# Research Papers — 2025-11 · bundle page 191 of 197

> Full-text markdown of papers #9501–9550 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/191
[← Previous bundle](https://aipod.dev/papers/archive/2025-11/page/190.md)
[Next bundle →](https://aipod.dev/papers/archive/2025-11/page/192.md)

### Stability of the Kim--Milman flow map

Authors: Sinho Chewi, Aram-Alexandre Pooladian, Matthew S. Zhang
Published: 2025-11-03
Categories: math.PR, cs.LG, math.ST
arXiv: https://arxiv.org/abs/2511.01154v2

In this short note, we characterize stability of the Kim--Milman flow map -- also known as the probability flow ODE -- with respect to variations in the target measure in relative Fisher information.

---

### Modular Task Decomposition and Dynamic Collaboration in Multi-Agent Systems Driven by Large Language Models

Authors: Shuaidong Pan, Di Wu
Published: 2025-11-03
Categories: cs.AI
arXiv: https://arxiv.org/abs/2511.01149v1

This paper addresses the limitations of a single agent in task decomposition and collaboration during complex task execution, and proposes a multi-agent architecture for modular task decomposition and dynamic collaboration based on large language models. The method first converts natural language task descriptions into unified semantic representations through a large language model. On this basis, a modular decomposition mechanism is introduced to break down the overall goal into multiple hierarchical sub-tasks. Then, dynamic scheduling and routing mechanisms enable reasonable division of labor and realtime collaboration among agents, allowing the system to adjust strategies continuously according to environmental feedback, thus maintaining efficiency and stability in complex tasks. Furthermore, a constraint parsing and global consistency mechanism is designed to ensure coherent connections between sub-tasks and balanced workload, preventing performance degradation caused by redundant communication or uneven resource allocation. The experiments validate the architecture across multiple dimensions, including task success rate, decomposition efficiency, sub-task coverage, and collaboration balance. The results show that the proposed method outperforms existing approaches in both overall performance and robustness, achieving a better balance between task complexity and communication overhead. In conclusion, this study demonstrates the effectiveness and feasibility of language-driven task decomposition and dynamic collaboration in multi-agent systems, providing a systematic solution for task execution in complex environments.

---

### AthenaBench: A Dynamic Benchmark for Evaluating LLMs in Cyber Threat Intelligence

Authors: Md Tanvirul Alam, Dipkamal Bhusal, Salman Ahmad, Nidhi Rastogi, Peter Worth
Published: 2025-11-03
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2511.01144v2

Large Language Models (LLMs) have demonstrated strong capabilities in natural language reasoning, yet their application to Cyber Threat Intelligence (CTI) remains limited. CTI analysis involves distilling large volumes of unstructured reports into actionable knowledge, a process where LLMs could substantially reduce analyst workload. CTIBench introduced a comprehensive benchmark for evaluating LLMs across multiple CTI tasks. In this work, we extend CTIBench by developing AthenaBench, an enhanced benchmark that includes an improved dataset creation pipeline, duplicate removal, refined evaluation metrics, and a new task focused on risk mitigation strategies. We evaluate twelve LLMs, including state-of-the-art proprietary models such as GPT-5 and Gemini-2.5 Pro, alongside seven open-source models from the LLaMA and Qwen families. While proprietary LLMs achieve stronger results overall, their performance remains subpar on reasoning-intensive tasks, such as threat actor attribution and risk mitigation, with open-source models trailing even further behind. These findings highlight fundamental limitations in the reasoning capabilities of current LLMs and underscore the need for models explicitly tailored to CTI workflows and automation.

---

### MicroAUNet: Boundary-Enhanced Multi-scale Fusion with Knowledge Distillation for Colonoscopy Polyp Image Segmentation

Authors: Ziyi Wang, Yuanmei Zhang, Baoying Ye, Yimei Jiang, Leilei Gu, Suncheng Xiang
Published: 2025-11-03
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2511.01143v2

Early and accurate segmentation of colorectal polyps is critical for reducing colorectal cancer mortality, which has been extensively explored by academia and industry. However, current deep learning-based polyp segmentation models either compromise clinical decision-making by providing ambiguous polyp margins in segmentation outputs or rely on heavy architectures with high computational complexity, resulting in insufficient inference speeds for real-time colorectal endoscopic applications. To address this problem, we propose MicroAUNet, a lightweight attention-based segmentation network, which synergistically combines depthwise-separable dilated convolutions with a single-path, parameter-shared channel-spatial attention block to effectively strengthen multi-scale boundary features. On the basis of it, a progressive two-stage knowledge-distillation scheme is introduced to transfer semantic and boundary cues from a high-capacity teacher. Extensive experiments on benchmarks also demonstrate the state-of-the-art accuracy under extremely low model complexity, indicating that MicroAUNet is suitable for real-time clinical polyp segmentation. The code is publicly available at https://github.com/JeremyXSC/MicroAUNet.

---

### Few-Shot Multimodal Medical Imaging: A Theoretical Framework

Authors: Md Talha Mohsin, Ismail Abdulrashid
Published: 2025-11-03
Categories: stat.ML, cs.AI, cs.CV, cs.LG, eess.IV
arXiv: https://arxiv.org/abs/2511.01140v2

Medical imaging often operates under limited labeled data, especially in rare disease and low resource clinical environments. Existing multimodal and meta learning approaches improve performance in these settings but lack a theoretical explanation of why or when they succeed. This paper presents a unified theoretical framework for few shot multimodal medical imaging that jointly characterizes sample complexity, uncertainty quantification, and interpretability. Using PAC learning, VC theory, and PAC Bayesian analysis, we derive bounds that describe the minimum number of labeled samples required for reliable performance and show how complementary modalities reduce effective capacity through an information gain term. We further introduce a formal metric for explanation stability, proving that explanation variance decreases at an inverse n rate. A sequential Bayesian interpretation of Chain of Thought reasoning is also developed to show stepwise posterior contraction. To illustrate these ideas, we implement a controlled multimodal dataset and evaluate an additive CNN MLP fusion model under few shot regimes, confirming predicted multimodal gains, modality interference at larger sample sizes, and shrinking predictive uncertainty. Together, the framework provides a principled foundation for designing data efficient, uncertainty aware, and interpretable diagnostic models in low resource settings.

---

### Learning with Category-Equivariant Architectures for Human Activity Recognition

Authors: Yoshihiro Maruyama
Published: 2025-11-03
Categories: cs.CV, cs.AI, cs.HC, cs.LG
arXiv: https://arxiv.org/abs/2511.01139v2

We propose CatEquiv, a category-equivariant neural network for Human Activity Recognition (HAR) from inertial sensors that systematically encodes temporal, amplitude, and structural symmetries. We introduce a symmetry category that jointly represents cyclic time shifts, positive gain scalings, and the sensor-hierarchy poset, capturing the categorical symmetry structure of the data. CatEquiv achieves equivariance with respect to the categorical symmetry product. On UCI-HAR under out-of-distribution perturbations, CatEquiv attains markedly higher robustness compared with circularly padded CNNs and plain CNNs. These results demonstrate that enforcing categorical symmetries yields strong invariance and generalization without additional model capacity.

---

### Regularization Implies balancedness in the deep linear network

Authors: Kathryn Lindsey, Govind Menon
Published: 2025-11-03
Categories: cs.LG, math.AG, math.DS, stat.ML
arXiv: https://arxiv.org/abs/2511.01137v2

We use geometric invariant theory (GIT) to study the deep linear network (DLN). The Kempf-Ness theorem is used to establish that the $L^2$ regularizer is minimized on the balanced manifold. We introduce related balancing flows using the Riemannian geometry of fibers. The balancing flow defined by the $L^2$ regularizer is shown to converge to the balanced manifold at a uniform exponential rate. The balancing flow defined by the squared moment map is computed explicitly and shown to converge globally. This framework allows us to decompose the training dynamics into two distinct gradient flows: a regularizing flow on fibers and a learning flow on the balanced manifold. It also provides a common mathematical framework for balancedness in deep learning and linear systems theory. We use this framework to interpret balancedness in terms of fast-slow systems, model reduction and Bayesian principles.

