# Research Papers — 2025-11 · bundle page 45 of 197

> Full-text markdown of papers #2201–2250 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/45
[← Previous bundle](https://aipod.dev/papers/archive/2025-11/page/44.md)
[Next bundle →](https://aipod.dev/papers/archive/2025-11/page/46.md)

### MonoMSK: Monocular 3D Musculoskeletal Dynamics Estimation

Authors: Farnoosh Koleini, Hongfei Xue, Ahmed Helmy, Pu Wang
Published: 2025-11-24
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.19326v2

Reconstructing biomechanically realistic 3D human motion - recovering both kinematics (motion) and kinetics (forces) - is a critical challenge. While marker-based systems are lab-bound and slow, popular monocular methods use oversimplified, anatomically inaccurate models (e.g., SMPL) and ignore physics, fundamentally limiting their biomechanical fidelity. In this work, we introduce MonoMSK, a hybrid framework that bridges data-driven learning and physics-based simulation for biomechanically realistic 3D human motion estimation from monocular video. MonoMSK jointly recovers both kinematics (motions) and kinetics (forces and torques) through an anatomically accurate musculoskeletal model. By integrating transformer-based inverse dynamics with differentiable forward kinematics and dynamics layers governed by ODE-based simulation, MonoMSK establishes a physics-regulated inverse-forward loop that enforces biomechanical causality and physical plausibility. A novel forward-inverse consistency loss further aligns motion reconstruction with the underlying kinetic reasoning. Experiments on BML-MoVi, BEDLAM, and OpenCap show that MonoMSK significantly outperforms state-of-the-art methods in kinematic accuracy, while for the first time enabling precise monocular kinetics estimation.

---

### Generative Query Expansion with Multilingual LLMs for Cross-Lingual Information Retrieval

Authors: Olivia Macmillan-Scott, Roksana Goworek, Eda B. Özyiğit
Published: 2025-11-24
Categories: cs.IR, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2511.19325v1

Query expansion is the reformulation of a user query by adding semantically related information, and is an essential component of monolingual and cross-lingual information retrieval used to ensure that relevant documents are not missed. Recently, multilingual large language models (mLLMs) have shifted query expansion from semantic augmentation with synonyms and related words to pseudo-document generation. Pseudo-documents both introduce additional relevant terms and bridge the gap between short queries and long documents, which is particularly beneficial in dense retrieval. This study evaluates recent mLLMs and fine-tuned variants across several generative expansion strategies to identify factors that drive cross-lingual retrieval performance. Results show that query length largely determines which prompting technique is effective, and that more elaborate prompts often do not yield further gains. Substantial linguistic disparities persist: cross-lingual query expansion can produce the largest improvements for languages with the weakest baselines, yet retrieval is especially poor between languages written in different scripts. Fine-tuning is found to lead to performance gains only when the training and test data are of similar format. These outcomes underline the need for more balanced multilingual and cross-lingual training and evaluation resources.

---

### What Drives Cross-lingual Ranking? Retrieval Approaches with Multilingual Language Models

Authors: Roksana Goworek, Olivia Macmillan-Scott, Eda B. Özyiğit
Published: 2025-11-24
Categories: cs.IR, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2511.19324v1

Cross-lingual information retrieval (CLIR) enables access to multilingual knowledge but remains challenging due to disparities in resources, scripts, and weak cross-lingual semantic alignment in embedding models. Existing pipelines often rely on translation and monolingual retrieval heuristics, which add computational overhead and noise, degrading performance. This work systematically evaluates four intervention types, namely document translation, multilingual dense retrieval with pretrained encoders, contrastive learning at word, phrase, and query-document levels, and cross-encoder re-ranking, across three benchmark datasets. We find that dense retrieval models trained specifically for CLIR consistently outperform lexical matching methods and derive little benefit from document translation. Contrastive learning mitigates language biases and yields substantial improvements for encoders with weak initial alignment, and re-ranking can be effective, but depends on the quality of the cross-encoder training data. Although high-resource languages still dominate overall performance, gains over lexical and document-translated baselines are most pronounced for low-resource and cross-script pairs. These findings indicate that cross-lingual search systems should prioritise semantic multilingual embeddings and targeted learning-based alignment over translation-based pipelines, particularly for cross-script and under-resourced languages.

