# Research Papers — 2025-11 · bundle page 117 of 197

> Full-text markdown of papers #5801–5850 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/117
[← Previous bundle](https://aipod.dev/papers/archive/2025-11/page/116.md)
[Next bundle →](https://aipod.dev/papers/archive/2025-11/page/118.md)

### Behaviour Policy Optimization: Provably Lower Variance Return Estimates for Off-Policy Reinforcement Learning

Authors: Alexander W. Goodall, Edwin Hamel-De le Court, Francesco Belardinelli
Published: 2025-11-13
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2511.10843v3

Many reinforcement learning algorithms, particularly those that rely on return estimates for policy improvement, can suffer from poor sample efficiency and training instability due to high-variance return estimates. In this paper we leverage new results from off-policy evaluation; it has recently been shown that well-designed behaviour policies can be used to collect off-policy data for provably lower variance return estimates. This result is surprising as it means collecting data on-policy is not variance optimal. We extend this key insight to the online reinforcement learning setting, where both policy evaluation and improvement are interleaved to learn optimal policies. Off-policy RL has been well studied (e.g., IMPALA), with correct and truncated importance weighted samples for de-biasing and managing variance appropriately. Generally these approaches are concerned with reconciling data collected from multiple workers in parallel, while the policy is updated asynchronously, mismatch between the workers and policy is corrected in a mathematically sound way. Here we consider only one worker - the behaviour policy, which is used to collect data for policy improvement, with provably lower variance return estimates. In our experiments we extend two policy-gradient methods with this regime, demonstrating better sample efficiency and performance over a diverse set of environments.

---

### HyperComplEx: Adaptive Multi-Space Knowledge Graph Embeddings

Authors: Jugal Gajjar, Kaustik Ranaware, Kamalasankari Subramaniakuppusamy, Vaibhav Gandhi
Published: 2025-11-13
Categories: cs.AI, cs.DB, cs.LG, cs.SI
arXiv: https://arxiv.org/abs/2511.10842v1

Knowledge graphs have emerged as fundamental structures for representing complex relational data across scientific and enterprise domains. However, existing embedding methods face critical limitations when modeling diverse relationship types at scale: Euclidean models struggle with hierarchies, vector space models cannot capture asymmetry, and hyperbolic models fail on symmetric relations. We propose HyperComplEx, a hybrid embedding framework that adaptively combines hyperbolic, complex, and Euclidean spaces via learned attention mechanisms. A relation-specific space weighting strategy dynamically selects optimal geometries for each relation type, while a multi-space consistency loss ensures coherent predictions across spaces. We evaluate HyperComplEx on computer science research knowledge graphs ranging from 1K papers (~25K triples) to 10M papers (~45M triples), demonstrating consistent improvements over state-of-the-art baselines including TransE, RotatE, DistMult, ComplEx, SEPA, and UltraE. Additional tests on standard benchmarks confirm significantly higher results than all baselines. On the 10M-paper dataset, HyperComplEx achieves 0.612 MRR, a 4.8% relative gain over the best baseline, while maintaining efficient training, achieving 85 ms inference per triple. The model scales near-linearly with graph size through adaptive dimension allocation. We release our implementation and dataset family to facilitate reproducible research in scalable knowledge graph embeddings.

---

### FlowPath: Learning Data-Driven Manifolds with Invertible Flows for Robust Irregularly-sampled Time Series Classification

Authors: YongKyung Oh, Dong-Young Lim, Sungil Kim
Published: 2025-11-13
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2511.10841v3

Modeling continuous-time dynamics from sparse and irregularly-sampled time series remains a fundamental challenge. Neural controlled differential equations provide a principled framework for such tasks, yet their performance is highly sensitive to the choice of control path constructed from discrete observations. Existing methods commonly employ fixed interpolation schemes, which impose simplistic geometric assumptions that often misrepresent the underlying data manifold, particularly under high missingness. We propose FlowPath, a novel approach that learns the geometry of the control path via an invertible neural flow. Rather than merely connecting observations, FlowPath constructs a continuous and data-adaptive manifold, guided by invertibility constraints that enforce information-preserving and well-behaved transformations. This inductive bias distinguishes FlowPath from prior unconstrained learnable path models. Empirical evaluations on 18 benchmark datasets and a real-world case study demonstrate that FlowPath consistently achieves statistically significant improvements in classification accuracy over baselines using fixed interpolants or non-invertible architectures. These results highlight the importance of modeling not only the dynamics along the path but also the geometry of the path itself, offering a robust and generalizable solution for learning from irregular time series.

---

### Tracing Multilingual Representations in LLMs with Cross-Layer Transcoders

Authors: Abir Harrasse, Florent Draye, Punya Syon Pandey, Zhijing Jin, Bernhard Schölkopf
Published: 2025-11-13
Categories: cs.CL
arXiv: https://arxiv.org/abs/2511.10840v3

Multilingual Large Language Models (LLMs) can process many languages, yet how they internally represent this diversity remains unclear. Do they form shared multilingual representations with language-specific decoding, and if so, why does performance favor the dominant training language? To address this, we train models on different multilingual mixtures and analyze their internal mechanisms using Cross-Layer Transcoders (CLTs) and Attribution Graphs. Our results reveal multilingual shared representations: the model employs highly similar features across languages, while language-specific decoding emerges in later layers. Training models without English shows identical multilingual shared space structures. Decoding relies partly on a small set of high-frequency features in the final layers, which linearly encode language identity from early layers. Intervening on these features allows one language to be suppressed and another substituted. Finally, to explain non-English failures, we perform a Model-Diffing experiment: underperformance arises from dim late-layer features, weak middle-layer clusters, and tokenizer bias toward English that forces early layers to specialize in word reassembly. Finetuning strengthens these features and their links, improving token assembly and language-specific decoding, providing a mechanistic explanation for multilingual gaps. Our models and CLTs are available at https://huggingface.co/collections/CausalNLP/multilingual-clts and https://huggingface.co/collections/CausalNLP/multilingual-gpt2-models. Our code is available at: https://github.com/abirharrasse/MultilingualCLTs

---

### The Map of Misbelief: Tracing Intrinsic and Extrinsic Hallucinations Through Attention Patterns

Authors: Elyes Hajji, Aymen Bouguerra, Fabio Arnez
Published: 2025-11-13
Categories: cs.LG, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2511.10837v1

Large Language Models (LLMs) are increasingly deployed in safety-critical domains, yet remain susceptible to hallucinations. While prior works have proposed confidence representation methods for hallucination detection, most of these approaches rely on computationally expensive sampling strategies and often disregard the distinction between hallucination types. In this work, we introduce a principled evaluation framework that differentiates between extrinsic and intrinsic hallucination categories and evaluates detection performance across a suite of curated benchmarks. In addition, we leverage a recent attention-based uncertainty quantification algorithm and propose novel attention aggregation strategies that improve both interpretability and hallucination detection performance. Our experimental findings reveal that sampling-based methods like Semantic Entropy are effective for detecting extrinsic hallucinations but generally fail on intrinsic ones. In contrast, our method, which aggregates attention over input tokens, is better suited for intrinsic hallucinations. These insights provide new directions for aligning detection strategies with the nature of hallucination and highlight attention as a rich signal for quantifying model uncertainty.

---

### EarthSight: A Distributed Framework for Low-Latency Satellite Intelligence

Authors: Ansel Kaplan Erol, Seungjun Lee, Divya Mahajan
Published: 2025-11-13
Categories: cs.LG, cs.DC
arXiv: https://arxiv.org/abs/2511.10834v3

Low-latency delivery of satellite imagery is essential for time-critical applications such as disaster response, intelligence, and infrastructure monitoring. However, traditional pipelines rely on downlinking all captured images before analysis, introducing delays of hours to days due to restricted communication bandwidth. To address these bottlenecks, emerging systems perform onboard machine learning to prioritize which images to transmit. However, these solutions typically treat each satellite as an isolated compute node, limiting scalability and efficiency. Redundant inference across satellites and tasks further strains onboard power and compute costs, constraining mission scope and responsiveness. We present EarthSight, a distributed runtime framework that redefines satellite image intelligence as a distributed decision problem between orbit and ground. EarthSight introduces three core innovations: (1) multi-task inference on satellites using shared backbones to amortize computation across multiple vision tasks; (2) a ground-station query scheduler that aggregates user requests, predicts priorities, and assigns compute budgets to incoming imagery; and (3) dynamic filter ordering, which integrates model selectivity, accuracy, and execution cost to reject low-value images early and conserve resources. EarthSight leverages global context from ground stations and resource-aware adaptive decisions in orbit to enable constellations to perform scalable, low-latency image analysis within strict downlink bandwidth and onboard power budgets. Evaluations using a prior established satellite simulator show that EarthSight reduces average compute time per image by 1.9x and lowers 90th percentile end-to-end latency from first contact to delivery from 51 to 21 minutes compared to the state-of-the-art baseline.