---

### Weakly Supervised Concept Learning with Class-Level Priors for Interpretable Medical Diagnosis

Authors: Md Nahiduzzaman, Steven Korevaar, Alireza Bab-Hadiashar, Ruwan Tennakoon
Published: 2025-11-03
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.01131v3

Human-interpretable predictions are essential for deploying AI in medical imaging, yet most interpretable-by-design (IBD) frameworks require concept annotations for training data, which are costly and impractical to obtain in clinical contexts. Recent attempts to bypass annotation, such as zero-shot vision-language models or concept-generation frameworks, struggle to capture domain-specific medical features, leading to poor reliability. In this paper, we propose a novel Prior-guided Concept Predictor (PCP), a weakly supervised framework that enables concept answer prediction without explicit supervision or reliance on language models. PCP leverages class-level concept priors as weak supervision and incorporates a refinement mechanism with KL divergence and entropy regularization to align predictions with clinical reasoning. Experiments on PH2 (dermoscopy) and WBCatt (hematology) show that PCP improves concept-level F1-score by over 33% compared to zero-shot baselines, while delivering competitive classification performance on four medical datasets (PH2, WBCatt, HAM10000, and CXR4) relative to fully supervised concept bottleneck models (CBMs) and V-IP.

---

### Boosting performance of computer vision applications through embedded GPUs on the edge

Authors: Fabio Diniz Rossi
Published: 2025-11-03
Categories: cs.CV, cs.DC
arXiv: https://arxiv.org/abs/2511.01129v1

Computer vision applications, especially those using augmented reality technology, are becoming quite popular in mobile devices. However, this type of application is known as presenting significant demands regarding resources. In order to enable its utilization in devices with more modest resources, edge computing can be used to offload certain high intensive tasks. Still, edge computing is usually composed of devices with limited capacity, which may impact in users quality of experience when using computer vision applications. This work proposes the use of embedded devices with graphics processing units (GPUs) to overcome such limitation. Experiments performed shown that GPUs can attain a performance gain when compared to using only CPUs, which guarantee a better experience to users using such kind of application.

---

### Stochastic Regret Guarantees for Online Zeroth- and First-Order Bilevel Optimization

Authors: Parvin Nazari, Bojian Hou, Davoud Ataee Tarzanagh, Li Shen, George Michailidis
Published: 2025-11-03
Categories: cs.LG, math.NA, math.OC, math.ST
arXiv: https://arxiv.org/abs/2511.01126v3

Online bilevel optimization (OBO) is a powerful framework for machine learning problems where both outer and inner objectives evolve over time, requiring dynamic updates. Current OBO approaches rely on deterministic \textit{window-smoothed} regret minimization, which may not accurately reflect system performance when functions change rapidly. In this work, we introduce a novel search direction and show that both first- and zeroth-order (ZO) stochastic OBO algorithms leveraging this direction achieve sublinear {stochastic bilevel regret without window smoothing}. Beyond these guarantees, our framework enhances efficiency by: (i) reducing oracle dependence in hypergradient estimation, (ii) updating inner and outer variables alongside the linear system solution, and (iii) employing ZO-based estimation of Hessians, Jacobians, and gradients. Experiments on online parametric loss tuning and black-box adversarial attacks validate our approach.

---

### One model to solve them all: 2BSDE families via neural operators

Authors: Takashi Furuya, Anastasis Kratsios, Dylan Possamaï, Bogdan Raonić
Published: 2025-11-03
Categories: cs.LG, math.AP, math.NA, math.PR, q-fin.CP
arXiv: https://arxiv.org/abs/2511.01125v1

We introduce a mild generative variant of the classical neural operator model, which leverages Kolmogorov--Arnold networks to solve infinite families of second-order backward stochastic differential equations ($2$BSDEs) on regular bounded Euclidean domains with random terminal time. Our first main result shows that the solution operator associated with a broad range of $2$BSDE families is approximable by appropriate neural operator models. We then identify a structured subclass of (infinite) families of $2$BSDEs whose neural operator approximation requires only a polynomial number of parameters in the reciprocal approximation rate, as opposed to the exponential requirement in general worst-case neural operator guarantees.

---

### Malliavin Calculus as Stochastic Backpropogation

Authors: Kevin D. Oden
Published: 2025-11-02
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.17013v1

We establish a rigorous connection between pathwise (reparameterization) and score-function (Malliavin) gradient estimators by showing that both arise from the Malliavin integration-by-parts identity. Building on this equivalence, we introduce a unified and variance-aware hybrid estimator that adaptively combines pathwise and Malliavin gradients using their empirical covariance structure. The resulting formulation provides a principled understanding of stochastic backpropagation and achieves minimum variance among all unbiased linear combinations, with closed-form finite-sample convergence bounds. We demonstrate 9% variance reduction on VAEs (CIFAR-10) and up to 35% on strongly-coupled synthetic problems. Exploratory policy gradient experiments reveal that non-stationary optimization landscapes present challenges for the hybrid approach, highlighting important directions for future work. Overall, this work positions Malliavin calculus as a conceptually unifying and practically interpretable framework for stochastic gradient estimation, clarifying when hybrid approaches provide tangible benefits and when they face inherent limitations.

---

### The Impact of LLM-Generated Reviews on Recommender Systems: Textual Shifts, Performance Effects, and Strategic Platform Control

Authors: Itzhak Ziv, Moshe Unger, Hilah Geva
Published: 2025-11-02
Categories: cs.IR, cs.AI
arXiv: https://arxiv.org/abs/2601.02362v1

The rise of generative AI technologies is reshaping content-based recommender systems (RSes), which increasingly encounter AI-generated content alongside human-authored content. This study examines how the introduction of AI-generated reviews influences RS performance and business outcomes. We analyze two distinct pathways through which AI content can enter RSes: user-centric, in which individuals use AI tools to refine their reviews, and platform-centric, in which platforms generate synthetic reviews directly from structured metadata. Using a large-scale dataset of hotel reviews from TripAdvisor, we generate synthetic reviews using LLMs and evaluate their impact across the training and deployment phases of RSes. We find that AI-generated reviews differ systematically from human-authored reviews across multiple textual dimensions. Although both user- and platform-centric AI reviews enhance RS performance relative to models without textual data, models trained on human reviews consistently achieve superior performance, underscoring the quality of authentic human data. Human-trained models generalize robustly to AI content, whereas AI-trained models underperform on both content types. Furthermore, tone-based framing strategies (encouraging, constructive, or critical) substantially enhance platform-generated review effectiveness. Our findings highlight the strategic importance of platform control in governing the generation and integration of AI-generated reviews, ensuring that synthetic content complements recommendation robustness and sustainable business value.

---

### Video Models Start to Solve Chess, Maze, Sudoku, Mental Rotation, and Raven' Matrices

Authors: Hokin Deng
Published: 2025-11-02
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2512.05969v1

We show that video generation models could reason now. Testing on tasks such as chess, maze, Sudoku, mental rotation, and Raven's Matrices, leading models such as Sora-2 achieve sixty percent success rates. We establish a robust experimental paradigm centered on the "Task Pair" design. We build a code framework, with 39 models available already, that supports this paradigm and allows for easy scaling - users can add models and tasks efficiently. We show our automated evaluation strongly correlates with human judgment, and therefore this paradigm is highly scalable. We see an opportunity, given the availability of our paradigm, to do reinforcement learning for improving reasoning in video models. You could checkout all of our raw $\href{https://grow-ai-like-a-child.com/video-reason/}{results}$ and our $\href{https://github.com/hokindeng/VMEvalKit}{VMEvalKit}$ codebase.