---

### SteadyDancer: Harmonized and Coherent Human Image Animation with First-Frame Preservation

Authors: Jiaming Zhang, Shengming Cao, Rui Li, Xiaotong Zhao, Yutao Cui, Xinglin Hou, Gangshan Wu, Haolan Chen, Yu Xu, Limin Wang, Kai Ma
Published: 2025-11-24
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.19320v2

Preserving first-frame identity while ensuring precise motion control is a fundamental challenge in human image animation. The Image-to-Motion Binding process of the dominant Reference-to-Video (R2V) paradigm overlooks critical spatio-temporal misalignments common in real-world applications, leading to failures such as identity drift and visual artifacts. We introduce SteadyDancer, an Image-to-Video (I2V) paradigm-based framework that achieves harmonized and coherent animation and is the first to ensure first-frame preservation robustly. Firstly, we propose a Condition-Reconciliation Mechanism to harmonize the two conflicting conditions, enabling precise control without sacrificing fidelity. Secondly, we design Synergistic Pose Modulation Modules to generate an adaptive and coherent pose representation that is highly compatible with the reference image. Finally, we employ a Staged Decoupled-Objective Training Pipeline that hierarchically optimizes the model for motion fidelity, visual quality, and temporal coherence. Experiments demonstrate that SteadyDancer achieves state-of-the-art performance in both appearance fidelity and motion control, while requiring significantly fewer training resources than comparable methods. The model has been publicly released at \url{https://mcg-nju.github.io/steadydancer-web}.

---

### SyncMV4D: Synchronized Multi-view Joint Diffusion of Appearance and Motion for Hand-Object Interaction Synthesis

Authors: Lingwei Dang, Zonghan Li, Juntong Li, Hongwen Zhang, Liang An, Yebin Liu, Qingyao Wu
Published: 2025-11-24
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.19319v2

Hand-Object Interaction (HOI) generation plays a critical role in advancing applications across animation and robotics. Current video-based methods are predominantly single-view, which impedes comprehensive 3D geometry perception and often results in geometric distortions or unrealistic motion patterns. While 3D HOI approaches can generate dynamically plausible motions, their dependence on high-quality 3D data captured in controlled laboratory settings severely limits their generalization to real-world scenarios. To overcome these limitations, we introduce SyncMV4D, the first model that jointly generates synchronized multi-view HOI videos and 4D motions by unifying visual prior, motion dynamics, and multi-view geometry. Our framework features two core innovations: (1) a Multi-view Joint Diffusion (MJD) model that co-generates HOI videos and intermediate motions, and (2) a Diffusion Points Aligner (DPA) that refines the coarse intermediate motion into globally aligned 4D metric point tracks. To tightly couple 2D appearance with 4D dynamics, we establish a closed-loop, mutually enhancing cycle. During the diffusion denoising process, the generated video conditions the refinement of the 4D motion, while the aligned 4D point tracks are reprojected to guide next-step joint generation. Experimentally, our method demonstrates superior performance to state-of-the-art alternatives in visual realism, motion plausibility, and multi-view consistency.

---

### MultiBanAbs: A Comprehensive Multi-Domain Bangla Abstractive Text Summarization Dataset

Authors: Md. Tanzim Ferdous, Naeem Ahsan Chowdhury, Prithwiraj Bhattacharjee
Published: 2025-11-24
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2511.19317v1

This study developed a new Bangla abstractive summarization dataset to generate concise summaries of Bangla articles from diverse sources. Most existing studies in this field have concentrated on news articles, where journalists usually follow a fixed writing style. While such approaches are effective in limited contexts, they often fail to adapt to the varied nature of real-world Bangla texts. In today's digital era, a massive amount of Bangla content is continuously produced across blogs, newspapers, and social media. This creates a pressing need for summarization systems that can reduce information overload and help readers understand content more quickly. To address this challenge, we developed a dataset of over 54,000 Bangla articles and summaries collected from multiple sources, including blogs such as Cinegolpo and newspapers such as Samakal and The Business Standard. Unlike single-domain resources, our dataset spans multiple domains and writing styles. It offers greater adaptability and practical relevance. To establish strong baselines, we trained and evaluated this dataset using several deep learning and transfer learning models, including LSTM, BanglaT5-small, and MTS-small. The results highlight its potential as a benchmark for future research in Bangla natural language processing. This dataset provides a solid foundation for building robust summarization systems and helps expand NLP resources for low-resource languages.

---

### Evaluating Dataset Watermarking for Fine-tuning Traceability of Customized Diffusion Models: A Comprehensive Benchmark and Removal Approach

Authors: Xincheng Wang, Hanchi Sun, Wenjun Sun, Kejun Xue, Wangqiu Zhou, Jianbo Zhang, Wei Sun, Dandan Zhu, Xiongkuo Min, Jun Jia, Zhijun Fang
Published: 2025-11-24
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2511.19316v2

Recent fine-tuning techniques for diffusion models enable them to reproduce specific image sets, such as particular faces or artistic styles, but also introduce copyright and security risks. Dataset watermarking has been proposed to ensure traceability by embedding imperceptible watermarks into training images, which remain detectable in outputs even after fine-tuning. However, current methods lack a unified evaluation framework. To address this, this paper establishes a general threat model and introduces a comprehensive evaluation framework encompassing Universality, Transmissibility, and Robustness. Experiments show that existing methods perform well in universality and transmissibility, and exhibit some robustness against common image processing operations, yet still fall short under real-world threat scenarios. To reveal these vulnerabilities, the paper further proposes a practical watermark removal method that fully eliminates dataset watermarks without affecting fine-tuning, highlighting a key challenge for future research.

