3times lower memory usage. Code will be available at https://github.com/Kishon-zzx/SpecQuant.

---

### AGENet: Adaptive Edge-aware Geodesic Distance Learning for Few-Shot Medical Image Segmentation

Authors: Ziyuan Gao
Published: 2025-11-11
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.11662v2

Medical image segmentation requires large annotated datasets, creating a significant bottleneck for clinical applications. While few-shot segmentation methods can learn from minimal examples, existing approaches demonstrate suboptimal performance in precise boundary delineation for medical images, particularly when anatomically similar regions appear without sufficient spatial context. We propose AGENet (Adaptive Geodesic Edge-aware Network), a novel framework that incorporates spatial relationships through edge-aware geodesic distance learning. Our key insight is that medical structures follow predictable geometric patterns that can guide prototype extraction even with limited training data. Unlike methods relying on complex architectural components or heavy neural networks, our approach leverages computationally lightweight geometric modeling. The framework combines three main components: (1) An edge-aware geodesic distance learning module that respects anatomical boundaries through iterative Fast Marching refinement, (2) adaptive prototype extraction that captures both global structure and local boundary details via spatially-weighted aggregation, and (3) adaptive parameter learning that automatically adjusts to different organ characteristics. Extensive experiments across diverse medical imaging datasets demonstrate improvements over state-of-the-art methods. Notably, our method reduces boundary errors compared to existing approaches while maintaining computational efficiency, making it highly suitable for clinical applications requiring precise segmentation with limited annotated data.

---

### DWFF-Net: A Multi-Scale Farmland System Habitat Identification Method with Adaptive Dynamic Weight Feature Fusion

Authors: Kesong Zheng, Zhi Song, Peizhou Li, Shuyi Yao, Tong Li, Yonglin Shen, Zhenxing Bian
Published: 2025-11-11
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.11659v3

To address insufficient accuracy in multi-scale segmentation for agricultural habitat recognition, this study proposes a Dynamic Weighted Feature Fusion Network (DWFF-Net). Its encoder uses frozen DINOv3 to extract basic features and introduces a data-level adaptive dynamic weighting strategy based on relationships between image categories and feature maps. The decoder employs a dynamic weight calculation network for deep fusion of multi-level features and a hybrid loss for optimization. Statistical analysis shows that weight entropy tends to decrease as habitat category count increases, indicating adaptive adjustment of fusion strategy according to scene complexity. Experiments on a previously constructed agricultural habitat dataset validate DWFF-Net. Ablations yield mIoU 0.6979 and mF1 0.8049, exceeding the Static Weighted Feature Fusion Network by 1.82% and 1.54%, respectively, confirming that dynamic weighting improves multi-level feature utilization. Compared with U-Net, DeepLabv3+, SegFormer, and DPT, DWFF-Net improves mIoU by 16.32%, 6.49%, 4.17%, and 3.18%, respectively. For tiny features like scattered trees, IoU reaches 0.2707, outperforming those models by 99.85%, 11.45%, 22.24%, and 19.32%, verifying effectiveness in tiny habitat segmentation. This framework enables low-cost, high-precision habitat mapping and supports refined monitoring in agricultural landscapes.

---

### Who Gets the Reward & Who Gets the Blame? Evaluation-Aligned Training Signals for Multi-LLM Agents

Authors: Chih-Hsuan, Yang, Tanwi Mallick, Le Chen, Krishnan Raghavan, Amal Gueroudji, Ian T. Foster, Rajeev Thakur
Published: 2025-11-11
Categories: cs.MA, cs.AI, cs.CL, cs.GT
arXiv: https://arxiv.org/abs/2511.10687v3

Large Language Models (LLMs) in multi-agent systems (MAS) have shown promise for complex tasks, yet current training methods lack principled ways to connect system-level evaluation with agent- and message-level learning. We propose a theoretical framework that unifies cooperative game-theoretic attribution with process reward modeling to transform system evaluation to agent credit to response-level signals. Unlike prior approaches that rely only on attribution (Shapley) or step-level labels (PRM), our method produces local, signed, and credit-conserving signals. In success cases, Shapley-based credit assignment fairly allocates outcomes across agents and is refined into per-message rewards that promote cooperation while discouraging redundancy or sabotage; in failure cases, first-error localization yields repair-aware preferences that penalize harmful steps while rewarding corrective attempts. The resulting signals are bounded, cooperative, and directly compatible with reinforcement- or preference-based post-training, providing a unified and auditable pathway from global evaluation to local supervision in LLM multi-agent training. Our contribution is conceptual: we present a theoretical foundation and training signals, leaving empirical validation for future work.

---

### A methodological analysis of prompt perturbations and their effect on attack success rates

Authors: Tiago Machado, Maysa Malfiza Garcia de Macedo, Rogerio Abreu de Paula, Marcelo Carpinette Grave, Aminat Adebiyi, Luan Soares de Souza, Enrico Santarelli, Claudio Pinhanez
Published: 2025-11-11
Categories: cs.CL
arXiv: https://arxiv.org/abs/2511.10686v1

This work aims to investigate how different Large Language Models (LLMs) alignment methods affect the models' responses to prompt attacks. We selected open source models based on the most common alignment methods, namely, Supervised Fine-Tuning (SFT), Direct Preference Optimization (DPO), and Reinforcement Learning with Human Feedback (RLHF). We conducted a systematic analysis using statistical methods to verify how sensitive the Attack Success Rate (ASR) is when we apply variations to prompts designed to elicit inappropriate content from LLMs. Our results show that even small prompt modifications can significantly change the Attack Success Rate (ASR) according to the statistical tests we run, making the models more or less susceptible to types of attack. Critically, our results demonstrate that running existing 'attack benchmarks' alone may not be sufficient to elicit all possible vulnerabilities of both models and alignment methods. This paper thus contributes to ongoing efforts on model attack evaluation by means of systematic and statistically-based analyses of the different alignment methods and how sensitive their ASR is to prompt variation.

---

### SpiderGen: Towards Procedure Generation For Carbon Life Cycle Assessments with Generative AI

Authors: Anupama Sitaraman, Bharathan Balaji, Yuvraj Agarwal
Published: 2025-11-11
Categories: cs.CL, cs.CY
arXiv: https://arxiv.org/abs/2511.10684v4

Investigating the effects of climate change and global warming caused by GHG emissions have been a key concern worldwide. These emissions are largely contributed to by the production, use and disposal of consumer products. Thus, it is important to build tools to estimate the environmental impact of consumer goods, an essential part of which is conducting Life Cycle Assessments (LCAs). LCAs specify and account for the appropriate processes involved with the production, use, and disposal of the products. We present SpiderGen, an LLM-based workflow which integrates the taxonomy and methodology of traditional LCA with the reasoning capabilities and world knowledge of LLMs to generate graphical representations of the key procedural information used for LCA, known as Product Category Rules Process Flow Graphs (PCR PFGs). We additionally evaluate the output of SpiderGen by comparing it with 65 real-world LCA documents. We find that SpiderGen provides accurate LCA process information that is either fully correct or has minor errors, achieving an F1-Score of 65% across 10 sample data points, as compared to 53% using a one-shot prompting method. We observe that the remaining errors occur primarily due to differences in detail between LCA documents, as well as differences in the "scope" of which auxiliary processes must also be included. We also demonstrate that SpiderGen performs better than several baselines techniques, such as chain-of-thought prompting and one-shot prompting. Finally, we highlight SpiderGen's potential to reduce the human effort and costs for estimating carbon impact, as it is able to produce LCA process information for less than \$1 USD in under 10 minutes as compared to the status quo LCA, which can cost over \$25000 USD and take up to 21-person days.

