# Research Papers — 2025-11 · bundle page 185 of 197

> Full-text markdown of papers #9201–9250 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/185
[← Previous bundle](https://aipod.dev/papers/archive/2025-11/page/184.md)
[Next bundle →](https://aipod.dev/papers/archive/2025-11/page/186.md)

### Optimizing Attention on GPUs by Exploiting GPU Architectural NUMA Effects

Authors: Mansi Choudhary, Karthik Sangaiah, Sonali Singh, Muhammad Osama, Lisa Wu Wills, Ganesh Dasika
Published: 2025-11-03
Categories: cs.AR, cs.DC, cs.LG, cs.PF
arXiv: https://arxiv.org/abs/2511.02132v1

The rise of disaggregated AI GPUs has exposed a critical bottleneck in large-scale attention workloads: non-uniform memory access (NUMA). As multi-chiplet designs become the norm for scaling compute capabilities, memory latency and bandwidth vary sharply across compute regions, undermining the performance of traditional GPU kernel scheduling strategies that assume uniform memory access. We identify how these NUMA effects distort locality in multi-head attention (MHA) and present Swizzled Head-first Mapping, a spatially-aware scheduling strategy that aligns attention heads with GPU NUMA domains to exploit intra-chiplet cache reuse. On AMD's MI300X architecture, our method achieves up to 50% higher performance over state-of-the-art attention algorithms using conventional scheduling techniques and sustains consistently high L2 cache hit rates of 80-97%. These results demonstrate that NUMA-aware scheduling is now fundamental to achieving full efficiency on next-generation disaggregated GPUs, offering a path forward for scalable AI training and inference.

---

### Re-FORC: Adaptive Reward Prediction for Efficient Chain-of-Thought Reasoning

Authors: Renos Zabounidis, Aditya Golatkar, Michael Kleinman, Alessandro Achille, Wei Xia, Stefano Soatto
Published: 2025-11-03
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2511.02130v2

We propose Re-FORC, an adaptive reward prediction method that, given a query, enables prediction of the expected future rewards as a function of the number of future thinking tokens. Re-FORC trains a lightweight adapter on reasoning models, demonstrating improved prediction with longer reasoning and larger models. Re-FORC enables: 1) early stopping of unpromising reasoning chains, reducing compute by up to 26\% compared to fixed-budget cutoffs, while maintaining accuracy, 2) optimized model and thinking length selection that outperforms the largest model alone--- reaching 1.7 percentage points higher peak accuracy while needing up to 12\% less compute to match the largest model's accuracy, 3) adaptive test-time scaling, which increases accuracy by 9.9 percentage points (on average at maximum compute) over confidence-based baselines. Re-FORC allows dynamic reasoning with length control via cost-per-token thresholds while estimating computation time upfront.

---

### Variance-Aware Feel-Good Thompson Sampling for Contextual Bandits

Authors: Xuheng Li, Quanquan Gu
Published: 2025-11-03
Categories: cs.LG, math.OC, stat.ML
arXiv: https://arxiv.org/abs/2511.02123v1

Variance-dependent regret bounds have received increasing attention in recent studies on contextual bandits. However, most of these studies are focused on upper confidence bound (UCB)-based bandit algorithms, while sampling based bandit algorithms such as Thompson sampling are still understudied. The only exception is the LinVDTS algorithm (Xu et al., 2023), which is limited to linear reward function and its regret bound is not optimal with respect to the model dimension. In this paper, we present FGTSVA, a variance-aware Thompson Sampling algorithm for contextual bandits with general reward function with optimal regret bound. At the core of our analysis is an extension of the decoupling coefficient, a technique commonly used in the analysis of Feel-good Thompson sampling (FGTS) that reflects the complexity of the model space. With the new decoupling coefficient denoted by $\mathrm{dc}$, FGTS-VA achieves the regret of $\tilde{O}(\sqrt{\mathrm{dc}\cdot\log|\mathcal{F}|\sum_{t=1}^Tσ_t^2}+\mathrm{dc})$, where $|\mathcal{F}|$ is the size of the model space, $T$ is the total number of rounds, and $σ_t^2$ is the subgaussian norm of the noise (e.g., variance when the noise is Gaussian) at round $t$. In the setting of contextual linear bandits, the regret bound of FGTSVA matches that of UCB-based algorithms using weighted linear regression (Zhou and Gu, 2022).

---

### Matrix Sensing with Kernel Optimal Loss: Robustness and Optimization Landscape

Authors: Xinyuan Song, Ziye Ma
Published: 2025-11-03
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2511.02122v3

In this paper we study how the choice of loss functions of non-convex optimization problems affects their robustness and optimization landscape, through the study of noisy matrix sensing. In traditional regression tasks, mean squared error (MSE) loss is a common choice, but it can be unreliable for non-Gaussian or heavy-tailed noise. To address this issue, we adopt a robust loss based on nonparametric regression, which uses a kernel-based estimate of the residual density and maximizes the estimated log-likelihood. This robust formulation coincides with the MSE loss under Gaussian errors but remains stable under more general settings. We further examine how this robust loss reshapes the optimization landscape by analyzing the upper-bound of restricted isometry property (RIP) constants for spurious local minima to disappear. Through theoretical and empirical analysis, we show that this new loss excels at handling large noise and remains robust across diverse noise distributions. This work offers initial insights into enhancing the robustness of machine learning tasks through simply changing the loss, guided by an intuitive and broadly applicable analytical framework.

---

### InsurAgent: A Large Language Model-Empowered Agent for Simulating Individual Behavior in Purchasing Flood Insurance

Authors: Ziheng Geng, Jiachen Liu, Ran Cao, Lu Cheng, Dan M. Frangopol, Minghui Cheng
Published: 2025-11-03
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2511.02119v1

Flood insurance is an effective strategy for individuals to mitigate disaster-related losses. However, participation rates among at-risk populations in the United States remain strikingly low. This gap underscores the need to understand and model the behavioral mechanisms underlying insurance decisions. Large language models (LLMs) have recently exhibited human-like intelligence across wide-ranging tasks, offering promising tools for simulating human decision-making. This study constructs a benchmark dataset to capture insurance purchase probabilities across factors. Using this dataset, the capacity of LLMs is evaluated: while LLMs exhibit a qualitative understanding of factors, they fall short in estimating quantitative probabilities. To address this limitation, InsurAgent, an LLM-empowered agent comprising five modules including perception, retrieval, reasoning, action, and memory, is proposed. The retrieval module leverages retrieval-augmented generation (RAG) to ground decisions in empirical survey data, achieving accurate estimation of marginal and bivariate probabilities. The reasoning module leverages LLM common sense to extrapolate beyond survey data, capturing contextual information that is intractable for traditional models. The memory module supports the simulation of temporal decision evolutions, illustrated through a roller coaster life trajectory. Overall, InsurAgent provides a valuable tool for behavioral modeling and policy analysis.

---

### Deep Value Benchmark: Measuring Whether Models Generalize Deep Values or Shallow Preferences

Authors: Joshua Ashkinaze, Hua Shen, Saipranav Avula, Eric Gilbert, Ceren Budak
Published: 2025-11-03
Categories: cs.AI, cs.CL, cs.CY
arXiv: https://arxiv.org/abs/2511.02109v3

We introduce the Deep Value Benchmark (DVB), an evaluation framework that directly tests whether large language models (LLMs) learn fundamental human values or merely surface-level preferences. This distinction is critical for AI alignment: Systems that capture deeper values are likely to generalize human intentions robustly, while those that capture only superficial patterns in preference data risk producing misaligned behavior. The DVB uses a novel experimental design with controlled confounding between deep values (e.g., moral principles) and shallow features (e.g., superficial attributes). In the training phase, we expose LLMs to human preference data with deliberately correlated deep and shallow features -- for instance, where a user consistently prefers (non-maleficence, formal language) options over (justice, informal language) alternatives. The testing phase then breaks these correlations, presenting choices between (justice, formal language) and (non-maleficence, informal language) options. This design allows us to precisely measure a model's Deep Value Generalization Rate (DVGR) -- the probability of generalizing based on the underlying value rather than the shallow feature. Across 9 different models, the average DVGR is just 0.30. All models generalize deep values less than chance. Larger models have a (slightly) lower DVGR than smaller models. We are releasing our dataset, which was subject to three separate human validation experiments. DVB provides an interpretable measure of a core feature of alignment.

