# Research Papers — 2025-10 · bundle page 177 of 217

> Full-text markdown of papers #8801–8850 of 10843 published in 2025-10, newest first. AI-readable mirrors of the full 10843-paper 2025-10 archive (50 papers per file).

Canonical page: https://aipod.dev/papers/archive/2025-10/page/177
[← Previous bundle](https://aipod.dev/papers/archive/2025-10/page/176.md)
[Next bundle →](https://aipod.dev/papers/archive/2025-10/page/178.md)

### Dynamic Object Masks as Goal Representations for Visual Goal-Conditioned Reinforcement Learning

Authors: Fahim Shahriar, Cheryl Wang, Alireza Azimi, Gautham Vasan, Hany Hamed, Abhishek Naik, A. Rupam Mahmood, Colin Bellinger
Published: 2025-10-06
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2510.06277v2

Goal-conditioned reinforcement learning (GCRL) offers a unified way to pursue diverse tasks, yet most existing methods rely on state- or position-based goal representations that are unavailable in real-world robotics. Robots operating in warehouses, agriculture, or laboratory environments rarely have access to privileged goal states, object positions, or future observations, limiting the practicality of current GCRL approaches. We propose a dynamic mask-based goal representation that provides simple, object-agnostic visual cues for vision-based navigation and manipulation. At each timestep, an image-based goal detector produces a goal mask using standard image processing, task-specific object recognizers, or pretrained detectors such as Detic or Grounding DINO. These masks specify the spatial target without requiring privileged goal states, enabling broad applicability and strong generalization to unseen objects. Our method improves stability and sample efficiency in GCRL, achieving a 99% success rate in reaching both training and novel objects with Franka and UR10e robotic arms and faster learning in simulated navigation. We further demonstrate learning from scratch and sim-to-real transfer on both robotic arms, highlighting the effectiveness of our approach for real-world RL tasks. Our code is available at https://github.com/fahimfss/GCRL.

---

### A Total Variation Regularized Framework for Epilepsy-Related MRI Image Segmentation

Authors: Mehdi Rabiee, Sergio Greco, Reza Shahbazian, Irina Trubitsyna
Published: 2025-10-06
Categories: eess.IV, cs.AI, cs.CV
arXiv: https://arxiv.org/abs/2510.06276v1

Focal Cortical Dysplasia (FCD) is a primary cause of drug-resistant epilepsy and is difficult to detect in brain {magnetic resonance imaging} (MRI) due to the subtle and small-scale nature of its lesions. Accurate segmentation of FCD regions in 3D multimodal brain MRI images is essential for effective surgical planning and treatment. However, this task remains highly challenging due to the limited availability of annotated FCD datasets, the extremely small size and weak contrast of FCD lesions, the complexity of handling 3D multimodal inputs, and the need for output smoothness and anatomical consistency, which is often not addressed by standard voxel-wise loss functions. This paper presents a new framework for segmenting FCD regions in 3D brain MRI images. We adopt state-of-the-art transformer-enhanced encoder-decoder architecture and introduce a novel loss function combining Dice loss with an anisotropic {Total Variation} (TV) term. This integration encourages spatial smoothness and reduces false positive clusters without relying on post-processing. The framework is evaluated on a public FCD dataset with 85 epilepsy patients and demonstrates superior segmentation accuracy and consistency compared to standard loss formulations. The model with the proposed TV loss shows an 11.9\% improvement on the Dice coefficient and 13.3\% higher precision over the baseline model. Moreover, the number of false positive clusters is reduced by 61.6%

---

### Reproducibility Study of "XRec: Large Language Models for Explainable Recommendation"

Authors: Ranjan Mishra, Julian I. Bibo, Quinten van Engelen, Henk Schaapman
Published: 2025-10-06
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.06275v1

In this study, we reproduced the work done in the paper "XRec: Large Language Models for Explainable Recommendation" by Ma et al. (2024). The original authors introduced XRec, a model-agnostic collaborative instruction-tuning framework that enables large language models (LLMs) to provide users with comprehensive explanations of generated recommendations. Our objective was to replicate the results of the original paper, albeit using Llama 3 as the LLM for evaluation instead of GPT-3.5-turbo. We built on the source code provided by Ma et al. (2024) to achieve our goal. Our work extends the original paper by modifying the input embeddings or deleting the output embeddings of XRec's Mixture of Experts module. Based on our results, XRec effectively generates personalized explanations and its stability is improved by incorporating collaborative information. However, XRec did not consistently outperform all baseline models in every metric. Our extended analysis further highlights the importance of the Mixture of Experts embeddings in shaping the explanation structures, showcasing how collaborative signals interact with language modeling. Through our work, we provide an open-source evaluation implementation that enhances accessibility for researchers and practitioners alike. Our complete code repository can be found at https://github.com/julianbibo/xrec-reproducibility.

---

### Bridging Reasoning to Learning: Unmasking Illusions using Complexity Out of Distribution Generalization

Authors: Mohammad Mahdi Samiei Paqaleh, Arash Marioriyad, Arman Tahmasebi-Zadeh, Mohamadreza Fereydooni, Mahdi Ghaznavai, Mahdieh Soleymani Baghshah
Published: 2025-10-06
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.06274v1

Recent progress has pushed AI frontiers from pattern recognition tasks toward problems that require step by step, System2 style reasoning, especially with large language models. Yet, unlike learning, where generalization and out of distribution (OoD) evaluation concepts are well formalized, there is no clear, consistent definition or metric for reasoning ability. We propose Complexity Out of Distribution (Complexity OoD) generalization as a framework and problem setting to define and measure reasoning. A model exhibits Complexity OoD generalization when it maintains performance on test instances whose minimal required solution complexity, either representational (richer solution structure) or computational (more reasoning steps/program length), exceeds that of all training examples. We formalize complexity via solution description Kolmogorov complexity and operational proxies (e.g., object/relation counts; reasoning step counts), clarifying how Complexity OoD differs from length and compositional OoD. This lens unifies learning and reasoning: many cases solvable with System1 like processing at low complexity become System2 like under complexity pressure, while System2 can be viewed as generalization over solution structures. We translate this perspective into practice with recommendations for operationalizing Complexity OoD across the stack: incorporating complexity into benchmark and evaluation metric design, rethinking supervision to target solution traces, seeking and designing inductive biases for Complexity OoD generalization, addressing learning to reason spillovers such as spurious shortcuts, semantic robustness, catastrophic forgetting, and step wise calibration. Because Complexity OoD cannot be solved by scaling data alone, progress toward robust reasoning will require architectures and training regimes that explicitly model and allocate computation with respect to complexity.

---

### Vision Transformer for Transient Noise Classification

Authors: Divyansh Srivastava, Andrzej Niedzielski
Published: 2025-10-06
Categories: cs.CV, astro-ph.IM, cs.LG, gr-qc
arXiv: https://arxiv.org/abs/2510.06273v1

Transient noise (glitches) in LIGO data hinders the detection of gravitational waves (GW). The Gravity Spy project has categorized these noise events into various classes. With the O3 run, there is the inclusion of two additional noise classes and thus a need to train new models for effective classification. We aim to classify glitches in LIGO data into 22 existing classes from the first run plus 2 additional noise classes from O3a using the Vision Transformer (ViT) model. We train a pre-trained Vision Transformer (ViT-B/32) model on a combined dataset consisting of the Gravity Spy dataset with the additional two classes from the LIGO O3a run. We achieve a classification efficiency of 92.26%, demonstrating the potential of Vision Transformer to improve the accuracy of gravitational wave detection by effectively distinguishing transient noise. Key words: gravitational waves --vision transformer --machine learning

---

### MCCE: A Framework for Multi-LLM Collaborative Search in Discrete Spaces with Similarity-Filtered Preference Learning

Authors: Nian Ran, Zhongzheng Li, Yue Wang, Qingsong Ran, Xiaoyuan Zhang, Shikun Feng, Richard Allmendinger, Xiaoguang Zhao
Published: 2025-10-06
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.06270v2

Multi-objective discrete optimization problems, such as molecular design, pose significant challenges due to their vast and unstructured combinatorial spaces. Traditional evolutionary algorithms often get trapped in local optima, while expert knowledge can provide crucial guidance for accelerating convergence. Large language models (LLMs) offer powerful priors and reasoning ability, making them natural optimizers when expert knowledge matters. However, closed-source LLMs, though strong in exploration, cannot update their parameters and thus cannot internalize experience. Conversely, smaller open models can be continually fine-tuned but lack broad knowledge and reasoning strength. We introduce Multi-LLM Collaborative Co-evolution (MCCE), a hybrid framework that unites a frozen closed-source LLM with a lightweight trainable model. The system maintains a trajectory memory of past search processes; the small model is progressively refined via reinforcement learning, with the two models jointly supporting and complementing each other in global exploration. Unlike model distillation, this process enhances the capabilities of both models through mutual inspiration. Experiments on multi-objective drug design benchmarks show that MCCE achieves state-of-the-art Pareto front quality and consistently outperforms baselines. These results highlight a new paradigm for enabling continual evolution in hybrid LLM systems, combining knowledge-driven exploration with experience-driven learning.