---

### LT-Soups: Bridging Head and Tail Classes via Subsampled Model Soups

Authors: Masih Aminbeidokhti, Subhankar Roy, Eric Granger, Elisa Ricci, Marco Pedersoli
Published: 2025-11-11
Categories: cs.LG, cs.CV
arXiv: https://arxiv.org/abs/2511.10683v2

Real-world datasets typically exhibit long-tailed (LT) distributions, where a few head classes dominate and many tail classes are severely underrepresented. While recent work shows that parameter-efficient fine-tuning (PEFT) methods like LoRA and AdaptFormer preserve tail-class performance on foundation models such as CLIP, we find that they do so at the cost of head-class accuracy. We identify the head-tail ratio, the proportion of head to tail classes, as a crucial but overlooked factor influencing this trade-off. Through controlled experiments on CIFAR100 with varying imbalance ratio ($ρ$) and head-tail ratio ($η$), we show that PEFT excels in tail-heavy scenarios but degrades in more balanced and head-heavy distributions. To overcome these limitations, we propose LT-Soups, a two-stage model soups framework designed to generalize across diverse LT regimes. In the first stage, LT-Soups averages models fine-tuned on balanced subsets to reduce head-class bias; in the second, it fine-tunes only the classifier on the full dataset to restore head-class accuracy. Experiments across six benchmark datasets show that LT-Soups achieves superior trade-offs compared to both PEFT and traditional model soups across a wide range of imbalance regimes.

---

### LAD-BNet: Lag-Aware Dual-Branch Networks for Real-Time Energy Forecasting on Edge Devices

Authors: Jean-Philippe Lignier
Published: 2025-11-11
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2511.10680v2

Real-time energy forecasting on edge devices represents a major challenge for smart grid optimization and intelligent buildings. We present LAD-BNet (Lag-Aware Dual-Branch Network), an innovative neural architecture optimized for edge inference with Google Coral TPU. Our hybrid approach combines a branch dedicated to explicit exploitation of temporal lags with a Temporal Convolutional Network (TCN) featuring dilated convolutions, enabling simultaneous capture of short and long-term dependencies. Tested on real energy consumption data with 10-minute temporal resolution, LAD-BNet achieves 14.49% MAPE at 1-hour horizon with only 18ms inference time on Edge TPU, representing an 8-12 x acceleration compared to CPU. The multi-scale architecture enables predictions up to 12 hours with controlled performance degradation. Our model demonstrates a 2.39% improvement over LSTM baselines and 3.04% over pure TCN architectures, while maintaining a 180MB memory footprint suitable for embedded device constraints. These results pave the way for industrial applications in real-time energy optimization, demand management, and operational planning.

---

### Group Averaging for Physics Applications: Accuracy Improvements at Zero Training Cost

Authors: Valentino F. Foit, David W. Hogg, Soledad Villar
Published: 2025-11-11
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2511.09573v1

Many machine learning tasks in the natural sciences are precisely equivariant to particular symmetries. Nonetheless, equivariant methods are often not employed, perhaps because training is perceived to be challenging, or the symmetry is expected to be learned, or equivariant implementations are seen as hard to build. Group averaging is an available technique for these situations. It happens at test time; it can make any trained model precisely equivariant at a (often small) cost proportional to the size of the group; it places no requirements on model structure or training. It is known that, under mild conditions, the group-averaged model will have a provably better prediction accuracy than the original model. Here we show that an inexpensive group averaging can improve accuracy in practice. We take well-established benchmark machine learning models of differential equations in which certain symmetries ought to be obeyed. At evaluation time, we average the models over a small group of symmetries. Our experiments show that this procedure always decreases the average evaluation loss, with improvements of up to 37\% in terms of the VRMSE. The averaging produces visually better predictions for continuous dynamics. This short paper shows that, under certain common circumstances, there are no disadvantages to imposing exact symmetries; the ML4PS community should consider group averaging as a cheap and simple way to improve model accuracy.

---

### SynthTools: A Framework for Scaling Synthetic Tools for Agent Development

Authors: Tommaso Castellani, Naimeng Ye, Daksh Mittal, Thomson Yen, Emmanouil Koukoumidis, William Zeng, Hongseok Namkoong
Published: 2025-11-11
Categories: cs.AI, cs.LG, cs.SE
arXiv: https://arxiv.org/abs/2511.09572v2

For agentic systems to use external tools to solve complex, long-horizon tasks, we need a large set of diverse and controllable tool-use environments. We introduce SynthTools, a fully LLM-based pipeline spanning the entire lifecycle: environment generation, simulation, validation and task construction. By operating end-to-end through LLMs, our framework complements other tool-use environments bottlenecked by the complexity of real APIs, and ensures scalability and controllability by design. The framework consists of three components: top-down environment generation, which hierarchically constructs diverse, domain-grounded tool environments; environment simulation and validation, which ensures tools can be reliably emulated and filters out those that cannot; and bottom-up task and trajectory generation, which produces solvable and verifiable tasks together with multi-step trajectories, exposing control over difficulty, length, trajectory composition, and domain focus to guarantee flexibility. As a concrete instantiation, we release the dataset comprising $73{,}883$ validated tools across $6{,}800$ environments and $100$ fields, $79{,}925$ verifiable tasks as well as the pipeline to generate trajectories at scale. Training Qwen3 models of various sizes on a corpus of trajectories generated from these tasks yields gains across multiple tool-use benchmarks, including real APIs, indicating tool-use capabilities trained on synthetic data may transfer to some real environments. Together, these results suggest that SynthTools can serve as a useful infrastructure for large-scale training of tool-use agents.

---

### General Intelligence-based Fragmentation (GIF): A framework for peak-labeled spectra simulation

Authors: Margaret R. Martin, Soha Hassoun
Published: 2025-11-11
Categories: q-bio.QM, cs.AI
arXiv: https://arxiv.org/abs/2511.09571v1

Despite growing reference libraries and advanced computational tools, progress in the field of metabolomics remains constrained by low rates of annotating measured spectra. The recent developments of large language models (LLMs) have led to strong performance across a wide range of generation and reasoning tasks, spurring increased interest in LLMs' application to domain-specific scientific challenges, such as mass spectra annotation. Here, we present a novel framework, General Intelligence-based Fragmentation (GIF), that guides pretrained LLMs through spectra simulation using structured prompting and reasoning. GIF utilizes tagging, structured inputs/outputs, system prompts, instruction-based prompts, and iterative refinement. Indeed, GIF offers a structured alternative to ad hoc prompting, underscoring the need for systematic guidance of LLMs on complex scientific tasks. Using GIF, we evaluate current generalist LLMs' ability to use reasoning towards fragmentation and to perform intensity prediction after fine-tuning. We benchmark performance on a novel QA dataset, the MassSpecGym QA-sim dataset, that we derive from the MassSpecGym dataset. Through these implementations of GIF, we find that GPT-4o and GPT-4o-mini achieve a cosine similarity of 0.36 and 0.35 between the simulated and true spectra, respectively, outperforming other pretrained models including GPT-5, Llama-3.1, and ChemDFM, despite GPT-5's recency and ChemDFM's domain specialization. GIF outperforms several deep learning baselines. Our evaluation of GIF highlights the value of using LLMs not only for spectra simulation but for enabling human-in-the-loop workflows and structured, explainable reasoning in molecular fragmentation.