---

### SURFACEBENCH: A Geometry-Aware Benchmark for Symbolic Surface Discovery

Authors: Sanchit Kabra, Shobhnik Kriplani, Parshin Shojaee, Chandan K. Reddy
Published: 2025-11-13
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.10833v2

Equation discovery from data is a central challenge in machine learning for science, which requires the recovery of concise symbolic expressions that govern complex physical and geometric phenomena. Recent large language model (LLM) approaches have shown promise in symbolic regression, yet existing benchmarks predominantly evaluate low-dimensional scalar functions and rely on string-level or regression-based metrics that fail to capture structural and geometric equivalence. We introduce SURFACEBENCH, the first geometry-aware benchmark for symbolic discovery of three-dimensional surfaces. Unlike scalar curve-fitting tasks, SURFACEBENCH targets surface-level reasoning, where multi-variable coupling, coordinate transformations, and geometric structure must be inferred directly from data. The benchmark comprises 183 analytically constructed, science-inspired surface equations across 15 categories and three representation paradigms: explicit, implicit, and parametric forms. Each task includes variable semantics and synthetically sampled 3D data, and is designed to stress symbolic composition, structural ambiguity, and representational non-uniqueness while mitigating memorization. To evaluate discovery quality, SURFACEBENCH incorporates symbolic equivalence checks with geometric metrics of the object-space (Chamfer and Hausdorff distances) and regression-based error measures, allowing evaluation of functional fidelity beyond algebraic syntax. Empirical evaluation across evolutionary, neural, and LLM-driven frameworks reveals that no current method achieves consistent performance across representation types, with LLM-based approaches exhibiting strong structural priors but limited robustness in parameter calibration and multi-equation reasoning.The code and data are available at this link: github.com/deep-symbolic-mathematics/surfacebench.

---

### A Versatile Variational Quantum Kernel Framework for Non-Trivial Classification

Authors: Jiang Yuhan, Matthew Otten
Published: 2025-11-13
Categories: cs.LG, quant-ph
arXiv: https://arxiv.org/abs/2511.10831v3

Quantum kernel methods are a promising branch of quantum machine learning, but their per- formance across data types and encoding choices remains incompletely understood. To address this gap, we developed an algorithmic framework for variational quantum kernels utilizing resource- efficient ansätze for complex classification tasks and introduced a parameter scaling technique to accelerate convergence. We conducted a comprehensive benchmark of this framework on eight chal- lenging, real-world and high-dimensional datasets covering tabular, image, time series, and graph data. Our results show that the proposed quantum kernel demonstrated competitive classification accuracy compared to standard classical kernels in classical simulation, such as the radial basis function (RBF) kernel. This work demonstrates that properly designed quantum kernels can func- tion as versatile, high-performance tools, laying a foundation for quantum-enhanced applications in machine learning. Further research is needed to fully assess the practical performance of quantum methods.

---

### Towards Universal Neural Operators through Multiphysics Pretraining

Authors: Mikhail Masliaev, Dmitry Gusarov, Ilya Markov, Alexander Hvatov
Published: 2025-11-13
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.10829v1

Although neural operators are widely used in data-driven physical simulations, their training remains computationally expensive. Recent advances address this issue via downstream learning, where a model pretrained on simpler problems is fine-tuned on more complex ones. In this research, we investigate transformer-based neural operators, which have previously been applied only to specific problems, in a more general transfer learning setting. We evaluate their performance across diverse PDE problems, including extrapolation to unseen parameters, incorporation of new variables, and transfer from multi-equation datasets. Our results demonstrate that advanced neural operator architectures can effectively transfer knowledge across PDE problems.

---

### Neural Local Wasserstein Regression

Authors: Inga Girshfeld, Xiaohui Chen
Published: 2025-11-13
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2511.10824v1

We study the estimation problem of distribution-on-distribution regression, where both predictors and responses are probability measures. Existing approaches typically rely on a global optimal transport map or tangent-space linearization, which can be restrictive in approximation capacity and distort geometry in multivariate underlying domains. In this paper, we propose the \emph{Neural Local Wasserstein Regression}, a flexible nonparametric framework that models regression through locally defined transport maps in Wasserstein space. Our method builds on the analogy with classical kernel regression: kernel weights based on the 2-Wasserstein distance localize estimators around reference measures, while neural networks parameterize transport operators that adapt flexibly to complex data geometries. This localized perspective broadens the class of admissible transformations and avoids the limitations of global map assumptions and linearization structures. We develop a practical training procedure using DeepSets-style architectures and Sinkhorn-approximated losses, combined with a greedy reference selection strategy for scalability. Through synthetic experiments on Gaussian and mixture models, as well as distributional prediction tasks on MNIST, we demonstrate that our approach effectively captures nonlinear and high-dimensional distributional relationships that elude existing methods.

---

### MECHBench: A Set of Black-Box Optimization Benchmarks originated from Structural Mechanics

Authors: Iván Olarte Rodríguez, Maria Laura Santoni, Fabian Duddeck, Carola Doerr, Thomas Bäck, Elena Raponi
Published: 2025-11-13
Categories: cs.NE, cs.CE
arXiv: https://arxiv.org/abs/2511.10821v1

Benchmarking is essential for developing and evaluating black-box optimization algorithms, providing a structured means to analyze their search behavior. Its effectiveness relies on carefully selected problem sets used for evaluation. To date, most established benchmark suites for black-box optimization consist of abstract or synthetic problems that only partially capture the complexities of real-world engineering applications, thereby severely limiting the insights that can be gained for application-oriented optimization scenarios and reducing their practical impact. To close this gap, we propose a new benchmarking suite that addresses it by presenting a curated set of optimization benchmarks rooted in structural mechanics. The current implemented benchmarks are derived from vehicle crashworthiness scenarios, which inherently require the use of gradient-free algorithms due to the non-smooth, highly non-linear nature of the underlying models. Within this paper, the reader will find descriptions of the physical context of each case, the corresponding optimization problem formulations, and clear guidelines on how to employ the suite.

---

### LLM-as-a-Grader: Practical Insights from Large Language Model for Short-Answer and Report Evaluation

Authors: Grace Byun, Swati Rajwal, Jinho D. Choi
Published: 2025-11-13
Categories: cs.CL
arXiv: https://arxiv.org/abs/2511.10819v2

Large Language Models (LLMs) are increasingly explored for educational tasks such as grading, yet their alignment with human evaluation in real classrooms remains underexamined. In this study, we investigate the feasibility of using an LLM (GPT-4o) to evaluate short-answer quizzes and project reports in an undergraduate Computational Linguistics course. We collect responses from approximately 50 students across five quizzes and receive project reports from 14 teams. LLM-generated scores are compared against human evaluations conducted independently by the course teaching assistants (TAs). Our results show that GPT-4o achieves strong correlation with human graders (up to 0.98) and exact score agreement in 55\% of quiz cases. For project reports, it also shows strong overall alignment with human grading, while exhibiting some variability in scoring technical, open-ended responses. We release all code and sample data to support further research on LLMs in educational assessment. This work highlights both the potential and limitations of LLM-based grading systems and contributes to advancing automated grading in real-world academic settings.