---

### PRInTS: Reward Modeling for Long-Horizon Information Seeking

Authors: Jaewoo Lee, Archiki Prasad, Justin Chih-Yao Chen, Zaid Khan, Elias Stengel-Eskin, Mohit Bansal
Published: 2025-11-24
Categories: cs.AI, cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2511.19314v2

Information-seeking is a core capability for AI agents, requiring them to gather and reason over tool-generated information across long trajectories. However, such multi-step information-seeking tasks remain challenging for agents backed by language models. While process reward models (PRMs) can guide agents by ranking candidate steps at test-time, existing PRMs - designed for short reasoning with binary judgment - cannot capture richer dimensions of information-seeking steps, such as tool interactions and reasoning over tool outputs, nor handle the rapidly growing context in long-horizon tasks. To address these limitations, we introduce PRInTS, a generative PRM trained with dual capabilities: (1) dense scoring based on the PRM's reasoning across multiple dimensions of step quality (e.g., interpretation of tool outputs, tool call informativeness) and (2) trajectory summarization that compresses the growing context while preserving essential information for step evaluation. Extensive evaluations across FRAMES, GAIA (levels 1-3), and WebWalkerQA (easy-hard) benchmarks on multiple models reveal that best-of-n sampling with PRInTS enhances information-seeking in open-source models as well as specialized agents, matching or surpassing frontier models with a much smaller backbone agent and outperforming other strong reward modeling baselines.

---

### Dual-Granularity Semantic Prompting for Language Guidance Infrared Small Target Detection

Authors: Zixuan Wang, Haoran Sun, Jiaming Lu, Wenxuan Wang, Zhongling Huang, Dingwen Zhang, Xuelin Qian, Junwei Han
Published: 2025-11-24
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.19306v1

Infrared small target detection remains challenging due to limited feature representation and severe background interference, resulting in sub-optimal performance. While recent CLIP-inspired methods attempt to leverage textual guidance for detection, they are hindered by inaccurate text descriptions and reliance on manual annotations. To overcome these limitations, we propose DGSPNet, an end-to-end language prompt-driven framework. Our approach integrates dual-granularity semantic prompts: coarse-grained textual priors (e.g., 'infrared image', 'small target') and fine-grained personalized semantic descriptions derived through visual-to-textual mapping within the image space. This design not only facilitates learning fine-grained semantic information but also can inherently leverage language prompts during inference without relying on any annotation requirements. By fully leveraging the precision and conciseness of text descriptions, we further introduce a text-guide channel attention (TGCA) mechanism and text-guide spatial attention (TGSA) mechanism that enhances the model's sensitivity to potential targets across both low- and high-level feature spaces. Extensive experiments demonstrate that our method significantly improves detection accuracy and achieves state-of-the-art performance on three benchmark datasets.

---

### AutoEnv: Automated Environments for Measuring Cross-Environment Agent Learning

Authors: Jiayi Zhang, Yiran Peng, Fanqi Kong, Cheng Yang, Yifan Wu, Zhaoyang Yu, Jinyu Xiang, Jianhao Ruan, Jinlin Wang, Maojia Song, HongZhang Liu, Xiangru Tang et al.
Published: 2025-11-24
Categories: cs.AI, cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2511.19304v2

Humans naturally adapt to diverse environments by learning underlying rules across worlds with different dynamics, observations, and reward structures. In contrast, existing agents typically demonstrate improvements via self-evolving within a single domain, implicitly assuming a fixed environment distribution. Cross-environment learning has remained largely unmeasured: there is no standard collection of controllable, heterogeneous environments, nor a unified way to represent how agents learn. We address these gaps in two steps. First, we propose AutoEnv, an automated framework that treats environments as factorizable distributions over transitions, observations, and rewards, enabling low-cost (4.12 USD on average) generation of heterogeneous worlds. Using AutoEnv, we construct AutoEnv-36, a dataset of 36 environments with 358 validated levels, on which seven language models achieve 12-49% normalized reward, demonstrating the challenge of AutoEnv-36. Second, we formalize agent learning as a component-centric process driven by three stages of Selection, Optimization, and Evaluation applied to an improvable agent component. Using this formulation, we design eight learning methods and evaluate them on AutoEnv-36. Empirically, the gain of any single learning method quickly decrease as the number of environments increases, revealing that fixed learning methods do not scale across heterogeneous environments. Environment-adaptive selection of learning methods substantially improves performance but exhibits diminishing returns as the method space expands. These results highlight both the necessity and the current limitations of agent learning for scalable cross-environment generalization, and position AutoEnv and AutoEnv-36 as a testbed for studying cross-environment agent learning. The code is avaiable at https://github.com/FoundationAgents/AutoEnv.