---

### Clustering-Based Weight Orthogonalization for Stabilizing Deep Reinforcement Learning

Authors: Guoqing Ma, Yuhan Zhang, Yuming Dai, Guangfu Hao, Yang Chen, Shan Yu
Published: 2025-11-02
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2511.11607v1

Reinforcement learning (RL) has made significant advancements, achieving superhuman performance in various tasks. However, RL agents often operate under the assumption of environmental stationarity, which poses a great challenge to learning efficiency since many environments are inherently non-stationary. This non-stationarity results in the requirement of millions of iterations, leading to low sample efficiency. To address this issue, we introduce the Clustering Orthogonal Weight Modified (COWM) layer, which can be integrated into the policy network of any RL algorithm and mitigate non-stationarity effectively. The COWM layer stabilizes the learning process by employing clustering techniques and a projection matrix. Our approach not only improves learning speed but also reduces gradient interference, thereby enhancing the overall learning efficiency. Empirically, the COWM outperforms state-of-the-art methods and achieves improvements of 9% and 12.6% in vision based and state-based DMControl benchmark. It also shows robustness and generality across various algorithms and tasks.

---

### Spectral Neuro-Symbolic Reasoning II: Semantic Node Merging, Entailment Filtering, and Knowledge Graph Alignment

Authors: Andrew Kiruluta, Priscilla Burity
Published: 2025-11-02
Categories: cs.CL, cs.AI, cs.NE
arXiv: https://arxiv.org/abs/2511.10655v1

This report extends the Spectral Neuro-Symbolic Reasoning (Spectral NSR) framework by introducing three semantically grounded enhancements: (1) transformer-based node merging using contextual embeddings (e.g., Sentence-BERT, SimCSE) to reduce redundancy, (2) sentence-level entailment validation with pretrained NLI classifiers (e.g., RoBERTa, DeBERTa) to improve edge quality, and (3) alignment with external knowledge graphs (e.g., ConceptNet, Wikidata) to augment missing context. These modifications enhance graph fidelity while preserving the core spectral reasoning pipeline. Experimental results on ProofWriter, EntailmentBank, and CLUTRR benchmarks show consistent accuracy gains (up to +3.8\%), improved generalization to adversarial cases, and reduced inference noise. The novelty lies in performing semantic and symbolic refinement entirely upstream of the spectral inference stage, enabling efficient, interpretable, and scalable reasoning without relying on quadratic attention mechanisms. In summary, this work extends the Spectral NSR framework with modular, semantically grounded preprocessing steps that improve graph quality without altering the core spectral reasoning engine. The result is a more robust, interpretable, and scalable reasoning system suitable for deployment in open-domain and real-world settings.

---

### Empirical Characterization of Temporal Constraint Processing in LLMs

Authors: Javier Marín
Published: 2025-11-02
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2511.10654v1

When deploying LLMs in agentic architectures requiring real-time decisions under temporal constraints, we assume they reliably determine whether action windows remain open or have closed. This assumption is untested. We characterize temporal constraint processing across eight production-scale models (2.8-8B parameters) using deadline detection tasks, revealing systematic deployment risks: bimodal performance distribution (models achieve either 95% or 50% accuracy), extreme prompt brittleness (30-60 percentage point swings from formatting changes alone), and systematic action bias (100% false positive rates in failing models). Parameter count shows no correlation with capability in this range-a 3.8B model matches 7B models while other 7B models fail completely. Fine-tuning on 200 synthetic examples improves models with partial capability by 12-37 percentage points. We demonstrate that temporal constraint satisfaction cannot be reliably learned through next-token prediction on natural language, even with targeted fine-tuning. This capability requires architectural mechanisms for: (1) continuous temporal state representation, (2) explicit constraint checking separate from linguistic pattern matching, (3) systematic compositional reasoning over temporal relations. Current autoregressive architectures lack these mechanisms. Deploying such systems in time-critical applications without hybrid architectures incorporating symbolic reasoning modules represents unacceptable risk.

---

### Hybrid Quantum Transformer for Language Generation

Authors: Desheng Kong, Xiangshuo Cui, Jiaying Jin, Jing Xu, Donglin Wang
Published: 2025-11-02
Categories: cs.CL, cs.AI, quant-ph
arXiv: https://arxiv.org/abs/2511.10653v1

Although quantum computing has been increasingly applied to replace classical computation, most existing quantum or hybrid models remain confined to simple tasks, with no successful application to large-scale natural language generation to date. In this work, we present the first hybrid quantum-classical large language model (LLM) for natural language generation, HyQuT, capable of performing coherent and context-aware dialogue. The proposed architecture integrates variational quantum circuits (VQCs) into the Transformer framework at both 8M and 150M parameter scales. Experimental results show that a minimal number of qubits (10 qubits with 80 quantum gates) can replace about 10% of the classical parameters in the 150M-parameter model, while achieving comparable convergence stability and generation quality. This study provides an early demonstration of the feasibility of integrating quantum computing to large-scale generative language models.

---

### Evaluating DisCoCirc in Translation Tasks & its Limitations: A Comparative Study Between Bengali & English

Authors: Nazmoon Falgunee Moon
Published: 2025-11-02
Categories: cs.CL
arXiv: https://arxiv.org/abs/2511.08601v1

In (4), the authors present the DisCoCirc (Distributed Compositional Circuits) formalism for the English language, a grammar-based framework derived from the production rules that incorporates circuit-like representations in order to give a precise categorical theoretical structure to the language. In this paper, we extend this approach to develop a similar framework for Bengali and apply it to translation tasks between English and Bengali. A central focus of our work lies in reassessing the effectiveness of DisCoCirc in reducing language bureaucracy. Unlike the result suggested in (5), our findings indicate that although it works well for a large part of the language, it still faces limitations due to the structural variation of the two languages. We discuss the possible methods that might handle these shortcomings and show that, in practice, DisCoCirc still struggles even with relatively simple sentences. This divergence from prior claims not only highlights the framework's constraints in translation but also suggest scope for future improvement. Apart from our primary focus on English-Bengali translation, we also take a short detour to examine English conjunctions, following (1), showing a connection between conjunctions and Boolean logic.

---

### Two Datasets Are Better Than One: Method of Double Moments for 3-D Reconstruction in Cryo-EM

Authors: Joe Kileel, Oscar Mickelin, Amit Singer, Sheng Xu
Published: 2025-11-02
Categories: cs.CV, math.NA, stat.ME
arXiv: https://arxiv.org/abs/2511.07438v3

Cryo-electron microscopy (cryo-EM) is a powerful imaging technique for reconstructing three-dimensional molecular structures from noisy tomographic projection images of randomly oriented particles. We introduce a new data fusion framework, termed the method of double moments (MoDM), which reconstructs molecular structures from two instances of the second-order moment of projection images obtained under distinct orientation distributions: one uniform, the other non-uniform and unknown. We prove that these moments generically uniquely determine the underlying structure, up to a global rotation and reflection, and we develop a convex-relaxation-based algorithm that achieves accurate recovery using only second-order statistics. Our results demonstrate the advantage of collecting and modeling multiple datasets under different experimental conditions, illustrating that leveraging dataset diversity can substantially enhance reconstruction quality in computational imaging tasks.

---

### Deep one-gate per layer networks with skip connections are universal classifiers

Authors: Raul Rojas
Published: 2025-11-02
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2511.05552v1

This paper shows how a multilayer perceptron with two hidden layers, which has been designed to classify two classes of data points, can easily be transformed into a deep neural network with one-gate layers and skip connections.

