# Research Papers — 2025-11 · bundle page 35 of 197

> Full-text markdown of papers #1701–1750 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/35
[← Previous bundle](https://aipod.dev/papers/archive/2025-11/page/34.md)
[Next bundle →](https://aipod.dev/papers/archive/2025-11/page/36.md)

### Adversarial Confusion Attack: Disrupting Multimodal Large Language Models

Authors: Jakub Hoscilowicz, Artur Janicki
Published: 2025-11-25
Categories: cs.CL
arXiv: https://arxiv.org/abs/2511.20494v3

We introduce the Adversarial Confusion Attack, a new class of threats against multimodal large language models (MLLMs). Unlike jailbreaks or targeted misclassification, the goal is to induce systematic disruption that makes the model generate incoherent or confidently incorrect outputs. Practical applications include embedding such adversarial images into websites to prevent MLLM-powered AI Agents from operating reliably. The proposed attack maximizes next-token entropy using a small ensemble of open-source MLLMs. In the white-box setting, we show that a single adversarial image can disrupt all models in the ensemble, both in the full-image and Adversarial CAPTCHA settings. Despite relying on a basic adversarial technique (PGD), the attack generates perturbations that transfer to both unseen open-source (e.g., Qwen3-VL) and proprietary (e.g., GPT-5.1) models.

---

### MTBBench: A Multimodal Sequential Clinical Decision-Making Benchmark in Oncology

Authors: Kiril Vasilev, Alexandre Misrahi, Eeshaan Jain, Phil F Cheng, Petros Liakopoulos, Olivier Michielin, Michael Moor, Charlotte Bunne
Published: 2025-11-25
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2511.20490v1

Multimodal Large Language Models (LLMs) hold promise for biomedical reasoning, but current benchmarks fail to capture the complexity of real-world clinical workflows. Existing evaluations primarily assess unimodal, decontextualized question-answering, overlooking multi-agent decision-making environments such as Molecular Tumor Boards (MTBs). MTBs bring together diverse experts in oncology, where diagnostic and prognostic tasks require integrating heterogeneous data and evolving insights over time. Current benchmarks lack this longitudinal and multimodal complexity. We introduce MTBBench, an agentic benchmark simulating MTB-style decision-making through clinically challenging, multimodal, and longitudinal oncology questions. Ground truth annotations are validated by clinicians via a co-developed app, ensuring clinical relevance. We benchmark multiple open and closed-source LLMs and show that, even at scale, they lack reliability -- frequently hallucinating, struggling with reasoning from time-resolved data, and failing to reconcile conflicting evidence or different modalities. To address these limitations, MTBBench goes beyond benchmarking by providing an agentic framework with foundation model-based tools that enhance multi-modal and longitudinal reasoning, leading to task-level performance gains of up to 9.0% and 11.2%, respectively. Overall, MTBBench offers a challenging and realistic testbed for advancing multimodal LLM reasoning, reliability, and tool-use with a focus on MTB environments in precision oncology.

---

### InferF: Declarative Factorization of AI/ML Inferences over Joins

Authors: Kanchan Chowdhury, Lixi Zhou, Lulu Xie, Xinwei Fu, Jia Zou
Published: 2025-11-25
Categories: cs.DB, cs.LG
arXiv: https://arxiv.org/abs/2511.20489v1

Real-world AI/ML workflows often apply inference computations to feature vectors joined from multiple datasets. To avoid the redundant AI/ML computations caused by repeated data records in the join's output, factorized ML has been proposed to decompose ML computations into sub-computations to be executed on each normalized dataset. However, there is insufficient discussion on how factorized ML could impact AI/ML inference over multi-way joins. To address the limitations, we propose a novel declarative InferF system, focusing on the factorization of arbitrary inference workflows represented as analyzable expressions over the multi-way joins. We formalize our problem to flexibly push down partial factorized computations to qualified nodes in the join tree to minimize the overall inference computation and join costs and propose two algorithms to resolve the problem: (1) a greedy algorithm based on a per-node cost function that estimates the influence on overall latency if a subset of factorized computations is pushed to a node, and (2) a genetic algorithm for iteratively enumerating and evaluating promising factorization plans. We implement InferF on Velox, an open-sourced database engine from Meta, evaluate it on real-world datasets, observed up to 11.3x speedups, and systematically summarized the factors that determine when factorized ML can benefit AI/ML inference workflows.

---

### Ranking-Enhanced Anomaly Detection Using Active Learning-Assisted Attention Adversarial Dual AutoEncoders

Authors: Sidahmed Benabderrahmane, James Cheney, Talal Rahwan
Published: 2025-11-25
Categories: cs.LG, cs.AI, cs.CR, cs.NE
arXiv: https://arxiv.org/abs/2511.20480v1

Advanced Persistent Threats (APTs) pose a significant challenge in cybersecurity due to their stealthy and long-term nature. Modern supervised learning methods require extensive labeled data, which is often scarce in real-world cybersecurity environments. In this paper, we propose an innovative approach that leverages AutoEncoders for unsupervised anomaly detection, augmented by active learning to iteratively improve the detection of APT anomalies. By selectively querying an oracle for labels on uncertain or ambiguous samples, we minimize labeling costs while improving detection rates, enabling the model to improve its detection accuracy with minimal data while reducing the need for extensive manual labeling. We provide a detailed formulation of the proposed Attention Adversarial Dual AutoEncoder-based anomaly detection framework and show how the active learning loop iteratively enhances the model. The framework is evaluated on real-world imbalanced provenance trace databases produced by the DARPA Transparent Computing program, where APT-like attacks constitute as little as 0.004\% of the data. The datasets span multiple operating systems, including Android, Linux, BSD, and Windows, and cover two attack scenarios. The results have shown significant improvements in detection rates during active learning and better performance compared to other existing approaches.

---

### NVIDIA Nemotron Parse 1.1

Authors: Kateryna Chumachenko, Amala Sanjay Deshmukh, Jarno Seppanen, Ilia Karmanov, Chia-Chih Chen, Lukas Voegtle, Philipp Fischer, Marek Wawrzos, Saeid Motiian, Roman Ageev, Kedi Wu, Alexandre Milesi et al.
Published: 2025-11-25
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.20478v1

We introduce Nemotron-Parse-1.1, a lightweight document parsing and OCR model that advances the capabilities of its predecessor, Nemoretriever-Parse-1.0. Nemotron-Parse-1.1 delivers improved capabilities across general OCR, markdown formatting, structured table parsing, and text extraction from pictures, charts, and diagrams. It also supports a longer output sequence length for visually dense documents. As with its predecessor, it extracts bounding boxes of text segments, as well as corresponding semantic classes. Nemotron-Parse-1.1 follows an encoder-decoder architecture with 885M parameters, including a compact 256M-parameter language decoder. It achieves competitive accuracy on public benchmarks making it a strong lightweight OCR solution. We release the model weights publicly on Huggingface, as well as an optimized NIM container, along with a subset of the training data as part of the broader Nemotron-VLM-v2 dataset. Additionally, we release Nemotron-Parse-1.1-TC which operates on a reduced vision token length, offering a 20% speed improvement with minimal quality degradation.

---

### Modular Deep Learning Framework for Assistive Perception: Gaze, Affect, and Speaker Identification

Authors: Akshit Pramod Anchan, Jewelith Thomas, Sritama Roy
Published: 2025-11-25
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2511.20474v1

Developing comprehensive assistive technologies requires the seamless integration of visual and auditory perception. This research evaluates the feasibility of a modular architecture inspired by core functionalities of perceptive systems like 'Smart Eye.' We propose and benchmark three independent sensing modules: a Convolutional Neural Network (CNN) for eye state detection (drowsiness/attention), a deep CNN for facial expression recognition, and a Long Short-Term Memory (LSTM) network for voice-based speaker identification. Utilizing the Eyes Image, FER2013, and customized audio datasets, our models achieved accuracies of 93.0%, 97.8%, and 96.89%, respectively. This study demonstrates that lightweight, domain-specific models can achieve high fidelity on discrete tasks, establishing a validated foundation for future real-time, multimodal integration in resource-constrained assistive devices.