---

### IDEAL-M3D: Instance Diversity-Enriched Active Learning for Monocular 3D Detection

Authors: Johannes Meier, Florian Günther, Riccardo Marin, Oussema Dhaouadi, Jacques Kaiser, Daniel Cremers
Published: 2025-11-24
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.19301v1

Monocular 3D detection relies on just a single camera and is therefore easy to deploy. Yet, achieving reliable 3D understanding from monocular images requires substantial annotation, and 3D labels are especially costly. To maximize performance under constrained labeling budgets, it is essential to prioritize annotating samples expected to deliver the largest performance gains. This prioritization is the focus of active learning. Curiously, we observed two significant limitations in active learning algorithms for 3D monocular object detection. First, previous approaches select entire images, which is inefficient, as non-informative instances contained in the same image also need to be labeled. Secondly, existing methods rely on uncertainty-based selection, which in monocular 3D object detection creates a bias toward depth ambiguity. Consequently, distant objects are selected, while nearby objects are overlooked. To address these limitations, we propose IDEAL-M3D, the first instance-level pipeline for monocular 3D detection. For the first time, we demonstrate that an explicitly diverse, fast-to-train ensemble improves diversity-driven active learning for monocular 3D. We induce diversity with heterogeneous backbones and task-agnostic features, loss weight perturbation, and time-dependent bagging. IDEAL-M3D shows superior performance and significant resource savings: with just 60% of the annotations, we achieve similar or better AP3D on KITTI validation and test set results compared to training the same detector on the whole dataset.

---

### Open-weight genome language model safeguards: Assessing robustness via adversarial fine-tuning

Authors: James R. M. Black, Moritz S. Hanke, Aaron Maiwald, Tina Hernandez-Boussard, Oliver M. Crook, Jaspreet Pannu
Published: 2025-11-24
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2511.19299v2

Novel deep learning architectures are increasingly being applied to biological data, including genetic sequences. These models, referred to as genomic language models (gLMs), have demonstrated impressive predictive and generative capabilities, raising concerns that such models may also enable misuse, for instance via the generation of genomes for human-infecting viruses. These concerns have catalyzed calls for risk mitigation measures. The de facto mitigation of choice is filtering of pretraining data (i.e., removing viral genomic sequences from training datasets) in order to limit gLM performance on virus-related tasks. However, it is not currently known how robust this approach is for securing open-source models that can be fine-tuned using sensitive pathogen data. Here, we evaluate a state-of-the-art gLM, Evo 2, and perform fine-tuning using sequences from 110 harmful human-infecting viruses to assess the rescue of misuse-relevant predictive capabilities. The fine-tuned model exhibited reduced perplexity on unseen viral sequences relative to 1) the pretrained model and 2) a version fine-tuned on bacteriophage sequences. The model fine-tuned on human-infecting viruses also identified immune escape variants from SARS-CoV-2 (achieving an AUROC of 0.6), despite having no exposure to SARS-CoV-2 sequences during fine-tuning. This work demonstrates that data exclusion might be circumvented by fine-tuning approaches that can, to some degree, rescue misuse-relevant capabilities of gLMs. We highlight the need for safety frameworks for gLMs and outline further work needed on evaluations and mitigation measures to enable the safe deployment of gLMs.

---

### DensifyBeforehand: LiDAR-assisted Content-aware Densification for Efficient and Quality 3D Gaussian Splatting

Authors: Phurtivilai Patt, Leyang Huang, Yinqiang Zhang, Yang Lei
Published: 2025-11-24
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.19294v1

This paper addresses the limitations of existing 3D Gaussian Splatting (3DGS) methods, particularly their reliance on adaptive density control, which can lead to floating artifacts and inefficient resource usage. We propose a novel densify beforehand approach that enhances the initialization of 3D scenes by combining sparse LiDAR data with monocular depth estimation from corresponding RGB images. Our ROI-aware sampling scheme prioritizes semantically and geometrically important regions, yielding a dense point cloud that improves visual fidelity and computational efficiency. This densify beforehand approach bypasses the adaptive density control that may introduce redundant Gaussians in the original pipeline, allowing the optimization to focus on the other attributes of 3D Gaussian primitives, reducing overlap while enhancing visual quality. Our method achieves comparable results to state-of-the-art techniques while significantly lowering resource consumption and training time. We validate our approach through extensive comparisons and ablation studies on four newly collected datasets, showcasing its effectiveness in preserving regions of interest in complex scenes.

---

### TorchQuantumDistributed

Authors: Oliver Knitter, Jonathan Mei, Masako Yamada, Martin Roetteler
Published: 2025-11-24
Categories: quant-ph, cs.CE, cs.LG
arXiv: https://arxiv.org/abs/2511.19291v1

TorchQuantumDistributed (tqd) is a PyTorch-based (Paszke et al., 2019) library for accelerator-agnostic differentiable quantum state vector simulation at scale. This enables studying the behavior of learnable parameterized near-term and fault- tolerant quantum circuits with high qubit counts.