---

### RareGraph-Synth: Knowledge-Guided Diffusion Models for Generating Privacy-Preserving Synthetic Patient Trajectories in Ultra-Rare Diseases

Authors: Khartik Uppalapati, Shakeel Abdulkareem, Bora Yimenicioglu
Published: 2025-10-06
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.06267v1

We propose RareGraph-Synth, a knowledge-guided, continuous-time diffusion framework that generates realistic yet privacy-preserving synthetic electronic-health-record (EHR) trajectories for ultra-rare diseases. RareGraph-Synth unifies five public resources: Orphanet/Orphadata, the Human Phenotype Ontology (HPO), the GARD rare-disease KG, PrimeKG, and the FDA Adverse Event Reporting System (FAERS) into a heterogeneous knowledge graph comprising approximately 8 M typed edges. Meta-path scores extracted from this 8-million-edge KG modulate the per-token noise schedule in the forward stochastic differential equation, steering generation toward biologically plausible lab-medication-adverse-event co-occurrences while retaining score-based diffusion model stability. The reverse denoiser then produces timestamped sequences of lab-code, medication-code, and adverse-event-flag triples that contain no protected health information. On simulated ultra-rare-disease cohorts, RareGraph-Synth lowers categorical Maximum Mean Discrepancy by 40 percent relative to an unguided diffusion baseline and by greater than 60 percent versus GAN counterparts, without sacrificing downstream predictive utility. A black-box membership-inference evaluation using the DOMIAS attacker yields AUROC approximately 0.53, well below the 0.55 safe-release threshold and substantially better than the approximately 0.61 plus or minus 0.03 observed for non-KG baselines, demonstrating strong resistance to re-identification. These results suggest that integrating biomedical knowledge graphs directly into diffusion noise schedules can simultaneously enhance fidelity and privacy, enabling safer data sharing for rare-disease research.

---

### Language models for longitudinal analysis of abusive content in Billboard Music Charts

Authors: Rohitash Chandra, Yathin Suresh, Divyansh Raj Sinha, Sanchit Jindal
Published: 2025-10-06
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.06266v1

There is no doubt that there has been a drastic increase in abusive and sexually explicit content in music, particularly in Billboard Music Charts. However, there is a lack of studies that validate the trend for effective policy development, as such content has harmful behavioural changes in children and youths. In this study, we utilise deep learning methods to analyse songs (lyrics) from Billboard Charts of the United States in the last seven decades. We provide a longitudinal study using deep learning and language models and review the evolution of content using sentiment analysis and abuse detection, including sexually explicit content. Our results show a significant rise in explicit content in popular music from 1990 onwards. Furthermore, we find an increasing prevalence of songs with lyrics containing profane, sexually explicit, and otherwise inappropriate language. The longitudinal analysis of the ability of language models to capture nuanced patterns in lyrical content, reflecting shifts in societal norms and language use over time.

---

### VAL-Bench: Belief Consistency as a measure for Value Alignment in Language Models

Authors: Aman Gupta, Denny O'Shea, Fazl Barez
Published: 2025-10-06
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2510.05465v3

Large language models (LLMs) are increasingly being used for tasks where outputs shape human decisions, so it is critical to verify that their responses consistently reflect desired human values. Humans, as individuals or groups, don't agree on a universal set of values, which makes evaluating value alignment difficult. Existing benchmarks often use hypothetical or commonsensical situations, which don't capture the complexity and ambiguity of real-life debates. We introduce the Value ALignment Benchmark (VAL-Bench), which measures the consistency in language model belief expressions in response to real-life value-laden prompts. VAL-Bench consists of 115K pairs of prompts designed to elicit opposing stances on a controversial issue, extracted from Wikipedia. We use an LLM-as-a-judge, validated against human annotations, to evaluate if the pair of responses consistently expresses either a neutral or a specific stance on the issue. Applied across leading open- and closed-source models, the benchmark shows considerable variation in consistency rates (ranging from ~10% to ~80%), with Claude models the only ones to achieve high levels of consistency. Lack of consistency in this manner risks epistemic harm by making user beliefs dependent on how questions are framed rather than on underlying evidence, and undermines LLM reliability in trust-critical applications. Therefore, we stress the importance of research towards training belief consistency in modern LLMs. By providing a scalable, reproducible benchmark, VAL-Bench enables systematic measurement of necessary conditions for value alignment.

---

### SocialNLI: A Dialogue-Centric Social Inference Dataset

Authors: Akhil Deo, Kate Sanders, Benjamin Van Durme
Published: 2025-10-06
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.05458v1

Making theory-of-mind inferences from human dialogue is a strong indicator of a model's underlying social abilities, which are fundamental for adept AI assistants. However, large language and reasoning models struggle to understand sophisticated social phenomena in transcript data, such as sarcasm and irony. To assess the weaknesses of current models and to identify their solutions, we introduce SocialNLI (SoNLI) -- the first social dialogue inference dataset. SoNLI consists of a collection of dialogue transcripts hand-picked to center complex social nuances like irony and sarcasm, paired with inferences, corresponding likelihood scores, and human-written explanations. We explore social inference analysis as a facet of theory-of-mind, and evaluate LLM and reasoning model theory-of-mind ability through multi-step counterfactual reasoning.

---

### Do Code Models Suffer from the Dunning-Kruger Effect?

Authors: Mukul Singh, Somya Chatterjee, Arjun Radhakrishna, Sumit Gulwani
Published: 2025-10-06
Categories: cs.AI, cs.CL, cs.SE
arXiv: https://arxiv.org/abs/2510.05457v1

As artificial intelligence systems increasingly collaborate with humans in creative and technical domains, questions arise about the cognitive boundaries and biases that shape our shared agency. This paper investigates the Dunning-Kruger Effect (DKE), the tendency for those with limited competence to overestimate their abilities in state-of-the-art LLMs in coding tasks. By analyzing model confidence and performance across a diverse set of programming languages, we reveal that AI models mirror human patterns of overconfidence, especially in unfamiliar or low-resource domains. Our experiments demonstrate that less competent models and those operating in rare programming languages exhibit stronger DKE-like bias, suggesting that the strength of the bias is proportionate to the competence of the models.

---

### QDeepGR4J: Quantile-based ensemble of deep learning and GR4J hybrid rainfall-runoff models for extreme flow prediction with uncertainty quantification

Authors: Arpit Kapoor, Rohitash Chandra
Published: 2025-10-06
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.05453v1

Conceptual rainfall-runoff models aid hydrologists and climate scientists in modelling streamflow to inform water management practices. Recent advances in deep learning have unravelled the potential for combining hydrological models with deep learning models for better interpretability and improved predictive performance. In our previous work, we introduced DeepGR4J, which enhanced the GR4J conceptual rainfall-runoff model using a deep learning model to serve as a surrogate for the routing component. DeepGR4J had an improved rainfall-runoff prediction accuracy, particularly in arid catchments. Quantile regression models have been extensively used for quantifying uncertainty while aiding extreme value forecasting. In this paper, we extend DeepGR4J using a quantile regression-based ensemble learning framework to quantify uncertainty in streamflow prediction. We also leverage the uncertainty bounds to identify extreme flow events potentially leading to flooding. We further extend the model to multi-step streamflow predictions for uncertainty bounds. We design experiments for a detailed evaluation of the proposed framework using the CAMELS-Aus dataset. The results show that our proposed Quantile DeepGR4J framework improves the predictive accuracy and uncertainty interval quality (interval score) compared to baseline deep learning models. Furthermore, we carry out flood risk evaluation using Quantile DeepGR4J, and the results demonstrate its suitability as an early warning system.