---

### Universe of Thoughts: A Computational Framework for Creative Reasoning in Large Language Models

Authors: Yuto Suzuki, Farnoush Banaei-Kashani
Published: 2025-11-25
Categories: cs.AI
arXiv: https://arxiv.org/abs/2511.20471v3

Recent advances in Large Language Model (LLM) reasoning have improved conventional problem solving, but creative reasoning remains comparatively underexplored. Inspired by cognitive science, we formalize combinational, exploratory, and transformational creativity as executable computational operators over structured problem and solution spaces, specifying how each mode combines, explores, or transforms those spaces. Combinational reasoning transfers ideas across domains to form unfamiliar combinations; exploratory reasoning searches for new solutions within an existing conceptual space; and transformational reasoning modifies the rules or constraints that define that space. This formalization yields distinct algorithmic procedures, which we instantiate in Universe of Thoughts (UoT), an LLM reasoning framework. Existing creativity benchmarks emphasize either open-ended ideation or highly constrained problem solving. We therefore introduce three novel creative-reasoning tasks requiring concrete solutions in low-constraint settings. Across 10 generations per method and task, T-UoT with GPT-4o performs strongest on the low-constraint, high-objective-specificity Bridge and Electricity tasks, while C-UoT shows its strongest relative performance on the low-constraint, lower-objective-specificity Society task. In addition, we evaluate UoT on HypoArena, an independent scientific hypothesis-generation benchmark with 100 tasks across biomedical, machine-learning, and social-science domains. With Qwen3-14B, Exploratory UoT ranks first among seven reasoning methods, achieving a 32.7\% pairwise win rate compared with 25.5\% for the next-best method. Our results suggest distinct performance patterns across task structures: T-UoT is strongest in low-constraint, high-specificity settings, E-UoT in more constrained, high-specificity settings, and C-UoT in low-constraint, lower-specificity settings.

---

### Efficient and Fast Generative-Based Singing Voice Separation using a Latent Diffusion Model

Authors: Genís Plaja-Roglans, Yun-Ning Hung, Xavier Serra, Igor Pereira
Published: 2025-11-25
Categories: cs.SD, cs.AI
arXiv: https://arxiv.org/abs/2511.20470v1

Extracting individual elements from music mixtures is a valuable tool for music production and practice. While neural networks optimized to mask or transform mixture spectrograms into the individual source(s) have been the leading approach, the source overlap and correlation in music signals poses an inherent challenge. Also, accessing all sources in the mixture is crucial to train these systems, while complicated. Attempts to address these challenges in a generative fashion exist, however, the separation performance and inference efficiency remain limited. In this work, we study the potential of diffusion models to advance toward bridging this gap, focusing on generative singing voice separation relying only on corresponding pairs of isolated vocals and mixtures for training. To align with creative workflows, we leverage latent diffusion: the system generates samples encoded in a compact latent space, and subsequently decodes these into audio. This enables efficient optimization and faster inference. Our system is trained using only open data. We outperform existing generative separation systems, and level the compared non-generative systems on a list of signal quality measures and on interference removal. We provide a noise robustness study on the latent encoder, providing insights on its potential for the task. We release a modular toolkit for further research on the topic.

---

### Dance Style Classification using Laban-Inspired and Frequency-Domain Motion Features

Authors: Ben Hamscher, Arnold Brosch, Nicolas Binninger, Maksymilian Jan Dejna, Kira Maag
Published: 2025-11-25
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2511.20469v1

Dance is an essential component of human culture and serves as a tool for conveying emotions and telling stories. Identifying and distinguishing dance genres based on motion data is a complex problem in human activity recognition, as many styles share similar poses, gestures, and temporal motion patterns. This work presents a lightweight framework for classifying dance styles that determines motion characteristics based on pose estimates extracted from videos. We propose temporal-spatial descriptors inspired by Laban Movement Analysis. These features capture local joint dynamics such as velocity, acceleration, and angular movement of the upper body, enabling a structured representation of spatial coordination. To further encode rhythmic and periodic aspects of movement, we integrate Fast Fourier Transform features that characterize movement patterns in the frequency domain. The proposed approach achieves robust classification of different dance styles with low computational effort, as complex model architectures are not required, and shows that interpretable motion representations can effectively capture stylistic nuances.

---

### DRAFT-RL: Multi-Agent Chain-of-Draft Reasoning for Reinforcement Learning-Enhanced LLMs

Authors: Yuanhao Li, Mingshan Liu, Hongbo Wang, Yiding Zhang, Yifei Ma, Wei Tan
Published: 2025-11-25
Categories: cs.AI
arXiv: https://arxiv.org/abs/2511.20468v1

Large Language Models (LLMs) have shown impressive capabilities in multi-step reasoning and problem-solving.Recent works introduce multi-agent reflection frameworks where multiple LLM agents critique and refine each other's outputs using reinforcement learning (RL). However, these approaches often rely on single-shot responses and lack structural diversity in reasoning exploration. In this paper, we propose DRAFT-RL, a novel framework that integrates Chain-of-Draft (CoD) reasoning into multi-agent RL training. Instead of generating single responses, each agent produces multiple drafts per query, which are then evaluated by peer agents and a learned reward model to identify the most promising trajectory. These selected drafts are used to refine future reasoning strategies through actor-critic learning.DRAFT-RL enables explicit multi-path exploration, peer-guided reflection, and reward-aligned selection, resulting in more robust and interpretable LLM agent behavior. We evaluate our method on complex reasoning tasks including code synthesis, symbolic math, and knowledge-intensive QA,demonstrating that DRAFT-RL outperforms existing reflective and RL-based agents by significant margins in both accuracy and convergence speed

---

### STARFlow-V: End-to-End Video Generative Modeling with Normalizing Flows

Authors: Jiatao Gu, Ying Shen, Tianrong Chen, Laurent Dinh, Yuyang Wang, Miguel Angel Bautista, David Berthelot, Josh Susskind, Shuangfei Zhai
Published: 2025-11-25
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2511.20462v2

Normalizing flows (NFs) are end-to-end likelihood-based generative models for continuous data, and have recently regained attention with encouraging progress on image generation. Yet in the video generation domain, where spatiotemporal complexity and computational cost are substantially higher, state-of-the-art systems almost exclusively rely on diffusion-based models. In this work, we revisit this design space by presenting STARFlow-V, a normalizing flow-based video generator with substantial benefits such as end-to-end learning, robust causal prediction, and native likelihood estimation. Building upon the recently proposed STARFlow, STARFlow-V operates in the spatiotemporal latent space with a global-local architecture which restricts causal dependencies to a global latent space while preserving rich local within-frame interactions. This eases error accumulation over time, a common pitfall of standard autoregressive diffusion model generation. Additionally, we propose flow-score matching, which equips the model with a light-weight causal denoiser to improve the video generation consistency in an autoregressive fashion. To improve the sampling efficiency, STARFlow-V employs a video-aware Jacobi iteration scheme that recasts inner updates as parallelizable iterations without breaking causality. Thanks to the invertible structure, the same model can natively support text-to-video, image-to-video as well as video-to-video generation tasks. Empirically, STARFlow-V achieves strong visual fidelity and temporal consistency with practical sampling throughput relative to diffusion-based baselines. These results present the first evidence, to our knowledge, that NFs are capable of high-quality autoregressive video generation, establishing them as a promising research direction for building world models. Code and generated samples are available at https://github.com/apple/ml-starflow.

---

### Look Where It Matters: Training-Free Ultra-HR Remote Sensing VQA via Adaptive Zoom Search

Authors: Yunqi Zhou, Chengjie Jiang, Chun Yuan, Jing Li
Published: 2025-11-25
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.20460v2

With advances in satellite constellations, sensor technologies, and imaging pipelines, ultra-high-resolution (Ultra-HR) remote sensing imagery is becoming increasingly widespread. However, current remote sensing foundation models are ill-suited to such inputs: full-image encoding exhausts token and memory budgets, while resize-based preprocessing loses fine-grained and answer-critical details. In this context, guiding the model look where it matters before prediction becomes crucial. Therefore, we present ZoomSearch, a training-free, plug-and-play pipeline that decouples 'where to look' from 'how to answer' for Ultra-HR Remote Sensing Visual Question Answering (RS-VQA). ZoomSearch combines Adaptive Multi-Branch Zoom Search, which performs a hierarchical search over image patches to localize query-relevant regions, with Layout-Aware Patch Reassembly, which reorganizes the selected patches into a compact, layout-faithful canvas. We conduct comprehensive experiments on Ultra-HR RS-VQA benchmarks MME-RealWorld-RS and LRS-VQA, comparing against (i) strong general foundation models, (ii) remote sensing foundation models, (iii) Ultra-HR RS-VQA methods, and (iv) plug-and-play search-based VQA methods. When integrated with LLaVA-ov, ZoomSearch attains state-of-the-art accuracy across diverse tasks, improving the LLaVA-ov baseline by 26.3% on LRS-VQA and 114.8% on MME-RealWorld-RS. Meanwhile, it achieves much higher inference efficiency, outperforming prior search-based methods by 20%~44% in speed.