---

### Variable Neighborhood Search for the Electric Vehicle Routing Problem

Authors: David Woller, Viktor Kozák, Miroslav Kulich, Libor Přeučil
Published: 2025-11-11
Categories: cs.AI
arXiv: https://arxiv.org/abs/2511.09570v1

The Electric Vehicle Routing Problem (EVRP) extends the classical Vehicle Routing Problem (VRP) to reflect the growing use of electric and hybrid vehicles in logistics. Due to the variety of constraints considered in the literature, comparing approaches across different problem variants remains challenging. A minimalistic variant of the EVRP, known as the Capacitated Green Vehicle Routing Problem (CGVRP), was the focus of the CEC-12 competition held during the 2020 IEEE World Congress on Computational Intelligence. This paper presents the competition-winning approach, based on the Variable Neighborhood Search (VNS) metaheuristic. The method achieves the best results on the full competition dataset and also outperforms a more recent algorithm published afterward.

---

### Filtering Jump Markov Systems with Partially Known Dynamics: A Model-Based Deep Learning Approach

Authors: George Stamatelis, George C. Alexandropoulos
Published: 2025-11-11
Categories: cs.LG, eess.SY
arXiv: https://arxiv.org/abs/2511.09569v1

This paper presents the Jump Markov Filtering Network (JMFNet), a novel model-based deep learning framework for real-time state-state estimation in jump Markov systems with unknown noise statistics and mode transition dynamics. A hybrid architecture comprising two Recurrent Neural Networks (RNNs) is proposed: one for mode prediction and another for filtering that is based on a mode-augmented version of the recently presented KalmanNet architecture. The proposed RNNs are trained jointly using an alternating least squares strategy that enables mutual adaptation without supervision of the latent modes. Extensive numerical experiments on linear and nonlinear systems, including target tracking, pendulum angle tracking, Lorenz attractor dynamics, and a real-life dataset demonstrate that the proposed JMFNet framework outperforms classical model-based filters (e.g., interacting multiple models and particle filters) as well as model-free deep learning baselines, particularly in non-stationary and high-noise regimes. It is also showcased that JMFNet achieves a small yet meaningful improvement over the KalmanNet framework, which becomes much more pronounced in complicated systems or long trajectories. Finally, the method's performance is empirically validated to be consistent and reliable, exhibiting low sensitivity to initial conditions, hyperparameter selection, as well as to incorrect model knowledge

---

### VEDA: Generation of 3D Molecules via Variance-Exploding Diffusion with Annealing

Authors: Peining Zhang, Jinbo Bi, Minghu Song
Published: 2025-11-11
Categories: physics.chem-ph, cs.AI, cs.CV
arXiv: https://arxiv.org/abs/2511.09568v3

Diffusion models show promise for 3D molecular generation, but face a fundamental trade-off between sampling efficiency and conformational accuracy. While flow-based models are fast, they often produce geometrically inaccurate structures, as they have difficulty capturing the multimodal distributions of molecular conformations. In contrast, denoising diffusion models are more accurate but suffer from slow sampling, a limitation attributed to sub-optimal integration between diffusion dynamics and SE(3)-equivariant architectures. To address this, we propose VEDA, a unified SE(3)-equivariant framework that combines variance-exploding diffusion with annealing to efficiently generate conformationally accurate 3D molecular structures. Specifically, our key technical contributions include: (1) a VE schedule that enables noise injection functionally analogous to simulated annealing, improving 3D accuracy and reducing relaxation energy; (2) a novel preconditioning scheme that reconciles the coordinate-predicting nature of SE(3)-equivariant networks with a residual-based diffusion objective, and (3) a new arcsin-based scheduler that concentrates sampling in critical intervals of the logarithmic signal-to-noise ratio. On the QM9 and GEOM-DRUGS datasets, VEDA matches the sampling efficiency of flow-based models, achieving state-of-the-art valency stability and validity with only 100 sampling steps. More importantly, VEDA's generated structures are remarkably stable, as measured by their relaxation energy during GFN2-xTB optimization. The median energy change is only 1.72 kcal/mol, significantly lower than the 32.3 kcal/mol from its architectural baseline, SemlaFlow. Our framework demonstrates that principled integration of VE diffusion with SE(3)-equivariant architectures can achieve both high chemical accuracy and computational efficiency.

---

### Let the Experts Speak: Improving Survival Prediction & Calibration via Mixture-of-Experts Heads

Authors: Todd Morrill, Aahlad Puli, Murad Megjhani, Soojin Park, Richard Zemel
Published: 2025-11-11
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.09567v2

Deep mixture-of-experts models have attracted a lot of attention for survival analysis problems, particularly for their ability to cluster similar patients together. In practice, grouping often comes at the expense of key metrics such as calibration error and predictive accuracy. This is due to the restrictive inductive bias that mixture-of-experts imposes, that predictions for individual patients must look like predictions for the group they're assigned to. Might we be able to discover patient group structure, where it exists, while improving calibration and predictive accuracy? In this work, we introduce several discrete-time deep mixture-of-experts (MoE)-based architectures for survival analysis problems, one of which achieves all desiderata: clustering, calibration, and predictive accuracy. We show that a key differentiator between this array of MoEs is how expressive their experts are. We find that more expressive experts that tailor predictions per patient outperform experts that rely on fixed group prototypes.

---

### Spatio-Temporal Context Learning with Temporal Difference Convolution for Moving Infrared Small Target Detection

Authors: Houzhang Fang, Shukai Guo, Qiuhuan Chen, Yi Chang, Luxin Yan
Published: 2025-11-11
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.09352v2

Moving infrared small target detection (IRSTD) plays a critical role in practical applications, such as surveillance of unmanned aerial vehicles (UAVs) and UAV-based search system. Moving IRSTD still remains highly challenging due to weak target features and complex background interference. Accurate spatio-temporal feature modeling is crucial for moving target detection, typically achieved through either temporal differences or spatio-temporal (3D) convolutions. Temporal difference can explicitly leverage motion cues but exhibits limited capability in extracting spatial features, whereas 3D convolution effectively represents spatio-temporal features yet lacks explicit awareness of motion dynamics along the temporal dimension. In this paper, we propose a novel moving IRSTD network (TDCNet), which effectively extracts and enhances spatio-temporal features for accurate target detection. Specifically, we introduce a novel temporal difference convolution (TDC) re-parameterization module that comprises three parallel TDC blocks designed to capture contextual dependencies across different temporal ranges. Each TDC block fuses temporal difference and 3D convolution into a unified spatio-temporal convolution representation. This re-parameterized module can effectively capture multi-scale motion contextual features while suppressing pseudo-motion clutter in complex backgrounds, significantly improving detection performance. Moreover, we propose a TDC-guided spatio-temporal attention mechanism that performs cross-attention between the spatio-temporal features from the TDC-based backbone and a parallel 3D backbone. This mechanism models their global semantic dependencies to refine the current frame's features. Extensive experiments on IRSTD-UAV and public infrared datasets demonstrate that our TDCNet achieves state-of-the-art detection performance in moving target detection.