---

### In-Context-Learning-Assisted Quality Assessment Vision-Language Models for Metal Additive Manufacturing

Authors: Qiaojie Zheng, Jiucai Zhang, Xiaoli Zhang
Published: 2025-11-02
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.05551v1

Vision-based quality assessment in additive manufacturing often requires dedicated machine learning models and application-specific datasets. However, data collection and model training can be expensive and time-consuming. In this paper, we leverage vision-language models' (VLMs') reasoning capabilities to assess the quality of printed parts and introduce in-context learning (ICL) to provide VLMs with necessary application-specific knowledge and demonstration samples. This method eliminates the requirement for large application-specific datasets for training models. We explored different sampling strategies for ICL to search for the optimal configuration that makes use of limited samples. We evaluated these strategies on two VLMs, Gemini-2.5-flash and Gemma3:27b, with quality assessment tasks in wire-laser direct energy deposition processes. The results show that ICL-assisted VLMs can reach quality classification accuracies similar to those of traditional machine learning models while requiring only a minimal number of samples. In addition, unlike traditional classification models that lack transparency, VLMs can generate human-interpretable rationales to enhance trust. Since there are no metrics to evaluate their interpretability in manufacturing applications, we propose two metrics, knowledge relevance and rationale validity, to evaluate the quality of VLMs' supporting rationales. Our results show that ICL-assisted VLMs can address application-specific tasks with limited data, achieving relatively high accuracy while also providing valid supporting rationales for improved decision transparency.

---

### Assessing Factual Music Comprehension in Large Audio Language Models

Authors: Daniel Chenyu Lin, Michael Freeman, John Thickstun
Published: 2025-11-02
Categories: cs.SD, cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2511.05550v3

Large audio language models (LALMs) leverage multimodal representations to generate open-ended answers to natural language queries about audio. In this paper, we (1) provide empirical evidence that assessment of LALMs using the popular MusicQA dataset fails to measure whether a model's responses about music are factually correct, and (2) develop a new protocol for assessing the music comprehension capabilities of LALMs. Specifically, we propose an evaluation protocol that prompts a LALM for factually verifiable information, and parses its open-ended response into a structured format that can be objectively assessed using Precision, Recall, and F1 scores. Using this protocol, we define a benchmark consisting of six factual information retrieval tasks defined on three diverse datasets: MusicNet, the Free Music Archive, and OverClocked ReMix. We benchmark nine recent LALMs, including frontier models like Gemini and the latest open models like Music Flamingo, and release the suite of evaluation scripts at https://github.com/DCL2004/LALM-Eval to facilitate benchmarking of new LALMs.

---

### AGRAG: Advanced Graph-based Retrieval-Augmented Generation for LLMs

Authors: Yubo Wang, Haoyang Li, Fei Teng, Lei Chen
Published: 2025-11-02
Categories: cs.LG, cs.AI, cs.IR
arXiv: https://arxiv.org/abs/2511.05549v2

Graph-based retrieval-augmented generation (Graph-based RAG) has demonstrated significant potential in enhancing Large Language Models (LLMs) with structured knowledge. However, existing methods face three critical challenges: Inaccurate Graph Construction, caused by LLM hallucination; Poor Reasoning Ability, caused by failing to generate explicit reasons telling LLM why certain chunks were selected; and Inadequate Answering, which only partially answers the query due to the inadequate LLM reasoning, making their performance lag behind NaiveRAG on certain tasks. To address these issues, we propose AGRAG, an advanced graph-based retrieval-augmented generation framework. When constructing the graph, AGRAG substitutes the widely used LLM entity extraction method with a statistics-based method, avoiding hallucination and error propagation. During retrieval, AGRAG formulates the graph reasoning procedure as the Minimum Cost Maximum Influence (MCMI) subgraph generation problem, where we try to include more nodes with high influence score, but with less involving edge cost, to make the generated reasoning paths more comprehensive. We prove this problem to be NP-hard, and propose a greedy algorithm to solve it. The MCMI subgraph generated can serve as explicit reasoning paths to tell LLM why certain chunks were retrieved, thereby making the LLM better focus on the query-related part contents of the chunks, reducing the impact of noise, and improving AGRAG's reasoning ability. Furthermore, compared with the simple tree-structured reasoning paths, our MCMI subgraph can allow more complex graph structures, such as cycles, and improve the comprehensiveness of the generated reasoning paths. The code and prompt of AGRAG are released at: https://github.com/Wyb0627/AGRAG.

---

### Communication-Constrained Private Decentralized Online Personalized Mean Estimation

Authors: Yauhen Yakimenka, Hsuan-Yin Lin, Eirik Rosnes, Jörg Kliewer
Published: 2025-11-02
Categories: cs.SI, cs.IT, cs.LG
arXiv: https://arxiv.org/abs/2511.04702v1

We consider the problem of communication-constrained collaborative personalized mean estimation under a privacy constraint in an environment of several agents continuously receiving data according to arbitrary unknown agent-specific distributions. A consensus-based algorithm is studied under the framework of differential privacy in order to protect each agent's data. We give a theoretical convergence analysis of the proposed consensus-based algorithm for any bounded unknown distributions on the agents' data, showing that collaboration provides faster convergence than a fully local approach where agents do not share data, under an oracle decision rule and under some restrictions on the privacy level and the agents' connectivity, which illustrates the benefit of private collaboration in an online setting under a communication restriction on the agents. The theoretical faster-than-local convergence guarantee is backed up by several numerical results.

---

### A Dynamic Recurrent Adjacency Memory Network for Mixed-Generation Power System Stability Forecasting

Authors: Guang An Ooi, Otavio Bertozzi, Mohd Asim Aftab, Charalambos Konstantinou, Shehab Ahmed
Published: 2025-11-02
Categories: eess.SY, cs.LG
arXiv: https://arxiv.org/abs/2511.03746v3

Modern power systems with high penetration of inverter-based resources exhibit complex dynamic behaviors that challenge the scalability and generalizability of traditional stability assessment methods. This paper presents a dynamic recurrent adjacency memory network (DRAMN) that combines physics-informed analysis with deep learning for real-time power system stability forecasting. The framework employs sliding-window dynamic mode decomposition to construct time-varying, multi-layer adjacency matrices from phasor measurement unit and sensor data to capture system dynamics such as modal participation factors, coupling strengths, phase relationships, and spectral energy distributions. As opposed to processing spatial and temporal dependencies separately, DRAMN integrates graph convolution operations directly within recurrent gating mechanisms, enabling simultaneous modeling of evolving dynamics and temporal dependencies. Extensive validations on modified IEEE 9-bus, 39-bus, and a multi-terminal HVDC network demonstrate high performance, achieving 99.85%, 99.90%, and 99.69% average accuracies, respectively, surpassing all tested benchmarks, including classical machine learning algorithms and recent graph-based models. The framework identifies optimal combinations of measurements that reduce feature dimensionality by 82% without performance degradation. Correlation analysis between dominant measurements for small-signal and transient stability events validates generalizability across different stability phenomena. DRAMN achieves state-of-the-art accuracy while providing enhanced interpretability for power system operators, making it suitable for real-time deployment in modern control centers.