---

### Transformers know more than they can tell -- Learning the Collatz sequence

Authors: François Charton, Ashvni Narayanan
Published: 2025-11-13
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.10811v1

We investigate transformer prediction of long Collatz steps, a complex arithmetic function that maps odd integers to their distant successors in the Collatz sequence ( $u_{n+1}=u_n/2$ if $u_n$ is even, $u_{n+1}=(3u_n+1)/2$ if $u_n$ is odd). Model accuracy varies with the base used to encode input and output. It can be as high as $99.7\%$ for bases $24$ and $32$, and as low as $37$ and $25\%$ for bases $11$ and $3$. Yet, all models, no matter the base, follow a common learning pattern. As training proceeds, they learn a sequence of classes of inputs that share the same residual modulo $2^p$. Models achieve near-perfect accuracy on these classes, and less than $1\%$ for all other inputs. This maps to a mathematical property of Collatz sequences: the length of the loops involved in the computation of a long Collatz step can be deduced from the binary representation of its input. The learning pattern reflects the model learning to predict inputs associated with increasing loop lengths. An analysis of failure cases reveals that almost all model errors follow predictable patterns. Hallucination, a common feature of large language models, almost never happens. In over $90\%$ of failures, the model performs the correct calculation, but wrongly estimates loop lengths. Our observations give a full account of the algorithms learned by the models. They suggest that the difficulty of learning such complex arithmetic function lies in figuring the control structure of the computation -- the length of the loops. We believe that the approach outlined here, using mathematical problems as tools for understanding, explaining, and perhaps improving language models, can be applied to a broad range of problems and bear fruitful results.

---

### HARNESS: Human-Agent Risk Navigation and Event Safety System for Proactive Hazard Forecasting in High-Risk DOE Environments

Authors: Ran Elgedawy, Sanjay Das, Ethan Seefried, Gavin Wiggins, Ryan Burchfield, Dana Hewit, Sudarshan Srinivasan, Todd Thomas, Prasanna Balaprakash, Tirthankar Ghosal
Published: 2025-11-13
Categories: cs.AI
arXiv: https://arxiv.org/abs/2511.10810v1

Operational safety at mission-critical work sites is a top priority given the complex and hazardous nature of daily tasks. This paper presents the Human-Agent Risk Navigation and Event Safety System (HARNESS), a modular AI framework designed to forecast hazardous events and analyze operational risks in U.S. Department of Energy (DOE) environments. HARNESS integrates Large Language Models (LLMs) with structured work data, historical event retrieval, and risk analysis to proactively identify potential hazards. A human-in-the-loop mechanism allows subject matter experts (SMEs) to refine predictions, creating an adaptive learning loop that enhances performance over time. By combining SME collaboration with iterative agentic reasoning, HARNESS improves the reliability and efficiency of predictive safety systems. Preliminary deployment shows promising results, with future work focusing on quantitative evaluation of accuracy, SME agreement, and decision latency reduction.

---

### Near-optimal Linear Predictive Clustering in Non-separable Spaces via MIP and QPBO Reductions

Authors: Jiazhou Liang, Hassan Khurram, Scott Sanner
Published: 2025-11-13
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.10809v3

Linear Predictive Clustering (LPC) partitions samples based on shared linear relationships between feature and target variables, with numerous applications including marketing, medicine, and education. Greedy optimization methods, commonly used for LPC, alternate between clustering and linear regression but lack global optimality. While effective for separable clusters, they struggle in non-separable settings where clusters overlap in feature space. In an alternative constrained optimization paradigm, Bertsimas and Shioda (2007) formulated LPC as a Mixed-Integer Program (MIP), ensuring global optimality regardless of separability but suffering from poor scalability. This work builds on the constrained optimization paradigm to introduce two novel approaches that improve the efficiency of global optimization for LPC. By leveraging key theoretical properties of separability, we derive near-optimal approximations with provable error bounds, significantly reducing the MIP formulation's complexity and improving scalability. Additionally, we can further approximate LPC as a Quadratic Pseudo-Boolean Optimization (QPBO) problem, achieving substantial computational improvements in some settings. Comparative analyses on synthetic and real-world datasets demonstrate that our methods consistently achieve near-optimal solutions with substantially lower regression errors than greedy optimization while exhibiting superior scalability over existing MIP formulations.

---

### From Attention to Frequency: Integration of Vision Transformer and FFT-ReLU for Enhanced Image Deblurring

Authors: Syed Mumtahin Mahmud, Mahdi Mohd Hossain Noki, Prothito Shovon Majumder, Abdul Mohaimen Al Radi, Md. Haider Ali, Md. Mosaddek Khan
Published: 2025-11-13
Categories: eess.IV, cs.AI, cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2511.10806v1

Image deblurring is vital in computer vision, aiming to recover sharp images from blurry ones caused by motion or camera shake. While deep learning approaches such as CNNs and Vision Transformers (ViTs) have advanced this field, they often struggle with complex or high-resolution blur and computational demands. We propose a new dual-domain architecture that unifies Vision Transformers with a frequency-domain FFT-ReLU module, explicitly bridging spatial attention modeling and frequency sparsity. In this structure, the ViT backbone captures local and global dependencies, while the FFT-ReLU component enforces frequency-domain sparsity to suppress blur-related artifacts and preserve fine details. Extensive experiments on benchmark datasets demonstrate that this architecture achieves superior PSNR, SSIM, and perceptual quality compared to state-of-the-art models. Both quantitative metrics, qualitative comparisons, and human preference evaluations confirm its effectiveness, establishing a practical and generalizable paradigm for real-world image restoration.

---

### Discounted Cuts: A Stackelberg Approach to Network Disruption

Authors: Pål Grønås Drange, Fedor V. Fomin, Petr Golovach, Danil Sagunov
Published: 2025-11-13
Categories: cs.DS, cs.AI
arXiv: https://arxiv.org/abs/2511.10804v1

We study a Stackelberg variant of the classical Most Vital Links problem, modeled as a one-round adversarial game between an attacker and a defender. The attacker strategically removes up to $k$ edges from a flow network to maximally disrupt flow between a source $s$ and a sink $t$, after which the defender optimally reroutes the remaining flow. To capture this attacker--defender interaction, we introduce a new mathematical model of discounted cuts, in which the cost of a cut is evaluated by excluding its $k$ most expensive edges. This model generalizes the Most Vital Links problem and uncovers novel algorithmic and complexity-theoretic properties. We develop a unified algorithmic framework for analyzing various forms of discounted cut problems, including minimizing or maximizing the cost of a cut under discount mechanisms that exclude either the $k$ most expensive or the $k$ cheapest edges. While most variants are NP-complete on general graphs, our main result establishes polynomial-time solvability for all discounted cut problems in our framework when the input is restricted to bounded-genus graphs, a relevant class that includes many real-world networks such as transportation and infrastructure networks. With this work, we aim to open collaborative bridges between artificial intelligence, algorithmic game theory, and operations research.

---

### GFT: Graph Feature Tuning for Efficient Point Cloud Analysis

Authors: Manish Dhakal, Venkat R. Dasari, Rajshekhar Sunderraman, Yi Ding
Published: 2025-11-13
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.10799v2

Parameter-efficient fine-tuning (PEFT) significantly reduces computational and memory costs by updating only a small subset of the model's parameters, enabling faster adaptation to new tasks with minimal loss in performance. Previous studies have introduced PEFTs tailored for point cloud data, as general approaches are suboptimal. To further reduce the number of trainable parameters, we propose a point-cloud-specific PEFT, termed Graph Features Tuning (GFT), which learns a dynamic graph from initial tokenized inputs of the transformer using a lightweight graph convolution network and passes these graph features to deeper layers via skip connections and efficient cross-attention modules. Extensive experiments on object classification and segmentation tasks show that GFT operates in the same domain, rivalling existing methods, while reducing the trainable parameters. Code is available at https://github.com/manishdhakal/GFT.