---

### 3D Guard-Layer: An Integrated Agentic AI Safety System for Edge Artificial Intelligence

Authors: Eren Kurshan, Yuan Xie, Paul Franzon
Published: 2025-11-11
Categories: cs.AR, cs.AI, cs.CR
arXiv: https://arxiv.org/abs/2511.08842v1

AI systems have found a wide range of real-world applications in recent years. The adoption of edge artificial intelligence, embedding AI directly into edge devices, is rapidly growing. Despite the implementation of guardrails and safety mechanisms, security vulnerabilities and challenges have become increasingly prevalent in this domain, posing a significant barrier to the practical deployment and safety of AI systems. This paper proposes an agentic AI safety architecture that leverages 3D to integrate a dedicated safety layer. It introduces an adaptive AI safety infrastructure capable of dynamically learning and mitigating attacks against the AI system. The system leverages the inherent advantages of co-location with the edge computing hardware to continuously monitor, detect and proactively mitigate threats to the AI system. The integration of local processing and learning capabilities enhances resilience against emerging network-based attacks while simultaneously improving system reliability, modularity, and performance, all with minimal cost and 3D integration overhead.

---

### Enhancing DPSGD via Per-Sample Momentum and Low-Pass Filtering

Authors: Xincheng Xu, Thilina Ranbaduge, Qing Wang, Thierry Rakotoarivelo, David Smith
Published: 2025-11-11
Categories: cs.LG, cs.AI, cs.CR
arXiv: https://arxiv.org/abs/2511.08841v1

Differentially Private Stochastic Gradient Descent (DPSGD) is widely used to train deep neural networks with formal privacy guarantees. However, the addition of differential privacy (DP) often degrades model accuracy by introducing both noise and bias. Existing techniques typically address only one of these issues, as reducing DP noise can exacerbate clipping bias and vice-versa. In this paper, we propose a novel method, \emph{DP-PMLF}, which integrates per-sample momentum with a low-pass filtering strategy to simultaneously mitigate DP noise and clipping bias. Our approach uses per-sample momentum to smooth gradient estimates prior to clipping, thereby reducing sampling variance. It further employs a post-processing low-pass filter to attenuate high-frequency DP noise without consuming additional privacy budget. We provide a theoretical analysis demonstrating an improved convergence rate under rigorous DP guarantees, and our empirical evaluations reveal that DP-PMLF significantly enhances the privacy-utility trade-off compared to several state-of-the-art DPSGD variants.

---

### Beyond Task-Oriented and Chitchat Dialogues: Proactive and Transition-Aware Conversational Agents

Authors: Yejin Yoon, Yuri Son, Namyoung So, Minseo Kim, Minsoo Cho, Chanhee Park, Seungshin Lee, Taeuk Kim
Published: 2025-11-11
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2511.08835v1

Conversational agents have traditionally been developed for either task-oriented dialogue (TOD) or open-ended chitchat, with limited progress in unifying the two. Yet, real-world conversations naturally involve fluid transitions between these modes. To address this gap, we introduce TACT (TOD-And-Chitchat Transition), a dataset designed for transition-aware dialogue modeling that incorporates structurally diverse and integrated mode flows. TACT supports both user- and agent-driven mode switches, enabling robust modeling of complex conversational dynamics. To evaluate an agent's ability to initiate and recover from mode transitions, we propose two new metrics -- Switch and Recovery. Models trained on TACT outperform baselines in both intent detection and mode transition handling. Moreover, applying Direct Preference Optimization (DPO) to TACT-trained models yields additional gains, achieving 75.74\% joint mode-intent accuracy and a 70.1\% win rate against GPT-4o in human evaluation. These results demonstrate that pairing structurally diverse data with DPO enhances response quality and transition control, paving the way for more proactive and transition-aware conversational agents.

---

### Enhancing Rotation-Invariant 3D Learning with Global Pose Awareness and Attention Mechanisms

Authors: Jiaxun Guo, Manar Amayri, Nizar Bouguila, Xin Liu, Wentao Fan
Published: 2025-11-11
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.08833v1

Recent advances in rotation-invariant (RI) learning for 3D point clouds typically replace raw coordinates with handcrafted RI features to ensure robustness under arbitrary rotations. However, these approaches often suffer from the loss of global pose information, making them incapable of distinguishing geometrically similar but spatially distinct structures. We identify that this limitation stems from the restricted receptive field in existing RI methods, leading to Wing-tip feature collapse, a failure to differentiate symmetric components (e.g., left and right airplane wings) due to indistinguishable local geometries. To overcome this challenge, we introduce the Shadow-informed Pose Feature (SiPF), which augments local RI descriptors with a globally consistent reference point (referred to as the 'shadow') derived from a learned shared rotation. This mechanism enables the model to preserve global pose awareness while maintaining rotation invariance. We further propose Rotation-invariant Attention Convolution (RIAttnConv), an attention-based operator that integrates SiPFs into the feature aggregation process, thereby enhancing the model's capacity to distinguish structurally similar components. Additionally, we design a task-adaptive shadow locating module based on the Bingham distribution over unit quaternions, which dynamically learns the optimal global rotation for constructing consistent shadows. Extensive experiments on 3D classification and part segmentation benchmarks demonstrate that our approach substantially outperforms existing RI methods, particularly in tasks requiring fine-grained spatial discrimination under arbitrary rotations.

---

### TIGER-MARL: Enhancing Multi-Agent Reinforcement Learning with Temporal Information through Graph-based Embeddings and Representations

Authors: Nikunj Gupta, Ludwika Twardecka, James Zachary Hare, Jesse Milzman, Rajgopal Kannan, Viktor Prasanna
Published: 2025-11-11
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2511.08832v1

In this paper, we propose capturing and utilizing \textit{Temporal Information through Graph-based Embeddings and Representations} or \textbf{TIGER} to enhance multi-agent reinforcement learning (MARL). We explicitly model how inter-agent coordination structures evolve over time. While most MARL approaches rely on static or per-step relational graphs, they overlook the temporal evolution of interactions that naturally arise as agents adapt, move, or reorganize cooperation strategies. Capturing such evolving dependencies is key to achieving robust and adaptive coordination. To this end, TIGER constructs dynamic temporal graphs of MARL agents, connecting their current and historical interactions. It then employs a temporal attention-based encoder to aggregate information across these structural and temporal neighborhoods, yielding time-aware agent embeddings that guide cooperative policy learning. Through extensive experiments on two coordination-intensive benchmarks, we show that TIGER consistently outperforms diverse value-decomposition and graph-based MARL baselines in task performance and sample efficiency. Furthermore, we conduct comprehensive ablation studies to isolate the impact of key design parameters in TIGER, revealing how structural and temporal factors can jointly shape effective policy learning in MARL. All codes can be found here: https://github.com/Nikunj-Gupta/tiger-marl.

---

### Physics-Informed Machine Learning for Characterizing System Stability

Authors: Tomoki Koike, Elizabeth Qian
Published: 2025-11-11
Categories: cs.LG, eess.SY, math.NA
arXiv: https://arxiv.org/abs/2511.08831v1

In the design and operation of complex dynamical systems, it is essential to ensure that all state trajectories of the dynamical system converge to a desired equilibrium within a guaranteed stability region. Yet, for many practical systems -- especially in aerospace -- this region cannot be determined a priori and is often challenging to compute. One of the most common methods for computing the stability region is to identify a Lyapunov function. A Lyapunov function is a positive function whose time derivative along system trajectories is non-positive, which provides a sufficient condition for stability and characterizes an estimated stability region. However, existing methods of characterizing a stability region via a Lyapunov function often rely on explicit knowledge of the system governing equations. In this work, we present a new physics-informed machine learning method of characterizing an estimated stability region by inferring a Lyapunov function from system trajectory data that treats the dynamical system as a black box and does not require explicit knowledge of the system governing equations. In our presented Lyapunov function Inference method (LyapInf), we propose a quadratic form for the unknown Lyapunov function and fit the unknown quadratic operator to system trajectory data by minimizing the average residual of the Zubov equation, a first-order partial differential equation whose solution yields a Lyapunov function. The inferred quadratic Lyapunov function can then characterize an ellipsoidal estimate of the stability region. Numerical results on benchmark examples demonstrate that our physics-informed stability analysis method successfully characterizes a near-maximal ellipsoid of the system stability region associated with the inferred Lyapunov function without requiring knowledge of the system governing equations.