---

### Generation, Evaluation, and Explanation of Novelists' Styles with Single-Token Prompts

Authors: Mosab Rezaei, Mina Rajaei Moghadam, Abdul Rahman Shaikh, Hamed Alhoori, Reva Freedman
Published: 2025-11-25
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2511.20459v1

Recent advances in large language models have created new opportunities for stylometry, the study of writing styles and authorship. Two challenges, however, remain central: training generative models when no paired data exist, and evaluating stylistic text without relying only on human judgment. In this work, we present a framework for both generating and evaluating sentences in the style of 19th-century novelists. Large language models are fine-tuned with minimal, single-token prompts to produce text in the voices of authors such as Dickens, Austen, Twain, Alcott, and Melville. To assess these generative models, we employ a transformer-based detector trained on authentic sentences, using it both as a classifier and as a tool for stylistic explanation. We complement this with syntactic comparisons and explainable AI methods, including attention-based and gradient-based analyses, to identify the linguistic cues that drive stylistic imitation. Our findings show that the generated text reflects the authors' distinctive patterns and that AI-based evaluation offers a reliable alternative to human assessment. All artifacts of this work are published online.

---

### A Fully Probabilistic Tensor Network for Regularized Volterra System Identification

Authors: Afra Kilic, Kim Batselier
Published: 2025-11-25
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2511.20457v1

Modeling nonlinear systems with Volterra series is challenging because the number of kernel coefficients grows exponentially with the model order. This work introduces Bayesian Tensor Network Volterra kernel machines (BTN-V), extending the Bayesian Tensor Network framework to Volterra system identification. BTN-V represents Volterra kernels using canonical polyadic decomposition, reducing model complexity from O(I^D) to O(DIR). By treating all tensor components and hyperparameters as random variables, BTN-V provides predictive uncertainty estimation at no additional computational cost. Sparsity-inducing hierarchical priors enable automatic rank determination and the learning of fading-memory behavior directly from data, improving interpretability and preventing overfitting. Empirical results demonstrate competitive accuracy, enhanced uncertainty quantification, and reduced computational cost.

---

### Towards Trustworthy Wi-Fi CSI-based Sensing: Systematic Evaluation of Adversarial Robustness

Authors: Shreevanth Krishnaa Gopalakrishnan, Stephen Hailes
Published: 2025-11-25
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.20456v2

Machine learning drives Channel State Information (CSI)-based human sensing in modern wireless networks, enabling applications like device-free human activity recognition (HAR) and identification (HID). However, the susceptibility of these models to adversarial perturbations raises security concerns that must be quantified prior to edge deployment. We present a systematic robustness evaluation of five diverse CSI architectures across four public datasets, jointly analyzing white-box, black-box transfer, and universal attacks, together with defense strategies, under unconstrained and physics-guided perturbation boundaries. Contrary to prior assumptions, our experiments reveal that model capacity does not guarantee robustness; simple architectures consistently exhibit superior resilience compared to high-capacity sequence and vision models. Furthermore, vulnerability is fundamentally task-dependent, with HAR proving highly susceptible to attack, while HID demonstrates stark inherent resistance. Crucially, enforcing physical signal constraints drastically reduces attack success rates and significantly taxes attacker computation, showing that standard unconstrained feature-space attacks substantially overestimate real-world Over-The-Air vulnerabilities. By synthesizing attack, defense, and security metrics with strict edge hardware considerations, this work establishes foundational design principles for secure, deployable, and physically realizable wireless sensing systems.

---

### Learning to Generate Human-Human-Object Interactions from Textual Descriptions

Authors: Jeonghyeon Na, Sangwon Baik, Inhee Lee, Junyoung Lee, Hanbyul Joo
Published: 2025-11-25
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.20446v3

The way humans interact with each other, including interpersonal distances, spatial configuration, and motion, varies significantly across different situations. To enable machines to understand such complex, context-dependent behaviors, it is essential to model multiple people in relation to the surrounding scene context. In this paper, we present a novel research problem to model the correlations between two people engaged in a shared interaction involving an object. We refer to this formulation as Human-Human-Object Interactions (HHOIs). To overcome the lack of dedicated datasets for HHOIs, we present a newly captured HHOIs dataset and a method to synthesize HHOI data by leveraging image generative models. As an intermediary, we obtain individual human-object interaction (HOIs) and human-human interaction (HHIs) from the HHOIs, and with these data, we train an text-to-HOI and text-to-HHI model using score-based diffusion model. Finally, we present a unified generative framework that integrates the two individual model, capable of synthesizing complete HHOIs in a single advanced sampling process. Our method extends HHOI generation to multi-human settings, enabling interactions involving more than two individuals. Experimental results show that our method generates realistic HHOIs conditioned on textual descriptions, outperforming previous approaches that focus only on single-human HOIs. Furthermore, we introduce multi-human motion generation involving objects as an application of our framework.

---

### Diffusion for Fusion: Designing Stellarators with Generative AI

Authors: Misha Padidar, Teresa Huang, Andrew Giuliani, Marina Spivak
Published: 2025-11-25
Categories: cs.LG, physics.plasm-ph
arXiv: https://arxiv.org/abs/2511.20445v2

Stellarators are a prospective class of fusion-based power plants that confine a hot plasma with three-dimensional magnetic fields. Typically framed as a PDE-constrained optimization problem, stellarator design is a time-consuming process that can take hours to solve on a computing cluster. Developing fast methods for designing stellarators is crucial for advancing fusion research. Given the recent development of large datasets of optimized stellarators, machine learning approaches have emerged as a potential candidate. Motivated by this, we present an open inverse problem to the machine learning community: to rapidly generate high-quality stellarator designs which have a set of desirable characteristics. As a case study in the problem space, we train a conditional diffusion model on data from the QUASR database to generate quasisymmetric stellarator designs with desirable characteristics (aspect ratio and mean rotational transform). The diffusion model is applied to design stellarators with characteristics not seen during training. We provide evaluation protocols and show that many of the generated stellarators exhibit solid performance: less than 5% deviation from quasisymmetry and the target characteristics. The modest deviation from quasisymmetry highlights an opportunity to reach the sub 1% target. Beyond the case study, we share multiple promising avenues for generative modeling to advance stellarator design.

---

### Object-Centric Vision Token Pruning for Vision Language Models

Authors: Guangyuan Li, Rongzhen Zhao, Jinhong Deng, Yanbo Wang, Joni Pajarinen
Published: 2025-11-25
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2511.20439v2

In Vision Language Models (VLMs), vision tokens are quantity-heavy yet information-dispersed compared with language tokens, thus consume too much unnecessary computation. Pruning redundant vision tokens for high VLM inference efficiency has been continuously studied but all existing methods resort to indirect and non-guaranteed ways. We propose OC-VTP, a direct and guaranteed approach to select the most representative vision tokens for high-efficiency yet accuracy-preserving VLM inference. Our OC-VTP requires merely light-weight pre-training of a small object-centric vision token pruner, which can then be inserted into existing VLMs, without fine-tuning of any models on any datasets. It is gauranteed that the most representative vision tokens are kept by minimizing the error in reconstructing the original unpruned tokens from the selected ones. Across any vision pruning ratios, i.e., inference efficiency, our OC-VTP consistently helps mainstream VLMs to preserve the highest inference accuracy. Our pruning also demonstrates interesting interpretability. Our codes are available at https://github.com/GarryLarry010131/OC-VTP.

---

### BRIC: Bridging Kinematic Plans and Physical Control at Test Time

Authors: Dohun Lim, Minji Kim, Jaewoon Lim, Sungchan Kim
Published: 2025-11-25
Categories: cs.CV, cs.RO
arXiv: https://arxiv.org/abs/2511.20431v3

We propose BRIC, a novel test-time adaptation (TTA) framework that enables long-term human motion generation by resolving execution discrepancies between diffusion-based kinematic motion planners and reinforcement learning-based physics controllers. While diffusion models can generate diverse and expressive motions conditioned on text and scene context, they often produce physically implausible outputs, leading to execution drift during simulation. To address this, BRIC dynamically adapts the physics controller to noisy motion plans at test time, while preserving pre-trained skills via a loss function that mitigates catastrophic forgetting. In addition, BRIC introduces a lightweight test-time guidance mechanism that steers the diffusion model in the signal space without updating its parameters. By combining both adaptation strategies, BRIC ensures consistent and physically plausible long-term executions across diverse environments in an effective and efficient manner. We validate the effectiveness of BRIC on a variety of long-term tasks, including motion composition, obstacle avoidance, and human-scene interaction, achieving state-of-the-art performance across all tasks.