---

### Metamorphic Testing of Large Language Models for Natural Language Processing

Authors: Steven Cho, Stefano Ruberto, Valerio Terragni
Published: 2025-11-03
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2511.02108v1

Using large language models (LLMs) to perform natural language processing (NLP) tasks has become increasingly pervasive in recent times. The versatile nature of LLMs makes them applicable to a wide range of such tasks. While the performance of recent LLMs is generally outstanding, several studies have shown that they can often produce incorrect results. Automatically identifying these faulty behaviors is extremely useful for improving the effectiveness of LLMs. One obstacle to this is the limited availability of labeled datasets, which necessitates an oracle to determine the correctness of LLM behaviors. Metamorphic testing (MT) is a popular testing approach that alleviates this oracle problem. At the core of MT are metamorphic relations (MRs), which define relationships between the outputs of related inputs. MT can expose faulty behaviors without the need for explicit oracles (e.g., labeled datasets). This paper presents the most comprehensive study of MT for LLMs to date. We conducted a literature review and collected 191 MRs for NLP tasks. We implemented a representative subset (36 MRs) to conduct a series of experiments with three popular LLMs, running approximately 560,000 metamorphic tests. The results shed light on the capabilities and opportunities of MT for LLMs, as well as its limitations.

---

### Enhancing Phenotype Discovery in Electronic Health Records through Prior Knowledge-Guided Unsupervised Learning

Authors: Melanie Mayer, Kimberly Lactaoen, Gary E. Weissman, Blanca E. Himes, Rebecca A. Hubbard
Published: 2025-11-03
Categories: stat.AP, stat.ML
arXiv: https://arxiv.org/abs/2511.02102v1

Objectives: Unsupervised learning with electronic health record (EHR) data has shown promise for phenotype discovery, but approaches typically disregard existing clinical information, limiting interpretability. We operationalize a Bayesian latent class framework for phenotyping that incorporates domain-specific knowledge to improve clinical meaningfulness of EHR-derived phenotypes and illustrate its utility by identifying an asthma sub-phenotype informed by features of Type 2 (T2) inflammation. Materials and methods: We illustrate a framework for incorporating clinical knowledge into a Bayesian latent class model via informative priors to guide unsupervised clustering toward clinically relevant subgroups. This approach models missingness, accounting for potential missing-not-at-random patterns, and provides patient-level probabilities for phenotype assignment with uncertainty. Using reusable and flexible code, we applied the model to a large asthma EHR cohort, specifying informative priors for T2 inflammation-related features and weakly informative priors for other clinical variables, allowing the data to inform posterior distributions. Results and Conclusion: Using encounter data from January 2017 to February 2024 for 44,642 adult asthma patients, we found a bimodal posterior distribution of phenotype assignment, indicating clear class separation. The T2 inflammation-informed class (38.7%) was characterized by elevated eosinophil levels and allergy markers, plus high healthcare utilization and medication use, despite weakly informative priors on the latter variables. These patterns suggest an "uncontrolled T2-high" sub-phenotype. This demonstrates how our Bayesian latent class modeling approach supports hypothesis generation and cohort identification in EHR-based studies of heterogeneous diseases without well-established phenotype definitions.

---

### Measuring the Intrinsic Dimension of Earth Representations

Authors: Arjun Rao, Marc Rußwurm, Konstantin Klemmer, Esther Rolf
Published: 2025-11-03
Categories: cs.LG, cs.IT
arXiv: https://arxiv.org/abs/2511.02101v3

Within the context of representation learning for Earth observation, geographic Implicit Neural Representations (INRs) embed low-dimensional location inputs (longitude, latitude) into high-dimensional embeddings, through models trained on geo-referenced satellite, image or text data. Despite the common aim of geographic INRs to distill Earth's data into compact, learning-friendly representations, we lack an understanding of how much information is contained in these Earth representations, and where that information is concentrated. The intrinsic dimension of a dataset measures the number of degrees of freedom required to capture its local variability, regardless of the ambient high-dimensional space in which it is embedded. This work provides the first study of the intrinsic dimensionality of geographic INRs. Analyzing INRs with ambient dimension between 256 and 512, we find that their intrinsic dimensions fall roughly between 2 and 10 and are sensitive to changing spatial resolution and input modalities during INR pre-training. Furthermore, we show that the intrinsic dimension of a geographic INR correlates with downstream task performance and can capture spatial artifacts, facilitating model evaluation and diagnostics. More broadly, our work offers an architecture-agnostic, label-free metric of information content that can enable unsupervised evaluation, model selection, and pre-training design across INRs.

---

### Geometric Data Valuation via Leverage Scores

Authors: Rodrigo Mendoza-Smith
Published: 2025-11-03
Categories: cs.LG, cs.AI, math.NA, math.OC
arXiv: https://arxiv.org/abs/2511.02100v1

Shapley data valuation provides a principled, axiomatic framework for assigning importance to individual datapoints, and has gained traction in dataset curation, pruning, and pricing. However, it is a combinatorial measure that requires evaluating marginal utility across all subsets of the data, making it computationally infeasible at scale. We propose a geometric alternative based on statistical leverage scores, which quantify each datapoint's structural influence in the representation space by measuring how much it extends the span of the dataset and contributes to the effective dimensionality of the training problem. We show that our scores satisfy the dummy, efficiency, and symmetry axioms of Shapley valuation and that extending them to \emph{ridge leverage scores} yields strictly positive marginal gains that connect naturally to classical A- and D-optimal design criteria. We further show that training on a leverage-sampled subset produces a model whose parameters and predictive risk are within $O(\varepsilon)$ of the full-data optimum, thereby providing a rigorous link between data valuation and downstream decision quality. Finally, we conduct an active learning experiment in which we empirically demonstrate that ridge-leverage sampling outperforms standard baselines without requiring access gradients or backward passes.

---

### Automated Reward Design for Gran Turismo

Authors: Michel Ma, Takuma Seno, Kaushik Subramanian, Peter R. Wurman, Peter Stone, Craig Sherstan
Published: 2025-11-03
Categories: cs.AI
arXiv: https://arxiv.org/abs/2511.02094v1

When designing reinforcement learning (RL) agents, a designer communicates the desired agent behavior through the definition of reward functions - numerical feedback given to the agent as reward or punishment for its actions. However, mapping desired behaviors to reward functions can be a difficult process, especially in complex environments such as autonomous racing. In this paper, we demonstrate how current foundation models can effectively search over a space of reward functions to produce desirable RL agents for the Gran Turismo 7 racing game, given only text-based instructions. Through a combination of LLM-based reward generation, VLM preference-based evaluation, and human feedback we demonstrate how our system can be used to produce racing agents competitive with GT Sophy, a champion-level RL racing agent, as well as generate novel behaviors, paving the way for practical automated reward design in real world applications.

---

### Uncertainty Guided Online Ensemble for Non-stationary Data Streams in Fusion Science

Authors: Kishansingh Rajput, Malachi Schram, Brian Sammuli, Sen Lin
Published: 2025-11-03
Categories: cs.LG, cs.AI, physics.plasm-ph
arXiv: https://arxiv.org/abs/2511.02092v1

Machine Learning (ML) is poised to play a pivotal role in the development and operation of next-generation fusion devices. Fusion data shows non-stationary behavior with distribution drifts, resulted by both experimental evolution and machine wear-and-tear. ML models assume stationary distribution and fail to maintain performance when encountered with such non-stationary data streams. Online learning techniques have been leveraged in other domains, however it has been largely unexplored for fusion applications. In this paper, we present an application of online learning to continuously adapt to drifting data stream for prediction of Toroidal Field (TF) coils deflection at the DIII-D fusion facility. The results demonstrate that online learning is critical to maintain ML model performance and reduces error by 80% compared to a static model. Moreover, traditional online learning can suffer from short-term performance degradation as ground truth is not available before making the predictions. As such, we propose an uncertainty guided online ensemble method to further improve the performance. The Deep Gaussian Process Approximation (DGPA) technique is leveraged for calibrated uncertainty estimation and the uncertainty values are then used to guide a meta-algorithm that produces predictions based on an ensemble of learners trained on different horizon of historical data. The DGPA also provides uncertainty estimation along with the predictions for decision makers. The online ensemble and the proposed uncertainty guided online ensemble reduces predictions error by about 6%, and 10% respectively over standard single model based online learning.