---

### AI-driven Large-scale Electron Microscopy enables Whole-tissue Subcellular Digitization

Authors: Li Xiao, Liqing Liu, Hongjun Wu, Jiayi Zhong, Xixia Li, Yan Zhang, Junjie Hu, Sun Fei, Ge Yang, Tao Xu
Published: 2025-11-02
Categories: physics.bio-ph, cs.AI
arXiv: https://arxiv.org/abs/2511.02860v2

The distribution and interactions of cellular organelles play a critical role in mediating cellular physiology and pathology. Large-scale electron microscopy enables visualization of organelle distribution and interactions at the tissue level with nanometer resolution, but robust and efficient computational analysis tools are lacking. Here, we present a deep learning tool for universal large-scale 2D/3D electron microscopy analysis, DeepOrganelle. This new tool enables high-throughput, cell-resolved spatiotemporal mapping and digitization of organelle distribution and interactions. When applied to spermatogenesis across 12 stages and 22 differentiation status of the germ cells, DeepOrganelle uncovered previously unrecognized, stage-dependent dynamics of mitochondria-endoplasmic reticulum contact sites within one subphase of prophase I during meiosis. It also revealed coordinated organelle redistribution in Sertoli cells towards the blood-testis barrier, digitizing the remodeling dynamics of the tissue. This study demonstrates that DeepOrganelle provides a powerful framework that captures subcellular dynamics at the whole-tissue level.

---

### The Geometry of Grokking: Norm Minimization on the Zero-Loss Manifold

Authors: Tiberiu Musat
Published: 2025-11-02
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2511.01938v3

Grokking is a puzzling phenomenon in neural networks where full generalization occurs only after a substantial delay following the complete memorization of the training data. Previous research has linked this delayed generalization to representation learning driven by weight decay, but the precise underlying dynamics remain elusive. In this paper, we argue that post-memorization learning can be understood through the lens of constrained optimization: gradient descent effectively minimizes the weight norm on the zero-loss manifold. We formally prove this in the limit of infinitesimally small learning rates and weight decay coefficients. To further dissect this regime, we introduce an approximation that decouples the learning dynamics of a subset of parameters from the rest of the network. Applying this framework, we derive a closed-form expression for the post-memorization dynamics of the first layer in a two-layer network. Experiments confirm that simulating the training process using our predicted gradients reproduces both the delayed generalization and representation learning characteristic of grokking.

---

### Shorter but not Worse: Frugal Reasoning via Easy Samples as Length Regularizers in Math RLVR

Authors: Abdelaziz Bounhar, Hadi Abdine, Evan Dufraisse, Ahmad Chamma, Amr Mohamed, Dani Bouch, Michalis Vazirgiannis, Guokan Shang
Published: 2025-11-02
Categories: cs.LG, cs.AI, stat.ML
arXiv: https://arxiv.org/abs/2511.01937v2

Large language models (LLMs) trained for step-by-step reasoning often become excessively verbose, raising inference cost. Standard Reinforcement Learning with Verifiable Rewards (RLVR) pipelines filter out ``easy'' problems for training efficiency, leaving the model to train primarily on harder problems that require longer reasoning chains. This skews the output length distribution upward, resulting in a \textbf{model that conflates ``thinking longer'' with ``thinking better''}. In this work, we show that retaining and modestly up-weighting moderately easy problems acts as an implicit length regularizer. Exposing the model to solvable short-chain tasks constrains its output distribution and prevents runaway verbosity. The result is \textbf{\emph{emergent brevity for free}}: the model learns to solve harder problems without inflating the output length, \textbf{ despite the absence of any explicit length penalization}. RLVR experiments using this approach on \textit{Qwen3-4B-Thinking-2507} (with a 16k token limit) achieve baseline pass@1 AIME25 accuracy while generating solutions that are, on average, nearly twice as short. The code is available at \href{https://github.com/MBZUAI-Paris/Frugal-AI}{GitHub}, with datasets and models on \href{https://huggingface.co/collections/MBZUAI-Paris/k2-think-mini-68dcfa8b114686a4bd3dc2bc}{Hugging Face}.

---

### Q-Sat AI: Machine Learning-Based Decision Support for Data Saturation in Qualitative Studies

Authors: Hasan Tutar, Caner Erden, Ümit Şentürk
Published: 2025-11-02
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2511.01935v1

The determination of sample size in qualitative research has traditionally relied on the subjective and often ambiguous principle of data saturation, which can lead to inconsistencies and threaten methodological rigor. This study introduces a new, systematic model based on machine learning (ML) to make this process more objective. Utilizing a dataset derived from five fundamental qualitative research approaches - namely, Case Study, Grounded Theory, Phenomenology, Narrative Research, and Ethnographic Research - we developed an ensemble learning model. Ten critical parameters, including research scope, information power, and researcher competence, were evaluated using an ordinal scale and used as input features. After thorough preprocessing and outlier removal, multiple ML algorithms were trained and compared. The K-Nearest Neighbors (KNN), Gradient Boosting (GB), Random Forest (RF), XGBoost, and Decision Tree (DT) algorithms showed the highest explanatory power (Test R2 ~ 0.85), effectively modeling the complex, non-linear relationships involved in qualitative sampling decisions. Feature importance analysis confirmed the vital roles of research design type and information power, providing quantitative validation of key theoretical assumptions in qualitative methodology. The study concludes by proposing a conceptual framework for a web-based computational application designed to serve as a decision support system for qualitative researchers, journal reviewers, and thesis advisors. This model represents a significant step toward standardizing sample size justification, enhancing transparency, and strengthening the epistemological foundation of qualitative inquiry through evidence-based, systematic decision-making.

---

### Tool Zero: Training Tool-Augmented LLMs via Pure RL from Scratch

Authors: Yirong Zeng, Xiao Ding, Yutai Hou, Yuxian Wang, Li Du, Juyi Dai, Qiuyang Ding, Duyu Tang, Dandan Tu, Weiwen Liu, Bing Qin, Ting Liu
Published: 2025-11-02
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2511.01934v2

Training tool-augmented LLMs has emerged as a promising approach to enhancing language models' capabilities for complex tasks. The current supervised fine-tuning paradigm relies on constructing extensive domain-specific datasets to train models. However, this approach often struggles to generalize effectively to unfamiliar or intricate tool-use scenarios. Recently, reinforcement learning (RL) paradigm can endow LLMs with superior reasoning and generalization abilities. In this work, we address a key question: Can the pure RL be used to effectively elicit a model's intrinsic reasoning capabilities and enhance the tool-agnostic generalization? We propose a dynamic generalization-guided reward design for rule-based RL, which progressively shifts rewards from exploratory to exploitative tool-use patterns. Based on this design, we introduce the Tool-Zero series models. These models are trained to enable LLMs to autonomously utilize general tools by directly scaling up RL from Zero models (i.e., base models without post-training). Experimental results demonstrate that our models achieve over 7% performance improvement compared to both SFT and RL-with-SFT models under the same experimental settings. These gains are consistently replicated across cross-dataset and intra-dataset evaluations, validating the effectiveness and robustness of our methods.

---

### Deciphering Personalization: Towards Fine-Grained Explainability in Natural Language for Personalized Image Generation Models

Authors: Haoming Wang, Wei Gao
Published: 2025-11-02
Categories: cs.LG, cs.AI, cs.CV, cs.MM
arXiv: https://arxiv.org/abs/2511.01932v1

Image generation models are usually personalized in practical uses in order to better meet the individual users' heterogeneous needs, but most personalized models lack explainability about how they are being personalized. Such explainability can be provided via visual features in generated images, but is difficult for human users to understand. Explainability in natural language is a better choice, but the existing approaches to explainability in natural language are limited to be coarse-grained. They are unable to precisely identify the multiple aspects of personalization, as well as the varying levels of personalization in each aspect. To address such limitation, in this paper we present a new technique, namely \textbf{FineXL}, towards \textbf{Fine}-grained e\textbf{X}plainability in natural \textbf{L}anguage for personalized image generation models. FineXL can provide natural language descriptions about each distinct aspect of personalization, along with quantitative scores indicating the level of each aspect of personalization. Experiment results show that FineXL can improve the accuracy of explainability by 56\%, when different personalization scenarios are applied to multiple types of image generation models.