---

### Performance Guarantees for Quantum Neural Estimation of Entropies

Authors: Sreejith Sreekumar, Ziv Goldfeld, Mark M. Wilde
Published: 2025-11-24
Categories: quant-ph, cs.IT, cs.LG
arXiv: https://arxiv.org/abs/2511.19289v2

Estimating quantum entropies and divergences is an important problem in quantum physics, information theory, and machine learning. Quantum neural estimators (QNEs), which utilize a hybrid classical-quantum architecture, have recently emerged as an appealing computational framework for estimating these measures. Such estimators combine classical neural networks with parametrized quantum circuits, and their deployment typically entails tedious tuning of hyperparameters controlling the sample size, network architecture, and circuit topology. This work initiates the study of formal guarantees for QNEs of measured (Rényi) relative entropies in the form of non-asymptotic error risk bounds. We further establish exponential tail bounds showing that the error is sub-Gaussian and thus sharply concentrates about the ground truth value. For an appropriate sub-class of density operator pairs on a space of dimension $d$ with bounded Thompson metric, our theory establishes a copy complexity of $O(|Θ(\mathcal{U})|d/ε^2)$ for QNE with a quantum circuit parameter set $Θ(\mathcal{U})$, which has minimax optimal dependence on the accuracy $ε$. Additionally, if the density operator pairs are permutation invariant, we improve the dimension dependence above to $O(|Θ(\mathcal{U})|\mathrm{polylog}(d)/ε^2)$. Our theory aims to facilitate principled implementation of QNEs for measured relative entropies and guide hyperparameter tuning in practice.

---

### The Unified Non-Convex Framework for Robust Causal Inference: Overcoming the Gaussian Barrier and Optimization Fragility

Authors: Eichi Uehara
Published: 2025-11-24
Categories: stat.ML, cs.LG, stat.ME
arXiv: https://arxiv.org/abs/2511.19284v1

This document proposes a Unified Robust Framework that re-engineers the estimation of the Average Treatment Effect on the Overlap (ATO). It synthesizes gamma-Divergence for outlier robustness, Graduated Non-Convexity (GNC) for global optimization, and a "Gatekeeper" mechanism to address the impossibility of higher-order orthogonality in Gaussian regimes.

---

### Data Flows and Colonial Regimes in Africa: A Critical Analysis of the Colonial Futurities Embedded in AI Ecosystems

Authors: Ndaka. A, Avila-Acosta. F, Mbula-Ndaka. H, Amera. C, Chauke. S, Majiwa. E
Published: 2025-11-24
Categories: cs.CY, cs.AI
arXiv: https://arxiv.org/abs/2511.19283v1

This chapter seeks to frame the elemental and invisible problems of AI and big data in the African context by examining digital sites and infrastructure through the lens of power and interests. It will present reflections on how these sites are using AI recommendation algorithms to recreate new digital societies in the region, how they have the potential to propagate algorithmic colonialism and negative gender norms, and what this means for the regional sustainable development agenda. The chapter proposes adopting business models that embrace response-ability and consider the existence of alternative socio-material worlds of AI. These reflections will mainly come from ongoing discussions with Kenyan social media users in this authors' user space talks, personal experiences and six months of active participant observations done by the authors.

---

### MapFormer: Self-Supervised Learning of Cognitive Maps with Input-Dependent Positional Embeddings

Authors: Victor Rambaud, Salvador Mascarenhas, Yair Lakretz
Published: 2025-11-24
Categories: cs.LG, cs.CL
arXiv: https://arxiv.org/abs/2511.19279v4

A cognitive map is an internal model which encodes the abstract relationships among entities in the world, giving humans and animals the flexibility to adapt to new situations, with a strong out-of-distribution (OOD) generalization that current AI systems still do not possess. To bridge this gap, we introduce $\textit{MapFormers}$, new Transformer-based architectures, which can learn cognitive maps from observational data and perform path-integration without supervision. Cognitive maps are learned in the model by disentangling structural relationships in the inputs from their specific content, a property that can be achieved by updating position encodings with input-dependent matrices, built as exponentials of learned combinations of Lie-algebra generators. We developed two variants of $\textit{MapFormers}$ that unify absolute and relative positional encoding to model episodic (EM) and working memory (WM), respectively. We tested $\textit{MapFormers}$ on several formal tasks targeting distinct cognitive capacities, including gating, 2D navigation and nested hierarchies (Dyck Languages). Our results demonstrate that $\textit{MapFormers}$ significantly outperform current AI architectures, achieving near-perfect OOD generalization where standard models fail. Furthermore, we show that $\textit{MapFormers}$ are scalable; evaluations on naturalistic data yield perplexity improvements over baselines, suggesting that these principles extend to large-scale, real-world domains. These results are obtained through efficient parallel computation on commutative maps, though our models can also learn non-commutative cognitive maps via sequential path-integration. Overall, these results suggest that input-dependent matrices provide a critical structural bias, by disentangling abstract relations from content in order to drive robust OOD generalization.