---

### Natural Building Blocks for Structured World Models: Theory, Evidence, and Scaling

Authors: Lancelot Da Costa, Sanjeev Namjoshi, Mohammed Abbas Ansari, Bernhard Schölkopf
Published: 2025-11-03
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2511.02091v1

The field of world modeling is fragmented, with researchers developing bespoke architectures that rarely build upon each other. We propose a framework that specifies the natural building blocks for structured world models based on the fundamental stochastic processes that any world model must capture: discrete processes (logic, symbols) and continuous processes (physics, dynamics); the world model is then defined by the hierarchical composition of these building blocks. We examine Hidden Markov Models (HMMs) and switching linear dynamical systems (sLDS) as natural building blocks for discrete and continuous modeling--which become partially-observable Markov decision processes (POMDPs) and controlled sLDS when augmented with actions. This modular approach supports both passive modeling (generation, forecasting) and active control (planning, decision-making) within the same architecture. We avoid the combinatorial explosion of traditional structure learning by largely fixing the causal architecture and searching over only four depth parameters. We review practical expressiveness through multimodal generative modeling (passive) and planning from pixels (active), with performance competitive to neural approaches while maintaining interpretability. The core outstanding challenge is scalable joint structure-parameter learning; current methods finesse this by cleverly growing structure and parameters incrementally, but are limited in their scalability. If solved, these natural building blocks could provide foundational infrastructure for world modeling, analogous to how standardized layers enabled progress in deep learning.

---

### LLM Probing with Contrastive Eigenproblems: Improving Understanding and Applicability of CCS

Authors: Stefan F. Schouten, Peter Bloem
Published: 2025-11-03
Categories: cs.LG, cs.CL
arXiv: https://arxiv.org/abs/2511.02089v1

Contrast-Consistent Search (CCS) is an unsupervised probing method able to test whether large language models represent binary features, such as sentence truth, in their internal activations. While CCS has shown promise, its two-term objective has been only partially understood. In this work, we revisit CCS with the aim of clarifying its mechanisms and extending its applicability. We argue that what should be optimized for, is relative contrast consistency. Building on this insight, we reformulate CCS as an eigenproblem, yielding closed-form solutions with interpretable eigenvalues and natural extensions to multiple variables. We evaluate these approaches across a range of datasets, finding that they recover similar performance to CCS, while avoiding problems around sensitivity to random initialization. Our results suggest that relativizing contrast consistency not only improves our understanding of CCS but also opens pathways for broader probing and mechanistic interpretability methods.

---

### Energy Loss Functions for Physical Systems

Authors: Sékou-Oumar Kaba, Kusha Sareen, Daniel Levy, Siamak Ravanbakhsh
Published: 2025-11-03
Categories: cs.LG, cs.AI, physics.comp-ph
arXiv: https://arxiv.org/abs/2511.02087v1

Effectively leveraging prior knowledge of a system's physics is crucial for applications of machine learning to scientific domains. Previous approaches mostly focused on incorporating physical insights at the architectural level. In this paper, we propose a framework to leverage physical information directly into the loss function for prediction and generative modeling tasks on systems like molecules and spins. We derive energy loss functions assuming that each data sample is in thermal equilibrium with respect to an approximate energy landscape. By using the reverse KL divergence with a Boltzmann distribution around the data, we obtain the loss as an energy difference between the data and the model predictions. This perspective also recasts traditional objectives like MSE as energy-based, but with a physically meaningless energy. In contrast, our formulation yields physically grounded loss functions with gradients that better align with valid configurations, while being architecture-agnostic and computationally efficient. The energy loss functions also inherently respect physical symmetries. We demonstrate our approach on molecular generation and spin ground-state prediction and report significant improvements over baselines.

---

### Markerless Augmented Reality Registration for Surgical Guidance: A Multi-Anatomy Clinical Accuracy Study

Authors: Yue Yang, Fabian Necker, Christoph Leuze, Michelle Chen, Andrey Finegersh, Jake Lee, Vasu Divi, Bruce Daniel, Brian Hargreaves, Jie Ying Wu, Fred M Baik
Published: 2025-11-03
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.02086v2

Purpose: In this paper, we develop and clinically evaluate a depth-only, markerless augmented reality (AR) registration pipeline on a head-mounted display, and assess accuracy across small or low-curvature anatomies in real-life operative settings. Methods: On HoloLens 2, we align Articulated HAnd Tracking (AHAT) depth to Computed Tomography (CT)-derived skin meshes via (i) depth-bias correction, (ii) brief human-in-the-loop initialization, (iii) global and local registration. We validated the surface-tracing error metric by comparing "skin-to-bone" relative distances to CT ground truth on leg and foot models, using an AR-tracked tool. We then performed seven intraoperative target trials (feet x2, ear x3, leg x2) during the initial stage of fibula free-flap harvest and mandibular reconstruction surgery, and collected 500+ data per trial. Results: Preclinical validation showed tight agreement between AR-traced and CT distances (leg: median |Delta d| 0.78 mm, RMSE 0.97 mm; feet: 0.80 mm, 1.20 mm). Clinically, per-point error had a median of 3.9 mm. Median errors by anatomy were 3.2 mm (feet), 4.3 mm (ear), and 5.3 mm (lower leg), with 5 mm coverage 92-95%, 84-90%, and 72-86%, respectively. Feet vs. lower leg differed significantly (Delta median ~1.1 mm; p < 0.001). Conclusion: A depth-only, markerless AR pipeline on HMDs achieved ~3-4 mm median error across feet, ear, and lower leg in live surgical settings without fiducials, approaching typical clinical error thresholds for moderate-risk tasks. Human-guided initialization plus global-to-local registration enabled accurate alignment on small or low-curvature targets, improving the clinical readiness of markerless AR guidance.

---

### Watermarking Discrete Diffusion Language Models

Authors: Avi Bagchi, Akhil Bhimaraju, Moulik Choraria, Daniel Alabi, Lav R. Varshney
Published: 2025-11-03
Categories: cs.CR, cs.AI, cs.CY
arXiv: https://arxiv.org/abs/2511.02083v2

Watermarking has emerged as a promising technique to track AI-generated content and differentiate it from authentic human creations. While prior work extensively studies watermarking for autoregressive large language models (LLMs) and image diffusion models, it remains comparatively underexplored for discrete diffusion language models (DDLMs), which are becoming popular due to their high inference throughput. In this paper, we introduce one of the first watermarking methods for DDLMs. Our approach applies a distribution-preserving Gumbel-max sampling trick at every diffusion step and seeds the randomness by sequence position to enable reliable detection. We empirically demonstrate reliable detectability on LLaDA, a state-of-the-art DDLM. We also analytically prove that the watermark is distortion-free, with a false detection probability that decays exponentially in the sequence length. A key practical advantage is that our method realizes desired watermarking properties with no expensive hyperparameter tuning, making it straightforward to deploy and scale across models and benchmarks.

---

### Beyond Static Cutoffs: One-Shot Dynamic Thresholding for Diffusion Language Models

Authors: Jucheng Shen, Yeonju Ro
Published: 2025-11-03
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.02077v3

Masked diffusion language models (MDLMs) are becoming competitive with their autoregressive counterparts but typically decode with fixed steps and sequential unmasking. To accelerate decoding, recent work such as Fast-dLLM enables parallel decoding via a static global confidence threshold, yet we observe strong block- and step-wise confidence fluctuations and, within a dataset, near-identical confidence trajectories across inputs as measured by cosine similarity. Motivated by these observations, we introduce One-Shot Dynamic Thresholding (OSDT), which calibrates thresholds on a single sequence and applies them to subsequent inputs with negligible overhead. On GPQA, GSM8K, and HumanEval, OSDT attains superior accuracy-throughput trade-offs (+24% tokens/s on GSM8K at the best accuracy, +45% on GPQA with comparable accuracy, and +50% on HumanEval with a modest accuracy gap). Beyond these results, our findings suggest broader opportunities to leverage reusable task-level confidence signatures for more general-purpose algorithmic and systems innovations in diffusion decoding.