---

### Fast Generalized Neural Tangent Kernel Statistics via Trace Estimation

Authors: James Hazelden, Balaaji Reddy Nagireddy, Eric Shea-Brown
Published: 2025-11-13
Categories: cs.LG, cs.AI, math.NA
arXiv: https://arxiv.org/abs/2511.10796v2

The empirical state-space Neural Tangent Kernel (NTK) describes the local learning geometry of a finite-width neural network, but computing it explicitly is almost always impractical in terms of computation and memory costs. Here, we show that many useful NTK statistics that characterize, for example, the dimensionality of learned updates or how two models or learning rules relate, can instead be efficiently approximated to very high accuracy via matrix-free products using randomized trace estimation. Namely, we use Hutch++ to estimate the NTK trace, Frobenius norm, effective rank, and alignment. Furthermore, we show that the positive-semidefinite structure of the NTK yields one-sided estimators that require only forward- or reverse-mode automatic differentiation. We validate these estimators across MLPs, recurrent GRUs, and a natural-language Transformer with up to 410 million parameters, in which the state-space contains high-dimensional four-tensors. We demonstrate orders-of-magnitude speedups, with the fastest estimator in a given application depending on the ratio of parameter and state dimensions. Equipped with these estimators, we examine rich and lazy RNN training using hidden-state NTK alignment and use NTK alignment as a regularizer for data-scarce knowledge distillation. We find that this regularization can modestly improve generalization, especially in very data-scarce settings. Together, these results suggest state-space NTK diagnostics are practical even at large scales.

---

### From Efficiency to Adaptivity: A Deeper Look at Adaptive Reasoning in Large Language Models

Authors: Chao Wu, Baoheng Li, Mingchen Gao, Yu Tian, Zhenyi Wang
Published: 2025-11-13
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2511.10788v3

Recent advances in large language models (LLMs) have made reasoning a central benchmark for evaluating intelligence. While prior surveys focus on efficiency by examining how to shorten reasoning chains or reduce computation, this view overlooks a fundamental challenge: current LLMs apply uniform reasoning strategies regardless of task complexity, generating long traces for trivial problems while failing to extend reasoning for difficult tasks. This survey reframes reasoning through the lens of {adaptivity}: the capability to allocate reasoning effort based on input characteristics such as difficulty and uncertainty. We make three contributions. First, we formalize deductive, inductive, and abductive reasoning within the LLM context, connecting these classical cognitive paradigms with their algorithmic realizations. Second, we formalize adaptive reasoning as a control-augmented policy optimization problem balancing task performance with computational cost, distinguishing learned policies from inference-time control mechanisms. Third, we propose a systematic taxonomy organizing existing methods into training-based approaches that internalize adaptivity through reinforcement learning, supervised fine-tuning, and learned controllers, and training-free approaches that achieve adaptivity through prompt conditioning, feedback-driven halting, and modular composition. This framework clarifies how different mechanisms realize adaptive reasoning in practice and enables systematic comparison across diverse strategies. We conclude by identifying open challenges in self-evaluation, meta-reasoning, and human-aligned reasoning control.

---

### Sabiá: Um Chatbot de Inteligência Artificial Generativa para Suporte no Dia a Dia do Ensino Superior

Authors: Guilherme Biava Rodrigues, Franciele Beal, Marlon Marcon, Alinne Cristinne Corrêa Souza, André Roberto Ortoncelli, Francisco Carlos Monteiro Souza, Rodolfo Adamshuk Silva
Published: 2025-11-13
Categories: cs.CL
arXiv: https://arxiv.org/abs/2511.10787v1

Students often report difficulties in accessing day-to-day academic information, which is usually spread across numerous institutional documents and websites. This fragmentation results in a lack of clarity and causes confusion about routine university information. This project proposes the development of a chatbot using Generative Artificial Intelligence (GenAI) and Retrieval-Augmented Generation (RAG) to simplify access to such information. Several GenAI models were tested and evaluated based on quality metrics and the LLM-as-a-Judge approach. Among them, Gemini 2.0 Flash stood out for its quality and speed, and Gemma 3n for its good performance and open-source nature.

---

### TEDxTN: A Three-way Speech Translation Corpus for Code-Switched Tunisian Arabic - English

Authors: Fethi Bougares, Salima Mdhaffar, Haroun Elleuch, Yannick Estève
Published: 2025-11-13
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2511.10780v1

In this paper, we introduce TEDxTN, the first publicly available Tunisian Arabic to English speech translation dataset. This work is in line with the ongoing effort to mitigate the data scarcity obstacle for a number of Arabic dialects. We collected, segmented, transcribed and translated 108 TEDx talks following our internally developed annotations guidelines. The collected talks represent 25 hours of speech with code-switching that cover speakers with various accents from over 11 different regions of Tunisia. We make the annotation guidelines and corpus publicly available. This will enable the extension of TEDxTN to new talks as they become available. We also report results for strong baseline systems of Speech Recognition and Speech Translation using multiple pre-trained and fine-tuned end-to-end models. This corpus is the first open source and publicly available speech translation corpus of Code-Switching Tunisian dialect. We believe that this is a valuable resource that can motivate and facilitate further research on the natural language processing of Tunisian Dialect.

---

### Potential Outcome Rankings for Counterfactual Decision Making

Authors: Yuta Kawakami, Jin Tian
Published: 2025-11-13
Categories: cs.AI, stat.ML
arXiv: https://arxiv.org/abs/2511.10776v1

Counterfactual decision-making in the face of uncertainty involves selecting the optimal action from several alternatives using causal reasoning. Decision-makers often rank expected potential outcomes (or their corresponding utility and desirability) to compare the preferences of candidate actions. In this paper, we study new counterfactual decision-making rules by introducing two new metrics: the probabilities of potential outcome ranking (PoR) and the probability of achieving the best potential outcome (PoB). PoR reveals the most probable ranking of potential outcomes for an individual, and PoB indicates the action most likely to yield the top-ranked outcome for an individual. We then establish identification theorems and derive bounds for these metrics, and present estimation methods. Finally, we perform numerical experiments to illustrate the finite-sample properties of the estimators and demonstrate their application to a real-world dataset.

---

### Frequency-Aware Vision-Language Multimodality Generalization Network for Remote Sensing Image Classification

Authors: Junjie Zhang, Feng Zhao, Hanqiang Liu, Jun Yu
Published: 2025-11-13
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.10774v1

The booming remote sensing (RS) technology is giving rise to a novel multimodality generalization task, which requires the model to overcome data heterogeneity while possessing powerful cross-scene generalization ability. Moreover, most vision-language models (VLMs) usually describe surface materials in RS images using universal texts, lacking proprietary linguistic prior knowledge specific to different RS vision modalities. In this work, we formalize RS multimodality generalization (RSMG) as a learning paradigm, and propose a frequency-aware vision-language multimodality generalization network (FVMGN) for RS image classification. Specifically, a diffusion-based training-test-time augmentation (DTAug) strategy is designed to reconstruct multimodal land-cover distributions, enriching input information for FVMGN. Following that, to overcome multimodal heterogeneity, a multimodal wavelet disentanglement (MWDis) module is developed to learn cross-domain invariant features by resampling low and high frequency components in the frequency domain. Considering the characteristics of RS vision modalities, shared and proprietary class texts is designed as linguistic inputs for the transformer-based text encoder to extract diverse text features. For multimodal vision inputs, a spatial-frequency-aware image encoder (SFIE) is constructed to realize local-global feature reconstruction and representation. Finally, a multiscale spatial-frequency feature alignment (MSFFA) module is suggested to construct a unified semantic space, ensuring refined multiscale alignment of different text and vision features in spatial and frequency domains. Extensive experiments show that FVMGN has the excellent multimodality generalization ability compared with state-of-the-art (SOTA) methods.

---

### Faithful Summarization of Consumer Health Queries: A Cross-Lingual Framework with LLMs

Authors: Ajwad Abrar, Nafisa Tabassum Oeshy, Prianka Maheru, Farzana Tabassum, Tareque Mohmud Chowdhury
Published: 2025-11-13
Categories: cs.CL
arXiv: https://arxiv.org/abs/2511.10768v1

Summarizing consumer health questions (CHQs) can ease communication in healthcare, but unfaithful summaries that misrepresent medical details pose serious risks. We propose a framework that combines TextRank-based sentence extraction and medical named entity recognition with large language models (LLMs) to enhance faithfulness in medical text summarization. In our experiments, we fine-tuned the LLaMA-2-7B model on the MeQSum (English) and BanglaCHQ-Summ (Bangla) datasets, achieving consistent improvements across quality (ROUGE, BERTScore, readability) and faithfulness (SummaC, AlignScore) metrics, and outperforming zero-shot baselines and prior systems. Human evaluation further shows that over 80\% of generated summaries preserve critical medical information. These results highlight faithfulness as an essential dimension for reliable medical summarization and demonstrate the potential of our approach for safer deployment of LLMs in healthcare contexts.