---

### Dynamic Population Distribution Aware Human Trajectory Generation with Diffusion Model

Authors: Qingyue Long, Can Rong, Tong Li, Yong Li
Published: 2025-11-02
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2511.01929v1

Human trajectory data is crucial in urban planning, traffic engineering, and public health. However, directly using real-world trajectory data often faces challenges such as privacy concerns, data acquisition costs, and data quality. A practical solution to these challenges is trajectory generation, a method developed to simulate human mobility behaviors. Existing trajectory generation methods mainly focus on capturing individual movement patterns but often overlook the influence of population distribution on trajectory generation. In reality, dynamic population distribution reflects changes in population density across different regions, significantly impacting individual mobility behavior. Thus, we propose a novel trajectory generation framework based on a diffusion model, which integrates the dynamic population distribution constraints to guide high-fidelity generation outcomes. Specifically, we construct a spatial graph to enhance the spatial correlation of trajectories. Then, we design a dynamic population distribution aware denoising network to capture the spatiotemporal dependencies of human mobility behavior as well as the impact of population distribution in the denoising process. Extensive experiments show that the trajectories generated by our model can resemble real-world trajectories in terms of some critical statistical metrics, outperforming state-of-the-art algorithms by over 54%.

---

### A Unified Model for Human Mobility Generation in Natural Disasters

Authors: Qingyue Long, Huandong Wang, Qi Ryan Wang, Yong Li
Published: 2025-11-02
Categories: cs.SI, cs.AI
arXiv: https://arxiv.org/abs/2511.01928v1

Human mobility generation in disaster scenarios plays a vital role in resource allocation, emergency response, and rescue coordination. During disasters such as wildfires and hurricanes, human mobility patterns often deviate from their normal states, which makes the task more challenging. However, existing works usually rely on limited data from a single city or specific disaster, significantly restricting the model's generalization capability in new scenarios. In fact, disasters are highly sudden and unpredictable, and any city may encounter new types of disasters without prior experience. Therefore, we aim to develop a one-for-all model for mobility generation that can generalize to new disaster scenarios. However, building a universal framework faces two key challenges: 1) the diversity of disaster types and 2) the heterogeneity among different cities. In this work, we propose a unified model for human mobility generation in natural disasters (named UniDisMob). To enable cross-disaster generalization, we design physics-informed prompt and physics-guided alignment that leverage the underlying common patterns in mobility changes after different disasters to guide the generation process. To achieve cross-city generalization, we introduce a meta-learning framework that extracts universal patterns across multiple cities through shared parameters and captures city-specific features via private parameters. Extensive experiments across multiple cities and disaster scenarios demonstrate that our method significantly outperforms state-of-the-art baselines, achieving an average performance improvement exceeding 13%.

---

### Learning-Guided Integration Contours Construction for Fast Large-Scale Generalized Eigensolvers

Authors: Yeqiu Chen, Ziyan Liu, Hong Wang, Lei Liu
Published: 2025-11-02
Categories: cs.LG, cs.AI, math.NA
arXiv: https://arxiv.org/abs/2511.01927v2

Solving large-scale Generalized Eigenvalue Problems (GEPs) is a fundamental yet computationally prohibitive task in science and engineering. As a promising direction, contour integral (CI) methods offer an efficient and parallelizable framework. However, their performance is critically dependent on the selection of integration contours -- improper selection without reliable prior knowledge of eigenvalue distribution can incur significant computational overhead and compromise numerical accuracy. To address this challenge, we propose Deepcontour, a novel hybrid framework that integrates a deep learning-based spectral predictor with Kernel Density Estimation (KDE) for principled contour design. Specifically, Deepcontour utilizes its specialized Eigen-Neural-Operator (ENO) to provide rapid spectral distribution priors, driving a KDE module to automatically construct the optimized integration contours, which guide the CI solver to efficiently find the desired eigenvalues. Deepcontour achieves up to a 5.63x speedup across diverse scientific datasets while maintaining strict numerical rigor. By merging the predictive power of deep learning with the numerical rigor of classical solvers, this work establishes an efficient and robust paradigm for solving large-scale GEPs.

---

### Neural Green's Functions

Authors: Seungwoo Yoo, Kyeongmin Yeo, Jisung Hwang, Minhyuk Sung
Published: 2025-11-02
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2511.01924v1

We introduce Neural Green's Function, a neural solution operator for linear partial differential equations (PDEs) whose differential operators admit eigendecompositions. Inspired by Green's functions, the solution operators of linear PDEs that depend exclusively on the domain geometry, we design Neural Green's Function to imitate their behavior, achieving superior generalization across diverse irregular geometries and source and boundary functions. Specifically, Neural Green's Function extracts per-point features from a volumetric point cloud representing the problem domain and uses them to predict a decomposition of the solution operator, which is subsequently applied to evaluate solutions via numerical integration. Unlike recent learning-based solution operators, which often struggle to generalize to unseen source or boundary functions, our framework is, by design, agnostic to the specific functions used during training, enabling robust and efficient generalization. In the steady-state thermal analysis of mechanical part geometries from the MCB dataset, Neural Green's Function outperforms state-of-the-art neural operators, achieving an average error reduction of 13.9\% across five shape categories, while being up to 350 times faster than a numerical solver that requires computationally expensive meshing.

---

### Generative Machine Learning Models for the Deconvolution of Charge Carrier Dynamics in Organic Photovoltaic Cells

Authors: Li Raymond, Salim Flora, Wang Sijin, Wright Brendan
Published: 2025-11-02
Categories: cond-mat.mtrl-sci, cs.LG
arXiv: https://arxiv.org/abs/2511.01118v1

Charge carrier dynamics critically affect the efficiency and stability of organic photovoltaic devices, but they are challenging to model with traditional analytical methods. We introduce \b{eta}-Linearly Decoded Latent Ordinary Differential Equations (\b{eta}-LLODE), a machine learning framework that disentangles and reconstructs extraction dynamics from time-resolved charge extraction measurements of P3HT:PCBM cells. This model enables the isolated analysis of the underlying charge carrier behaviour, which was found to be well described by a compressed exponential decay. Furthermore, the learnt interpretable latent space enables simulation, including both interpolation and extrapolation of experimental measurement conditions, offering a predictive tool for solar cell research to support device study and optimisation.

---

### S2Doc -- Spatial-Semantic Document Format

Authors: Sebastian Kempf, Frank Puppe
Published: 2025-11-02
Categories: cs.DL, cs.CL
arXiv: https://arxiv.org/abs/2511.01113v1

Documents are a common way to store and share information, with tables being an important part of many documents. However, there is no real common understanding of how to model documents and tables in particular. Because of this lack of standardization, most scientific approaches have their own way of modeling documents and tables, leading to a variety of different data structures and formats that are not directly compatible. Furthermore, most data models focus on either the spatial or the semantic structure of a document, neglecting the other aspect. To address this, we developed S2Doc, a flexible data structure for modeling documents and tables that combines both spatial and semantic information in a single format. It is designed to be easily extendable to new tasks and supports most modeling approaches for documents and tables, including multi-page documents. To the best of our knowledge, it is the first approach of its kind to combine all these aspects in a single format.