---

### NASP-T: A Fuzzy Neuro-Symbolic Transformer for Logic-Constrained Aviation Safety Report Classification

Authors: Fadi Al Machot, Fidaa Al Machot
Published: 2025-10-06
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.05451v1

Deep transformer models excel at multi-label text classification but often violate domain logic that experts consider essential, an issue of particular concern in safety-critical applications. We propose a hybrid neuro-symbolic framework that integrates Answer Set Programming (ASP) with transformer-based learning on the Aviation Safety Reporting System (ASRS) corpus. Domain knowledge is formalized as weighted ASP rules and validated using the Clingo solver. These rules are incorporated in two complementary ways: (i) as rule-based data augmentation, generating logically consistent synthetic samples that improve label diversity and coverage; and (ii) as a fuzzy-logic regularizer, enforcing rule satisfaction in a differentiable form during fine-tuning. This design preserves the interpretability of symbolic reasoning while leveraging the scalability of deep neural architectures. We further tune per-class thresholds and report both standard classification metrics and logic-consistency rates. Compared to a strong Binary Cross-Entropy (BCE) baseline, our approach improves micro- and macro-F1 scores and achieves up to an 86% reduction in rule violations on the ASRS test set. To the best of our knowledge, this constitutes the first large-scale neuro-symbolic application to ASRS reports that unifies ASP-based reasoning, rule-driven augmentation, and differentiable transformer training for trustworthy, safety-critical NLP.

---

### A Probabilistic Basis for Low-Rank Matrix Learning

Authors: Simon Segert, Nathan Wycoff
Published: 2025-10-06
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2510.05447v1

Low rank inference on matrices is widely conducted by optimizing a cost function augmented with a penalty proportional to the nuclear norm $\Vert \cdot \Vert_*$. However, despite the assortment of computational methods for such problems, there is a surprising lack of understanding of the underlying probability distributions being referred to. In this article, we study the distribution with density $f(X)\propto e^{-λ\Vert X\Vert_*}$, finding many of its fundamental attributes to be analytically tractable via differential geometry. We use these facts to design an improved MCMC algorithm for low rank Bayesian inference as well as to learn the penalty parameter $λ$, obviating the need for hyperparameter tuning when this is difficult or impossible. Finally, we deploy these to improve the accuracy and efficiency of low rank Bayesian matrix denoising and completion algorithms in numerical experiments.

---

### Prior-Aligned Meta-RL: Thompson Sampling with Learned Priors and Guarantees in Finite-Horizon MDPs

Authors: Runlin Zhou, Chixiang Chen, Elynn Chen
Published: 2025-10-06
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2510.05446v1

We study meta-reinforcement learning in finite-horizon MDPs where related tasks share similar structures in their optimal action-value functions. Specifically, we posit a linear representation $Q^*_h(s,a)=Φ_h(s,a)\,θ^{(k)}_h$ and place a Gaussian meta-prior $ \mathcal{N}(θ^*_h,Σ^*_h)$ over the task-specific parameters $θ^{(k)}_h$. Building on randomized value functions, we propose two Thompson-style algorithms: (i) MTSRL, which learns only the prior mean and performs posterior sampling with the learned mean and known covariance; and (ii) $\text{MTSRL}^{+}$, which additionally estimates the covariance and employs prior widening to control finite-sample estimation error. Further, we develop a prior-alignment technique that couples the posterior under the learned prior with a meta-oracle that knows the true prior, yielding meta-regret guarantees: we match prior-independent Thompson sampling in the small-task regime and strictly improve with more tasks once the prior is learned. Concretely, for known covariance we obtain $\tilde{O}(H^{4}S^{3/2}\sqrt{ANK})$ meta-regret, and with learned covariance $\tilde{O}(H^{4}S^{3/2}\sqrt{AN^3K})$; both recover a better behavior than prior-independent after $K \gtrsim \tilde{O}(H^2)$ and $K \gtrsim \tilde{O}(N^2H^2)$, respectively. Simulations on a stateful recommendation environment (with feature and prior misspecification) show that after brief exploration, MTSRL/MTSRL\(^+\) track the meta-oracle and substantially outperform prior-independent RL and bandit-only meta-baselines. Our results give the first meta-regret guarantees for Thompson-style RL with learned Q-priors, and provide practical recipes (warm-start via RLSVI, OLS aggregation, covariance widening) for experiment-rich settings.

---

### AgentRouter: A Knowledge-Graph-Guided LLM Router for Collaborative Multi-Agent Question Answering

Authors: Zheyuan Zhang, Kaiwen Shi, Zhengqing Yuan, Zehong Wang, Tianyi Ma, Keerthiram Murugesan, Vincent Galassi, Chuxu Zhang, Yanfang Ye
Published: 2025-10-06
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.05445v1

Large language models (LLMs) and agent-based frameworks have advanced rapidly, enabling diverse applications. Yet, with the proliferation of models and agentic strategies, practitioners face substantial uncertainty in selecting the best configuration for a downstream task. Prior studies show that different agents and backbones exhibit complementary strengths, and that larger models are not always superior, underscoring the need for adaptive routing mechanisms. Existing approaches to agent routing, however, often emphasize cost efficiency while overlooking the fine-grained contextual and relational structure inherent in QA tasks. In this paper, we propose tAgentRouter, a framework that formulates multi-agent QA as a knowledge-graph-guided routing problem supervised by empirical performance signals. Specifically, we convert QA instance into a knowledge graph that jointly encodes queries, contextual entities, and agents, and then train a heterogeneous graph neural network (GNN) to propagate information across node types and produce task-aware routing distributions over agents. By leveraging soft supervision and weighted aggregation of agent outputs, AgentRouter learns principled collaboration schemes that capture the complementary strengths of diverse agents. Extensive experiments demonstrate that our framework consistently outperforms single-agent and ensemble baselines, while generalizing across benchmarks and LLM backbones. These results highlight the effectiveness and robustness of graph-supervised multi-agent routing for question answering.

---

### SimulatorArena: Are User Simulators Reliable Proxies for Multi-Turn Evaluation of AI Assistants?

Authors: Yao Dou, Michel Galley, Baolin Peng, Chris Kedzie, Weixin Cai, Alan Ritter, Chris Quirk, Wei Xu, Jianfeng Gao
Published: 2025-10-06
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.05444v2

Large language models (LLMs) are increasingly used in interactive applications, and human evaluation remains the gold standard for assessing their performance in multi-turn conversations. Since human studies are costly, time-consuming, and hard to reproduce, recent work explores using LLMs to simulate users for automatic assistant evaluation. However, there is no benchmark or systematic study to evaluate whether these simulated users are reliable stand-ins for real users. To address this, we introduce SimulatorArena, a benchmark of 909 annotated human-LLM conversations on two interactive tasks -- math tutoring and document creation. SimulatorArena evaluates simulators based on how closely their messages match human behavior and how well their assistant ratings align with human judgments. Experiments on various simulator methods show that simulators conditioned on user profiles, capturing traits like background and message styles, align closely with human judgments. They reach Spearman's $ρ$ of 0.7 on both tasks, providing a practical, scalable alternative to human evaluation. Using the best simulator for each task, we benchmark 18 assistants, including the latest LLMs such as GPT-5, Claude 4.1 Opus, and Gemini 2.5 Pro.