---

### Block Cascading: Training Free Acceleration of Block-Causal Video Models

Authors: Hmrishav Bandyopadhyay, Nikhil Pinnaparaju, Rahim Entezari, Jim Scott, Yi-Zhe Song, Varun Jampani
Published: 2025-11-25
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2511.20426v1

Block-causal video generation faces a stark speed-quality trade-off: small 1.3B models manage only 16 FPS while large 14B models crawl at 4.5 FPS, forcing users to choose between responsiveness and quality. Block Cascading significantly mitigates this trade-off through training-free parallelization. Our key insight: future video blocks do not need fully denoised current blocks to begin generation. By starting block generation with partially denoised context from predecessors, we transform sequential pipelines into parallel cascades where multiple blocks denoise simultaneously. With 5 GPUs exploiting temporal parallelism, we achieve ~2x acceleration across all model scales: 1.3B models accelerate from 16 to 30 FPS, 14B models from 4.5 to 12.5 FPS. Beyond inference speed, Block Cascading eliminates overhead from KV-recaching (of ~200ms) during context switches for interactive generation. Extensive evaluations validated against multiple block-causal pipelines demonstrate no significant loss in generation quality when switching from block-causal to Block Cascading pipelines for inference. Project Page: https://hmrishavbandy.github.io/block_cascading_page/

---

### VibraVerse: A Large-Scale Geometry-Acoustics Alignment Dataset for Physically-Consistent Multimodal Learning

Authors: Bo Pang, Chenxi Xu, Jierui Ren, Guoping Wang, Sheng Li
Published: 2025-11-25
Categories: cs.AI, cs.CV, cs.GR, cs.RO
arXiv: https://arxiv.org/abs/2511.20422v1

Understanding the physical world requires perceptual models grounded in physical laws rather than mere statistical correlations. However, existing multimodal learning frameworks, focused on vision and language, lack physical consistency and overlook the intrinsic causal relationships among an object's geometry, material, vibration modes, and the sounds it produces. We introduce VibraVerse, a large-scale geometry-acoustics alignment dataset that explicitly bridges the causal chain from 3D geometry -> physical attributes -> modal parameters -> acoustic signals. Each 3D model has explicit physical properties (density, Young's modulus, Poisson's ratio) and volumetric geometry, from which modal eigenfrequencies and eigenvectors are computed for impact sound synthesis under controlled excitations. To establish this coherence, we introduce CLASP, a contrastive learning framework for cross-modal alignment that preserves the causal correspondence between an object's physical structure and its acoustic response. This framework enforces physically consistent alignment across modalities, ensuring that every sample is coherent, traceable to the governing equations, and embedded within a unified representation space spanning shape, image, and sound. Built upon VibraVerse, we define a suite of benchmark tasks for geometry-to-sound prediction, sound-guided shape reconstruction, and cross-modal representation learning. Extensive validations on these tasks demonstrate that models trained on VibraVerse exhibit superior accuracy, interpretability, and generalization across modalities. These results establish VibraVerse as a benchmark for physically consistent and causally interpretable multimodal learning, providing a foundation for sound-guided embodied perception and a deeper understanding of the physical world. The dataset will be open-sourced.

---

### StableTrack: Stabilizing Multi-Object Tracking on Low-Frequency Detections

Authors: Matvei Shelukhan, Timur Mamedov, Karina Kvanchiani
Published: 2025-11-25
Categories: cs.CV, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2511.20418v1

Multi-object tracking (MOT) is one of the most challenging tasks in computer vision, where it is important to correctly detect objects and associate these detections across frames. Current approaches mainly focus on tracking objects in each frame of a video stream, making it almost impossible to run the model under conditions of limited computing resources. To address this issue, we propose StableTrack, a novel approach that stabilizes the quality of tracking on low-frequency detections. Our method introduces a new two-stage matching strategy to improve the cross-frame association between low-frequency detections. We propose a novel Bbox-Based Distance instead of the conventional Mahalanobis distance, which allows us to effectively match objects using the Re-ID model. Furthermore, we integrate visual tracking into the Kalman Filter and the overall tracking pipeline. Our method outperforms current state-of-the-art trackers in the case of low-frequency detections, achieving $\textit{11.6%}$ HOTA improvement at $\textit{1}$ Hz on MOT17-val, while keeping up with the best approaches on the standard MOT17, MOT20, and DanceTrack benchmarks with full-frequency detections.

---

### MajutsuCity: Language-driven Aesthetic-adaptive City Generation with Controllable 3D Assets and Layouts

Authors: Zilong Huang, Jun He, Xiaobin Huang, Ziyi Xiong, Yang Luo, Junyan Ye, Weijia Li, Yiping Chen, Ting Han
Published: 2025-11-25
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.20415v2

Generating realistic 3D cities is fundamental to world models, virtual reality, and game development, where an ideal urban scene must satisfy both stylistic diversity, fine-grained, and controllability. However, existing methods struggle to balance the creative flexibility offered by text-based generation with the object-level editability enabled by explicit structural representations. We introduce MajutsuCity, a natural language-driven and aesthetically adaptive framework for synthesizing structurally consistent and stylistically diverse 3D urban scenes. MajutsuCity represents a city as a composition of controllable layouts, assets, and materials, and operates through a four-stage pipeline. To extend controllability beyond initial generation, we further integrate MajutsuAgent, an interactive language-grounded editing agent} that supports five object-level operations. To support photorealistic and customizable scene synthesis, we also construct MajutsuDataset, a high-quality multimodal dataset} containing 2D semantic layouts and height maps, diverse 3D building assets, and curated PBR materials and skyboxes, each accompanied by detailed annotations. Meanwhile, we develop a practical set of evaluation metrics, covering key dimensions such as structural consistency, scene complexity, material fidelity, and lighting atmosphere. Extensive experiments demonstrate MajutsuCity reduces layout FID by 83.7% compared with CityDreamer and by 20.1% over CityCraft. Our method ranks first across all AQS and RDR scores, outperforming existing methods by a clear margin. These results confirm MajutsuCity as a new state-of-the-art in geometric fidelity, stylistic adaptability, and semantic controllability for 3D city generation. We expect our framework can inspire new avenues of research in 3D city generation. Our project page: https://longhz140516.github.io/MajutsuCity/.

---

### MajutsuCity: Language-driven Aesthetic-adaptive City Generation with Controllable 3D Assets and Layouts

Authors: Zilong Huang, Jun He, Xiaobin Huang, Ziyi Xiong, Yang Luo, Junyan Ye, Weijia Li, Yiping Chen, Ting Han
Published: 2025-11-25
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.20415v1

Generating realistic 3D cities is fundamental to world models, virtual reality, and game development, where an ideal urban scene must satisfy both stylistic diversity, fine-grained, and controllability. However, existing methods struggle to balance the creative flexibility offered by text-based generation with the object-level editability enabled by explicit structural representations. We introduce MajutsuCity, a natural language-driven and aesthetically adaptive framework for synthesizing structurally consistent and stylistically diverse 3D urban scenes. MajutsuCity represents a city as a composition of controllable layouts, assets, and materials, and operates through a four-stage pipeline. To extend controllability beyond initial generation, we further integrate MajutsuAgent, an interactive language-grounded editing agent} that supports five object-level operations. To support photorealistic and customizable scene synthesis, we also construct MajutsuDataset, a high-quality multimodal dataset} containing 2D semantic layouts and height maps, diverse 3D building assets, and curated PBR materials and skyboxes, each accompanied by detailed annotations. Meanwhile, we develop a practical set of evaluation metrics, covering key dimensions such as structural consistency, scene complexity, material fidelity, and lighting atmosphere. Extensive experiments demonstrate MajutsuCity reduces layout FID by 83.7% compared with CityDreamer and by 20.1% over CityCraft. Our method ranks first across all AQS and RDR scores, outperforming existing methods by a clear margin. These results confirm MajutsuCity as a new state-of-the-art in geometric fidelity, stylistic adaptability, and semantic controllability for 3D city generation. We expect our framework can inspire new avenues of research in 3D city generation. Our dataset and code will be released at https://github.com/LongHZ140516/MajutsuCity.