---

### ReMatch: Boosting Representation through Matching for Multimodal Retrieval

Authors: Qianying Liu, Xiao Liang, Zhiqiang Zhang, Zhongfei Qing, Fengfan Zhou, Yibo Chen, Xu Tang, Yao Hu, Paul Henderson
Published: 2025-11-24
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.19278v2

We present ReMatch, a framework that leverages the generative strength of MLLMs for multimodal retrieval. Previous approaches treated an MLLM as a simple encoder, ignoring its generative nature, and under-utilising its compositional reasoning and world knowledge. We instead train the embedding MLLM end-to-end with a chat-style generative matching stage. The matching stage uses the same MLLM to autoregressively decide relevance from multi-view inputs, including both raw data and its own projected embeddings for each query and document. It provides instance-wise discrimination supervision that complements a standard contrastive loss, offering stronger gradients on hard negatives and preserving the compositional strengths of the original MLLM. To obtain semantically richer multimodal embeddings, we use multiple learnable tokens to augment each input, generating fine-grained contextual, mutually orthogonal embeddings with low inference cost. Leveraging our established high-performance baseline,we assemble the ideas mentioned above into a powerful training recipe and achieve a new state-of-the-art on the Massive Multimodal Embedding Benchmark (MMEB). Our experiments show particularly strong zero-shot generalization results on five datasets, highlighting the robustness and transferability of ReMatch.

---

### Closing Gaps in Emissions Monitoring with Climate TRACE

Authors: Brittany V. Lancellotti, Jordan M. Malof, Aaron Davitt, Gavin McCormick, Shelby Anderson, Pol Carbó-Mestre, Gary Collins, Verity Crane, Zoheyr Doctor, George Ebri, Kevin Foster, Trey M. Gowdy et al.
Published: 2025-11-24
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.19277v2

Global greenhouse gas emissions estimates are essential for monitoring and mitigation planning. Existing emissions datasets provide critical foundations for understanding emissions patterns across sectors, geographies, and time scales. Through a structured assessment of recent emissions datasets, we identified opportunities to further increase the actionability of emissions data through more comprehensive source-level coverage, finer spatial and temporal resolution, and more frequent updates. Building on existing resources to address these opportunities, we present the Climate TRACE framework and resulting dataset, which is available on an open-access platform (climatetrace.org). The Climate TRACE framework synthesizes existing emissions data, prioritizing accuracy, coverage, and resolution, and fills remaining gaps using sector-specific estimation approaches. The resulting dataset is the first to provide global emissions estimates for individual sources (e.g., individual power plants) for most anthropogenic emitting sectors. The dataset spans January 1, 2021, to the present, with a two-month reporting lag and monthly updates. This dataset and open-access platform provides access to detailed emissions estimates for most subnational governments worldwide. By combining source-level spatial detail, monthly updates, and broad sectoral coverage, the dataset is designed to support analyses relevant to emissions monitoring and mitigation planning.

---

### Dynamic Multi-Species Bird Soundscape Generation with Acoustic Patterning and 3D Spatialization

Authors: Ellie L. Zhang, Duoduo Liao, Callie C. Liao
Published: 2025-11-24
Categories: cs.SD, cs.AI, eess.AS, eess.SP
arXiv: https://arxiv.org/abs/2511.19275v1

Generation of dynamic, scalable multi-species bird soundscapes remains a significant challenge in computer music and algorithmic sound design. Birdsongs involve rapid frequency-modulated chirps, complex amplitude envelopes, distinctive acoustic patterns, overlapping calls, and dynamic inter-bird interactions, all of which require precise temporal and spatial control in 3D environments. Existing approaches, whether Digital Signal Processing (DSP)-based or data-driven, typically focus only on single species modeling, static call structures, or synthesis directly from recordings, and often suffer from noise, limited flexibility, or large data needs. To address these challenges, we present a novel, fully algorithm-driven framework that generates dynamic multi-species bird soundscapes using DSP-based chirp generation and 3D spatialization, without relying on recordings or training data. Our approach simulates multiple independently-moving birds per species along different moving 3D trajectories, supporting controllable chirp sequences, overlapping choruses, and realistic 3D motion in scalable soundscapes while preserving species-specific acoustic patterns. A visualization interface provides bird trajectories, spectrograms, activity timelines, and sound waves for analytical and creative purposes. Both visual and audio evaluations demonstrate the ability of the system to generate dense, immersive, and ecologically inspired soundscapes, highlighting its potential for computer music, interactive virtual environments, and computational bioacoustics research.