---

### Neural Value Iteration

Authors: Yang You, Ufuk Çakır, Alex Schutz, Nick Hawes
Published: 2025-11-11
Categories: cs.AI
arXiv: https://arxiv.org/abs/2511.08825v3

The value function of a POMDP exhibits the piecewise-linear-convex (PWLC) property and can be represented as a finite set of hyperplanes, known as $α$-vectors. Most state-of-the-art POMDP solvers (offline planners) follow the point-based value iteration scheme, which performs Bellman backups on $α$-vectors at reachable belief points until convergence. However, since each $α$-vector is $|S|$-dimensional, these methods quickly become intractable for large-scale problems due to the prohibitive computational cost of Bellman backups. In this work, we demonstrate that the PWLC property allows a POMDP's value function to be alternatively represented as a finite set of neural networks. This insight enables a novel POMDP planning algorithm called \emph{Neural Value Iteration}, which combines the generalization capability of neural networks with the classical value iteration framework. Our approach achieves near-optimal solutions even in extremely large POMDPs that are intractable for existing offline solvers.

---

### DT-NVS: Diffusion Transformers for Novel View Synthesis

Authors: Wonbong Jang, Jonathan Tremblay, Lourdes Agapito
Published: 2025-11-11
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2511.08823v1

Generating novel views of a natural scene, e.g., every-day scenes both indoors and outdoors, from a single view is an under-explored problem, even though it is an organic extension to the object-centric novel view synthesis. Existing diffusion-based approaches focus rather on small camera movements in real scenes or only consider unnatural object-centric scenes, limiting their potential applications in real-world settings. In this paper we move away from these constrained regimes and propose a 3D diffusion model trained with image-only losses on a large-scale dataset of real-world, multi-category, unaligned, and casually acquired videos of everyday scenes. We propose DT-NVS, a 3D-aware diffusion model for generalized novel view synthesis that exploits a transformer-based architecture backbone. We make significant contributions to transformer and self-attention architectures to translate images to 3d representations, and novel camera conditioning strategies to allow training on real-world unaligned datasets. In addition, we introduce a novel training paradigm swapping the role of reference frame between the conditioning image and the sampled noisy input. We evaluate our approach on the 3D task of generalized novel view synthesis from a single input image and show improvements over state-of-the-art 3D aware diffusion models and deterministic approaches, while generating diverse outputs.

---

### BayesQ: Uncertainty-Guided Bayesian Quantization

Authors: Ismail Lamaakal, Chaymae Yahyati, Yassine Maleh, Khalid El Makkaoui, Ibrahim Ouahbi
Published: 2025-11-11
Categories: cs.LG, cs.CL, cs.CV
arXiv: https://arxiv.org/abs/2511.08821v1

We present BayesQ, an uncertainty-guided post-training quantization framework that is the first to optimize quantization under the posterior expected loss. BayesQ fits a lightweight Gaussian posterior over weights (diagonal Laplace by default; optional K-FAC/low-rank), whitens by the posterior covariance, designs codebooks to minimize posterior-expected distortion, and allocates mixed precision via a greedy knapsack that maximizes marginal expected-loss reduction per bit under a global budget. For scalar quantizers, posterior-expected MSE yields closed-form tables; task-aware proxies are handled by short Monte Carlo on a small calibration set. An optional calibration-only distillation aligns the quantized model with the posterior predictive teacher. At matched average bits/weight of 3.0/3.5/4.0, BayesQ improves over strong PTQ baselines on ResNet-50 (ImageNet) and BERT-base (GLUE) e.g., vs. GPTQ by $+1.5/+0.7/+0.3$ top-1 percentage points on RN50 and $+1.1/+0.4/+0.2$ GLUE points on BERT, while requiring one-time preprocessing comparable to a GPTQ pass. BayesQ reframes low-bit quantization as uncertainty-aware risk minimization in a practical, post-training pipeline.

---

### BNLI: A Linguistically-Refined Bengali Dataset for Natural Language Inference

Authors: Farah Binta Haque, Md Yasin, Shishir Saha, Md Shoaib Akhter Rafi, Farig Sadeque
Published: 2025-11-11
Categories: cs.CL
arXiv: https://arxiv.org/abs/2511.08813v1

Despite the growing progress in Natural Language Inference (NLI) research, resources for the Bengali language remain extremely limited. Existing Bengali NLI datasets exhibit several inconsistencies, including annotation errors, ambiguous sentence pairs, and inadequate linguistic diversity, which hinder effective model training and evaluation. To address these limitations, we introduce BNLI, a refined and linguistically curated Bengali NLI dataset designed to support robust language understanding and inference modeling. The dataset was constructed through a rigorous annotation pipeline emphasizing semantic clarity and balance across entailment, contradiction, and neutrality classes. We benchmarked BNLI using a suite of state-of-the-art transformer-based architectures, including multilingual and Bengali-specific models, to assess their ability to capture complex semantic relations in Bengali text. The experimental findings highlight the improved reliability and interpretability achieved with BNLI, establishing it as a strong foundation for advancing research in Bengali and other low-resource language inference tasks.

---

### A Neural-Operator Preconditioned Newton Method for Accelerated Nonlinear Solvers

Authors: Youngkyu Lee, Shanqing Liu, Jerome Darbon, George Em Karniadakis
Published: 2025-11-11
Categories: math.NA, cs.LG
arXiv: https://arxiv.org/abs/2511.08811v1

We propose a novel neural preconditioned Newton (NP-Newton) method for solving parametric nonlinear systems of equations. To overcome the stagnation or instability of Newton iterations caused by unbalanced nonlinearities, we introduce a fixed-point neural operator (FPNO) that learns the direct mapping from the current iterate to the solution by emulating fixed-point iterations. Unlike traditional line-search or trust-region algorithms, the proposed FPNO adaptively employs negative step sizes to effectively mitigate the effects of unbalanced nonlinearities. Through numerical experiments we demonstrate the computational efficiency and robustness of the proposed NP-Newton method across multiple real-world applications, especially for very strong nonlinearities.

---

### SIFT-Graph: Benchmarking Multimodal Defense Against Image Adversarial Attacks With Robust Feature Graph

Authors: Jingjie He, Weijie Liang, Zihan Shan, Matthew Caesar
Published: 2025-11-11
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.08810v1

Adversarial attacks expose a fundamental vulnerability in modern deep vision models by exploiting their dependence on dense, pixel-level representations that are highly sensitive to imperceptible perturbations. Traditional defense strategies typically operate within this fragile pixel domain, lacking mechanisms to incorporate inherently robust visual features. In this work, we introduce SIFT-Graph, a multimodal defense framework that enhances the robustness of traditional vision models by aggregating structurally meaningful features extracted from raw images using both handcrafted and learned modalities. Specifically, we integrate Scale-Invariant Feature Transform keypoints with a Graph Attention Network to capture scale and rotation invariant local structures that are resilient to perturbations. These robust feature embeddings are then fused with traditional vision model, such as Vision Transformer and Convolutional Neural Network, to form a unified, structure-aware and perturbation defensive model. Preliminary results demonstrate that our method effectively improves the visual model robustness against gradient-based white box adversarial attacks, while incurring only a marginal drop in clean accuracy.