---

### Structure-Aware Encodings of Argumentation Properties for Clique-width

Authors: Yasir Mahmood, Markus Hecher, Johanna Groven, Johannes K. Fichte
Published: 2025-11-13
Categories: cs.AI, cs.CC
arXiv: https://arxiv.org/abs/2511.10767v1

Structural measures of graphs, such as treewidth, are central tools in computational complexity resulting in efficient algorithms when exploiting the parameter. It is even known that modern SAT solvers work efficiently on instances of small treewidth. Since these solvers are widely applied, research interests in compact encodings into (Q)SAT for solving and to understand encoding limitations. Even more general is the graph parameter clique-width, which unlike treewidth can be small for dense graphs. Although algorithms are available for clique-width, little is known about encodings. We initiate the quest to understand encoding capabilities with clique-width by considering abstract argumentation, which is a robust framework for reasoning with conflicting arguments. It is based on directed graphs and asks for computationally challenging properties, making it a natural candidate to study computational properties. We design novel reductions from argumentation problems to (Q)SAT. Our reductions linearly preserve the clique-width, resulting in directed decomposition-guided (DDG) reductions. We establish novel results for all argumentation semantics, including counting. Notably, the overhead caused by our DDG reductions cannot be significantly improved under reasonable assumptions.

---

### Expert Consensus-based Video-Based Assessment Tool for Workflow Analysis in Minimally Invasive Colorectal Surgery: Development and Validation of ColoWorkflow

Authors: Pooja P Jain, Pietro Mascagni, Giuseppe Massimiani, Nabani Banik, Marta Goglia, Lorenzo Arboit, Britty Baby, Andrea Balla, Ludovica Baldari, Gianfranco Silecchia, Claudio Fiorillo, CompSurg Colorectal Experts Group et al.
Published: 2025-11-13
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.10766v2

Minimally invasive colorectal surgery is characterized by procedural variability, a difficult learning curve, and complications that impact quality and outcomes. Video-based assessment (VBA) offers an opportunity to generate data-driven insights to reduce variability, optimize training, and improve surgical performance. However, existing tools for workflow analysis remain difficult to standardize and implement. This study aims to develop and validate a VBA tool for workflow analysis across minimally invasive colorectal procedures. A Delphi process was conducted to achieve consensus on generalizable workflow descriptors. The resulting framework informed the development of a new VBA tool, ColoWorkflow. Independent raters then applied ColoWorkflow to a multicentre video dataset of laparoscopic and robotic colorectal surgery (CRS). Applicability and inter-rater reliability were evaluated. Consensus was achieved for 10 procedure-agnostic phases and 34 procedure-specific steps describing CRS workflows. ColoWorkflow was developed and applied to 54 colorectal operative videos (left and right hemicolectomies, sigmoid and rectosigmoid resections, and total proctocolectomies) from five centres. The tool demonstrated broad applicability, with all but one label utilized. Inter-rater reliability was moderate, with mean Cohen's K of 0.71 for phases and 0.66 for steps. Most discrepancies arose at phase transitions and step boundary definitions. ColoWorkflow is the first consensus-based, validated VBA tool for comprehensive workflow analysis in minimally invasive CRS. It establishes a reproducible framework for video-based performance assessment, enabling benchmarking across institutions and supporting the development of artificial intelligence-driven workflow recognition. Its adoption may standardize training, accelerate competency acquisition, and advance data-informed surgical quality improvement.

---

### Attentive Feature Aggregation or: How Policies Learn to Stop Worrying about Robustness and Attend to Task-Relevant Visual Cues

Authors: Nikolaos Tsagkas, Andreas Sochopoulos, Duolikun Danier, Sethu Vijayakumar, Alexandros Kouris, Oisin Mac Aodha, Chris Xiaoxuan Lu
Published: 2025-11-13
Categories: cs.RO, cs.CV
arXiv: https://arxiv.org/abs/2511.10762v2

The adoption of pre-trained visual representations (PVRs), leveraging features from large-scale vision models, has become a popular paradigm for training visuomotor policies. However, these powerful representations can encode a broad range of task-irrelevant scene information, making the resulting trained policies vulnerable to out-of-domain visual changes and distractors. In this work we address visuomotor policy feature pooling as a solution to the observed lack of robustness in perturbed scenes. We achieve this via Attentive Feature Aggregation (AFA), a lightweight, trainable pooling mechanism that learns to naturally attend to task-relevant visual cues, ignoring even semantically rich scene distractors. Through extensive experiments in both simulation and the real world, we demonstrate that policies trained with AFA significantly outperform standard pooling approaches in the presence of visual perturbations, without requiring expensive dataset augmentation or fine-tuning of the PVR. Our findings show that ignoring extraneous visual information is a crucial step towards deploying robust and generalisable visuomotor policies. Project Page: tsagkas.github.io/afa

---

### Surrogate-Based Differentiable Pipeline for Shape Optimization

Authors: Andrin Rehmann, Nolan Black, Josiah Bjorgaard, Alessandro Angioi, Andrei Paleyes, Niklas Heim, Dion Häfner, Alexander Lavin
Published: 2025-11-13
Categories: cs.CE, cs.AI, cs.LG, math.DG
arXiv: https://arxiv.org/abs/2511.10761v1

Gradient-based optimization of engineering designs is limited by non-differentiable components in the typical computer-aided engineering (CAE) workflow, which calculates performance metrics from design parameters. While gradient-based methods could provide noticeable speed-ups in high-dimensional design spaces, codes for meshing, physical simulations, and other common components are not differentiable even if the math or physics underneath them is. We propose replacing non-differentiable pipeline components with surrogate models which are inherently differentiable. Using a toy example of aerodynamic shape optimization, we demonstrate an end-to-end differentiable pipeline where a 3D U-Net full-field surrogate replaces both meshing and simulation steps by training it on the mapping between the signed distance field (SDF) of the shape and the fields of interest. This approach enables gradient-based shape optimization without the need for differentiable solvers, which can be useful in situations where adjoint methods are unavailable and/or hard to implement.

---

### Understanding the Nature of Depth-1 Equivariant Quantum Circuit

Authors: Jonathan Teo, Lee Xin Wei, Hoong Chuin Lau
Published: 2025-11-13
Categories: quant-ph, cs.AI
arXiv: https://arxiv.org/abs/2511.10756v2

The Equivariant Quantum Circuit (EQC) for the Travelling Salesman Problem (TSP) has been shown to achieve near-optimal performance in solving small TSP problems (up to 20 nodes) using only two parameters at depth 1. However, extending EQCs to larger TSP problem sizes remains challenging due to the exponential time and memory for quantum circuit simulation, as well as increasing noise and decoherence when running on actual quantum hardware. In this work, we propose the Size-Invariant Grid Search (SIGS), an efficient training optimization for Quantum Reinforcement Learning (QRL), and use it to simulate the outputs of a trained Depth-1 EQC up to 350-node TSP instances - well beyond previously tractable limits. At TSP with 100 nodes, we reduce total simulation times by 96.4%, when comparing to RL simulations with the analytical expression (151 minutes using RL to under 6 minutes using SIGS on TSP-100), while achieving a mean optimality gap within 0.005 of the RL trained model on the test set. SIGS provides a practical benchmarking tool for the QRL community, allowing us to efficiently analyze the performance of QRL algorithms on larger problem sizes. We provide a theoretical explanation for SIGS called the Size-Invariant Properties that goes beyond the concept of equivariance discussed in prior literature.