---

### Diffusion Reconstruction-based Data Likelihood Estimation for Core-Set Selection

Authors: Mingyang Chen, Jiawei Du, Bo Huang, Yi Wang, Xiaobo Zhang, Wei Wang
Published: 2025-11-24
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.19274v1

Existing core-set selection methods predominantly rely on heuristic scoring signals such as training dynamics or model uncertainty, lacking explicit modeling of data likelihood. This omission may hinder the constructed subset from capturing subtle yet critical distributional structures that underpin effective model training. In this work, we propose a novel, theoretically grounded approach that leverages diffusion models to estimate data likelihood via reconstruction deviation induced by partial reverse denoising. Specifically, we establish a formal connection between reconstruction error and data likelihood, grounded in the Evidence Lower Bound (ELBO) of Markovian diffusion processes, thereby enabling a principled, distribution-aware scoring criterion for data selection. Complementarily, we introduce an efficient information-theoretic method to identify the optimal reconstruction timestep, ensuring that the deviation provides a reliable signal indicative of underlying data likelihood. Extensive experiments on ImageNet demonstrate that reconstruction deviation offers an effective scoring criterion, consistently outperforming existing baselines across selection ratios, and closely matching full-data training using only 50% of the data. Further analysis shows that the likelihood-informed nature of our score reveals informative insights in data selection, shedding light on the interplay between data distributional characteristics and model learning preferences.

---

### Scalable Bayesian Network Structure Learning Using Tsetlin Machine to Constrain the Search Space

Authors: Kunal Dumbre, Lei Jiao, Ole-Christoffer Granmo
Published: 2025-11-24
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.19273v1

The PC algorithm is a widely used method in causal inference for learning the structure of Bayesian networks. Despite its popularity, the PC algorithm suffers from significant time complexity, particularly as the size of the dataset increases, which limits its applicability in large-scale real-world problems. In this study, we propose a novel approach that utilises the Tsetlin Machine (TM) to construct Bayesian structures more efficiently. Our method leverages the most significant literals extracted from the TM and performs conditional independence (CI) tests on these selected literals instead of the full set of variables, resulting in a considerable reduction in computational time. We implemented our approach and compared it with various state-of-the-art methods. Our evaluation includes categorical datasets from the bnlearn repository, such as Munin1, Hepar2. The findings indicate that the proposed TM-based method not only reduces computational complexity but also maintains competitive accuracy in causal discovery, making it a viable alternative to traditional PC algorithm implementations by offering improved efficiency without compromising performance.

---

### Tiny-TSM: Efficiently Training a Lightweight SOTA Time Series Foundation Model

Authors: Felix Birkel
Published: 2025-11-24
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.19272v1

We present Tiny-TSM, a time series foundation model characterized by small scale, economical training, and state-of-the-art performance. It comprises 23M total parameters, trained on a single A100 GPU in less than a week using a new synthetic data generation and data augmentation pipeline (SynthTS). Without any neural architecture search, hyperparameter tuning, or scaling up model size, Tiny-TSM achieves state-of-the-art performance on a wide range of time series benchmark datasets, often outperforming much larger models and even matching the performance of much larger, industrial-scale, likely highly tuned foundation models. Specifically, Tiny-TSM outperforms all other time series foundation models we evaluated on medium- and long-term forecasting tasks under MSE loss, while short-term accuracy is still competitive with state-of-the-art models. We also introduce a causal input normalization scheme that enables time series models to be trained with dense next-token prediction loss, significantly accelerating convergence speed and reducing training time. All experiments were conducted on a single A100 GPU, illustrating the practicality of the proposed approach in a resource-constrained setting.

---

### CDLM: Consistency Diffusion Language Models For Faster Sampling

Authors: Minseo Kim, Chenfeng Xu, Coleman Hooper, Harman Singh, Ben Athiwaratkun, Ce Zhang, Kurt Keutzer, Amir Gholami
Published: 2025-11-24
Categories: cs.LG, cs.CL
arXiv: https://arxiv.org/abs/2511.19269v2

Diffusion Language Models (DLMs) offer a promising parallel generation paradigm but suffer from slow inference due to numerous refinement steps and the inability to use standard KV caching. We introduce CDLM (Consistency Diffusion Language Models), a training-based acceleration method that simultaneously tackles both bottlenecks. CDLM integrates consistency modeling to drastically reduce the number of required sampling steps by enabling multi-token finalization. Furthermore, we enforce a block-wise causal attention mask during fine-tuning, making the model fully compatible with KV caching. Experiments show CDLM achieves 3.6x-14.5x lower latency while maintaining competitive accuracy on math and coding tasks. The full training and evaluation code is available at https://github.com/SqueezeAILab/CDLM.