---

### Anatomically Constrained Transformers for Echocardiogram Analysis

Authors: Alexander Thorley, Agis Chartsias, Jordan Strom, Jeremy Slivnick, Dipak Kotecha, Alberto Gomez, Jinming Duan
Published: 2025-11-02
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.01109v1

Video transformers have recently demonstrated strong potential for echocardiogram (echo) analysis, leveraging self-supervised pre-training and flexible adaptation across diverse tasks. However, like other models operating on videos, they are prone to learning spurious correlations from non-diagnostic regions such as image backgrounds. To overcome this limitation, we propose the Video Anatomically Constrained Transformer (ViACT), a novel framework that integrates anatomical priors directly into the transformer architecture. ViACT represents a deforming anatomical structure as a point set and encodes both its spatial geometry and corresponding image patches into transformer tokens. During pre-training, ViACT follows a masked autoencoding strategy that masks and reconstructs only anatomical patches, enforcing that representation learning is focused on the anatomical region. The pre-trained model can then be fine-tuned for tasks localized to this region. In this work we focus on the myocardium, demonstrating the framework on echo analysis tasks such as left ventricular ejection fraction (EF) regression and cardiac amyloidosis (CA) detection. The anatomical constraint focuses transformer attention within the myocardium, yielding interpretable attention maps aligned with regions of known CA pathology. Moreover, ViACT generalizes to myocardium point tracking without requiring task-specific components such as correlation volumes used in specialized tracking networks.

---

### SLAP: Shortcut Learning for Abstract Planning

Authors: Y. Isabel Liu, Bowen Li, Benjamin Eysenbach, Tom Silver
Published: 2025-11-02
Categories: cs.RO, cs.LG
arXiv: https://arxiv.org/abs/2511.01107v2

Long-horizon decision-making with sparse rewards and continuous states and actions remains a fundamental challenge in AI and robotics. Task and motion planning (TAMP) is a model-based framework that addresses this challenge by planning hierarchically with abstract actions (options). These options are manually defined, limiting the agent to behaviors that we as human engineers know how to program (pick, place, move). In this work, we propose Shortcut Learning for Abstract Planning (SLAP), a method that leverages existing TAMP options to automatically discover new ones. Our key idea is to use model-free reinforcement learning (RL) to learn shortcuts in the abstract planning graph induced by the existing options in TAMP. Without any additional assumptions or inputs, shortcut learning leads to shorter solutions than pure planning, and higher task success rates than flat and hierarchical RL. Qualitatively, SLAP discovers dynamic physical improvisations (e.g., slap, wiggle, wipe) that differ significantly from the manually-defined ones. In experiments in four simulated robotic environments, we show that SLAP solves and generalizes to a wide range of tasks, reducing overall plan lengths by over 50% and consistently outperforming planning and RL baselines.

---

### HarnessLLM: Automatic Testing Harness Generation via Reinforcement Learning

Authors: Yujian Liu, Jiabao Ji, Yang Zhang, Wenbo Guo, Tommi Jaakkola, Shiyu Chang
Published: 2025-11-02
Categories: cs.SE, cs.CL
arXiv: https://arxiv.org/abs/2511.01104v1

Existing LLM-based automatic test generation methods mainly produce input and expected output pairs to categorize the intended behavior of correct programs. Although straightforward, these methods have limited diversity in generated tests and cannot provide enough debugging information. We propose HarnessLLM, a two-stage training pipeline that enables LLMs to write harness code for testing. Particularly, LLMs generate code that synthesizes inputs and validates the observed outputs, allowing complex test cases and flexible output validation such as invariant checking. To achieve this, we train LLMs with SFT followed by RLVR with a customized reward design. Experiments show that HarnessLLM outperforms input-output-based testing in bug finding and testing strategy diversity. HarnessLLM further benefits the code generation performance through test-time scaling with our generated test cases as inference-phase validation. Our code is available at https://github.com/UCSB-NLP-Chang/HarnessLLM.git.

---

### TSVer: A Benchmark for Fact Verification Against Time-Series Evidence

Authors: Marek Strong, Andreas Vlachos
Published: 2025-11-02
Categories: cs.CL
arXiv: https://arxiv.org/abs/2511.01101v2

Reasoning over temporal and numerical data, such as time series, is a crucial aspect of fact-checking. While many systems have recently been developed to handle this form of evidence, their evaluation remains limited by existing datasets, which often lack structured evidence, provide insufficient justifications for verdicts, or rely on synthetic claims. In this paper, we introduce TSVer, a new benchmark dataset for fact verification focusing on temporal and numerical reasoning with time-series evidence. TSVer contains 304 real-world claims sourced from 41 fact-checking organizations and a curated database of 400 time series covering diverse domains. Each claim is annotated with time frames across all pertinent time series, along with a verdict and justifications reflecting how the evidence is used to reach the verdict. Using an LLM-assisted multi-step annotation process, we improve the quality of our annotations and achieve an inter-annotator agreement of kappa=0.77 on verdicts. We also develop a baseline for verifying claims against time-series evidence and show that even the state-of-the-art reasoning models like Gemini-2.5-Pro are challenged by time series, achieving a 63.57 accuracy score on verdicts and an Ev2R score of 47.36 on verdict justifications.

---

### Epanechnikov nonparametric kernel density estimation based feature-learning in respiratory disease chest X-ray images

Authors: Veronica Marsico, Antonio Quintero-Rincon, Hadj Batatia
Published: 2025-11-02
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.01098v1

This study presents a novel method for diagnosing respiratory diseases using image data. It combines Epanechnikov's non-parametric kernel density estimation (EKDE) with a bimodal logistic regression classifier in a statistical-model-based learning scheme. EKDE's flexibility in modeling data distributions without assuming specific shapes and its adaptability to pixel intensity variations make it valuable for extracting key features from medical images. The method was tested on 13808 randomly selected chest X-rays from the COVID-19 Radiography Dataset, achieved an accuracy of 70.14%, a sensitivity of 59.26%, and a specificity of 74.18%, demonstrating moderate performance in detecting respiratory disease while showing room for improvement in sensitivity. While clinical expertise remains essential for further refining the model, this study highlights the potential of EKDE-based approaches to enhance diagnostic accuracy and reliability in medical imaging.

---

### Hyper Hawkes Processes: Interpretable Models of Marked Temporal Point Processes

Authors: Alex Boyd, Andrew Warrington, Taha Kass-Hout, Parminder Bhatia, Danica Xiao
Published: 2025-11-02
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2511.01096v1

Foundational marked temporal point process (MTPP) models, such as the Hawkes process, often use inexpressive model families in order to offer interpretable parameterizations of event data. On the other hand, neural MTPPs models forego this interpretability in favor of absolute predictive performance. In this work, we present a new family MTPP models: the hyper Hawkes process (HHP), which aims to be as flexible and performant as neural MTPPs, while retaining interpretable aspects. To achieve this, the HHP extends the classical Hawkes process to increase its expressivity by first expanding the dimension of the process into a latent space, and then introducing a hypernetwork to allow time- and data-dependent dynamics. These extensions define a highly performant MTPP family, achieving state-of-the-art performance across a range of benchmark tasks and metrics. Furthermore, by retaining the linearity of the recurrence, albeit now piecewise and conditionally linear, the HHP also retains much of the structure of the original Hawkes process, which we exploit to create direct probes into how the model creates predictions. HHP models therefore offer both state-of-the-art predictions, while also providing an opportunity to ``open the box'' and inspect how predictions were generated.

---

### Continual Learning, Not Training: Online Adaptation For Agents

Authors: Aman Jaglan, Jarrod Barnes
Published: 2025-11-02
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2511.01093v1

Continual Learning (CL) methods have traditionally focused on mitigating catastrophic forgetting through gradient-based retraining, an approach ill-suited for deployed agents that must adapt in real time. We introduce our Adaptive Teaching and Learning System (ATLAS), a dual-agent architecture that decouples reasoning (Teacher) from execution (Student) and incorporates a persistent learning memory that stores distilled guidance from experience. This informs the orchestration layer, enabling the system to dynamically adjust its operational strategies, such as supervision level or initial plan selection, at inference time. In doing so, ATLAS achieves gradient-free continual learning, shifting the locus of adaptation from model parameters to system-level orchestration. We formulate this as a system-centric paradigm for continual learning, where the objective is adaptive efficiency: maximizing task success while minimizing computational cost through inference-time orchestration rather than parameter updates. Evaluated on Microsoft's ExCyTIn-Bench, an open-source benchmark simulating complex cyberthreat investigation, ATLAS achieves 54.1% success with GPT-5-mini as its Student, outperforming the larger GPT-5 (High) by 13% while reducing cost by 86%. Cross-incident validation demonstrates generalization: frozen pamphlets from Incident #5 improve accuracy from 28% to 41% with zero retraining, while shifting output composition from verbose exploration to structured reasoning. Together, these findings establish gradient-free continual learning as a viable path toward adaptive, deployable AI systems and provide causally annotated traces valuable for training explicit world models.