---

### BOCO: Bayesian Online Contextual Optimization for Decision-Focused Online Learning

Authors: Zhuojun Xie, Adam Abdin, Yiping Fang
Published: 2025-11-25
Categories: math.OC, stat.ML
arXiv: https://arxiv.org/abs/2511.20413v2

\emph{Decision-focused learning} (DFL) trains predictive models to optimize downstream decisions rather than prediction accuracy alone. While recent studies have extended this paradigm to online settings with streaming data, existing online DFL methods generally maintain a point estimate, while their gradient-based updates require either a differentiable optimization layer or a problem-specific surrogate loss. Consequently, they can be unstable under limited data and difficult to apply across heterogeneous optimization problems. We introduce Bayesian Online Contextual Optimization (\texttt{BOCO}), a framework that maintains a decision-focused posterior over model parameters. \texttt{BOCO} aggregates the resulting predictions when prescribing decisions, thereby accounting for parameter uncertainty. To track this posterior in evolving environments, we develop two particle-based inference algorithms: a sequential Monte Carlo sampler for nondifferentiable problems and a function-space Stein variational gradient descent algorithm for differentiable problems. Across both real-world tasks, \texttt{BOCO} reduces running mean regret and temporal regret variability relative to two frequentist online DFL baselines. At the full horizon, relative to the best frequentist baseline, BOCO reduces running mean regret and temporal regret variability by 6.9\% and 6.3\% on knapsack and by 49.3\% and 38.1\% on energy scheduling, respectively. The gains are larger early in the data stream, a pattern consistent with a benefit from accounting for parameter uncertainty when data are limited.

---

### PAC-Bayes Meets Online Contextual Optimization

Authors: Zhuojun Xie, Adam Abdin, Yiping Fang
Published: 2025-11-25
Categories: math.OC, stat.ML
arXiv: https://arxiv.org/abs/2511.20413v1

The predict-then-optimize paradigm bridges online learning and contextual optimization in dynamic environments. Previous works have investigated the sequential updating of predictors using feedback from downstream decisions to minimize regret in the full-information settings. However, existing approaches are predominantly frequentist, rely heavily on gradient-based strategies, and employ deterministic predictors that could yield high variance in practice despite their asymptotic guarantees. This work introduces, to the best of our knowledge, the first Bayesian online contextual optimization framework. Grounded in PAC-Bayes theory and general Bayesian updating principles, our framework achieves $\mathcal{O}(\sqrt{T})$ regret for bounded and mixable losses via a Gibbs posterior, eliminates the dependence on gradients through sequential Monte Carlo samplers, and thereby accommodates nondifferentiable problems. Theoretical developments and numerical experiments substantiate our claims.

---

### Image-Free Timestep Distillation via Continuous-Time Consistency with Trajectory-Sampled Pairs

Authors: Bao Tang, Shuai Zhang, Yueting Zhu, Jijun Xiang, Xin Yang, Li Yu, Wenyu Liu, Xinggang Wang
Published: 2025-11-25
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.20410v1

Timestep distillation is an effective approach for improving the generation efficiency of diffusion models. The Consistency Model (CM), as a trajectory-based framework, demonstrates significant potential due to its strong theoretical foundation and high-quality few-step generation. Nevertheless, current continuous-time consistency distillation methods still rely heavily on training data and computational resources, hindering their deployment in resource-constrained scenarios and limiting their scalability to diverse domains. To address this issue, we propose Trajectory-Backward Consistency Model (TBCM), which eliminates the dependence on external training data by extracting latent representations directly from the teacher model's generation trajectory. Unlike conventional methods that require VAE encoding and large-scale datasets, our self-contained distillation paradigm significantly improves both efficiency and simplicity. Moreover, the trajectory-extracted samples naturally bridge the distribution gap between training and inference, thereby enabling more effective knowledge transfer. Empirically, TBCM achieves 6.52 FID and 28.08 CLIP scores on MJHQ-30k under one-step generation, while reducing training time by approximately 40% compared to Sana-Sprint and saving a substantial amount of GPU memory, demonstrating superior efficiency without sacrificing quality. We further reveal the diffusion-generation space discrepancy in continuous-time consistency distillation and analyze how sampling strategies affect distillation performance, offering insights for future distillation research. GitHub Link: https://github.com/hustvl/TBCM.

---

### NormEval: A Unified Multi-Metric Framework for Evaluating Semantic Fidelity in Text Normalization

Authors: Md Abdullah Al Kafi, Raka Moni, Walayat Hussain
Published: 2025-11-25
Categories: cs.CL
arXiv: https://arxiv.org/abs/2511.20409v2

Text normalization methods such as stemming and lemmatization are fundamental components of NLP pipelines. As new normalization tools are developed for diverse languages, evaluation methodologies remain fragmented, relying on Compression Ratio, downstream accuracy, or sequence-to-sequence prediction scores in isolation, failing to distinguish between beneficial vocabulary reduction and harmful semantic distortion. Moreover, text normalization underpins intelligent systems in high-stakes domains, including clinical decision support and legal document analysis, and principled evaluation methodology is essential. This paper proposes NormEval, a unified, multilingual evaluation framework comprising five complementary metrics: Compression Ratio (CR), Model Performance Delta (MPD), Information Retention Score (IRS), Algorithm Effectiveness Score (AES), and Average Normalized Levenshtein Distance (ANLD). These metrics assess normalization quality across three dimensions: macro-level efficiency, downstream utility, and micro-level morphological fidelity. The framework operationalizes a Safety Gate hypothesis: ANLD functions as an intrinsic structural hygiene check, utilizing character-level divergence ($Δ$) to reveal aggressive mutations that macro-level embeddings and downstream tasks mask. Comprehensive ablation experiments on both Bangla and English datasets show that all the components are indispensable, and that the removal of any individual metric leads to a decrease in at least one evaluation aspect, which ultimately results in misleading algorithm rankings.

---

### A Task-Oriented Evaluation Framework for Text Normalization in Modern NLP Pipelines

Authors: Md Abdullah Al Kafi, Raka Moni, Sumit Kumar Banshal
Published: 2025-11-25
Categories: cs.CL
arXiv: https://arxiv.org/abs/2511.20409v1

Text normalization is an essential preprocessing step in many natural language processing (NLP) tasks, and stemming is one such normalization technique that reduces words to their base or root form. However, evaluating stemming methods is challenging because current evaluation approaches are limited and do not capture the potential harm caused by excessive stemming; therefore, it is essential to develop new approaches to evaluate stemming methods. To address this issue, this study propose a novel, task-oriented approach to evaluate stemming methods, which considers three aspects: (1) the utility of stemming using Stemming Effectiveness Score (SES), (2) the impact of stemming on downstream tasks using Model Performance Delta (MPD), and (3) the semantic similarity between stemmed and original words using Average Normalized Levenshtein Distance (ANLD), thus providing a comprehensive evaluation framework. We apply our evaluation framework to compare two stemmers for Bangla (BNLTK) and English (Snowball), and our results reveal a significant issue, prompting us to analyze their performance in detail. While the Bangla stemmer achieves the highest SES (1.67) due to effective word reduction (CR = 1.90), SES alone is insufficient because our proposed safety measure, ANLD, reveals that this high SES is due to harmful over-stemming (ANLD = 0.26), which correlates with the observed decrease in downstream performance.In contrast, the English stemmer achieves a moderate SES (1.31) with a safe meaning distance (ANLD = 0.14), allowing its word reduction to contribute positively to downstream performance; therefore, it is a more reliable stemmer. Our study provides a valuable tool for distinguishing between potential efficiency gains (high SES) and meaning preservation (low ANLD).

---

### Tight Margin-Based Generalization Bounds for Voting Classifiers over Finite Hypothesis Sets

Authors: Kasper Green Larsen, Natascha Schalburg
Published: 2025-11-25
Categories: cs.LG, math.ST
arXiv: https://arxiv.org/abs/2511.20407v1

We prove the first margin-based generalization bound for voting classifiers, that is asymptotically tight in the tradeoff between the size of the hypothesis set, the margin, the fraction of training points with the given margin, the number of training samples and the failure probability.