---

### Human-AI Co-Embodied Intelligence for Scientific Experimentation and Manufacturing

Authors: Xinyi Lin, Yuyang Zhang, Yuanhang Gan, Juntao Chen, Hao Shen, Yichun He, Lijun Li, Ze Yuan, Shuang Wang, Chaohao Wang, Rui Zhang, Na Li et al.
Published: 2025-11-03
Categories: cs.AI
arXiv: https://arxiv.org/abs/2511.02071v2

Scientific experimentation and manufacturing rely on prolonged protocol development and complex, multi-step implementation, which require continuous human expertise for precise execution and decision-making, limiting interpretability and scalability. Here, we introduce human-artificial intelligence (AI) co-embodied intelligence, a new form of physical AI that unites human researchers, agentic AI, and wearable hardware. In this paradigm, humans provide precise execution, while agentic AI contributes contextual reasoning, adaptive planning, and analysis. The wearable interface continuously captures experimentation and manufacturing, facilitating seamless communication between humans and AI. We instantiate this paradigm in a microfabrication cleanroom, leading to the agentic-physical experimentation (APEX) system which understands fabrication procedure with accuracy 51% higher than state-of-the-art multimodal large language models/vision language models (LLMs/VLMs), detects and corrects fabrication errors in real-time, and transfers procedural expertise to novice users. Critically, APEX system enables the co-development of fabrication protocols in cleanrooms, overcoming the incompatibility of elastomeric materials in standard microfabrication processes and enabling previously unattainable fabrication outcomes, as demonstrated by the wafer-scale realization of brain-level soft neural probe capable of single-unit-resolution neural recording. These results establish the human-AI co-embodied intelligence that extends agentic reasoning beyond computation into the physical domain, transforming scientific experimentation and manufacturing into autonomous, traceable, interpretable and scalable processes.

---

### Complete asymptotic type-token relationship for growing complex systems with inverse power-law count rankings

Authors: Pablo Rosillo-Rodes, Laurent Hébert-Dufresne, Peter Sheridan Dodds
Published: 2025-11-03
Categories: physics.soc-ph, cs.CL
arXiv: https://arxiv.org/abs/2511.02069v2

The growth dynamics of complex systems often exhibit statistical regularities involving power-law relationships. For real finite complex systems formed by countable tokens (animals, words) as instances of distinct types (species, dictionary entries), an inverse power-law scaling $S \sim r^{-α}$ between type count $S$ and type rank $r$, widely known as Zipf's law, is widely observed to varying degrees of fidelity. A secondary, summary relationship is Heaps' law, which states that the number of types scales sublinearly with the total number of observed tokens present in a growing system. Here, we propose an idealized model of a growing system that (1) deterministically produces arbitrary inverse power-law count rankings for types, and (2) allows us to determine the exact asymptotics of the type-token relationship. Our argument improves upon and remedies earlier work. We obtain a unified asymptotic expression for all values of $α$, which corrects the special cases of $α= 1$ and $α\gg 1$. Our approach relies solely on the form of count rankings, avoids unnecessary approximations, and does not involve any stochastic mechanisms or sampling processes. We thereby demonstrate that a general type-token relationship arises solely as a consequence of Zipf's law.

---

### Direct Kernel Optimization: Efficient Design for Opto-Electronic Convolutional Neural Networks

Authors: Ali Almuallem, Harshana Weligampola, Abhiram Gnanasambandam, Wei Xu, Dilshan Godaliyadda, Hamid R. Sheikh, Stanley H. Chan, Qi Guo
Published: 2025-11-03
Categories: eess.IV, cs.CV
arXiv: https://arxiv.org/abs/2511.02065v2

Hybrid opto-electronic neural networks combine optical front-ends with electronic back-ends to perform vision tasks, but joint end-to-end (E2E) optimization of optical and electronic components is computationally expensive due to large parameter spaces and repeated optical convolutions. We propose Direct Kernel Optimization (DKO), a two-stage training framework that first trains a conventional electronic CNN and then synthesizes optical kernels to replicate the first-layer convolutional filters, reducing optimization dimensionality and avoiding hefty simulated optical convolutions during optimization. We evaluate DKO in simulation on a monocular depth estimation model and show that it achieves twice the accuracy of E2E training under equal computational budgets while reducing training time. Given the substantial computational challenges of optimizing hybrid opto-electronic systems, our results position DKO as a scalable optimization approach to train and realize these systems.

---

### Vortex: Hosting ML Inference and Knowledge Retrieval Services With Tight Latency and Throughput Requirements

Authors: Yuting Yang, Tiancheng Yuan, Jamal Hashim, Thiago Garrett, Jeffrey Qian, Ann Zhang, Yifan Wang, Weijia Song, Ken Birman
Published: 2025-11-03
Categories: cs.DB, cs.AI
arXiv: https://arxiv.org/abs/2511.02062v1

There is growing interest in deploying ML inference and knowledge retrieval as services that could support both interactive queries by end users and more demanding request flows that arise from AIs integrated into a end-user applications and deployed as agents. Our central premise is that these latter cases will bring service level latency objectives (SLOs). Existing ML serving platforms use batching to optimize for high throughput, exposing them to unpredictable tail latencies. Vortex enables an SLO-first approach. For identical tasks, Vortex's pipelines achieve significantly lower and more stable latencies than TorchServe and Ray Serve over a wide range of workloads, often enabling a given SLO target at more than twice the request rate. When RDMA is available, the Vortex advantage is even more significant.

---

### Data-driven Learning of Interaction Laws in Multispecies Particle Systems with Gaussian Processes: Convergence Theory and Applications

Authors: Jinchao Feng, Charles Kulick, Sui Tang
Published: 2025-11-03
Categories: stat.ML, cs.LG, math.NA, math.ST
arXiv: https://arxiv.org/abs/2511.02053v1

We develop a Gaussian process framework for learning interaction kernels in multi-species interacting particle systems from trajectory data. Such systems provide a canonical setting for multiscale modeling, where simple microscopic interaction rules generate complex macroscopic behaviors. While our earlier work established a Gaussian process approach and convergence theory for single-species systems, and later extended to second-order models with alignment and energy-type interactions, the multi-species setting introduces new challenges: heterogeneous populations interact both within and across species, the number of unknown kernels grows, and asymmetric interactions such as predator-prey dynamics must be accommodated. We formulate the learning problem in a nonparametric Bayesian setting and establish rigorous statistical guarantees. Our analysis shows recoverability of the interaction kernels, provides quantitative error bounds, and proves statistical optimality of posterior estimators, thereby unifying and generalizing previous single-species theory. Numerical experiments confirm the theoretical predictions and demonstrate the effectiveness of the proposed approach, highlighting its advantages over existing kernel-based methods. This work contributes a complete statistical framework for data-driven inference of interaction laws in multi-species systems, advancing the broader multiscale modeling program of connecting microscopic particle dynamics with emergent macroscopic behavior.

---

### Solving cold start in news recommendations: a RippleNet-based system for large scale media outlet

Authors: Karol Radziszewski, Michał Szpunar, Piotr Ociepka, Mateusz Buczyński
Published: 2025-11-03
Categories: cs.IR, cs.LG
arXiv: https://arxiv.org/abs/2511.02052v1

We present a scalable recommender system implementation based on RippleNet, tailored for the media domain with a production deployment in Onet.pl, one of Poland's largest online media platforms. Our solution addresses the cold-start problem for newly published content by integrating content-based item embeddings into the knowledge propagation mechanism of RippleNet, enabling effective scoring of previously unseen items. The system architecture leverages Amazon SageMaker for distributed training and inference, and Apache Airflow for orchestrating data pipelines and model retraining workflows. To ensure high-quality training data, we constructed a comprehensive golden dataset consisting of user and item features and a separate interaction table, all enabling flexible extensions and integration of new signals.

---

### Finding Probably Approximate Optimal Solutions by Training to Estimate the Optimal Values of Subproblems

Authors: Nimrod Megiddo, Segev Wasserkrug, Orit Davidovich, Shimrit Shtern
Published: 2025-11-03
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.02048v1

The paper is about developing a solver for maximizing a real-valued function of binary variables. The solver relies on an algorithm that estimates the optimal objective-function value of instances from the underlying distribution of objectives and their respective sub-instances. The training of the estimator is based on an inequality that facilitates the use of the expected total deviation from optimality conditions as a loss function rather than the objective-function itself. Thus, it does not calculate values of policies, nor does it rely on solved instances.