---

### Improving Romanian LLM Pretraining Data using Diversity and Quality Filtering

Authors: Vlad Negoita, Mihai Masala, Traian Rebedea
Published: 2025-11-02
Categories: cs.CL
arXiv: https://arxiv.org/abs/2511.01090v1

Large Language Models (LLMs) have recently exploded in popularity, often matching or outperforming human abilities on many tasks. One of the key factors in training LLMs is the availability and curation of high-quality data. Data quality is especially crucial for under-represented languages, where high-quality corpora are scarce. In this work we study the characteristics and coverage of Romanian pretraining corpora and we examine how they differ from English data. By training a lightweight multitask model on carefully LLM-annotated Romanian texts, we are able to analyze and perform multi-level filtering (e.g., educational value, topic, format) to generate high-quality pretraining datasets. Our experiments show noteworthy trends in the topics present in Romanian and English data, while also proving the effectiveness of filtering data through improved LLM pretraining performance across multiple benchmarks.

---

### SliceVision-F2I: A Synthetic Feature-to-Image Dataset for Visual Pattern Representation on Network Slices

Authors: Md. Abid Hasan Rafi, Mst. Fatematuj Johora, Pankaj Bhowmik
Published: 2025-11-02
Categories: cs.CV, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2511.01087v1

The emergence of 5G and 6G networks has established network slicing as a significant part of future service-oriented architectures, demanding refined identification methods supported by robust datasets. The article presents SliceVision-F2I, a dataset of synthetic samples for studying feature visualization in network slicing for next-generation networking systems. The dataset transforms multivariate Key Performance Indicator (KPI) vectors into visual representations through four distinct encoding methods: physically inspired mappings, Perlin noise, neural wallpapering, and fractal branching. For each encoding method, 30,000 samples are generated, each comprising a raw KPI vector and a corresponding RGB image at low-resolution pixels. The dataset simulates realistic and noisy network conditions to reflect operational uncertainties and measurement imperfections. SliceVision-F2I is suitable for tasks involving visual learning, network state classification, anomaly detection, and benchmarking of image-based machine learning techniques applied to network data. The dataset is publicly available and can be reused in various research contexts, including multivariate time series analysis, synthetic data generation, and feature-to-image transformations.

---

### GeoToken: Hierarchical Geolocalization of Images via Next Token Prediction

Authors: Narges Ghasemi, Amir Ziashahabi, Salman Avestimehr, Cyrus Shahabi
Published: 2025-11-02
Categories: cs.CV, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2511.01082v1

Image geolocalization, the task of determining an image's geographic origin, poses significant challenges, largely due to visual similarities across disparate locations and the large search space. To address these issues, we propose a hierarchical sequence prediction approach inspired by how humans narrow down locations from broad regions to specific addresses. Analogously, our model predicts geographic tokens hierarchically, first identifying a general region and then sequentially refining predictions to increasingly precise locations. Rather than relying on explicit semantic partitions, our method uses S2 cells, a nested, multiresolution global grid, and sequentially predicts finer-level cells conditioned on visual inputs and previous predictions. This procedure mirrors autoregressive text generation in large language models. Much like in language modeling, final performance depends not only on training but also on inference-time strategy. We investigate multiple top-down traversal methods for autoregressive sampling, incorporating techniques from test-time compute scaling used in language models. Specifically, we integrate beam search and multi-sample inference while exploring various selection strategies to determine the final output. This enables the model to manage uncertainty by exploring multiple plausible paths through the hierarchy. We evaluate our method on the Im2GPS3k and YFCC4k datasets against two distinct sets of baselines: those that operate without a Multimodal Large Language Model (MLLM) and those that leverage one. In the MLLM-free setting, our model surpasses other comparable baselines on nearly all metrics, achieving state-of-the-art performance with accuracy gains of up to 13.9%. When augmented with an MLLM, our model outperforms all baselines, setting a new state-of-the-art across all metrics. The source code is available at https://github.com/NNargesNN/GeoToken.

---

### T-MLA: A targeted multiscale log-exponential attack framework for neural image compression

Authors: Nikolay I. Kalmykov, Razan Dibo, Kaiyu Shen, Xu Zhonghan, Anh-Huy Phan, Yipeng Liu, Ivan Oseledets
Published: 2025-11-02
Categories: cs.CV, math.NA
arXiv: https://arxiv.org/abs/2511.01079v2

Neural image compression (NIC) has become the state-of-the-art for rate-distortion performance, yet its security vulnerabilities remain significantly less understood than those of classifiers. Existing adversarial attacks on NICs are often naive adaptations of pixel-space methods, overlooking the unique, structured nature of the compression pipeline. In this work, we propose a more advanced class of vulnerabilities by introducing T-MLA, the first targeted multiscale log-exponential attack framework. We introduce adversarial perturbations in the wavelet domain that concentrate on less perceptually salient coefficients, improving the stealth of the attack. Extensive evaluation across multiple state-of-the-art NIC architectures on standard image compression benchmarks reveals a large drop in reconstruction quality while the perturbations remain visually imperceptible. On standard NIC benchmarks, T-MLA achieves targeted degradation of reconstruction quality while improving perturbation imperceptibility (higher PSNR/VIF of the perturbed inputs) compared to PGD-style baselines at comparable attack success, as summarized in our main results. Our findings reveal a critical security flaw at the core of generative and content delivery pipelines.

---

### AI Progress Should Be Measured by Capability-Per-Resource, Not Scale Alone: A Framework for Gradient-Guided Resource Allocation in LLMs

Authors: David McCoy, Yulun Wu, Zachary Butzin-Dozier
Published: 2025-11-02
Categories: cs.LG, stat.CO
arXiv: https://arxiv.org/abs/2511.01077v1

This position paper challenges the "scaling fundamentalism" dominating AI research, where unbounded growth in model size and computation has led to unsustainable environmental impacts and widening resource inequality. We argue that LLM development should be fundamentally reoriented toward capability-per-resource rather than capability alone. We present a theoretical framework demonstrating that resource-allocation decisions guided by gradient influence patterns can dramatically improve efficiency throughout the AI lifecycle. Our analysis shows that in transformer-based models, where a small fraction of parameters exert outsized influence (following heavy-tailed distributions), three critical insights emerge: (1) updating only high-influence parameters strictly outperforms full-parameter tuning on a performance-per-resource basis; (2) simple gradient norms provide computationally efficient proxies for identifying these high-influence components; and (3) coordinated parameter and data selection yields multiplicative efficiency gains, potentially reducing resource requirements by orders of magnitude. Building on these theoretical foundations, we propose a two stage paradigm marginal-return pretraining for foundation developers and influence guided adaptation for downstream users bridged by gradient blueprints, metadata describing which parameters matter most for various tasks. This capability-per-resource perspective transforms what were once considered pragmatic hardware workarounds into theoretically optimal strategies, democratizing access to cutting-edge AI capabilities while significantly reducing environmental impact. By embedding resource consciousness into how we develop, adapt, and evaluate models, we can reshape AI progress toward a more sustainable and equitable future.

---