---

### Short-Range Oversquashing

Authors: Yaaqov Mishayev, Yonatan Sverdlov, Tal Amir, Nadav Dym
Published: 2025-11-25
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2511.20406v1

Message Passing Neural Networks (MPNNs) are widely used for learning on graphs, but their ability to process long-range information is limited by the phenomenon of oversquashing. This limitation has led some researchers to advocate Graph Transformers as a better alternative, whereas others suggest that it can be mitigated within the MPNN framework, using virtual nodes or other rewiring techniques. In this work, we demonstrate that oversquashing is not limited to long-range tasks, but can also arise in short-range problems. This observation allows us to disentangle two distinct mechanisms underlying oversquashing: (1) the bottleneck phenomenon, which can arise even in low-range settings, and (2) the vanishing gradient phenomenon, which is closely associated with long-range tasks. We further show that the short-range bottleneck effect is not captured by existing explanations for oversquashing, and that adding virtual nodes does not resolve it. In contrast, transformers do succeed in such tasks, positioning them as the more compelling solution to oversquashing, compared to specialized MPNNs.

---

### LLMs for Automated Unit Test Generation and Assessment in Java: The AgoneTest Framework

Authors: Andrea Lops, Fedelucio Narducci, Azzurra Ragone, Michelantonio Trizio, Claudio Bartolini
Published: 2025-11-25
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2511.20403v2

Unit testing is an essential but resource-intensive step in software development, ensuring individual code units function correctly. This paper introduces AgoneTest, an automated evaluation framework for Large Language Model-generated (LLM) unit tests in Java. AgoneTest does not aim to propose a novel test generation algorithm; rather, it supports researchers and developers in comparing different LLMs and prompting strategies through a standardized end-to-end evaluation pipeline under realistic conditions. We introduce the Classes2Test dataset, which maps Java classes under test to their corresponding test classes, and a framework that integrates advanced evaluation metrics, such as mutation score and test smells, for a comprehensive assessment. Experimental results show that, for the subset of tests that compile, LLM-generated tests can match or exceed human-written tests in terms of coverage and defect detection. Our findings also demonstrate that enhanced prompting strategies contribute to test quality. AgoneTest clarifies the potential of LLMs in software testing and offers insights for future improvements in model design, prompt engineering, and testing practices.

---

### LLMs for Automated Unit Test Generation and Assessment in Java: The AgoneTest Framework

Authors: Andrea Lops, Fedelucio Narducci, Azzurra Ragone, Michelantonio Trizio, Claudio Barto
Published: 2025-11-25
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2511.20403v1

Unit testing is an essential but resource-intensive step in software development, ensuring individual code units function correctly. This paper introduces AgoneTest, an automated evaluation framework for Large Language Model-generated (LLM) unit tests in Java. AgoneTest does not aim to propose a novel test generation algorithm; rather, it supports researchers and developers in comparing different LLMs and prompting strategies through a standardized end-to-end evaluation pipeline under realistic conditions. We introduce the Classes2Test dataset, which maps Java classes under test to their corresponding test classes, and a framework that integrates advanced evaluation metrics, such as mutation score and test smells, for a comprehensive assessment. Experimental results show that, for the subset of tests that compile, LLM-generated tests can match or exceed human-written tests in terms of coverage and defect detection. Our findings also demonstrate that enhanced prompting strategies contribute to test quality. AgoneTest clarifies the potential of LLMs in software testing and offers insights for future improvements in model design, prompt engineering, and testing practices.

---

### A Training-Free Approach for Multi-ID Customization via Attention Adjustment and Spatial Control

Authors: Jiawei Lin, Guanlong Jiao, Jianjin Xu
Published: 2025-11-25
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.20401v1

Multi-ID customization is an interesting topic in computer vision and attracts considerable attention recently. Given the ID images of multiple individuals, its purpose is to generate a customized image that seamlessly integrates them while preserving their respective identities. Compared to single-ID customization, multi-ID customization is much more difficult and poses two major challenges. First, since the multi-ID customization model is trained to reconstruct an image from the cropped person regions, it often encounters the copy-paste issue during inference, leading to lower quality. Second, the model also suffers from inferior text controllability. The generated result simply combines multiple persons into one image, regardless of whether it is aligned with the input text. In this work, we propose MultiID to tackle this challenging task in a training-free manner. Since the existing single-ID customization models have less copy-paste issue, our key idea is to adapt these models to achieve multi-ID customization. To this end, we present an ID-decoupled cross-attention mechanism, injecting distinct ID embeddings into the corresponding image regions and thus generating multi-ID outputs. To enhance the generation controllability, we introduce three critical strategies, namely the local prompt, depth-guided spatial control, and extended self-attention, making the results more consistent with the text prompts and ID images. We also carefully build a benchmark, called IDBench, for evaluation. The extensive qualitative and quantitative results demonstrate the effectiveness of MultiID in solving the aforementioned two challenges. Its performance is comparable or even better than the training-based multi-ID customization methods.

---

### BengaliFig: A Low-Resource Challenge for Figurative and Culturally Grounded Reasoning in Bengali

Authors: Abdullah Al Sefat
Published: 2025-11-25
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2511.20399v2

Large language models excel on broad multilingual benchmarks but remain to be evaluated extensively in figurative and culturally grounded reasoning, especially in low-resource contexts. We present BengaliFig, a compact yet richly annotated challenge set that targets this gap in Bengali, a widely spoken low-resourced language. The dataset contains 435 unique riddles drawn from Bengali oral and literary traditions. Each item is annotated along five orthogonal dimensions capturing reasoning type, trap type, cultural depth, answer category, and difficulty, and is automatically converted to multiple-choice format through a constraint-aware, AI-assisted pipeline. We evaluate eight frontier LLMs from major providers under zero-shot and few-shot chain-of-thought prompting, revealing consistent weaknesses in metaphorical and culturally specific reasoning. BengaliFig thus contributes both a diagnostic probe for evaluating LLM robustness in low-resource cultural contexts and a step toward inclusive and heritage-aware NLP evaluation.

---

### BengaliFig: A Low-Resource Challenge for Figurative and Culturally Grounded Reasoning in Bengali

Authors: Abdullah Al Sefat
Published: 2025-11-25
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2511.20399v1

Large language models excel on broad multilingual benchmarks but remain to be evaluated extensively in figurative and culturally grounded reasoning, especially in low-resource contexts. We present BengaliFig, a compact yet richly annotated challenge set that targets this gap in Bengali, a widely spoken low-resourced language. The dataset contains 435 unique riddles drawn from Bengali oral and literary traditions. Each item is annotated along five orthogonal dimensions capturing reasoning type, trap type, cultural depth, answer category, and difficulty, and is automatically converted to multiple-choice format through a constraint-aware, AI-assisted pipeline. We evaluate eight frontier LLMs from major providers under zero-shot and few-shot chain-of-thought prompting, revealing consistent weaknesses in metaphorical and culturally specific reasoning. BengaliFig thus contributes both a diagnostic probe for evaluating LLM robustness in low-resource cultural contexts and a step toward inclusive and heritage-aware NLP evaluation.

---

### Model-Based Learning of Whittle indices

Authors: Joël Charles-Rebuffé, Nicolas Gast, Bruno Gaujal
Published: 2025-11-25
Categories: cs.LG, cs.DS, math.NA
arXiv: https://arxiv.org/abs/2511.20397v2

We present BLINQ, a new model-based algorithm that learns the Whittle indices of an indexable, communicating and unichain Markov Decision Process (MDP). Our approach relies on building an empirical estimate of the MDP and then computing its Whittle indices using an extended version of a state-of-the-art existing algorithm. We provide a proof of convergence to the Whittle indices we want to learn as well as a bound on the time needed to learn them with arbitrary precision. Moreover, we investigate its computational complexity. Our numerical experiments suggest that BLINQ significantly outperforms existing Q-learning approaches in terms of the number of samples needed to get an accurate approximation. In addition, it has a total computational cost even lower than Q-learning for any reasonably high number of samples. These observations persist even when the Q-learning algorithms are speeded up using neural networks to predict Q-values.

---

### Model-Based Learning of Whittle indices

Authors: Joël Charles-Rebuffé, Nicolas Gast, Bruno Gaujal
Published: 2025-11-25
Categories: cs.LG, cs.DS, math.NA
arXiv: https://arxiv.org/abs/2511.20397v1

We present BLINQ, a new model-based algorithm that learns the Whittle indices of an indexable, communicating and unichain Markov Decision Process (MDP). Our approach relies on building an empirical estimate of the MDP and then computing its Whittle indices using an extended version of a state-of-the-art existing algorithm. We provide a proof of convergence to the Whittle indices we want to learn as well as a bound on the time needed to learn them with arbitrary precision. Moreover, we investigate its computational complexity. Our numerical experiments suggest that BLINQ significantly outperforms existing Q-learning approaches in terms of the number of samples needed to get an accurate approximation. In addition, it has a total computational cost even lower than Q-learning for any reasonably high number of samples. These observations persist even when the Q-learning algorithms are speeded up using pre-trained neural networks to predict Q-values.