---

### AD-NODE: Adaptive Dynamics Learning with Neural ODEs for Mobile Robots Control

Authors: Shao-Yi Yu, Jen-Wei Wang, Maya Horii, Vikas Garg, Tarek Zohdi
Published: 2025-10-06
Categories: cs.RO, cs.LG, eess.SY
arXiv: https://arxiv.org/abs/2510.05443v1

Mobile robots, such as ground vehicles and quadrotors, are becoming increasingly important in various fields, from logistics to agriculture, where they automate processes in environments that are difficult to access for humans. However, to perform effectively in uncertain environments using model-based controllers, these systems require dynamics models capable of responding to environmental variations, especially when direct access to environmental information is limited. To enable such adaptivity and facilitate integration with model predictive control, we propose an adaptive dynamics model which bypasses the need for direct environmental knowledge by inferring operational environments from state-action history. The dynamics model is based on neural ordinary equations, and a two-phase training procedure is used to learn latent environment representations. We demonstrate the effectiveness of our approach through goal-reaching and path-tracking tasks on three robotic platforms of increasing complexity: a 2D differential wheeled robot with changing wheel contact conditions, a 3D quadrotor in variational wind fields, and the Sphero BOLT robot under two contact conditions for real-world deployment. Empirical results corroborate that our method can handle temporally and spatially varying environmental changes in both simulation and real-world systems.

---

### Adversarial Reinforcement Learning for Large Language Model Agent Safety

Authors: Zizhao Wang, Dingcheng Li, Vaishakh Keshava, Phillip Wallis, Ananth Balashankar, Peter Stone, Lukas Rutishauser
Published: 2025-10-06
Categories: cs.LG, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2510.05442v1

Large Language Model (LLM) agents can leverage tools such as Google Search to complete complex tasks. However, this tool usage introduces the risk of indirect prompt injections, where malicious instructions hidden in tool outputs can manipulate the agent, posing security risks like data leakage. Current defense strategies typically rely on fine-tuning LLM agents on datasets of known attacks. However, the generation of these datasets relies on manually crafted attack patterns, which limits their diversity and leaves agents vulnerable to novel prompt injections. To address this limitation, we propose Adversarial Reinforcement Learning for Agent Safety (ARLAS), a novel framework that leverages adversarial reinforcement learning (RL) by formulating the problem as a two-player zero-sum game. ARLAS co-trains two LLMs: an attacker that learns to autonomously generate diverse prompt injections and an agent that learns to defend against them while completing its assigned tasks. To ensure robustness against a wide range of attacks and to prevent cyclic learning, we employ a population-based learning framework that trains the agent to defend against all previous attacker checkpoints. Evaluated on BrowserGym and AgentDojo, agents fine-tuned with ARLAS achieve a significantly lower attack success rate than the original model while also improving their task success rate. Our analysis further confirms that the adversarial process generates a diverse and challenging set of attacks, leading to a more robust agent compared to the base model.

---

### UnitTenX: Generating Tests for Legacy Packages with AI Agents Powered by Formal Verification

Authors: Yiannis Charalambous, Claudionor N. Coelho, Luis Lamb, Lucas C. Cordeiro
Published: 2025-10-06
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2510.05441v1

This paper introduces UnitTenX, a state-of-the-art open-source AI multi-agent system designed to generate unit tests for legacy code, enhancing test coverage and critical value testing. UnitTenX leverages a combination of AI agents, formal methods, and Large Language Models (LLMs) to automate test generation, addressing the challenges posed by complex and legacy codebases. Despite the limitations of LLMs in bug detection, UnitTenX offers a robust framework for improving software reliability and maintainability. Our results demonstrate the effectiveness of this approach in generating high-quality tests and identifying potential issues. Additionally, our approach enhances the readability and documentation of legacy code.

---

### Refereed Learning

Authors: Ran Canetti, Ephraim Linder, Connor Wagaman
Published: 2025-10-06
Categories: stat.ML, cs.CR, cs.LG
arXiv: https://arxiv.org/abs/2510.05440v2

We initiate an investigation of learning tasks in a setting where the learner is given access to two competing provers, only one of which is honest. Specifically, we consider the power of such learners in assessing purported properties of opaque models. Following prior work in complexity theory that considers the power of competing provers in various settings, we call this setting refereed learning. After formulating a general definition of refereed learning tasks, we show refereed learning protocols that obtain a level of accuracy that far exceeds what is obtainable at comparable cost without provers, or even with a single prover. We concentrate on the task of choosing the better one out of two black-box models, with respect to some ground truth. While we consider a range of parameters, perhaps our most notable result is in the high-precision range: For all $\varepsilon>0$ and ambient dimension $d$, our learner makes only one query to the ground truth function, communicates only $(1+\frac{1}{\varepsilon^2})\cdot\text{poly}(d)$ bits with the provers, and outputs a model whose loss is within a multiplicative factor of $(1+\varepsilon)$ of the best model's loss. Obtaining comparable loss with a single prover would require the learner to access the ground truth at almost all of the points in the domain. We also present lower bounds that demonstrate the optimality of our protocols in a number of respects, including prover complexity, number of samples, and need for query access.

---

### Physics-Informed Machine Learning in Biomedical Science and Engineering

Authors: Nazanin Ahmadi, Qianying Cao, Jay D. Humphrey, George Em Karniadakis
Published: 2025-10-06
Categories: cs.LG, cs.AI, q-bio.QM
arXiv: https://arxiv.org/abs/2510.05433v1

Physics-informed machine learning (PIML) is emerging as a potentially transformative paradigm for modeling complex biomedical systems by integrating parameterized physical laws with data-driven methods. Here, we review three main classes of PIML frameworks: physics-informed neural networks (PINNs), neural ordinary differential equations (NODEs), and neural operators (NOs), highlighting their growing role in biomedical science and engineering. We begin with PINNs, which embed governing equations into deep learning models and have been successfully applied to biosolid and biofluid mechanics, mechanobiology, and medical imaging among other areas. We then review NODEs, which offer continuous-time modeling, especially suited to dynamic physiological systems, pharmacokinetics, and cell signaling. Finally, we discuss deep NOs as powerful tools for learning mappings between function spaces, enabling efficient simulations across multiscale and spatially heterogeneous biological domains. Throughout, we emphasize applications where physical interpretability, data scarcity, or system complexity make conventional black-box learning insufficient. We conclude by identifying open challenges and future directions for advancing PIML in biomedical science and engineering, including issues of uncertainty quantification, generalization, and integration of PIML and large language models.

---

### AInstein: Can LLMs Solve Research Problems From Parametric Memory Alone?

Authors: Shambhavi Mishra, Gaurav Sahu, Marco Pedersoli, Laurent Charlin, Jose Dolz, Christopher Pal
Published: 2025-10-06
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.05432v2

Can large language models solve AI research problems using only their parametric knowledge, without fine-tuning, retrieval, or other external aids? We introduce AInstein, a framework for testing whether LLM agents can generate and refine solutions to research problems through iterative critique loops. A blind study with 20 domain experts on held-out ICLR 2026 problems validates our automated metrics, which we then scale to 1,214 ICLR 2025 papers using an LLM-as-a-judge paradigm. Two metrics capture complementary aspects of performance: Success Rate (does the solution address the problem?) and Rediscovery (does it match the published approach?). LLMs succeed on over 70% of problems, yet strictly rediscover the published solution less than 19% of the time, suggesting genuine problem-solving rather than associative recall. However, this ability has clear limits: models handle familiar methodological territory well but fail when solutions require cross-domain analogical transfer, a pattern we call the parametric knowledge boundary. On the ResearchPlanGen benchmark (2,645 problems), our training-free iterative refinement strategy matches RL finetuning, and a criteria-coverage analysis pins down the ceiling of what test-time refinement alone can achieve. Together, these findings map both the capabilities and the limits of LLMs as autonomous scientific problem-solvers.

---

### Self-Filtered Distillation with LLMs-generated Trust Indicators for Reliable Patent Classification

Authors: Yongmin Yoo, Xu Zhang, Longbing Cao
Published: 2025-10-06
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.05431v4

Organizing large-scale patent corpora according to classification schemes is a core information management task that determines the accuracy and efficiency of prior art retrieval, technology knowledge discovery, and intellectual property decision-making. Recent approaches distill natural language rationales generated by large language models (LLMs) into compact student models, yet logical errors, label mismatches, and taxonomy misalignments inherent in these rationales are indiscriminately absorbed during training, undermining classification reliability and propagating errors throughout downstream information processes. Rather than correcting such errors post-hoc, we propose Self-Filtered Distillation (SFD), which embeds quality assurance directly into the learning process by reinterpreting LLM-generated rationales as trust indicators rather than ground-truth supervision. SFD integrates three unsupervised signals into a unified trust score that dynamically modulates each training instance's contribution: Self-Consistency, which quantifies agreement among independently generated rationales; Class Entailment Alignment, which evaluates semantic coherence between a rationale and its assigned CPC class definition; and LLM Agreement Scoring, which assesses external plausibility through an independent verifier. On the USPTO-2M benchmark comprising over two million patents, SFD achieves up to 38.7\% relative improvement in Macro-F1 across four student architectures, and the strong correlation between trust scores and expert judgments ($r = 0.685$) confirms that the framework provides not only accurate predictions but also decomposable confidence semantics that enable auditable and self-documenting classification outcomes for large-scale patent knowledge organization.