---

### Adaptive graph Kolmogorov-Arnold network for 3D human pose estimation

Authors: Abu Taib Mohammed Shahjahan, A. Ben Hamza
Published: 2025-11-11
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.08809v1

Graph convolutional network (GCN)-based methods have shown strong performance in 3D human pose estimation by leveraging the natural graph structure of the human skeleton. However, their local receptive field limits their ability to capture long-range dependencies essential for handling occlusions and depth ambiguities. They also exhibit spectral bias, which prioritizes low-frequency components while struggling to model high-frequency details. In this paper, we introduce PoseKAN, an adaptive graph Kolmogorov-Arnold Network (KAN), framework that extends KANs to graph-based learning for 2D-to-3D pose lifting from a single image. Unlike GCNs that use fixed activation functions, KANs employ learnable functions on graph edges, allowing data-driven, adaptive feature transformations. This enhances the model's adaptability and expressiveness, making it more expressive in learning complex pose variations. Our model employs multi-hop feature aggregation, ensuring the body joints can leverage information from both local and distant neighbors, leading to improved spatial awareness. It also incorporates residual PoseKAN blocks for deeper feature refinement, and a global response normalization for improved feature selectivity and contrast. Extensive experiments on benchmark datasets demonstrate the competitive performance of our model against state-of-the-art methods.

---

### Effects of label noise on the classification of outlier observations

Authors: Matheus Vinícius Barreto de Farias, Mario de Castro
Published: 2025-11-11
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2511.08808v1

This study investigates the impact of adding noise to the training set classes in classification tasks using the BCOPS algorithm (Balanced and Conformal Optimized Prediction Sets), proposed by Guan & Tibshirani (2022). The BCOPS algorithm is an application of conformal prediction combined with a machine learning method to construct prediction sets such that the probability of the true class being included in the prediction set for a test observation meets a specified coverage guarantee. An observation is considered an outlier if its true class is not present in the training set. The study employs both synthetic and real datasets and conducts experiments to evaluate the prediction abstention rate for outlier observations and the model's robustness in this previously untested scenario. The results indicate that the addition of noise, even in small amounts, can have a significant effect on model performance.

---

### Toward Automated Cognitive Assessment in Parkinson's Disease Using Pretrained Language Models

Authors: Varada Khanna, Nilay Bhatt, Ikgyu Shin, Sule Tinaz, Yang Ren, Hua Xu, Vipina K. Keloth
Published: 2025-11-11
Categories: cs.CL
arXiv: https://arxiv.org/abs/2511.08806v1

Understanding how individuals with Parkinson's disease (PD) describe cognitive experiences in their daily lives can offer valuable insights into disease-related cognitive and emotional changes. However, extracting such information from unstructured patient narratives is challenging due to the subtle, overlapping nature of cognitive constructs. This study developed and evaluated natural language processing (NLP) models to automatically identify categories that reflect various cognitive processes from de-identified first-person narratives. Three model families, a Bio_ClinicalBERT-based span categorization model for nested entity recognition, a fine-tuned Meta-Llama-3-8B-Instruct model using QLoRA for instruction following, and GPT-4o mini evaluated under zero- and few-shot settings, were compared on their performance on extracting seven categories. Our findings indicated that model performance varied substantially across categories and model families. The fine-tuned Meta-Llama-3-8B-Instruct achieved the highest overall F1-scores (0.74 micro-average and 0.59 macro-average), particularly excelling in context-dependent categories such as thought and social interaction. Bio_ClinicalBERT exhibited high precision but low recall and performed comparable to Llama for some category types such as location and time but failed on other categories such as thought, emotion and social interaction. Compared to conventional information extraction tasks, this task presents a greater challenge due to the abstract and overlapping nature of narrative accounts of complex cognitive processes. Nonetheless, with continued refinement, these NLP systems hold promise for enabling low-burden, longitudinal monitoring of cognitive function and serving as a valuable complement to formal neuropsychological assessments in PD.

---

### Structured Uncertainty guided Clarification for LLM Agents

Authors: Manan Suri, Puneet Mathur, Nedim Lipka, Franck Dernoncourt, Ryan A. Rossi, Dinesh Manocha
Published: 2025-11-11
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2511.08798v2

LLM agents with tool-calling capabilities often fail when user instructions are ambiguous or incomplete, leading to incorrect invocations and task failures. Existing approaches operate in unstructured language spaces, generating clarifying questions through prompting strategies that lack principled criteria for determining which questions to ask and when to stop. We introduce a principled formulation of structured uncertainty that operates directly over tool parameters and their domains, cleanly separating specification uncertainty (what the user wants) from model uncertainty (what the LLM predicts). Our formulation uses Expected Value of Perfect Information (EVPI) to quantify the disambiguation value of each potential question, balanced against aspect-based cost modeling that prevents redundant questioning. We demonstrate the versatility of this formulation through two applications. First, SAGE-Agent uses structured uncertainty for inference-time question selection, achieving 7-39% higher coverage on ambiguous tasks while reducing clarification questions by 1.5-2.7x compared to strong prompting and uncertainty-based baselines. Second, we show that structured uncertainty provides effective training signals: uncertainty-guided reward modeling boosts When2Call accuracy from 36.5% to 65.2% (3B model) and 36.7% to 62.9% (7B model) through uncertainty-weighted GRPO training, demonstrating more sample-efficient reinforcement learning for tool-calling agents. To enable evaluation, we present ClarifyBench, the first multi-turn dynamic tool-calling disambiguation benchmark. Our results establish structured uncertainty as a principled framework that improves both inference-time interaction efficiency and training-time sample efficiency in tool-augmented agents.

---

### The Probably Approximately Correct Learning Model in Computational Learning Theory

Authors: Rocco A. Servedio
Published: 2025-11-11
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2511.08791v1

This survey paper gives an overview of various known results on learning classes of Boolean functions in Valiant's Probably Approximately Correct (PAC) learning model and its commonly studied variants.

---

### A Generalized Bias-Variance Decomposition for Bregman Divergences

Authors: David Pfau
Published: 2025-11-11
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2511.08789v1

The bias-variance decomposition is a central result in statistics and machine learning, but is typically presented only for the squared error. We present a generalization of the bias-variance decomposition where the prediction error is a Bregman divergence, which is relevant to maximum likelihood estimation with exponential families. While the result is already known, there was not previously a clear, standalone derivation, so we provide one for pedagogical purposes. A version of this note previously appeared on the author's personal website without context. Here we provide additional discussion and references to the relevant prior literature.