---

### Identifying environmental factors associated with tetrodotoxin contamination in bivalve mollusks using eXplainable AI

Authors: M. C. Schoppema, B. H. M. van der Velden, A. Hürriyetoğlu, M. D. Klijnstra, E. J. Faassen, A. Gerssen, H. J. van der Fels-Klerx
Published: 2025-11-25
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.20395v2

Since 2012, tetrodotoxin (TTX) has been found in seafoods such as bivalve mollusks in temperate European waters. TTX contamination leads to food safety risks and economic losses, making early prediction of TTX contamination vital to the food industry and competent authorities. Recent studies have pointed to shallow habitats and water temperature as main drivers to TTX contamination in bivalve mollusks. However, the temporal relationships between abiotic factors, biotic factors, and TTX contamination remain unexplored. We have developed an explainable, deep learning-based model to predict TTX contamination in the Dutch Zeeland estuary. Inputs for the model were meteorological and hydrological features; output was the presence or absence of TTX contamination. Results showed that the time of sunrise, time of sunset, global radiation, water temperature, and chloride concentration contributed most to TTX contamination. Thus, the effective number of sun hours, represented by day length and global radiation, was an important driver for tetrodotoxin contamination in bivalve mollusks. To conclude, our explainable deep learning model identified the aforementioned environmental factors (number of sun hours, global radiation, water temperature, and water chloride concentration) to be associated with tetrodotoxin contamination in bivalve mollusks; making our approach a valuable tool to mitigate marine toxin risks for food industry and competent authorities.

---

### Identifying environmental factors associated with tetrodotoxin contamination in bivalve mollusks using eXplainable AI

Authors: M. C. Schoppema, B. H. M. van der Velden, A. Hürriyetoğlu, M. D. Klijnstra, E. J. Faassen, A. Gerssen, H. J. van der Fels-Klerx
Published: 2025-11-25
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.20395v1

Since 2012, tetrodotoxin (TTX) has been found in seafoods such as bivalve mollusks in temperate European waters. TTX contamination leads to food safety risks and economic losses, making early prediction of TTX contamination vital to the food industry and competent authorities. Recent studies have pointed to shallow habitats and water temperature as main drivers to TTX contamination in bivalve mollusks. However, the temporal relationships between abiotic factors, biotic factors, and TTX contamination remain unexplored. We have developed an explainable, deep learning-based model to predict TTX contamination in the Dutch Zeeland estuary. Inputs for the model were meteorological and hydrological features; output was the presence or absence of TTX contamination. Results showed that the time of sunrise, time of sunset, global radiation, water temperature, and chloride concentration contributed most to TTX contamination. Thus, the effective number of sun hours, represented by day length and global radiation, was an important driver for tetrodotoxin contamination in bivalve mollusks. To conclude, our explainable deep learning model identified the aforementioned environmental factors (number of sun hours, global radiation, water temperature, and water chloride concentration) to be associated with tetrodotoxin contamination in bivalve mollusks; making our approach a valuable tool to mitigate marine toxin risks for food industry and competent authorities.

---

### FREE: Uncertainty-Aware Autoregression for Parallel Diffusion Transformers

Authors: Xinwan Wen, Bowen Li, Jiajun Luo, Ye Li, Zhi Wang
Published: 2025-11-25
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.20390v1

Diffusion Transformers (DiTs) achieve state-of-the-art generation quality but require long sequential denoising trajectories, leading to high inference latency. Recent speculative inference methods enable lossless parallel sampling in U-Net-based diffusion models via a drafter-verifier scheme, but their acceleration is limited on DiTs due to insufficient draft accuracy during verification. To address this limitation, we analyze the DiTs' feature dynamics and find the features of the final transformer layer (top-block) exhibit strong temporal consistency and rich semantic abstraction. Based on this insight, we propose FREE, a novel framework that employs a lightweight drafter to perform feature-level autoregression with parallel verification, guaranteeing lossless acceleration with theoretical and empirical support. Meanwhile, prediction variance (uncertainty) of DiTs naturally increases in later denoising steps, reducing acceptance rates under speculative sampling. To mitigate this effect, we further introduce an uncertainty-guided relaxation strategy, forming FREE (relax), which dynamically adjusts the acceptance probability in response to uncertainty levels. Experiments on ImageNet-$512^2$ show that FREE achieves up to $1.86 \times$ acceleration, and FREE (relax) further reaches $2.25 \times$ speedup while maintaining high perceptual and quantitative fidelity in generation quality.

---

### MoRE: Batch-Robust Multi-Omics Representations from Frozen Pre-trained Transformers

Authors: Audrey Pei-Hsuan Chen
Published: 2025-11-25
Categories: cs.LG, q-bio.GN
arXiv: https://arxiv.org/abs/2511.20382v2

Representation learning on multi-omics data is challenging due to extreme dimensionality, modality heterogeneity, and cohort-specific batch effects. While pre-trained transformer backbones have shown broad generalization capabilities in biological sequence modeling, their application to multi-omics integration remains underexplored. We present MoRE (Multi-Omics Representation Embedding), a framework that repurposes frozen pre-trained transformers to align heterogeneous assays into a shared latent space. Unlike purely generative approaches, MoRE employs a parameter-efficient fine-tuning (PEFT) strategy, prioritizing cross-sample and cross-modality alignment over simple sequence reconstruction. Specifically, MoRE attaches lightweight, modality-specific adapters and a task-adaptive fusion layer to the frozen backbone. It optimizes a masked modeling objective jointly with supervised contrastive and batch-invariant alignment losses, yielding structure-preserving embeddings that generalize across unseen cell types and platforms. We benchmark MoRE against established baselines, including scGPT, scVI, and Harmony with Scrublet, evaluating integration fidelity, rare population detection, and modality transfer. Our results demonstrate that MoRE achieves competitive batch robustness and biological conservation while significantly reducing trainable parameters compared to fully fine-tuned models. This work positions MoRE as a practical step toward general-purpose omics foundation models.

---

### MoRE: Batch-Robust Multi-Omics Representations from Frozen Pre-trained Transformers

Authors: Audrey Pei-Hsuan Chen
Published: 2025-11-25
Categories: cs.LG, q-bio.GN
arXiv: https://arxiv.org/abs/2511.20382v1

Representation learning on multi-omics data is challenging due to extreme dimensionality, modality heterogeneity, and cohort-specific batch effects. While pre-trained transformer backbones have shown broad generalization capabilities in biological sequence modeling, their application to multi-omics integration remains underexplored. We present MoRE (Multi-Omics Representation Embedding), a framework that repurposes frozen pre-trained transformers to align heterogeneous assays into a shared latent space. Unlike purely generative approaches, MoRE employs a parameter-efficient fine-tuning (PEFT) strategy, prioritizing cross-sample and cross-modality alignment over simple sequence reconstruction. Specifically, MoRE attaches lightweight, modality-specific adapters and a task-adaptive fusion layer to the frozen backbone. It optimizes a masked modeling objective jointly with supervised contrastive and batch-invariant alignment losses, yielding structure-preserving embeddings that generalize across unseen cell types and platforms. We benchmark MoRE against established baselines, including scGPT, scVI, and Harmony with scArches, evaluating integration fidelity, rare population detection, and modality transfer. Our results demonstrate that MoRE achieves competitive batch robustness and biological conservation while significantly reducing trainable parameters compared to fully fine-tuned models. This work positions MoRE as a practical step toward general-purpose omics foundation models.

---

### Differentiable Attenuation Filters for Feedback Delay Networks

Authors: Ilias Ibnyahya, Joshua D. Reiss
Published: 2025-11-25
Categories: cs.SD, cs.LG
arXiv: https://arxiv.org/abs/2511.20380v1

We introduce a novel method for designing attenuation filters in digital audio reverberation systems based on Feedback Delay Networks (FDNs). Our approach uses Second Order Sections (SOS) of Infinite Impulse Response (IIR) filters arranged as parametric equalizers (PEQ), enabling fine control over frequency-dependent reverberation decay. Unlike traditional graphic equalizer designs, which require numerous filters per delay line, we propose a scalable solution where the number of filters can be adjusted. The frequency, gain, and quality factor (Q) parameters are shared parameters across delay lines and only the gain is adjusted based on delay length. This design not only reduces the number of optimization parameters, but also remains fully differentiable and compatible with gradient-based learning frameworks. Leveraging principles of analog filter design, our method allows for efficient and accurate filter fitting using supervised learning. Our method delivers a flexible and differentiable design, achieving state-of-the-art performance while significantly reducing computational cost.