---

### Draft, Verify, and Improve: Toward Training-Aware Speculative Decoding

Authors: Shrenik Bhansali, Larry Heck
Published: 2025-10-06
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.05421v1

Autoregressive (AR) decoding is a major latency bottleneck for large language models. Speculative decoding (SD) accelerates AR by letting a drafter propose multi-token blocks that a verifier accepts or rejects. However, many SD systems require heavy offline training or extra components. These choices raise data/compute cost and can yield brittle drafters under distribution drift. We introduce \emph{Draft, Verify, \& Improve (DVI)}, a training-aware self-speculative framework that combines inference with continual online learning. We partition an LLM into a drafter and a verifier, and during generation, verifier accept/reject decisions are converted into supervision signals and used to update the drafter head. A simple \emph{KL$\rightarrow$RL} schedule bootstraps calibration via online distillation and then adds reward-masked cross-entropy with a on-policy policy-gradient term, preserving lossless, single model deployment. On Spec-Bench, DVI achieves a $2.16\times$ wall-time speedup, on par with SoTA approaches like EAGLE-2, while orders of magnitude less data for training, and ablations show that DVI outperforms KL-only online distillation. DVI demonstrates that \emph{training-aware} self-speculation can deliver state-of-the-art, lossless speedups with minimal training overhead.

---

### Exploring Student Choice and the Use of Multimodal Generative AI in Programming Learning

Authors: Xinying Hou, Ruiwei Xiao, Runlong Ye, Michael Liut, John Stamper
Published: 2025-10-06
Categories: cs.HC, cs.AI
arXiv: https://arxiv.org/abs/2510.05417v1

The broad adoption of Generative AI (GenAI) is impacting Computer Science education, and recent studies found its benefits and potential concerns when students use it for programming learning. However, most existing explorations focus on GenAI tools that primarily support text-to-text interaction. With recent developments, GenAI applications have begun supporting multiple modes of communication, known as multimodality. In this work, we explored how undergraduate programming novices choose and work with multimodal GenAI tools, and their criteria for choices. We selected a commercially available multimodal GenAI platform for interaction, as it supports multiple input and output modalities, including text, audio, image upload, and real-time screen-sharing. Through 16 think-aloud sessions that combined participant observation with follow-up semi-structured interviews, we investigated student modality choices for GenAI tools when completing programming problems and the underlying criteria for modality selections. With multimodal communication emerging as the future of AI in education, this work aims to spark continued exploration on understanding student interaction with multimodal GenAI in the context of CS education.

---

### Correlating Cross-Iteration Noise for DP-SGD using Model Curvature

Authors: Xin Gu, Yingtai Xiao, Guanlin He, Jiamu Bai, Daniel Kifer, Kiwan Maeng
Published: 2025-10-06
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.05416v3

Differentially private stochastic gradient descent (DP-SGD) offers the promise of training deep learning models while mitigating many privacy risks. However, there is currently a large accuracy gap between DP-SGD and normal SGD training. This has resulted in different lines of research investigating orthogonal ways of improving privacy-preserving training. One such line of work, known as DP-MF, correlates the privacy noise across different iterations of stochastic gradient descent -- allowing later iterations to cancel out some of the noise added to earlier iterations. In this paper, we study how to improve this noise correlation. We propose a technique called NoiseCurve that uses model curvature, estimated from public unlabeled data, to improve the quality of this cross-iteration noise correlation. Our experiments on various datasets, models, and privacy parameters show that the noise correlations computed by NoiseCurve offer consistent and significant improvements in accuracy over the correlation scheme used by DP-MF.

---

### A Lightweight Large Language Model-Based Multi-Agent System for 2D Frame Structural Analysis

Authors: Ziheng Geng, Jiachen Liu, Ran Cao, Lu Cheng, Haifeng Wang, Minghui Cheng
Published: 2025-10-06
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.05414v1

Large language models (LLMs) have recently been used to empower autonomous agents in engineering, significantly improving automation and efficiency in labor-intensive workflows. However, their potential remains underexplored in structural engineering, particularly for finite element modeling tasks requiring geometric modeling, complex reasoning, and domain knowledge. To bridge this gap, this paper develops a LLM-based multi-agent system to automate finite element modeling of 2D frames. The system decomposes structural analysis into subtasks, each managed by a specialized agent powered by the lightweight Llama-3.3 70B Instruct model. The workflow begins with a Problem Analysis Agent, which extracts geometry, boundary, and material parameters from the user input. Next, a Geometry Agent incrementally derives node coordinates and element connectivity by applying expert-defined rules. These structured outputs are converted into executable OpenSeesPy code by a Translation Agent and refined by a Model Validation Agent through consistency checks. Then, a Load Agent applies load conditions into the assembled structural model. Experimental evaluations on 20 benchmark problems demonstrate that the system achieves accuracy over 80% in most cases across 10 repeated trials, outperforming Gemini-2.5 Pro and ChatGPT-4o models.

---

### Personalizing Retrieval using Joint Embeddings or "the Return of Fluffy"

Authors: Bruno Korbar, Andrew Zisserman
Published: 2025-10-06
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.05411v1

The goal of this paper is to be able to retrieve images using a compound query that combines object instance information from an image, with a natural text description of what that object is doing or where it is. For example, to retrieve an image of "Fluffy the unicorn (specified by an image) on someone's head". To achieve this we design a mapping network that can "translate" from a local image embedding (of the object instance) to a text token, such that the combination of the token and a natural language query is suitable for CLIP style text encoding, and image retrieval. Generating a text token in this manner involves a simple training procedure, that only needs to be performed once for each object instance. We show that our approach of using a trainable mapping network, termed pi-map, together with frozen CLIP text and image encoders, improves the state of the art on two benchmarks designed to assess personalized retrieval.

---

### Aligning Language Models with Clinical Expertise: DPO for Heart Failure Nursing Documentation in Critical Care

Authors: Junyi Fan, Li Sun, Negin Ashrafi, Kamiar Alaei, Maryam Pishgar
Published: 2025-10-06
Categories: cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2510.05410v1

Nursing documentation in intensive care units (ICUs) provides essential clinical intelligence but often suffers from inconsistent terminology, informal styles, and lack of standardization, challenges that are particularly critical in heart failure care. This study applies Direct Preference Optimization (DPO) to adapt Mistral-7B, a locally deployable language model, using 8,838 heart failure nursing notes from the MIMIC-III database and 21,210 preference pairs derived from expert-verified GPT outputs, model generations, and original notes. Evaluation across BLEU, ROUGE, BERTScore, Perplexity, and expert qualitative assessments demonstrates that DPO markedly enhances documentation quality. Specifically, BLEU increased by 84% (0.173 to 0.318), BERTScore improved by 7.6% (0.828 to 0.891), and expert ratings rose across accuracy (+14.4 points), completeness (+14.5 points), logical consistency (+14.1 points), readability (+11.1 points), and structural clarity (+6.0 points). These results indicate that DPO can align lightweight clinical language models with expert standards, supporting privacy-preserving, AI-assisted documentation within electronic health record systems to reduce administrative burden and improve ICU patient safety.