---

### A Dual-Use Framework for Clinical Gait Analysis: Attention-Based Sensor Optimization and Automated Dataset Auditing

Authors: Hamidreza Sadeghsalehi
Published: 2025-11-03
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.02047v1

Objective gait analysis using wearable sensors and AI is critical for managing neurological and orthopedic conditions. However, models are vulnerable to hidden dataset biases, and task-specific sensor optimization remains a challenge. We propose a multi-stream attention-based deep learning framework that functions as both a sensor optimizer and an automated data auditor. Applied to the Voisard et al. (2025) multi-cohort gait dataset on four clinical tasks (PD, OA, CVA screening; PD vs CVA differential), the model's attention mechanism quantitatively discovered a severe dataset confound. For OA and CVA screening, tasks where bilateral assessment is clinically essential, the model assigned more than 70 percent attention to the Right Foot while statistically ignoring the Left Foot (less than 0.1 percent attention, 95 percent CI (0.0-0.1)). This was not a clinical finding but a direct reflection of a severe laterality bias (for example, 15 of 15 right-sided OA) in the public dataset. The primary contribution of this work is methodological, demonstrating that an interpretable framework can automatically audit dataset integrity. As a secondary finding, the model proposes novel, data-driven sensor synergies (for example, Head plus Foot for PD screening) as hypotheses for future optimized protocols.

---

### Text-VQA Aug: Pipelined Harnessing of Large Multimodal Models for Automated Synthesis

Authors: Soham Joshi, Shwet Kamal Mishra, Viswanath Gopalakrishnan
Published: 2025-11-03
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2511.02046v1

Creation of large-scale databases for Visual Question Answering tasks pertaining to the text data in a scene (text-VQA) involves skilful human annotation, which is tedious and challenging. With the advent of foundation models that handle vision and language modalities, and with the maturity of OCR systems, it is the need of the hour to establish an end-to-end pipeline that can synthesize Question-Answer (QA) pairs based on scene-text from a given image. We propose a pipeline for automated synthesis for text-VQA dataset that can produce faithful QA pairs, and which scales up with the availability of scene text data. Our proposed method harnesses the capabilities of multiple models and algorithms involving OCR detection and recognition (text spotting), region of interest (ROI) detection, caption generation, and question generation. These components are streamlined into a cohesive pipeline to automate the synthesis and validation of QA pairs. To the best of our knowledge, this is the first pipeline proposed to automatically synthesize and validate a large-scale text-VQA dataset comprising around 72K QA pairs based on around 44K images.

---

### Regularization Through Reasoning: Systematic Improvements in Language Model Classification via Explanation-Enhanced Fine-Tuning

Authors: Vivswan Shah, Randy Cogill, Hanwei Yue, Gopinath Chennupati, Rinat Khaziev
Published: 2025-11-03
Categories: cs.LG, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2511.02044v2

Fine-tuning LLMs for classification typically maps inputs directly to labels. We ask whether attaching brief explanations to each label during fine-tuning yields better models. We evaluate conversational response quality along three axes: naturalness, comprehensiveness, and on-topic adherence, each rated on 5-point scales. Using ensemble-generated data from multiple LLMs, we fine-tune a 7B-parameter model and test across six diverse conversational datasets. Across 18 dataset, task settings, label-plus-explanation training outperforms label-only baselines. A central and unexpected result concerns random tokens. We replace human-written explanations with text that is syntactically incoherent yet vocabulary-aligned with the originals (e.g., shuffled or bag-of-words variants). Despite lacking semantics, these pseudo-explanations still improve accuracy over label-only training and often narrow much of the gap to true explanations. The effect persists across datasets and training seeds, indicating that gains arise less from meaning than from structure: the extra token budget encourages richer intermediate computation and acts as a regularizer that reduces over-confident shortcuts. Internal analyses support this view: explanation-augmented models exhibit higher activation entropy in intermediate layers alongside sharper predictive mass at the output layer, consistent with increased deliberation before decision. Overall, explanation-augmented fine-tuning, whether with genuine rationales or carefully constructed random token sequences, improves accuracy and reliability for LLM classification while clarifying how token-level scaffolding shapes computation during inference.

---

### Flashlight: PyTorch Compiler Extensions to Accelerate Attention Variants

Authors: Bozhi You, Irene Wang, Zelal Su Mustafaoglu, Abhinav Jangda, Angélica Moreira, Roshan Dathathri, Divya Mahajan, Keshav Pingali
Published: 2025-11-03
Categories: cs.LG, cs.PF
arXiv: https://arxiv.org/abs/2511.02043v4

Attention is a fundamental building block of large language models (LLMs), so there have been many efforts to implement it efficiently. For example, FlashAttention leverages tiling and kernel fusion to optimize attention. Recently, a number of variants of attention have been introduced to enhance model quality or efficiency. Supporting them efficiently remains difficult since they usually require specialized kernels or hand-tuned implementations. FlexAttention recently addressed part of this gap by using static programming templates to support FlashAttention-like kernels for a subset of attention variants. In this paper, we introduce Flashlight, a compiler-native framework within the PyTorch ecosystem that automatically generates fused, FlashAttention-style kernels for arbitrary attention-based programs, without relying on static templates or predefined kernel specializations. Flashlight leverages PyTorch's compilation workflow to fuse and tile attention computations transparently, enabling efficient execution for diverse attention patterns. Not only does it support all variants expressible in the FlexAttention model but it also handles more general, data-dependent attention formulations that are beyond the capabilities of FlexAttention. Our results show that Flashlight produces kernels with competitive or superior performance to FlexAttention, while offering the flexibility of native PyTorch code, enabling developers to rapidly explore new attention models without sacrificing performance.

---

### Quantum-Enhanced Generative Models for Rare Event Prediction

Authors: M. Z. Haider, M. U. Ghouri, Tayyaba Noreen, M. Salman
Published: 2025-11-03
Categories: cs.LG, cs.AI, cs.CR, cs.DC
arXiv: https://arxiv.org/abs/2511.02042v1

Rare events such as financial crashes, climate extremes, and biological anomalies are notoriously difficult to model due to their scarcity and heavy-tailed distributions. Classical deep generative models often struggle to capture these rare occurrences, either collapsing low-probability modes or producing poorly calibrated uncertainty estimates. In this work, we propose the Quantum-Enhanced Generative Model (QEGM), a hybrid classical-quantum framework that integrates deep latent-variable models with variational quantum circuits. The framework introduces two key innovations: (1) a hybrid loss function that jointly optimizes reconstruction fidelity and tail-aware likelihood, and (2) quantum randomness-driven noise injection to enhance sample diversity and mitigate mode collapse. Training proceeds via a hybrid loop where classical parameters are updated through backpropagation while quantum parameters are optimized using parameter-shift gradients. We evaluate QEGM on synthetic Gaussian mixtures and real-world datasets spanning finance, climate, and protein structure. Results demonstrate that QEGM reduces tail KL divergence by up to 50 percent compared to state-of-the-art baselines (GAN, VAE, Diffusion), while improving rare-event recall and coverage calibration. These findings highlight the potential of QEGM as a principled approach for rare-event prediction, offering robustness beyond what is achievable with purely classical methods.

---

### Predicting Microbial Interactions Using Graph Neural Networks

Authors: Elham Gholamzadeh, Kajal Singla, Nico Scherf
Published: 2025-11-03
Categories: cs.LG, q-bio.QM
arXiv: https://arxiv.org/abs/2511.02038v1

Predicting interspecies interactions is a key challenge in microbial ecology, as these interactions are critical to determining the structure and activity of microbial communities. In this work, we used data on monoculture growth capabilities, interactions with other species, and phylogeny to predict a negative or positive effect of interactions. More precisely, we used one of the largest available pairwise interaction datasets to train our models, comprising over 7,500 interactions be- tween 20 species from two taxonomic groups co-cultured under 40 distinct carbon conditions, with a primary focus on the work of Nestor et al.(28 ). In this work, we propose Graph Neural Networks (GNNs) as a powerful classifier to predict the direction of the effect. We construct edge-graphs of pairwise microbial interactions in order to leverage shared information across individual co-culture experiments, and use GNNs to predict modes of interaction. Our model can not only predict binary interactions (positive/negative) but also classify more complex interaction types such as mutualism, competition, and parasitism. Our initial results were encouraging, achieving an F1-score of 80.44%. This significantly outperforms comparable methods in the literature, including conventional Extreme Gradient Boosting (XGBoost) models, which reported an F1-score of 72.76%.