---

### WATSON-Net: Vetting, Validation, and Analysis of Transits from Space Observations with Neural Networks

Authors: M. Dévora-Pajares, F. J. Pozuelos, J. C. Suárez, M. González-Penedo, C. Dafonte
Published: 2025-11-11
Categories: astro-ph.EP, astro-ph.IM, cs.LG
arXiv: https://arxiv.org/abs/2511.08768v1

Context. As the number of detected transiting exoplanet candidates continues to grow, the need for robust and scalable automated tools to prioritize or validate them has become increasingly critical. Among the most promising solutions, deep learning models offer the ability to interpret complex diagnostic metrics traditionally used in the vetting process. Aims. In this work, we present WATSON-Net, a new open-source neural network classifier and data preparation package designed to compete with current state-of-the-art tools for vetting and validation of transiting exoplanet signals from space-based missions. Methods. Trained on Kepler Q1-Q17 DR25 data using 10-fold cross-validation, WATSON-Net produces ten independent models, each evaluated on dedicated validation and test sets. The ten models are calibrated and prepared to be extensible for TESS data by standardizing the input pipeline, allowing for performance assessment across different space missions. Results. For Kepler targets, WATSON-Net achieves a recall-at-precision of 0.99 (R@P0.99) of 0.903, ranking second, with only the ExoMiner network performing better (R@P0.99 = 0.936). For TESS signals, WATSON-Net emerges as the best-performing non-fine-tuned machine learning classifier, achieving a precision of 0.93 and a recall of 0.76 on a test set comprising confirmed planets and false positives. Both the model and its data preparation tools are publicly available in the dearwatson Python package, fully open-source and integrated into the vetting engine of the SHERLOCK pipeline.

---

### Hey Pentti, We Did (More of) It!: A Vector-Symbolic Lisp With Residue Arithmetic

Authors: Connor Hanley, Eilene Tomkins-Flanaganm, Mary Alexandria Kelly
Published: 2025-11-11
Categories: cs.LG, cs.AI, cs.PL
arXiv: https://arxiv.org/abs/2511.08767v1

Using Frequency-domain Holographic Reduced Representations (FHRRs), we extend a Vector-Symbolic Architecture (VSA) encoding of Lisp 1.5 with primitives for arithmetic operations using Residue Hyperdimensional Computing (RHC). Encoding a Turing-complete syntax over a high-dimensional vector space increases the expressivity of neural network states, enabling network states to contain arbitrarily structured representations that are inherently interpretable. We discuss the potential applications of the VSA encoding in machine learning tasks, as well as the importance of encoding structured representations and designing neural networks whose behavior is sensitive to the structure of their representations in virtue of attaining more general intelligent agents than exist at present.

---

### Information-Driven Fault Detection and Identification for Multi-Agent Spacecraft Systems: Collaborative On-Orbit Inspection Mission

Authors: Akshita Gupta, Arna Bhardwaj, Yashwanth Kumar Nakka, Changrak Choi, Amir Rahmani
Published: 2025-11-11
Categories: eess.SY, cs.AI, cs.MA, cs.RO
arXiv: https://arxiv.org/abs/2511.08752v1

This work presents a global-to-local, task-aware fault detection and identification (FDI) framework for multi-spacecraft systems conducting collaborative inspection missions in low Earth orbit. The inspection task is represented by a global information-driven cost functional that integrates the sensor model, spacecraft poses, and mission-level information-gain objectives. This formulation links guidance, control, and FDI by using the same cost function to drive both global task allocation and local sensing or motion decisions. Fault detection is achieved through comparisons between expected and observed task metrics, while higher-order cost-gradient measures enable the identification of faults among sensors, actuators, and state estimators. An adaptive thresholding mechanism captures the time-varying inspection geometry and dynamic mission conditions. Simulation results for representative multi-spacecraft inspection scenarios demonstrate the reliability of fault localization and classification under uncertainty, providing a unified, information-driven foundation for resilient autonomous inspection architectures.

---

### Interpretable by Design: Query-Specific Neural Modules for Explainable Reinforcement Learning

Authors: Mehrdad Zakershahrak
Published: 2025-11-11
Categories: cs.AI
arXiv: https://arxiv.org/abs/2511.08749v1

Reinforcement learning has traditionally focused on a singular objective: learning policies that select actions to maximize reward. We challenge this paradigm by asking: what if we explicitly architected RL systems as inference engines that can answer diverse queries about their environment? In deterministic settings, trained agents implicitly encode rich knowledge about reachability, distances, values, and dynamics - yet current architectures are not designed to expose this information efficiently. We introduce Query Conditioned Deterministic Inference Networks (QDIN), a unified architecture that treats different types of queries (policy, reachability, paths, comparisons) as first-class citizens, with specialized neural modules optimized for each inference pattern. Our key empirical finding reveals a fundamental decoupling: inference accuracy can reach near-perfect levels (99% reachability IoU) even when control performance remains suboptimal (31% return), suggesting that the representations needed for accurate world knowledge differ from those required for optimal control. Experiments demonstrate that query specialized architectures outperform both unified models and post-hoc extraction methods, while maintaining competitive control performance. This work establishes a research agenda for RL systems designed from inception as queryable knowledge bases, with implications for interpretability, verification, and human-AI collaboration.

---

### WiCV at CVPR 2025: The Women in Computer Vision Workshop

Authors: Estefania Talavera, Deblina Bhattacharjee, Himangi Mittal, Mengwei Ren, Karen Sanchez, Carla Muntean, JungEun Kim, Mona Jalal
Published: 2025-11-11
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.08748v1

The Women in Computer Vision Workshop (WiCV@CVPR 2025) was held in conjunction with the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2025) in Nashville, Tennessee, United States. This report presents an overview of the workshop program, participation statistics, mentorship outcomes, and historical trends from previous WiCV editions. The goal is to document the impact and evolution of WiCV as a reference for future editions and for other initiatives aimed at advancing diversity, equity, and inclusion within the AI and computer vision communities. WiCV@CVPR 2025 marked the 16th edition of this long-standing event dedicated to increasing the visibility, inclusion, and professional growth of women and underrepresented minorities in the computer vision community. This year's workshop featured 14 accepted papers in the CVPR Workshop Proceedings out of 32 full-paper submissions. Five of these were selected for oral presentations, while all 14 were also presented as posters, along with 36 extended abstract posters accepted from 62 short-paper submissions, which are not included in the proceedings. The mentoring program matched 80 mentees with 37 mentors from both academia and industry. The 2025 edition attracted over 100 onsite participants, fostering rich technical and networking interactions across all career stages. Supported by 10 sponsors and approximately $44,000 USD in travel grants and diversity awards, WiCV continued its mission to empower emerging researchers and amplify diverse voices in computer vision.

---

### Vector Symbolic Algebras for the Abstraction and Reasoning Corpus

Authors: Isaac Joffe, Chris Eliasmith
Published: 2025-11-11
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2511.08747v1

The Abstraction and Reasoning Corpus for Artificial General Intelligence (ARC-AGI) is a generative, few-shot fluid intelligence benchmark. Although humans effortlessly solve ARC-AGI, it remains extremely difficult for even the most advanced artificial intelligence systems. Inspired by methods for modelling human intelligence spanning neuroscience to psychology, we propose a cognitively plausible ARC-AGI solver. Our solver integrates System 1 intuitions with System 2 reasoning in an efficient and interpretable process using neurosymbolic methods based on Vector Symbolic Algebras (VSAs). Our solver works by object-centric program synthesis, leveraging VSAs to represent abstract objects, guide solution search, and enable sample-efficient neural learning. Preliminary results indicate success, with our solver scoring 10.8% on ARC-AGI-1-Train and 3.0% on ARC-AGI-1-Eval. Additionally, our solver performs well on simpler benchmarks, scoring 94.5% on Sort-of-ARC and 83.1% on 1D-ARC -- the latter outperforming GPT-4 at a tiny fraction of the computational cost. Importantly, our approach is unique; we believe we are the first to apply VSAs to ARC-AGI and have developed the most cognitively plausible ARC-AGI solver yet. Our code is available at: https://github.com/ijoffe/ARC-VSA-2025.