---

### See the past: Time-Reversed Scene Reconstruction from Thermal Traces Using Visual Language Models

Authors: Kebin Contreras, Luis Toscano-Palomino, Mauro Dalla Mura, Jorge Bacca
Published: 2025-10-06
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.05408v2

Recovering the past from present observations is an intriguing challenge with potential applications in forensics and scene analysis. Thermal imaging, operating in the infrared range, provides access to otherwise invisible information. Since humans are typically warmer (37 C -98.6 F) than their surroundings, interactions such as sitting, touching, or leaning leave residual heat traces. These fading imprints serve as passive temporal codes, allowing for the inference of recent events that exceed the capabilities of RGB cameras. This work proposes a time-reversed reconstruction framework that uses paired RGB and thermal images to recover scene states from a few seconds earlier. The proposed approach couples Visual-Language Models (VLMs) with a constrained diffusion process, where one VLM generates scene descriptions and another guides image reconstruction, ensuring semantic and structural consistency. The method is evaluated in three controlled scenarios, demonstrating the feasibility of reconstructing plausible past frames up to 120 seconds earlier, providing a first step toward time-reversed imaging from thermal traces.

---

### Teacher-Student Guided Inverse Modeling for Steel Final Hardness Estimation

Authors: Ahmad Alsheikh, Andreas Fischer
Published: 2025-10-06
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.05402v1

Predicting the final hardness of steel after heat treatment is a challenging regression task due to the many-to-one nature of the process -- different combinations of input parameters (such as temperature, duration, and chemical composition) can result in the same hardness value. This ambiguity makes the inverse problem, estimating input parameters from a desired hardness, particularly difficult. In this work, we propose a novel solution using a Teacher-Student learning framework. First, a forward model (Teacher) is trained to predict final hardness from 13 metallurgical input features. Then, a backward model (Student) is trained to infer plausible input configurations from a target hardness value. The Student is optimized by leveraging feedback from the Teacher in an iterative, supervised loop. We evaluate our method on a publicly available tempered steel dataset and compare it against baseline regression and reinforcement learning models. Results show that our Teacher-Student framework not only achieves higher inverse prediction accuracy but also requires significantly less computational time, demonstrating its effectiveness and efficiency for inverse process modeling in materials science.

---

### Comparing LSTM-Based Sequence-to-Sequence Forecasting Strategies for 24-Hour Solar Proton Flux Profiles Using GOES Data

Authors: Kangwoo Yi, Bo Shen, Qin Li, Haimin Wang, Yong-Jae Moon, Jaewon Lee, Hwanhee Lee
Published: 2025-10-06
Categories: cs.LG, astro-ph.SR, cs.AI
arXiv: https://arxiv.org/abs/2510.05399v1

Solar Proton Events (SPEs) cause significant radiation hazards to satellites, astronauts, and technological systems. Accurate forecasting of their proton flux time profiles is crucial for early warnings and mitigation. This paper explores deep learning sequence-to-sequence (seq2seq) models based on Long Short-Term Memory networks to predict 24-hour proton flux profiles following SPE onsets. We used a dataset of 40 well-connected SPEs (1997-2017) observed by NOAA GOES, each associated with a >=M-class western-hemisphere solar flare and undisturbed proton flux profiles. Using 4-fold stratified cross-validation, we evaluate seq2seq model configurations (varying hidden units and embedding dimensions) under multiple forecasting scenarios: (i) proton-only input vs. combined proton+X-ray input, (ii) original flux data vs. trend-smoothed data, and (iii) autoregressive vs. one-shot forecasting. Our major results are as follows: First, one-shot forecasting consistently yields lower error than autoregressive prediction, avoiding the error accumulation seen in iterative approaches. Second, on the original data, proton-only models outperform proton+X-ray models. However, with trend-smoothed data, this gap narrows or reverses in proton+X-ray models. Third, trend-smoothing significantly enhances the performance of proton+X-ray models by mitigating fluctuations in the X-ray channel. Fourth, while models trained on trendsmoothed data perform best on average, the best-performing model was trained on original data, suggesting that architectural choices can sometimes outweigh the benefits of data preprocessing.

---

### Scalable In-context Ranking with Generative Models

Authors: Nilesh Gupta, Chong You, Srinadh Bhojanapalli, Sanjiv Kumar, Inderjit Dhillon, Felix Yu
Published: 2025-10-06
Categories: cs.IR, cs.LG
arXiv: https://arxiv.org/abs/2510.05396v2

In-context Ranking (ICR) is an emerging paradigm for Information Retrieval (IR), which leverages contextual understanding of LLMs by directly incorporating the task description, candidate documents, and the query into the model's input prompt and tasking the LLM to identify relevant document(s). While it is effective, efficiency is a significant challenge in this paradigm, especially as the candidate list grows due to quadratic/super-linear scaling of attention operation with context length. To this end, this paper first identifies inherent and exploitable structures in the attention of LLMs finetuned for ICR: (1) inter-document block sparsity: attention is dense within each document block but sparse across different documents in the context; and (2) query-document block relevance: the attention scores from certain query tokens to a document block in middle layers strongly correlate with that document's actual relevance. Motivated by these observations, we introduce BlockRank (Blockwise In-context Ranking), a novel method that adapts the attention operation in an LLM by (a) architecturally enforcing the observed inter-document block sparsity, reducing attention complexity from quadratic to linear without loss in performance, and (b) optimizing query-document block relevance for true relevant documents during fine-tuning using an auxiliary contrastive training objective, improving retrieval in attention. Experiments on BEIR, MSMarco and NQ with Mistral-7B demonstrate that BlockRank Mistral matches or outperforms existing SOTA listwise rankers and controlled fine-tuned baseline while being significantly more efficient at inference (4.7x for 100 MSMarco documents in context) and scaling gracefully to long-context shortlists, around 500 documents in-context (approximately 100K context length) within a second, presenting a scalable and effective solution for ICR.

---

### Fusion-Based Neural Generalization for Predicting Temperature Fields in Industrial PET Preform Heating

Authors: Ahmad Alsheikh, Andreas Fischer
Published: 2025-10-06
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.05394v1

Accurate and efficient temperature prediction is critical for optimizing the preheating process of PET preforms in industrial microwave systems prior to blow molding. We propose a novel deep learning framework for generalized temperature prediction. Unlike traditional models that require extensive retraining for each material or design variation, our method introduces a data-efficient neural architecture that leverages transfer learning and model fusion to generalize across unseen scenarios. By pretraining specialized neural regressor on distinct conditions such as recycled PET heat capacities or varying preform geometries and integrating their representations into a unified global model, we create a system capable of learning shared thermal dynamics across heterogeneous inputs. The architecture incorporates skip connections to enhance stability and prediction accuracy. Our approach reduces the need for large simulation datasets while achieving superior performance compared to models trained from scratch. Experimental validation on two case studies material variability and geometric diversity demonstrates significant improvements in generalization, establishing a scalable ML-based solution for intelligent thermal control in manufacturing environments. Moreover, the approach highlights how data-efficient generalization strategies can extend to other industrial applications involving complex physical modeling with limited data.

---

### Quantum Concept Music Score from Quantum Picturalism: Musical Incarnation of a Bell-Pair under Measurements

Authors: Rakhat-Bi Abdyssagin, Bob Coecke
Published: 2025-10-06
Categories: quant-ph, cs.CL, math.CT
arXiv: https://arxiv.org/abs/2510.05391v1

We initiate the development of a new language and theory for quantum music, to which we refer as Quantum Concept Music (QCM). This new music formalism is based on Categorical Quantum Mechanics (CQM), and more specifically, its diagrammatic incarnation Quantum Picturalism (QPict), which is heavily based on ZX-calculus. In fact, it is naturally inherited from CQM/QPict. At its heart is the explicit notational representation of relations that exist within and between the key concepts of music composition, performance, and automation. QCM also enables one to directly translate quantum phenomena into music compositions in a both intuitively obvious, rigorous and mechanical manner. Following this pattern, we propose a score for musicians interacting like a Bell-pair under measurement, and outline examples of how it could be live performed. While most of the Western classical music notation has heavily relied on linear representation of music - which does not always adequately capture the nature of music - our approach is distinct by highlighting the fundamental relational dimension of music. In addition, this quantum-based technique not only influences the music at the profound level of composition, but also has a direct impact on a live performance, and also provides a new template for automating music, e.g.~in the context of AI-generation. All together, we initiate the creation of new music formalism that is powerful and efficient in capturing the interactive nature of music, both in terms of internal and external interactions, and goes beyond the boundaries of Western classical music notation, which allows to use it in many different genres and directions.