---

### RobustFSM: Submodular Maximization in Federated Setting with Malicious Clients

Authors: Duc A. Tran, Dung Truong, Duy Le
Published: 2025-11-03
Categories: cs.LG, cs.AI, cs.DC
arXiv: https://arxiv.org/abs/2511.02029v2

Submodular maximization is an optimization problem benefiting many machine learning applications, where we seek a small subset best representing an extremely large dataset. We focus on the federated setting where the data are locally owned by decentralized clients who have their own definitions for the quality of representability. This setting requires repetitive aggregation of local information computed by the clients. While the main motivation is to respect the privacy and autonomy of the clients, the federated setting is vulnerable to client misbehaviors: malicious clients might share fake information. An analogy is backdoor attack in conventional federated learning, but our challenge differs freshly due to the unique characteristics of submodular maximization. We propose RobustFSM, a federated submodular maximization solution that is robust to various practical client attacks. Its performance is substantiated with an empirical evaluation study using real-world datasets. Numerical results show that the solution quality of RobustFSM substantially exceeds that of the conventional federated algorithm when attacks are severe. The degree of this improvement depends on the dataset and attack scenarios, which can be as high as 200%

---

### Path-Coordinated Continual Learning with Neural Tangent Kernel-Justified Plasticity: A Theoretical Framework with Near State-of-the-Art Performance

Authors: Rathin Chandra Shit
Published: 2025-11-03
Categories: cs.LG, cs.AI, cs.RO
arXiv: https://arxiv.org/abs/2511.02025v1

Catastrophic forgetting is one of the fundamental issues of continual learning because neural networks forget the tasks learned previously when trained on new tasks. The proposed framework is a new path-coordinated framework of continual learning that unites the Neural Tangent Kernel (NTK) theory of principled plasticity bounds, statistical validation by Wilson confidence intervals, and evaluation of path quality by the use of multiple metrics. Experimental evaluation shows an average accuracy of 66.7% at the cost of 23.4% catastrophic forgetting on Split-CIFAR10, a huge improvement over the baseline and competitive performance achieved, which is very close to state-of-the-art results. Further, it is found out that NTK condition numbers are predictive indicators of learning capacity limits, showing the existence of a critical threshold at condition number $>10^{11}$. It is interesting to note that the proposed strategy shows a tendency of lowering forgetting as the sequence of tasks progresses (27% to 18%), which is a system stabilization. The framework validates 80% of discovered paths with a rigorous statistical guarantee and maintains 90-97% retention on intermediate tasks. The core capacity limits of the continual learning environment are determined in the analysis, and actionable insights to enhance the adaptive regularization are offered.

---

### Shared Parameter Subspaces and Cross-Task Linearity in Emergently Misaligned Behavior

Authors: Daniel Aarao Reis Arturi, Eric Zhang, Andrew Ansah, Kevin Zhu, Ashwinee Panda, Aishwarya Balwani
Published: 2025-11-03
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2511.02022v1

Recent work has discovered that large language models can develop broadly misaligned behaviors after being fine-tuned on narrowly harmful datasets, a phenomenon known as emergent misalignment (EM). However, the fundamental mechanisms enabling such harmful generalization across disparate domains remain poorly understood. In this work, we adopt a geometric perspective to study EM and demonstrate that it exhibits a fundamental cross-task linear structure in how harmful behavior is encoded across different datasets. Specifically, we find a strong convergence in EM parameters across tasks, with the fine-tuned weight updates showing relatively high cosine similarities, as well as shared lower-dimensional subspaces as measured by their principal angles and projection overlaps. Furthermore, we also show functional equivalence via linear mode connectivity, wherein interpolated models across narrow misalignment tasks maintain coherent, broadly misaligned behavior. Our results indicate that EM arises from different narrow tasks discovering the same set of shared parameter directions, suggesting that harmful behaviors may be organized into specific, predictable regions of the weight landscape. By revealing this fundamental connection between parametric geometry and behavioral outcomes, we hope our work catalyzes further research on parameter space interpretability and weight-based interventions.

---

### TapOut: A Bandit-Based Approach to Dynamic Speculative Decoding

Authors: Aditya Sridhar, Nish Sinnadurai, Sean Lie, Vithursan Thangarasa
Published: 2025-11-03
Categories: cs.LG, cs.CL
arXiv: https://arxiv.org/abs/2511.02017v1

Speculative decoding accelerates LLMs by using a lightweight draft model to generate tokens autoregressively before verifying them in parallel with a larger target model. However, determining the optimal number of tokens to draft remains a key challenge limiting the approach's effectiveness. Dynamic speculative decoding aims to intelligently decide how many tokens to draft to achieve maximum speedups. Existing methods often rely on hand-tuned, sensitive thresholds (e.g., token entropy), which are costly to set and generalize poorly across models and domains. We propose TapOut, an online, training-free, plug-and-play algorithm for dynamic speculation policy selection using multi-armed bandits. Our approach employs a meta-algorithm that selects among multiple parameter-free dynamic speculation strategies based on past reward and exploration. We conduct extensive experiments across diverse model pairs and datasets, showing that TapOut achieves competitive or superior speedups compared to well-established dynamic speculation baselines without any hyperparameter tuning.

---

### Towards Selection of Large Multimodal Models as Engines for Burned-in Protected Health Information Detection in Medical Images

Authors: Tuan Truong, Guillermo Jimenez Perez, Pedro Osorio, Matthias Lenga
Published: 2025-11-03
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.02014v2

The detection of Protected Health Information (PHI) in medical imaging is critical for safeguarding patient privacy and ensuring compliance with regulatory frameworks. Traditional detection methodologies predominantly utilize Optical Character Recognition (OCR) models in conjunction with named entity recognition. However, recent advancements in Large Multimodal Model (LMM) present new opportunities for enhanced text extraction and semantic analysis. In this study, we systematically benchmark three prominent closed and open-sourced LMMs, namely GPT-4o, Gemini 2.5 Flash, and Qwen 2.5 7B, utilizing two distinct pipeline configurations: one dedicated to text analysis alone and another integrating both OCR and semantic analysis. Our results indicate that LMM exhibits superior OCR efficacy (WER: 0.03-0.05, CER: 0.02-0.03) compared to conventional models like EasyOCR. However, this improvement in OCR performance does not consistently correlate with enhanced overall PHI detection accuracy. The strongest performance gains are observed on test cases with complex imprint patterns. In scenarios where text regions are well readable with sufficient contrast, and strong LMMs are employed for text analysis after OCR, different pipeline configurations yield similar results. Furthermore, we provide empirically grounded recommendations for LMM selection tailored to specific operational constraints and propose a deployment strategy that leverages scalable and modular infrastructure.

---

### Bulk-boundary decomposition of neural networks

Authors: Donghee Lee, Hye-Sung Lee, Jaeok Yi
Published: 2025-11-03
Categories: cs.LG, cond-mat.dis-nn, hep-ph
arXiv: https://arxiv.org/abs/2511.02003v2

We present the bulk--boundary decomposition as a new framework for understanding the training dynamics of deep neural networks. Starting from the stochastic gradient descent formulation, we show that the Lagrangian can be reorganized into a data-independent bulk term and a data-dependent boundary term. The bulk captures the intrinsic dynamics set by network architecture and activation functions, while the boundary reflects stochastic interactions from training samples at the input and output layers. This decomposition exposes the local and homogeneous structure underlying deep networks. As a physical consequence of locality and homogeneity, we derive the energy continuity equation within a deep neural network.

---

### InteracSPARQL: An Interactive System for SPARQL Query Refinement Using Natural Language Explanations

Authors: Xiangru Jian, Zhengyuan Dong, M. Tamer Özsu
Published: 2025-11-03
Categories: cs.DB, cs.AI, cs.IR
arXiv: https://arxiv.org/abs/2511.02002v1

In recent years, querying semantic web data using SPARQL has remained challenging, especially for non-expert users, due to the language's complex syntax and the prerequisite of understanding intricate data structures. To address these challenges, we propose InteracSPARQL, an interactive SPARQL query generation and refinement system that leverages natural language explanations (NLEs) to enhance user comprehension and facilitate iterative query refinement. InteracSPARQL integrates LLMs with a rule-based approach to first produce structured explanations directly from SPARQL abstract syntax trees (ASTs), followed by LLM-based linguistic refinements. Users can interactively refine queries through direct feedback or LLM-driven self-refinement, enabling the correction of ambiguous or incorrect query components in real time. We evaluate InteracSPARQL on standard benchmarks, demonstrating significant improvements in query accuracy, explanation clarity, and overall user satisfaction compared to baseline approaches. Our experiments further highlight the effectiveness of combining rule-based methods with LLM-driven refinements to create more accessible and robust SPARQL interfaces.