---

### A Deep Learning-Based Method for Fully Coupled Non-Markovian FBSDEs with Applications

Authors: Hasib Uddin Molla, Matthew Backhouse, Ankit Banarjee, Jinniao Qiu
Published: 2025-11-11
Categories: q-fin.MF, cs.LG
arXiv: https://arxiv.org/abs/2511.08735v2

In this work, we extend deep learning-based numerical methods to fully coupled forward-backward stochastic differential equations (FBSDEs) within a non-Markovian framework. Error estimates and convergence are provided. In contrast to the existing literature, our approach not only analyzes the non-Markovian framework but also addresses fully coupled settings, in which both the drift and diffusion coefficients of the forward process may be random and depend on the backward components $Y$ and $Z$. Furthermore, we illustrate the practical applicability of our framework by addressing utility maximization problems under rough volatility, which are solved numerically with the proposed deep learning-based methods.

---

### Gromov-Wasserstein Graph Coarsening

Authors: Carlos A. Taveras, Santiago Segarra, César A. Uribe
Published: 2025-11-11
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.08733v1

We study the problem of graph coarsening within the Gromov-Wasserstein geometry. Specifically, we propose two algorithms that leverage a novel representation of the distortion induced by merging pairs of nodes. The first method, termed Greedy Pair Coarsening (GPC), iteratively merges pairs of nodes that locally minimize a measure of distortion until the desired size is achieved. The second method, termed $k$-means Greedy Pair Coarsening (KGPC), leverages clustering based on pairwise distortion metrics to directly merge clusters of nodes. We provide conditions guaranteeing optimal coarsening for our methods and validate their performance on six large-scale datasets and a downstream clustering task. Results show that the proposed methods outperform existing approaches on a wide range of parameters and scenarios.

---

### Intuitive Programming, Adaptive Task Planning, and Dynamic Role Allocation in Human-Robot Collaboration

Authors: Marta Lagomarsino, Elena Merlo, Andrea Pupa, Timo Birr, Franziska Krebs, Cristian Secchi, Tamim Asfour, Arash Ajoudani
Published: 2025-11-11
Categories: cs.RO, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2511.08732v1

Remarkable capabilities have been achieved by robotics and AI, mastering complex tasks and environments. Yet, humans often remain passive observers, fascinated but uncertain how to engage. Robots, in turn, cannot reach their full potential in human-populated environments without effectively modeling human states and intentions and adapting their behavior. To achieve a synergistic human-robot collaboration (HRC), a continuous information flow should be established: humans must intuitively communicate instructions, share expertise, and express needs. In parallel, robots must clearly convey their internal state and forthcoming actions to keep users informed, comfortable, and in control. This review identifies and connects key components enabling intuitive information exchange and skill transfer between humans and robots. We examine the full interaction pipeline: from the human-to-robot communication bridge translating multimodal inputs into robot-understandable representations, through adaptive planning and role allocation, to the control layer and feedback mechanisms to close the loop. Finally, we highlight trends and promising directions toward more adaptive, accessible HRC.

---

### Macroscopic Emission Modeling of Urban Traffic Using Probe Vehicle Data: A Machine Learning Approach

Authors: Mohammed Ali El Adlouni, Ling Jin, Xiaodan Xu, C. Anna Spurlock, Alina Lazar, Kaveh Farokhi Sadabadi, Mahyar Amirgholy, Mona Asudegi
Published: 2025-11-11
Categories: cs.LG, cs.CY
arXiv: https://arxiv.org/abs/2511.08722v1

Urban congestions cause inefficient movement of vehicles and exacerbate greenhouse gas emissions and urban air pollution. Macroscopic emission fundamental diagram (eMFD)captures an orderly relationship among emission and aggregated traffic variables at the network level, allowing for real-time monitoring of region-wide emissions and optimal allocation of travel demand to existing networks, reducing urban congestion and associated emissions. However, empirically derived eMFD models are sparse due to historical data limitation. Leveraging a large-scale and granular traffic and emission data derived from probe vehicles, this study is the first to apply machine learning methods to predict the network wide emission rate to traffic relationship in U.S. urban areas at a large scale. The analysis framework and insights developed in this work generate data-driven eMFDs and a deeper understanding of their location dependence on network, infrastructure, land use, and vehicle characteristics, enabling transportation authorities to measure carbon emissions from urban transport of given travel demand and optimize location specific traffic management and planning decisions to mitigate network-wide emissions.

---

### Benevolent Dictators? On LLM Agent Behavior in Dictator Games

Authors: Andreas Einwiller, Kanishka Ghosh Dastidar, Artur Romazanov, Annette Hautli-Janisz, Michael Granitzer, Florian Lemmerich
Published: 2025-11-11
Categories: cs.LG, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2511.08721v1

In behavioral sciences, experiments such as the ultimatum game are conducted to assess preferences for fairness or self-interest of study participants. In the dictator game, a simplified version of the ultimatum game where only one of two players makes a single decision, the dictator unilaterally decides how to split a fixed sum of money between themselves and the other player. Although recent studies have explored behavioral patterns of AI agents based on Large Language Models (LLMs) instructed to adopt different personas, we question the robustness of these results. In particular, many of these studies overlook the role of the system prompt - the underlying instructions that shape the model's behavior - and do not account for how sensitive results can be to slight changes in prompts. However, a robust baseline is essential when studying highly complex behavioral aspects of LLMs. To overcome previous limitations, we propose the LLM agent behavior study (LLM-ABS) framework to (i) explore how different system prompts influence model behavior, (ii) get more reliable insights into agent preferences by using neutral prompt variations, and (iii) analyze linguistic features in responses to open-ended instructions by LLM agents to better understand the reasoning behind their behavior. We found that agents often exhibit a strong preference for fairness, as well as a significant impact of the system prompt on their behavior. From a linguistic perspective, we identify that models express their responses differently. Although prompt sensitivity remains a persistent challenge, our proposed framework demonstrates a robust foundation for LLM agent behavior studies. Our code artifacts are available at https://github.com/andreaseinwiller/LLM-ABS.

---

### Practical considerations when designing an online learning algorithm for an app-based mHealth intervention

Authors: Rachel T Gonzalez, Madeline R Abbott, Brahmajee Nallamothu, Scott Hummel, Michael Dorsch, Walter Dempsey
Published: 2025-11-11
Categories: stat.ME, cs.LG, stat.AP, stat.ML
arXiv: https://arxiv.org/abs/2511.08719v1

The ubiquitous nature of mobile health (mHealth) technology has expanded opportunities for the integration of reinforcement learning into traditional clinical trial designs, allowing researchers to learn individualized treatment policies during the study. LowSalt4Life 2 (LS4L2) is a recent trial aimed at reducing sodium intake among hypertensive individuals through an app-based intervention. A reinforcement learning algorithm, which was deployed in one of the trial arms, was designed to send reminder notifications to promote app engagement in contexts where the notification would be effective, i.e., when a participant is likely to open the app in the next 30-minute and not when prior data suggested reduced effectiveness. Such an algorithm can improve app-based mHealth interventions by reducing participant burden and more effectively promoting behavior change. We encountered various challenges during the implementation of the learning algorithm, which we present as a template to solving challenges in future trials that deploy reinforcement learning algorithms. We provide template solutions based on LS4L2 for solving the key challenges of (i) defining a relevant reward, (ii) determining a meaningful timescale for optimization, (iii) specifying a robust statistical model that allows for automation, (iv) balancing model flexibility with computational cost, and (v) addressing missing values in gradually collected data.

---