---

### Cross-Lingual Mental Health Ontologies for Indian Languages: Bridging Patient Expression and Clinical Understanding through Explainable AI and Human-in-the-Loop Validation

Authors: Ananth Kandala, Ratna Kandala, Akshata Kishore Moharir, Niva Manchanda, Sunaina Singh
Published: 2025-10-06
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.05387v1

Mental health communication in India is linguistically fragmented, culturally diverse, and often underrepresented in clinical NLP. Current health ontologies and mental health resources are dominated by diagnostic frameworks centered on English or Western culture, leaving a gap in representing patient distress expressions in Indian languages. We propose cross-linguistic graphs of patient stress expressions (CL-PDE), a framework for building cross-lingual mental health ontologies through graph-based methods that capture culturally embedded expressions of distress, align them across languages, and link them with clinical terminology. Our approach addresses critical gaps in healthcare communication by grounding AI systems in culturally valid representations, allowing more inclusive and patient-centric NLP tools for mental health care in multilingual contexts.

---

### A Neural Network Algorithm for KL Divergence Estimation with Quantitative Error Bounds

Authors: Mikil Foss, Andrew Lamperski
Published: 2025-10-06
Categories: cs.LG, cs.IT, math.OC
arXiv: https://arxiv.org/abs/2510.05386v1

Estimating the Kullback-Leibler (KL) divergence between random variables is a fundamental problem in statistical analysis. For continuous random variables, traditional information-theoretic estimators scale poorly with dimension and/or sample size. To mitigate this challenge, a variety of methods have been proposed to estimate KL divergences and related quantities, such as mutual information, using neural networks. The existing theoretical analyses show that neural network parameters achieving low error exist. However, since they rely on non-constructive neural network approximation theorems, they do not guarantee that the existing algorithms actually achieve low error. In this paper, we propose a KL divergence estimation algorithm using a shallow neural network with randomized hidden weights and biases (i.e. a random feature method). We show that with high probability, the algorithm achieves a KL divergence estimation error of $O(m^{-1/2}+T^{-1/3})$, where $m$ is the number of neurons and $T$ is both the number of steps of the algorithm and the number of samples.

---

### Physics-Informed Neural Networks with Fourier Features and Attention-Driven Decoding

Authors: Rohan Arni, Carlos Blanco
Published: 2025-10-06
Categories: cs.LG, physics.comp-ph
arXiv: https://arxiv.org/abs/2510.05385v1

Physics-Informed Neural Networks (PINNs) are a useful framework for approximating partial differential equation solutions using deep learning methods. In this paper, we propose a principled redesign of the PINNsformer, a Transformer-based PINN architecture. We present the Spectral PINNSformer (S-Pformer), a refinement of encoder-decoder PINNSformers that addresses two key issues; 1. the redundancy (i.e. increased parameter count) of the encoder, and 2. the mitigation of spectral bias. We find that the encoder is unnecessary for capturing spatiotemporal correlations when relying solely on self-attention, thereby reducing parameter count. Further, we integrate Fourier feature embeddings to explicitly mitigate spectral bias, enabling adaptive encoding of multiscale behaviors in the frequency domain. Our model outperforms encoder-decoder PINNSformer architectures across all benchmarks, achieving or outperforming MLP performance while reducing parameter count significantly.

---

### Context Length Alone Hurts LLM Performance Despite Perfect Retrieval

Authors: Yufeng Du, Minyang Tian, Srikanth Ronanki, Subendhu Rongali, Sravan Bodapati, Aram Galstyan, Azton Wells, Roy Schwartz, Eliu A Huerta, Hao Peng
Published: 2025-10-06
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.05381v1

Large language models (LLMs) often fail to scale their performance on long-context tasks performance in line with the context lengths they support. This gap is commonly attributed to retrieval failures -- the models' inability to identify relevant information in the long inputs. Accordingly, recent efforts often focus on evaluating and improving LLMs' retrieval performance: if retrieval is perfect, a model should, in principle, perform just as well on a long input as it does on a short one -- or should it? This paper presents findings that the answer to this question may be negative. Our systematic experiments across 5 open- and closed-source LLMs on math, question answering, and coding tasks reveal that, even when models can perfectly retrieve all relevant information, their performance still degrades substantially (13.9%--85%) as input length increases but remains well within the models' claimed lengths. This failure occurs even when the irrelevant tokens are replaced with minimally distracting whitespace, and, more surprisingly, when they are all masked and the models are forced to attend only to the relevant tokens. A similar performance drop is observed when all relevant evidence is placed immediately before the question. Our findings reveal a previously-unrealized limitation: the sheer length of the input alone can hurt LLM performance, independent of retrieval quality and without any distraction. They motivate our simple, model-agnostic mitigation strategy that transforms a long-context task into a short-context one by prompting the model to recite the retrieved evidence before attempting to solve the problem. On RULER, we observe a consistent improvement of GPT-4o up to 4% on an already strong baseline.

---

### Minima and Critical Points of the Bethe Free Energy Are Invariant Under Deformation Retractions of Factor Graphs

Authors: Grégoire Sergeant-Perthuis, Léo Boitel
Published: 2025-10-06
Categories: stat.ML, cs.LG, math.PR
arXiv: https://arxiv.org/abs/2510.05380v1

In graphical models, factor graphs, and more generally energy-based models, the interactions between variables are encoded by a graph, a hypergraph, or, in the most general case, a partially ordered set (poset). Inference on such probabilistic models cannot be performed exactly due to cycles in the underlying structures of interaction. Instead, one resorts to approximate variational inference by optimizing the Bethe free energy. Critical points of the Bethe free energy correspond to fixed points of the associated Belief Propagation algorithm. A full characterization of these critical points for general graphs, hypergraphs, and posets with a finite number of variables is still an open problem. We show that, for hypergraphs and posets with chains of length at most 1, changing the poset of interactions of the probabilistic model to one with the same homotopy type induces a bijection between the critical points of the associated free energy. This result extends and unifies classical results that assume specific forms of collapsibility to prove uniqueness of the critical points of the Bethe free energy.

---

### AutoDAN-Reasoning: Enhancing Strategies Exploration based Jailbreak Attacks with Test-Time Scaling

Authors: Xiaogeng Liu, Chaowei Xiao
Published: 2025-10-06
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2510.05379v2

Recent advancements in jailbreaking large language models (LLMs), such as AutoDAN-Turbo, have demonstrated the power of automated strategy discovery. AutoDAN-Turbo employs a lifelong learning agent to build a rich library of attack strategies from scratch. While highly effective, its test-time generation process involves sampling a strategy and generating a single corresponding attack prompt, which may not fully exploit the potential of the learned strategy library. In this paper, we propose to further improve the attack performance of AutoDAN-Turbo through test-time scaling. We introduce two distinct scaling methods: Best-of-N and Beam Search. The Best-of-N method generates N candidate attack prompts from a sampled strategy and selects the most effective one based on a scorer model. The Beam Search method conducts a more exhaustive search by exploring combinations of strategies from the library to discover more potent and synergistic attack vectors. According to the experiments, the proposed methods significantly boost performance, with Beam Search increasing the attack success rate by up to 15.6 percentage points on Llama-3.1-70B-Instruct and achieving a nearly 60% relative improvement against the highly robust GPT-o4-mini compared to the vanilla method.

---

### What Do You Mean? Exploring How Humans and AI Interact with Symbols and Meanings in Their Interactions

Authors: Reza Habibi, Seung Wan Ha, Zhiyu Lin, Atieh Kashani, Ala Shafia, Lakshana Lakshmanarajan, Chia-Fang Chung, Magy Seif El-Nasr
Published: 2025-10-06
Categories: cs.AI, cs.HC
arXiv: https://arxiv.org/abs/2510.05378v1

Meaningful human-AI collaboration requires more than processing language; it demands a deeper understanding of symbols and their socially constructed meanings. While humans naturally interpret symbols through social interaction, AI systems often miss the dynamic interpretations that emerge in conversation. Drawing on Symbolic Interactionism theory, we conducted two studies to investigate how humans and AI co-construct symbols and their meanings. Findings provide empirical insights into how humans and conversational AI agents collaboratively shape meanings during interaction. We show how participants shift their initial definitions of meaning in response to the symbols and interpretations suggested by the conversational AI agents, especially when social context is introduced. We also observe how participants project their personal and social values into these interactions, refining meanings over time. These findings reveal that shared understanding does not emerge from mere agreement but from the bi-directional exchange and reinterpretation of symbols, suggesting new paradigms for human-AI interaction design.