---

### VGGTFace: Topologically Consistent Facial Geometry Reconstruction in the Wild

Authors: Xin Ming, Yuxuan Han, Tianyu Huang, Feng Xu
Published: 2025-11-25
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.20366v2

Reconstructing topologically consistent facial geometry is crucial for the digital avatar creation pipelines. Existing methods either require tedious manual efforts, lack generalization to in-the-wild data, or are constrained by the limited expressiveness of 3D Morphable Models. To address these limitations, we propose VGGTFace, an automatic approach that innovatively applies the 3D foundation model, i.e. VGGT, for topologically consistent facial geometry reconstruction from in-the-wild multi-view images captured by everyday users. Our key insight is that, by leveraging VGGT, our method naturally inherits strong generalization ability and expressive power from its large-scale training and point map representation. However, it is unclear how to reconstruct a topologically consistent mesh from VGGT, as the topology information is missing in its prediction. To this end, we augment VGGT with Pixel3DMM for injecting topology information via pixel-aligned UV values. In this manner, we convert the pixel-aligned point map of VGGT to a point cloud with topology. Tailored to this point cloud with known topology, we propose a novel Topology-Aware Bundle Adjustment strategy to fuse them, where we construct a Laplacian energy for the Bundle Adjustment objective. Our method achieves high-quality reconstruction in 10 seconds for 16 views on a single NVIDIA RTX 4090. Experiments demonstrate state-of-the-art results on benchmarks and impressive generalization to in-the-wild data. Code is available at https://github.com/grignarder/vggtface.

---

### VGGTFace: Topologically Consistent Facial Geometry Reconstruction in the Wild

Authors: Xin Ming, Yuxuan Han, Tianyu Huang, Feng Xu
Published: 2025-11-25
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.20366v1

Reconstructing topologically consistent facial geometry is crucial for the digital avatar creation pipelines. Existing methods either require tedious manual efforts, lack generalization to in-the-wild data, or are constrained by the limited expressiveness of 3D Morphable Models. To address these limitations, we propose VGGTFace, an automatic approach that innovatively applies the 3D foundation model, \emph{i.e.} VGGT, for topologically consistent facial geometry reconstruction from in-the-wild multi-view images captured by everyday users. Our key insight is that, by leveraging VGGT, our method naturally inherits strong generalization ability and expressive power from its large-scale training and point map representation. However, it is unclear how to reconstruct a topologically consistent mesh from VGGT, as the topology information is missing in its prediction. To this end, we augment VGGT with Pixel3DMM for injecting topology information via pixel-aligned UV values. In this manner, we convert the pixel-aligned point map of VGGT to a point cloud with topology. Tailored to this point cloud with known topology, we propose a novel Topology-Aware Bundle Adjustment strategy to fuse them, where we construct a Laplacian energy for the Bundle Adjustment objective. Our method achieves high-quality reconstruction in 10 seconds for 16 views on a single NVIDIA RTX 4090. Experiments demonstrate state-of-the-art results on benchmarks and impressive generalization to in-the-wild data. Code is available at https://github.com/grignarder/vggtface.

---

### PRISM: Periodic Representation with multIscale and Similarity graph Modelling for enhanced crystal structure property prediction

Authors: Àlex Solé, Albert Mosella-Montoro, Joan Cardona, Daniel Aravena, Silvia Gómez-Coca, Eliseo Ruiz, Javier Ruiz-Hidalgo
Published: 2025-11-25
Categories: cs.LG, cond-mat.mtrl-sci
arXiv: https://arxiv.org/abs/2511.20362v1

Crystal structures are characterised by repeating atomic patterns within unit cells across three-dimensional space, posing unique challenges for graph-based representation learning. Current methods often overlook essential periodic boundary conditions and multiscale interactions inherent to crystalline structures. In this paper, we introduce PRISM, a graph neural network framework that explicitly integrates multiscale representations and periodic feature encoding by employing a set of expert modules, each specialised in encoding distinct structural and chemical aspects of periodic systems. Extensive experiments across crystal structure-based benchmarks demonstrate that PRISM improves state-of-the-art predictive accuracy, significantly enhancing crystal property prediction.

---

### Extension and neural operator approximation of the electrical impedance tomography inverse map

Authors: Maarten V. de Hoop, Nikola B. Kovachki, Matti Lassas, Nicholas H. Nelsen
Published: 2025-11-25
Categories: math.NA, cs.LG, math.AP
arXiv: https://arxiv.org/abs/2511.20361v1

This paper considers the problem of noise-robust neural operator approximation for the solution map of Calderón's inverse conductivity problem. In this continuum model of electrical impedance tomography (EIT), the boundary measurements are realized as a noisy perturbation of the Neumann-to-Dirichlet map's integral kernel. The theoretical analysis proceeds by extending the domain of the inversion operator to a Hilbert space of kernel functions. The resulting extension shares the same stability properties as the original inverse map from kernels to conductivities, but is now amenable to neural operator approximation. Numerical experiments demonstrate that Fourier neural operators excel at reconstructing infinite-dimensional piecewise constant and lognormal conductivities in noisy setups both within and beyond the theory's assumptions. The methodology developed in this paper for EIT exemplifies a broader strategy for addressing nonlinear inverse problems with a noise-aware operator learning framework.

---

### From Passive Perception to Active Memory: A Weakly Supervised Image Manipulation Localization Framework Driven by Coarse-Grained Annotations

Authors: Zhiqing Guo, Dongdong Xi, Songlin Li, Gaobo Yang
Published: 2025-11-25
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2511.20359v1

Image manipulation localization (IML) faces a fundamental trade-off between minimizing annotation cost and achieving fine-grained localization accuracy. Existing fully-supervised IML methods depend heavily on dense pixel-level mask annotations, which limits scalability to large datasets or real-world deployment.In contrast, the majority of existing weakly-supervised IML approaches are based on image-level labels, which greatly reduce annotation effort but typically lack precise spatial localization. To address this dilemma, we propose BoxPromptIML, a novel weakly-supervised IML framework that effectively balances annotation cost and localization performance. Specifically, we propose a coarse region annotation strategy, which can generate relatively accurate manipulation masks at lower cost. To improve model efficiency and facilitate deployment, we further design an efficient lightweight student model, which learns to perform fine-grained localization through knowledge distillation from a fixed teacher model based on the Segment Anything Model (SAM). Moreover, inspired by the human subconscious memory mechanism, our feature fusion module employs a dual-guidance strategy that actively contextualizes recalled prototypical patterns with real-time observational cues derived from the input. Instead of passive feature extraction, this strategy enables a dynamic process of knowledge recollection, where long-term memory is adapted to the specific context of the current image, significantly enhancing localization accuracy and robustness. Extensive experiments across both in-distribution and out-of-distribution datasets show that BoxPromptIML outperforms or rivals fully-supervised models, while maintaining strong generalization, low annotation cost, and efficient deployment characteristics.

---

### GS-Checker: Tampering Localization for 3D Gaussian Splatting

Authors: Haoliang Han, Ziyuan Luo, Jun Qi, Anderson Rocha, Renjie Wan
Published: 2025-11-25
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.20354v1

Recent advances in editing technologies for 3D Gaussian Splatting (3DGS) have made it simple to manipulate 3D scenes. However, these technologies raise concerns about potential malicious manipulation of 3D content. To avoid such malicious applications, localizing tampered regions becomes crucial. In this paper, we propose GS-Checker, a novel method for locating tampered areas in 3DGS models. Our approach integrates a 3D tampering attribute into the 3D Gaussian parameters to indicate whether the Gaussian has been tampered. Additionally, we design a 3D contrastive mechanism by comparing the similarity of key attributes between 3D Gaussians to seek tampering cues at 3D level. Furthermore, we introduce a cyclic optimization strategy to refine the 3D tampering attribute, enabling more accurate tampering localization. Notably, our approach does not require expensive 3D labels for supervision. Extensive experimental results demonstrate the effectiveness of our proposed method to locate the tampered 3DGS area.

---