---

### Fast Data Attribution for Text-to-Image Models

Authors: Sheng-Yu Wang, Aaron Hertzmann, Alexei A Efros, Richard Zhang, Jun-Yan Zhu
Published: 2025-11-13
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2511.10721v1

Data attribution for text-to-image models aims to identify the training images that most significantly influenced a generated output. Existing attribution methods involve considerable computational resources for each query, making them impractical for real-world applications. We propose a novel approach for scalable and efficient data attribution. Our key idea is to distill a slow, unlearning-based attribution method to a feature embedding space for efficient retrieval of highly influential training images. During deployment, combined with efficient indexing and search methods, our method successfully finds highly influential images without running expensive attribution algorithms. We show extensive results on both medium-scale models trained on MSCOCO and large-scale Stable Diffusion models trained on LAION, demonstrating that our method can achieve better or competitive performance in a few seconds, faster than existing methods by 2,500x - 400,000x. Our work represents a meaningful step towards the large-scale application of data attribution methods on real-world models such as Stable Diffusion.

---

### PISanitizer: Preventing Prompt Injection to Long-Context LLMs via Prompt Sanitization

Authors: Runpeng Geng, Yanting Wang, Chenlong Yin, Minhao Cheng, Ying Chen, Jinyuan Jia
Published: 2025-11-13
Categories: cs.CR, cs.AI, cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2511.10720v1

Long context LLMs are vulnerable to prompt injection, where an attacker can inject an instruction in a long context to induce an LLM to generate an attacker-desired output. Existing prompt injection defenses are designed for short contexts. When extended to long-context scenarios, they have limited effectiveness. The reason is that an injected instruction constitutes only a very small portion of a long context, making the defense very challenging. In this work, we propose PISanitizer, which first pinpoints and sanitizes potential injected tokens (if any) in a context before letting a backend LLM generate a response, thereby eliminating the influence of the injected instruction. To sanitize injected tokens, PISanitizer builds on two observations: (1) prompt injection attacks essentially craft an instruction that compels an LLM to follow it, and (2) LLMs intrinsically leverage the attention mechanism to focus on crucial input tokens for output generation. Guided by these two observations, we first intentionally let an LLM follow arbitrary instructions in a context and then sanitize tokens receiving high attention that drive the instruction-following behavior of the LLM. By design, PISanitizer presents a dilemma for an attacker: the more effectively an injected instruction compels an LLM to follow it, the more likely it is to be sanitized by PISanitizer. Our extensive evaluation shows that PISanitizer can successfully prevent prompt injection, maintain utility, outperform existing defenses, is efficient, and is robust to optimization-based and strong adaptive attacks. The code is available at https://github.com/sleeepeer/PISanitizer.

---

### Picking a Representative Set of Solutions in Multiobjective Optimization: Axioms, Algorithms, and Experiments

Authors: Niclas Boehmer, Maximilian T. Wittmann
Published: 2025-11-13
Categories: cs.AI, cs.CE, cs.GT
arXiv: https://arxiv.org/abs/2511.10716v1

Many real-world decision-making problems involve optimizing multiple objectives simultaneously, rendering the selection of the most preferred solution a non-trivial problem: All Pareto optimal solutions are viable candidates, and it is typically up to a decision maker to select one for implementation based on their subjective preferences. To reduce the cognitive load on the decision maker, previous work has introduced the Pareto pruning problem, where the goal is to compute a fixed-size subset of Pareto optimal solutions that best represent the full set, as evaluated by a given quality measure. Reframing Pareto pruning as a multiwinner voting problem, we conduct an axiomatic analysis of existing quality measures, uncovering several unintuitive behaviors. Motivated by these findings, we introduce a new measure, directed coverage. We also analyze the computational complexity of optimizing various quality measures, identifying previously unknown boundaries between tractable and intractable cases depending on the number and structure of the objectives. Finally, we present an experimental evaluation, demonstrating that the choice of quality measure has a decisive impact on the characteristics of the selected set of solutions and that our proposed measure performs competitively or even favorably across a range of settings.

---

### BadThink: Triggered Overthinking Attacks on Chain-of-Thought Reasoning in Large Language Models

Authors: Shuaitong Liu, Renjue Li, Lijia Yu, Lijun Zhang, Zhiming Liu, Gaojie Jin
Published: 2025-11-13
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2511.10714v1

Recent advances in Chain-of-Thought (CoT) prompting have substantially improved the reasoning capabilities of large language models (LLMs), but have also introduced their computational efficiency as a new attack surface. In this paper, we propose BadThink, the first backdoor attack designed to deliberately induce "overthinking" behavior in CoT-enabled LLMs while ensuring stealth. When activated by carefully crafted trigger prompts, BadThink manipulates the model to generate inflated reasoning traces - producing unnecessarily redundant thought processes while preserving the consistency of final outputs. This subtle attack vector creates a covert form of performance degradation that significantly increases computational costs and inference time while remaining difficult to detect through conventional output evaluation methods. We implement this attack through a sophisticated poisoning-based fine-tuning strategy, employing a novel LLM-based iterative optimization process to embed the behavior by generating highly naturalistic poisoned data. Our experiments on multiple state-of-the-art models and reasoning tasks show that BadThink consistently increases reasoning trace lengths - achieving an over 17x increase on the MATH-500 dataset - while remaining stealthy and robust. This work reveals a critical, previously unexplored vulnerability where reasoning efficiency can be covertly manipulated, demonstrating a new class of sophisticated attacks against CoT-enabled systems.

---

### Movement-Specific Analysis for FIM Score Classification Using Spatio-Temporal Deep Learning

Authors: Jun Masaki, Ariaki Higashi, Naoko Shinagawa, Kazuhiko Hirata, Yuichi Kurita, Akira Furui
Published: 2025-11-13
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.10713v1

The functional independence measure (FIM) is widely used to evaluate patients' physical independence in activities of daily living. However, traditional FIM assessment imposes a significant burden on both patients and healthcare professionals. To address this challenge, we propose an automated FIM score estimation method that utilizes simple exercises different from the designated FIM assessment actions. Our approach employs a deep neural network architecture integrating a spatial-temporal graph convolutional network (ST-GCN), bidirectional long short-term memory (BiLSTM), and an attention mechanism to estimate FIM motor item scores. The model effectively captures long-term temporal dependencies and identifies key body-joint contributions through learned attention weights. We evaluated our method in a study of 277 rehabilitation patients, focusing on FIM transfer and locomotion items. Our approach successfully distinguishes between completely independent patients and those requiring assistance, achieving balanced accuracies of 70.09-78.79 % across different FIM items. Additionally, our analysis reveals specific movement patterns that serve as reliable predictors for particular FIM evaluation items.

---

### Do Not Merge My Model! Safeguarding Open-Source LLMs Against Unauthorized Model Merging

Authors: Qinfeng Li, Miao Pan, Jintao Chen, Fu Teng, Zhiqiang Shen, Ge Su, Hao Peng, Xuhong Zhang
Published: 2025-11-13
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2511.10712v2

Model merging has emerged as an efficient technique for expanding large language models (LLMs) by integrating specialized expert models. However, it also introduces a new threat: model merging stealing, where free-riders exploit models through unauthorized model merging. Unfortunately, existing defense mechanisms fail to provide effective protection. Specifically, we identify three critical protection properties that existing methods fail to simultaneously satisfy: (1) proactively preventing unauthorized merging; (2) ensuring compatibility with general open-source settings; (3) achieving high security with negligible performance loss. To address the above issues, we propose MergeBarrier, a plug-and-play defense that proactively prevents unauthorized merging. The core design of MergeBarrier is to disrupt the Linear Mode Connectivity (LMC) between the protected model and its homologous counterparts, thereby eliminating the low-loss path required for effective model merging. Extensive experiments show that MergeBarrier effectively prevents model merging stealing with negligible accuracy loss.

---

### Towards Uncertainty Quantification in Generative Model Learning

Authors: Giorgio Morales, Frederic Jurie, Jalal Fadili
Published: 2025-11-13
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2511.10710v1

While generative models have become increasingly prevalent across various domains, fundamental concerns regarding their reliability persist. A crucial yet understudied aspect of these models is the uncertainty quantification surrounding their distribution approximation capabilities. Current evaluation methodologies focus predominantly on measuring the closeness between the learned and the target distributions, neglecting the inherent uncertainty in these measurements. In this position paper, we formalize the problem of uncertainty quantification in generative model learning. We discuss potential research directions, including the use of ensemble-based precision-recall curves. Our preliminary experiments on synthetic datasets demonstrate the effectiveness of aggregated precision-recall curves in capturing model approximation uncertainty, enabling systematic comparison among different model architectures based on their uncertainty characteristics.