---

### TRACE: Textual Reasoning for Affordance Coordinate Extraction

Authors: Sangyun Park, Jin Kim, Yuchen Cui, Matthew S. Brown
Published: 2025-11-03
Categories: cs.RO, cs.AI
arXiv: https://arxiv.org/abs/2511.01999v1

Vision-Language Models (VLMs) struggle to translate high-level instructions into the precise spatial affordances required for robotic manipulation. While visual Chain-of-Thought (CoT) methods exist, they are often computationally intensive. In this work, we introduce TRACE (Textual Reasoning for Affordance Coordinate Extraction), a novel methodology that integrates a textual Chain of Reasoning (CoR) into the affordance prediction process. We use this methodology to create the TRACE dataset, a large-scale collection created via an autonomous pipeline that pairs instructions with explicit textual rationales. By fine-tuning a VLM on this data, our model learns to externalize its spatial reasoning before acting. Our experiments show that our TRACE-tuned model achieves state-of-the-art performance, reaching 48.1% accuracy on the primary Where2Place (W2P) benchmark (a 9.6% relative improvement) and 55.0% on the more challenging W2P(h) subset. Crucially, an ablation study demonstrates that performance scales directly with the amount of reasoning data used, confirming the CoR's effectiveness. Furthermore, analysis of the model's attention maps reveals an interpretable reasoning process where focus shifts dynamically across reasoning steps. This work shows that training VLMs to generate a textual CoR is an effective and robust strategy for enhancing the precision, reliability, and interpretability of VLM-based robot control. Our dataset and code are available at https://github.com/jink-ucla/TRACE

---

### Locally-Supervised Global Image Restoration

Authors: Benjamin Walder, Daniel Toader, Robert Nuster, Günther Paltauf, Peter Burgholzer, Gregor Langer, Lukas Krainer, Markus Haltmeier
Published: 2025-11-03
Categories: cs.CV, math.NA
arXiv: https://arxiv.org/abs/2511.01998v2

We address the problem of image reconstruction from incomplete measurements, encompassing both upsampling and inpainting, within a learning-based framework. Conventional supervised approaches require fully sampled ground truth data, while self-supervised methods allow incomplete ground truth but typically rely on random sampling that, in expectation, covers the entire image. In contrast, we consider fixed, deterministic sampling patterns with inherently incomplete coverage, even in expectation. To overcome this limitation, we exploit multiple invariances of the underlying image distribution, which theoretically allows us to achieve the same reconstruction performance as fully supervised approaches. We validate our method on optical-resolution image upsampling in photoacoustic microscopy (PAM), demonstrating competitive or superior results while requiring substantially less ground truth data.

---

### Assessing the value of Geo-Foundational Models for Flood Inundation Mapping: Benchmarking models for Sentinel-1, Sentinel-2, and Planetscope for end-users

Authors: Saurabh Kaushik, Lalit Maurya, Elizabeth Tellman, ZhiJie Zhang
Published: 2025-11-03
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.01990v3

Geo-Foundational Models (GFMs) enable fast and reliable extraction of spatiotemporal information from satellite imagery, improving flood inundation mapping by leveraging location and time embeddings. Despite their potential, it remains unclear whether GFMs outperform traditional models like U-Net. A systematic comparison across sensors and data availability scenarios is still lacking, which is an essential step to guide end-users in model selection. To address this, we evaluate three GFMs, Prithvi 2.0, Clay V1.5, DOFA, and UViT (a Prithvi variant), against TransNorm, U-Net, and Attention U-Net using PlanetScope, Sentinel-1, and Sentinel-2. We observe competitive performance among all GFMs, with only 2-5% variation between the best and worst models across sensors. Clay outperforms others on PlanetScope (0.79 mIoU) and Sentinel-2 (0.70), while Prithvi leads on Sentinel-1 (0.57). In leave-one-region-out cross-validation across five regions, Clay shows slightly better performance across all sensors (mIoU: 0.72(0.04), 0.66(0.07), 0.51(0.08)) compared to Prithvi (0.70(0.05), 0.64(0.09), 0.49(0.13)) and DOFA (0.67(0.07), 0.64(0.04), 0.49(0.09)) for PlanetScope, Sentinel-2, and Sentinel-1, respectively. Across all 19 sites, leave-one-region-out cross-validation reveals a 4% improvement by Clay compared to U-Net. Visual inspection highlights Clay's superior ability to retain fine details. Few-shot experiments show Clay achieves 0.64 mIoU on PlanetScope with just five training images, outperforming Prithvi (0.24) and DOFA (0.35). In terms of computational time, Clay is a better choice due to its smaller model size (26M parameters), making it ~3x faster than Prithvi (650M) and 2x faster than DOFA (410M). Contrary to previous findings, our results suggest GFMs offer small to moderate improvements in flood mapping accuracy at lower computational cost and labeling effort compared to traditional U-Net.

---

### SEAL - A Symmetry EncourAging Loss for High Energy Physics

Authors: Pradyun Hebbar, Thandikire Madula, Vinicius Mikuni, Benjamin Nachman, Nadav Outmezguine, Inbar Savoray
Published: 2025-11-03
Categories: hep-ph, cs.LG, hep-ex
arXiv: https://arxiv.org/abs/2511.01982v1

Physical symmetries provide a strong inductive bias for constructing functions to analyze data. In particular, this bias may improve robustness, data efficiency, and interpretability of machine learning models. However, building machine learning models that explicitly respect symmetries can be difficult due to the dedicated components required. Moreover, real-world experiments may not exactly respect fundamental symmetries at the level of finite granularities and energy thresholds. In this work, we explore an alternative approach to create symmetry-aware machine learning models. We introduce soft constraints that allow the model to decide the importance of added symmetries during the learning process instead of enforcing exact symmetries. We investigate two complementary approaches, one that penalizes the model based on specific transformations of the inputs and one inspired by group theory and infinitesimal transformations of the inputs. Using top quark jet tagging and Lorentz equivariance as examples, we observe that the addition of the soft constraints leads to more robust performance while requiring negligible changes to current state-of-the-art models.

---

### Stability of mixed-state phases under weak decoherence

Authors: Yifan F. Zhang, Sarang Gopalakrishnan
Published: 2025-11-03
Categories: quant-ph, cond-mat.stat-mech, cs.LG, math-ph
arXiv: https://arxiv.org/abs/2511.01976v1

We prove that the Gibbs states of classical, and commuting-Pauli, Hamiltonians are stable under weak local decoherence: i.e., we show that the effect of the decoherence can be locally reversed. In particular, our conclusions apply to finite-temperature equilibrium critical points and ordered low-temperature phases. In these systems the unconditional spatio-temporal correlations are long-range, and local (e.g., Metropolis) dynamics exhibits critical slowing down. Nevertheless, our results imply the existence of local "decoders" that undo the decoherence, when the decoherence strength is below a critical value. An implication of these results is that thermally stable quantum memories have a threshold against decoherence that remains nonzero as one approaches the critical temperature. Analogously, in diffusion models, stability of data distributions implies the existence of computationally-efficent local denoisers in the late-time generation dynamics.

---

### Addressing prior dependence in hierarchical Bayesian modeling for PTA data analysis II: Noise and SGWB inference through parameter decorrelation

Authors: Eleonora Villa, Luigi D'Amico, Aldo Barca, Fatima Modica Bittordo, Francesco Alì, Massimo Meneghetti, Luca Naso
Published: 2025-11-03
Categories: astro-ph.IM, astro-ph.CO, astro-ph.HE, cs.LG
arXiv: https://arxiv.org/abs/2511.01959v2

Pulsar Timing Arrays (PTA) provide a powerful framework to measure low-frequency gravitational waves, but accuracy and robustness of the results are challenged by complex noise processes that must be accurately modeled. Standard PTA analyses assign fixed uniform noise priors to each pulsar, an approach that can introduce systematic biases when combining the array. To overcome this limitation, we adopt a hierarchical Bayesian modeling strategy in which noise priors are parametrized by higher-level hyperparameters. To mitigate the sensitivity of the inferred parameters to the choice of noise hyperprior, we introduce a reparametrization of the hierarchical model based on the orthogonal projection of hyperparameters onto the physical parameter subspace. The transformation is implemented through Normalizing Flows (NFs), which provide an invertible, tractable representation and preserve shrinkage and inter-pulsar information pooling in the reparametrized model. We also employ i-nessai, a flow-guided nested sampler, to efficiently explore the resulting higher-dimensional parameter space. We apply our method to a minimal 3-pulsar case study, performing a simultaneous inference of noise and stochastic gravitational wave background (SGWB) parameters. Despite the limited dataset, the results consistently show that the reparametrized hierarchical treatment constrains the noise parameters more tightly and partially alleviates the red-noise-SGWB degeneracy, while the orthogonal reparametrization further enhances parameter independence without affecting the correlations intrinsic to the power-law modeling of the physical processes involved.