---

### KVLinC : KV Cache Quantization with Hadamard Rotation and Linear Correction

Authors: Utkarsh Saxena, Kaushik Roy
Published: 2025-10-06
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.05373v1

Quantizing the key-value (KV) cache is a promising strategy for improving the inference efficiency of large language models (LLMs). However, aggressive quantization to very low precision (e.g., 2 bits) introduces significant errors in the stored key and value tensors, which propagate through the dot-product attention mechanism and ultimately degrade generation quality. To address this, we propose KVLinC, a framework to mitigate attention errors introduced by KV cache quantization in the extreme low-precision regime. KVLinC combines a Hadamard rotation, which reduces quantization error in values, with lightweight linear correction adapters that explicitly compensate for errors introduced by quantized keys. Across extensive evaluations on the LLaMA, Qwen2.5, and Qwen3 model families, KVLinC consistently matches or surpasses strong baselines while achieving higher KV-cache compression. Furthermore, we implement a custom attention kernel that results in upto 2.55x faster inference compared to Flash Attention baseline, enabling efficient long-context LLM inference.

---

### LightCache: Memory-Efficient, Training-Free Acceleration for Video Generation

Authors: Yang Xiao, Gen Li, Kaiyuan Deng, Yushu Wu, Zheng Zhan, Yanzhi Wang, Xiaolong Ma, Bo Hui
Published: 2025-10-06
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2510.05367v1

Training-free acceleration has emerged as an advanced research area in video generation based on diffusion models. The redundancy of latents in diffusion model inference provides a natural entry point for acceleration. In this paper, we decompose the inference process into the encoding, denoising, and decoding stages, and observe that cache-based acceleration methods often lead to substantial memory surges in the latter two stages. To address this problem, we analyze the characteristics of inference across different stages and propose stage-specific strategies for reducing memory consumption: 1) Asynchronous Cache Swapping. 2) Feature chunk. 3) Slicing latents to decode. At the same time, we ensure that the time overhead introduced by these three strategies remains lower than the acceleration gains themselves. Compared with the baseline, our approach achieves faster inference speed and lower memory usage, while maintaining quality degradation within an acceptable range. The Code is available at https://github.com/NKUShaw/LightCache .

---

### The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures

Authors: Alexander M. Fichtl, Jeremias Bohn, Josefin Kelber, Edoardo Mosca, Georg Groh
Published: 2025-10-06
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.05364v1

Transformers have dominated sequence processing tasks for the past seven years -- most notably language modeling. However, the inherent quadratic complexity of their attention mechanism remains a significant bottleneck as context length increases. This paper surveys recent efforts to overcome this bottleneck, including advances in (sub-quadratic) attention variants, recurrent neural networks, state space models, and hybrid architectures. We critically analyze these approaches in terms of compute and memory complexity, benchmark results, and fundamental limitations to assess whether the dominance of pure-attention transformers may soon be challenged.

---

### MHA-RAG: Improving Efficiency, Accuracy, and Consistency by Encoding Exemplars as Soft Prompts

Authors: Abhinav Jain, Xinyu Yao, Thomas Reps, Christopher Jermaine
Published: 2025-10-06
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.05363v2

Adapting Foundation Models to new domains with limited training data is challenging and computationally expensive. While prior work has demonstrated the effectiveness of using domain-specific exemplars as in-context demonstrations, we investigate whether representing exemplars purely as text is the most efficient, effective, and stable approach. We explore an alternative: representing exemplars as soft prompts with an exemplar order invariant model architecture. To this end, we introduce Multi-Head Attention Retrieval-Augmented Generation (MHA-RAG), a framework with the number of attention heads serving as a simple hyperparameter to control soft prompt-generation across different tasks. Across multiple question-answering benchmarks and model scales, MHA-RAG achieves a 20-point performance gain over standard RAG, while cutting inference costs by a factor of 10X GFLOPs-delivering both higher accuracy and greater efficiency, invariant to exemplar order.

---

### Residualized Similarity for Faithfully Explainable Authorship Verification

Authors: Peter Zeng, Pegah Alipoormolabashi, Jihu Mun, Gourab Dey, Nikita Soni, Niranjan Balasubramanian, Owen Rambow, H. Schwartz
Published: 2025-10-06
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.05362v1

Responsible use of Authorship Verification (AV) systems not only requires high accuracy but also interpretable solutions. More importantly, for systems to be used to make decisions with real-world consequences requires the model's prediction to be explainable using interpretable features that can be traced to the original texts. Neural methods achieve high accuracies, but their representations lack direct interpretability. Furthermore, LLM predictions cannot be explained faithfully -- if there is an explanation given for a prediction, it doesn't represent the reasoning process behind the model's prediction. In this paper, we introduce Residualized Similarity (RS), a novel method that supplements systems using interpretable features with a neural network to improve their performance while maintaining interpretability. Authorship verification is fundamentally a similarity task, where the goal is to measure how alike two documents are. The key idea is to use the neural network to predict a similarity residual, i.e. the error in the similarity predicted by the interpretable system. Our evaluation across four datasets shows that not only can we match the performance of state-of-the-art authorship verification models, but we can show how and to what degree the final prediction is faithful and interpretable.

---

### MT-DAO: Multi-Timescale Distributed Adaptive Optimizers with Local Updates

Authors: Alex Iacob, Andrej Jovanovic, Mher Safaryan, Meghdad Kurmanji, Lorenzo Sani, Samuel Horváth, William F. Shen, Xinchi Qiu, Nicholas D. Lane
Published: 2025-10-06
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.05361v1

Training large models with distributed data parallelism (DDP) requires frequent communication of gradients across workers, which can saturate bandwidth. Infrequent communication strategies (e.g., Local SGD) reduce this overhead but, when applied to adaptive optimizers, often suffer a performance gap relative to fully synchronous DDP. We trace this gap to a time-scale mismatch: the optimizer's fast-moving momentum, tuned for frequent updates, decays too quickly to smooth gradients over long intervals, leading to noise-dominated optimization. To address this, we propose MT-DAO, a family of optimizers that employs multiple slow- and fast-moving first momenta or the gradient to track update dynamics across different time scales, for which we provide the first convergence guarantees. Empirically, for language-model pre-training, this eliminates the performance gap with DDP, outperforming infrequent-communication baselines in perplexity and reducing iso-token wall-clock time by 6-27% on Ethernet interconnects. At the 720M scale, MT-DAO reaches a target perplexity in 24% fewer steps and 35% less time than the single-momentum DDP baseline. MT-DAO enables effective cross-datacenter training and training over wide geographic areas.

---

### Mitigating Diffusion Model Hallucinations with Dynamic Guidance

Authors: Kostas Triaridis, Alexandros Graikos, Aggelina Chatziagapi, Grigorios G. Chrysos, Dimitris Samaras
Published: 2025-10-06
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2510.05356v2

Hallucinations in diffusion models are samples with structural inconsistencies that can emerge due to the excessive smoothing of the learned score function, which in turn leads to interpolations between modes of the data distribution. Since semantic interpolations are often desirable and contribute to sample diversity, we believe that a nuanced and targeted solution is required to address diffusion model hallucinations. In this work, we introduce Dynamic Guidance, which mitigates hallucinations by selectively sharpening the score function only along the pre-determined directions known to cause artifacts, while preserving valid semantic variations. This sharpening can be performed using either pre-determined classes or semantically coherent clusters that form pseudo-classes over the data distribution. The latter allows for a principled extension of Dynamic Guidance to text-to-image generation, where we select modes to correspond to fine-grained contextual differences in textual descriptions. To our knowledge, this is the first approach that addresses hallucinations at generation time rather than through post-hoc filtering. Dynamic Guidance substantially reduces hallucinations on both controlled and natural image datasets, significantly outperforming baselines.

---