---

### Limitations of Quantum Advantage in Unsupervised Machine Learning

Authors: Apoorva D. Patel
Published: 2025-11-13
Categories: quant-ph, cs.LG
arXiv: https://arxiv.org/abs/2511.10709v2

Machine learning models are used for pattern recognition analysis of big data, without direct human intervention. The task of unsupervised learning is to find the probability distribution that would best describe the available data, and then use it to make predictions for observables of interest. Classical models generally fit the data to Boltzmann distribution of Hamiltonians with a large number of tunable parameters. Quantum extensions of these models replace classical probability distributions with quantum density matrices. An advantage can be obtained only when features of density matrices that are absent in classical probability distributions are exploited. Such situations depend on the input data as well as the targeted observables. Explicit examples are discussed that bring out the constraints limiting possible quantum advantage. The problem-dependent extent of quantum advantage has implications for both data analysis and sensing applications.

---

### Bias-Restrained Prefix Representation Finetuning for Mathematical Reasoning

Authors: Sirui Liang, Pengfei Cao, Jian Zhao, Cong Huang, Jun Zhao, Kang Liu
Published: 2025-11-13
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2511.10707v1

Parameter-Efficient finetuning (PEFT) enhances model performance on downstream tasks by updating a minimal subset of parameters. Representation finetuning (ReFT) methods further improve efficiency by freezing model weights and optimizing internal representations with fewer parameters than PEFT, outperforming PEFT on several tasks. However, ReFT exhibits a significant performance decline on mathematical reasoning tasks. To address this problem, the paper demonstrates that ReFT's poor performance on mathematical tasks primarily stems from its struggle to generate effective reasoning prefixes during the early inference phase. Moreover, ReFT disturbs the numerical encoding and the error accumulats during the CoT stage. Based on these observations, this paper proposes Bias-REstrained Prefix Representation FineTuning (BREP ReFT), which enhances ReFT's mathematical reasoning capability by truncating training data to optimize the generation of initial reasoning prefixes, intervening on the early inference stage to prevent error accumulation, and constraining the intervention vectors' magnitude to avoid disturbing numerical encoding. Extensive experiments across diverse model architectures demonstrate BREP's superior effectiveness, efficiency, and robust generalization capability, outperforming both standard ReFT and weight-based PEFT methods on the task of mathematical reasoning. The source code is available at https://github.com/LiangThree/BREP.

---

### Differentiable Sparse Identification of Lagrangian Dynamics

Authors: Zitong Zhang, Hao Sun
Published: 2025-11-13
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.10706v1

Data-driven discovery of governing equations from data remains a fundamental challenge in nonlinear dynamics. Although sparse regression techniques have advanced system identification, they struggle with rational functions and noise sensitivity in complex mechanical systems. The Lagrangian formalism offers a promising alternative, as it typically avoids rational expressions and provides a more concise representation of system dynamics. However, existing Lagrangian identification methods are significantly affected by measurement noise and limited data availability. This paper presents a novel differentiable sparse identification framework that addresses these limitations through three key contributions: (1) the first integration of cubic B-Spline approximation into Lagrangian system identification, enabling accurate representation of complex nonlinearities, (2) a robust equation discovery mechanism that effectively utilizes measurements while incorporating known physical constraints, (3) a recursive derivative computation scheme based on B-spline basis functions, effectively constraining higher-order derivatives and reducing noise sensitivity on second-order dynamical systems. The proposed method demonstrates superior performance and enables more accurate and reliable extraction of physical laws from noisy data, particularly in complex mechanical systems compared to baseline methods.

---

### Co-EPG: A Framework for Co-Evolution of Planning and Grounding in Autonomous GUI Agents

Authors: Yuan Zhao, Hualei Zhu, Tingyu Jiang, Shen Li, Xiaohang Xu, Hao Henry Wang
Published: 2025-11-13
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2511.10705v1

Graphical User Interface (GUI) task automation constitutes a critical frontier in artificial intelligence research. While effective GUI agents synergistically integrate planning and grounding capabilities, current methodologies exhibit two fundamental limitations: (1) insufficient exploitation of cross-model synergies, and (2) over-reliance on synthetic data generation without sufficient utilization. To address these challenges, we propose Co-EPG, a self-iterative training framework for Co-Evolution of Planning and Grounding. Co-EPG establishes an iterative positive feedback loop: through this loop, the planning model explores superior strategies under grounding-based reward guidance via Group Relative Policy Optimization (GRPO), generating diverse data to optimize the grounding model. Concurrently, the optimized Grounding model provides more effective rewards for subsequent GRPO training of the planning model, fostering continuous improvement. Co-EPG thus enables iterative enhancement of agent capabilities through self-play optimization and training data distillation. On the Multimodal-Mind2Web and AndroidControl benchmarks, our framework outperforms existing state-of-the-art methods after just three iterations without requiring external data. The agent consistently improves with each iteration, demonstrating robust self-enhancement capabilities. This work establishes a novel training paradigm for GUI agents, shifting from isolated optimization to an integrated, self-driven co-evolution approach.

---

### The Second Law of Intelligence: Controlling Ethical Entropy in Autonomous Systems

Authors: Samih Fadli
Published: 2025-11-13
Categories: cs.AI
arXiv: https://arxiv.org/abs/2511.10704v1

We propose that unconstrained artificial intelligence obeys a Second Law analogous to thermodynamics, where ethical entropy, defined as a measure of divergence from intended goals, increases spontaneously without continuous alignment work. For gradient-based optimizers, we define this entropy over a finite set of goals {g_i} as S = -Σ p(g_i; theta) ln p(g_i; theta), and we prove that its time derivative dS/dt >= 0, driven by exploration noise and specification gaming. We derive the critical stability boundary for alignment work as gamma_crit = (lambda_max / 2) ln N, where lambda_max is the dominant eigenvalue of the Fisher Information Matrix and N is the number of model parameters. Simulations validate this theory. A 7-billion-parameter model (N = 7 x 10^9) with lambda_max = 1.2 drifts from an initial entropy of 0.32 to 1.69 +/- 1.08 nats, while a system regularized with alignment work gamma = 20.4 (1.5 gamma_crit) maintains stability at 0.00 +/- 0.00 nats (p = 4.19 x 10^-17, n = 20 trials). This framework recasts AI alignment as a problem of continuous thermodynamic control, providing a quantitative foundation for maintaining the stability and safety of advanced autonomous systems.

---

### Enhancing the Outcome Reward-based RL Training of MLLMs with Self-Consistency Sampling

Authors: Jiahao Wang, Weiye Xu, Aijun Yang, Wengang Zhou, Lewei Lu, Houqiang Li, Xiaohua Wang, Jinguo Zhu
Published: 2025-11-13
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.10648v1

Outcome-reward reinforcement learning (RL) is a common and increasingly significant way to refine the step-by-step reasoning of multimodal large language models (MLLMs). In the multiple-choice setting - a dominant format for multimodal reasoning benchmarks - the paradigm faces a significant yet often overlooked obstacle: unfaithful trajectories that guess the correct option after a faulty chain of thought receive the same reward as genuine reasoning, which is a flaw that cannot be ignored. We propose Self-Consistency Sampling (SCS) to correct this issue. For each question, SCS (i) introduces small visual perturbations and (ii) performs repeated truncation and resampling of an initial trajectory; agreement among the resulting trajectories yields a differentiable consistency score that down-weights unreliable traces during policy updates. Based on Qwen2.5-VL-7B-Instruct, plugging SCS into RLOO, GRPO, and REINFORCE++ series improves accuracy by up to 7.7 percentage points on six multimodal benchmarks with negligible extra computation. SCS also yields notable gains on both Qwen2.5-VL-3B-Instruct and InternVL3-8B, offering a simple, general remedy for outcome-reward RL in MLLMs.