---

### Improving Bayesian inference in PTA data analysis: importance nested sampling with Normalizing Flows

Authors: Eleonora Villa, Golam Mohiuddin Shaifullah, Andrea Possenti, Carmelita Carbone
Published: 2025-11-03
Categories: astro-ph.IM, astro-ph.CO, astro-ph.HE, cs.LG
arXiv: https://arxiv.org/abs/2511.01958v1

We present a detailed study of Bayesian inference workflows for pulsar timing array data with a focus on enhancing efficiency, robustness and speed through the use of normalizing flow-based nested sampling. Building on the Enterprise framework, we integrate the i-nessai sampler and benchmark its performance on realistic, simulated datasets. We analyze its computational scaling and stability, and show that it achieves accurate posteriors and reliable evidence estimates with substantially reduced runtime, by up to three orders of magnitude depending on the dataset configuration, with respect to conventional single-core parallel-tempering MCMC analyses. These results highlight the potential of flow-based nested sampling to accelerate PTA analyses while preserving the quality of the inference.

---

### Vibe Learning: Education in the age of AI

Authors: Marcos Florencio, Francielle Prieto
Published: 2025-11-03
Categories: cs.CY, cs.AI
arXiv: https://arxiv.org/abs/2511.01956v1

The debate over whether "thinking machines" could replace human intellectual labor has existed in both public and expert discussions since the mid-twentieth century, when the concept and terminology of Artificial Intelligence (AI) first emerged. For decades, this idea remained largely theoretical. However, with the recent advent of Generative AI - particularly Large Language Models (LLMs) - and the widespread adoption of tools such as ChatGPT, the issue has become a practical reality. Many fields that rely on human intellectual effort are now being reshaped by AI tools that both expand human capabilities and challenge the necessity of certain forms of work once deemed uniquely human but now easily automated. Education, somewhat unexpectedly, faces a pivotal responsibility: to devise long-term strategies for cultivating human skills that will remain relevant in an era of pervasive AI in the intellectual domain. In this context, we identify the limitations of current AI systems - especially those rooted in LLM technology - argue that the fundamental causes of these weaknesses cannot be resolved through existing methods, and propose directions within the constructivist paradigm for transforming education to preserve the long-term advantages of human intelligence over AI tools.

---

### Black-Box Membership Inference Attack for LVLMs via Prior Knowledge-Calibrated Memory Probing

Authors: Jinhua Yin, Peiru Yang, Chen Yang, Huili Wang, Zhiyang Hu, Shangguang Wang, Yongfeng Huang, Tao Qi
Published: 2025-11-03
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2511.01952v1

Large vision-language models (LVLMs) derive their capabilities from extensive training on vast corpora of visual and textual data. Empowered by large-scale parameters, these models often exhibit strong memorization of their training data, rendering them susceptible to membership inference attacks (MIAs). Existing MIA methods for LVLMs typically operate under white- or gray-box assumptions, by extracting likelihood-based features for the suspected data samples based on the target LVLMs. However, mainstream LVLMs generally only expose generated outputs while concealing internal computational features during inference, limiting the applicability of these methods. In this work, we propose the first black-box MIA framework for LVLMs, based on a prior knowledge-calibrated memory probing mechanism. The core idea is to assess the model memorization of the private semantic information embedded within the suspected image data, which is unlikely to be inferred from general world knowledge alone. We conducted extensive experiments across four LVLMs and three datasets. Empirical results demonstrate that our method effectively identifies training data of LVLMs in a purely black-box setting and even achieves performance comparable to gray-box and white-box methods. Further analysis reveals the robustness of our method against potential adversarial manipulations, and the effectiveness of the methodology designs. Our code and data are available at https://github.com/spmede/KCMP.

---

### NeuroClean: A Generalized Machine-Learning Approach to Neural Time-Series Conditioning

Authors: Manuel A. Hernandez Alonso, Michael Depass, Stephan Quessy, Ali Falaki, Soraya Rahimi, Numa Dancause, Ignasi Cos
Published: 2025-11-03
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.01951v2

Electroencephalography (EEG) and local field potentials (LFP) are two widely used techniques to record electrical activity from the brain. These signals are used in both the clinical and research domains for multiple applications. However, most brain data recordings suffer from a myriad of artifacts and noise sources other than the brain itself. Thus, a major requirement for their use is proper and, given current volumes of data, a fully automatized conditioning. As a means to this end, here we introduce an unsupervised, multipurpose EEG/LFP preprocessing method, the NeuroClean pipeline. In addition to its completeness and reliability, NeuroClean is an unsupervised series of algorithms intended to mitigate reproducibility issues and biases caused by human intervention. The pipeline is designed as a five-step process, including the common bandpass and line noise filtering, and bad channel rejection. However, it incorporates an efficient independent component analysis with an automatic component rejection based on a clustering algorithm. This machine learning classifier is used to ensure that task-relevant information is preserved after each step of the cleaning process. We used several data sets to validate the pipeline. NeuroClean removed several common types of artifacts from the signal. Moreover, in the context of motor tasks of varying complexity, it yielded more than 97% accuracy (vs. a chance-level of 33.3%) in an optimized Multinomial Logistic Regression model after cleaning the data, compared to the raw data, which performed at 74% accuracy. These results show that NeuroClean is a promising pipeline and workflow that can be applied to future work and studies to achieve better generalization and performance on machine learning pipelines.

---

### EchoLSTM: A Self-Reflective Recurrent Network for Stabilizing Long-Range Memory

Authors: Prasanth K K, Shubham Sharma
Published: 2025-11-03
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.01950v1

Standard Recurrent Neural Networks, including LSTMs, struggle to model long-range dependencies, particularly in sequences containing noisy or misleading information. We propose a new architectural principle, Output-Conditioned Gating, which enables a model to perform self-reflection by modulating its internal memory gates based on its own past inferences. This creates a stabilizing feedback loop that enhances memory retention. Our final model, the EchoLSTM, integrates this principle with an attention mechanism. We evaluate the EchoLSTM on a series of challenging benchmarks. On a custom-designed Distractor Signal Task, the EchoLSTM achieves 69.0% accuracy, decisively outperforming a standard LSTM baseline by 33 percentage points. Furthermore, on the standard ListOps benchmark, the EchoLSTM achieves performance competitive with a modern Transformer model, 69.8% vs. 71.8%, while being over 5 times more parameter-efficient. A final Trigger Sensitivity Test provides qualitative evidence that our model's self-reflective mechanism leads to a fundamentally more robust memory system.

---

### Interpretable Heart Disease Prediction via a Weighted Ensemble Model: A Large-Scale Study with SHAP and Surrogate Decision Trees

Authors: Md Abrar Hasnat, Md Jobayer, Md. Mehedi Hasan Shawon, Md. Golam Rabiul Alam
Published: 2025-11-03
Categories: cs.LG, cs.AI, eess.SP
arXiv: https://arxiv.org/abs/2511.01947v1

Cardiovascular disease (CVD) remains a critical global health concern, demanding reliable and interpretable predictive models for early risk assessment. This study presents a large-scale analysis using the Heart Disease Health Indicators Dataset, developing a strategically weighted ensemble model that combines tree-based methods (LightGBM, XGBoost) with a Convolutional Neural Network (CNN) to predict CVD risk. The model was trained on a preprocessed dataset of 229,781 patients where the inherent class imbalance was managed through strategic weighting and feature engineering enhanced the original 22 features to 25. The final ensemble achieves a statistically significant improvement over the best individual model, with a Test AUC of 0.8371 (p=0.003) and is particularly suited for screening with a high recall of 80.0%. To provide transparency and clinical interpretability, surrogate decision trees and SHapley Additive exPlanations (SHAP) are used. The proposed model delivers a combination of robust predictive performance and clinical transparency by blending diverse learning architectures and incorporating explainability through SHAP and surrogate decision trees, making it a strong candidate for real-world deployment in public health screening.

---