---

### Depth Anything 3: Recovering the Visual Space from Any Views

Authors: Haotong Lin, Sili Chen, Junhao Liew, Donny Y. Chen, Zhenyu Li, Guang Shi, Jiashi Feng, Bingyi Kang
Published: 2025-11-13
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.10647v1

We present Depth Anything 3 (DA3), a model that predicts spatially consistent geometry from an arbitrary number of visual inputs, with or without known camera poses. In pursuit of minimal modeling, DA3 yields two key insights: a single plain transformer (e.g., vanilla DINO encoder) is sufficient as a backbone without architectural specialization, and a singular depth-ray prediction target obviates the need for complex multi-task learning. Through our teacher-student training paradigm, the model achieves a level of detail and generalization on par with Depth Anything 2 (DA2). We establish a new visual geometry benchmark covering camera pose estimation, any-view geometry and visual rendering. On this benchmark, DA3 sets a new state-of-the-art across all tasks, surpassing prior SOTA VGGT by an average of 44.3% in camera pose accuracy and 25.1% in geometric accuracy. Moreover, it outperforms DA2 in monocular depth estimation. All models are trained exclusively on public academic datasets.

---

### ParoQuant: Pairwise Rotation Quantization for Efficient Reasoning LLM Inference

Authors: Yesheng Liang, Haisheng Chen, Zihan Zhang, Song Han, Zhijian Liu
Published: 2025-11-13
Categories: cs.CL
arXiv: https://arxiv.org/abs/2511.10645v2

Post-training quantization (PTQ) compresses the weights and activations of large language models (LLMs) into low-precision representations to reduce memory footprint and accelerate inference. However, the presence of outliers in weights and activations often leads to large quantization errors and severe accuracy degradation, especially in recent reasoning LLMs where errors accumulate across long chains of thought. Existing PTQ methods either fail to sufficiently suppress outliers or introduce significant overhead during inference. In this paper, we propose Pairwise Rotation Quantization (ParoQuant), a PTQ method that combines hardware-efficient and optimizable independent Givens rotations with channel-wise scaling to even out the magnitudes across channels and narrow the dynamic range within each quantization group, effectively addressing the outlier issue. We further co-design the inference kernel to fully exploit GPU parallelism and keep the rotations and scaling lightweight at runtime. Under weight-only quantization, ParoQuant achieves an average 2.4% accuracy improvement over AWQ on reasoning tasks, with less than 10% overhead. ParoQuant also matches the accuracy of state-of-the-art weight-activation quantization methods. This paves the way for more efficient and accurate deployment of reasoning LLMs.

---

### ParoQuant: Pairwise Rotation Quantization for Efficient Reasoning LLM Inference

Authors: Yesheng Liang, Haisheng Chen, Song Han, Zhijian Liu
Published: 2025-11-13
Categories: cs.CL
arXiv: https://arxiv.org/abs/2511.10645v1

Weight-only post-training quantization (PTQ) compresses the weights of Large Language Models (LLMs) into low-precision representations to reduce memory footprint and accelerate inference. However, the presence of outliers in weights and activations often leads to large quantization errors and severe accuracy degradation, especially in recent reasoning LLMs where errors accumulate across long chains of thought. Existing PTQ methods either fail to sufficiently suppress outliers or introduce significant overhead during inference. In this paper, we propose Pairwise Rotation Quantization (ParoQuant), a weight-only PTQ method that combines hardware-efficient and optimizable independent Givens rotations with channel-wise scaling to even out the magnitude across channels and narrow the dynamic range within each quantization group. We further co-design the inference kernel to fully exploit GPU parallelism and keep the rotations and scaling lightweight at runtime. ParoQuant achieves an average 2.4% accuracy improvement over AWQ on reasoning tasks with less than 10% overhead. This paves the way for more efficient and accurate deployment of reasoning LLMs.

---

### Black-Box On-Policy Distillation of Large Language Models

Authors: Tianzhu Ye, Li Dong, Zewen Chi, Xun Wu, Shaohan Huang, Furu Wei
Published: 2025-11-13
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2511.10643v3

Black-box distillation creates student large language models (LLMs) by learning from a proprietary teacher model's text outputs alone, without access to its internal logits or parameters. In this work, we introduce Generative Adversarial Distillation (GAD), which enables on-policy and black-box distillation. GAD frames the student LLM as a generator and trains a discriminator to distinguish its responses from the teacher LLM's, creating a minimax game. The discriminator acts as an on-policy reward model that co-evolves with the student, providing stable, adaptive feedback. Experimental results show that GAD consistently surpasses the commonly used sequence-level knowledge distillation. In particular, Qwen2.5-14B-Instruct (student) trained with GAD becomes comparable to its teacher, GPT-5-Chat, on the LMSYS-Chat automatic evaluation. The results establish GAD as a promising and effective paradigm for black-box LLM distillation.

---

### Black-Box On-Policy Distillation of Large Language Models

Authors: Tianzhu Ye, Li Dong, Zewen Chi, Xun Wu, Shaohan Huang, Furu Wei
Published: 2025-11-13
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2511.10643v1

Black-box distillation creates student large language models (LLMs) by learning from a proprietary teacher model's text outputs alone, without access to its internal logits or parameters. In this work, we introduce Generative Adversarial Distillation (GAD), which enables on-policy and black-box distillation. GAD frames the student LLM as a generator and trains a discriminator to distinguish its responses from the teacher LLM's, creating a minimax game. The discriminator acts as an on-policy reward model that co-evolves with the student, providing stable, adaptive feedback. Experimental results show that GAD consistently surpasses the commonly used sequence-level knowledge distillation. In particular, Qwen2.5-14B-Instruct (student) trained with GAD becomes comparable to its teacher, GPT-5-Chat, on the LMSYS-Chat automatic evaluation. The results establish GAD as a promising and effective paradigm for black-box LLM distillation.

---

### Robot Crash Course: Learning Soft and Stylized Falling

Authors: Pascal Strauch, David Müller, Sammy Christen, Agon Serifi, Ruben Grandia, Espen Knoop, Moritz Bächer
Published: 2025-11-13
Categories: cs.RO, cs.LG
arXiv: https://arxiv.org/abs/2511.10635v1

Despite recent advances in robust locomotion, bipedal robots operating in the real world remain at risk of falling. While most research focuses on preventing such events, we instead concentrate on the phenomenon of falling itself. Specifically, we aim to reduce physical damage to the robot while providing users with control over a robot's end pose. To this end, we propose a robot agnostic reward function that balances the achievement of a desired end pose with impact minimization and the protection of critical robot parts during reinforcement learning. To make the policy robust to a broad range of initial falling conditions and to enable the specification of an arbitrary and unseen end pose at inference time, we introduce a simulation-based sampling strategy of initial and end poses. Through simulated and real-world experiments, our work demonstrates that even bipedal robots can perform controlled, soft falls.

---

### One Small Step in Latent, One Giant Leap for Pixels: Fast Latent Upscale Adapter for Your Diffusion Models

Authors: Aleksandr Razin, Danil Kazantsev, Ilya Makarov
Published: 2025-11-13
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.10629v2

Diffusion models struggle to scale beyond their training resolutions, as direct high-resolution sampling is slow and costly, while post-hoc image super-resolution (ISR) introduces artifacts and additional latency by operating after decoding. We present the Latent Upscaler Adapter (LUA), a lightweight module that performs super-resolution directly on the generator's latent code before the final VAE decoding step. LUA integrates as a drop-in component, requiring no modifications to the base model or additional diffusion stages, and enables high-resolution synthesis through a single feed-forward pass in latent space. A shared Swin-style backbone with scale-specific pixel-shuffle heads supports 2x and 4x factors and remains compatible with image-space SR baselines, achieving comparable perceptual quality with nearly 3x lower decoding and upscaling time (adding only +0.42 s for 1024 px generation from 512 px, compared to 1.87 s for pixel-space SR using the same SwinIR architecture). Furthermore, LUA shows strong generalization across the latent spaces of different VAEs, making it easy to deploy without retraining from scratch for each new decoder. Extensive experiments demonstrate that LUA closely matches the fidelity of native high-resolution generation while offering a practical and efficient path to scalable, high-fidelity image synthesis in modern diffusion pipelines.

---