---

### BideDPO: Conditional Image Generation with Simultaneous Text and Condition Alignment

Authors: Dewei Zhou, Mingwei Li, Zongxin Yang, Yu Lu, Yunqiu Xu, Zhizhong Wang, Zeyi Huang, Yi Yang
Published: 2025-11-24
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.19268v1

Conditional image generation enhances text-to-image synthesis with structural, spatial, or stylistic priors, but current methods face challenges in handling conflicts between sources. These include 1) input-level conflicts, where the conditioning image contradicts the text prompt, and 2) model-bias conflicts, where generative biases disrupt alignment even when conditions match the text. Addressing these conflicts requires nuanced solutions, which standard supervised fine-tuning struggles to provide. Preference-based optimization techniques like Direct Preference Optimization (DPO) show promise but are limited by gradient entanglement between text and condition signals and lack disentangled training data for multi-constraint tasks. To overcome this, we propose a bidirectionally decoupled DPO framework (BideDPO). Our method creates two disentangled preference pairs-one for the condition and one for the text-to reduce gradient entanglement. The influence of pairs is managed using an Adaptive Loss Balancing strategy for balanced optimization. We introduce an automated data pipeline to sample model outputs and generate conflict-aware data. This process is embedded in an iterative optimization strategy that refines both the model and the data. We construct a DualAlign benchmark to evaluate conflict resolution between text and condition. Experiments show BideDPO significantly improves text success rates (e.g., +35%) and condition adherence. We also validate our approach using the COCO dataset. Project Pages: https://limuloo.github.io/BideDPO/.

---

### Leveraging Spatiotemporal Graph Neural Networks for Multi-Store Sales Forecasting

Authors: Manish Singh, Arpita Dayama
Published: 2025-11-24
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.19267v1

This work evaluates the effectiveness of spatiotemporal Graph Neural Networks (GNNs) for multi-store retail sales forecasting and compares their performance against ARIMA, LSTM, and XGBoost baselines. Using weekly sales data from 45 Walmart stores, we construct a relational forecasting framework that models inter-store dependencies through a learned adaptive graph. The proposed STGNN predicts log-differenced sales and reconstructs final values through a residual path, enabling stable training and improved generalisation. Experiments show that STGNN achieves the lowest overall forecasting error, outperforming all baselines in Normalised Total Absolute Error, P90 MAPE, and variance of MAPE across stores. Analysis of the learned adjacency matrix reveals meaningful functional store clusters and high-influence nodes that emerge without geographic metadata. These results demonstrate that relational structure significantly improves forecast quality in interconnected retail environments and establishes STGNNs as a robust modelling choice for multi-store demand prediction.

---

### Unboxing the Black Box: Mechanistic Interpretability for Algorithmic Understanding of Neural Networks

Authors: Bianka Kowalska, Halina Kwaśnicka
Published: 2025-11-24
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.19265v1

The black box nature of deep neural networks poses a significant challenge for the deployment of transparent and trustworthy artificial intelligence (AI) systems. With the growing presence of AI in society, it becomes increasingly important to develop methods that can explain and interpret the decisions made by these systems. To address this, mechanistic interpretability (MI) emerged as a promising and distinctive research program within the broader field of explainable artificial intelligence (XAI). MI is the process of studying the inner computations of neural networks and translating them into human-understandable algorithms. It encompasses reverse engineering techniques aimed at uncovering the computational algorithms implemented by neural networks. In this article, we propose a unified taxonomy of MI approaches and provide a detailed analysis of key techniques, illustrated with concrete examples and pseudo-code. We contextualize MI within the broader interpretability landscape, comparing its goals, methods, and insights to other strands of XAI. Additionally, we trace the development of MI as a research area, highlighting its conceptual roots and the accelerating pace of recent work. We argue that MI holds significant potential to support a more scientific understanding of machine learning systems -- treating models not only as tools for solving tasks, but also as systems to be studied and understood. We hope to invite new researchers into the field of mechanistic interpretability.

---

### Interpreting GFlowNets for Drug Discovery: What probes can and cannot show

Authors: Amirtha Varshini A S, Duminda S. Ranasinghe, Hok Hei Tam
Published: 2025-11-24
Categories: cs.LG, cs.AI, q-bio.BM
arXiv: https://arxiv.org/abs/2511.19264v2

Generative Flow Networks (GFlowNets) construct molecules through sequential decisions, but their internal policies remain opaque, limiting adoption in drug discovery, where chemists need interpretable rationales for proposed structures. We present a control-validated interpretability study of SynFlowNet, a synthesis-aware GFlowNet trained with a drug-likeness (QED) reward. Our framework combines gradient saliency and counterfactual edits, an undercomplete factor analysis, and an overcomplete BatchTopK sparse autoencoder, evaluated with shuffled-label controls, RDKit-descriptor baselines, a scaffold-disjoint split, cross-seed stability, and an architecture-matched untrained network. These controls materially change the interpretation. Physicochemical properties and functional groups are highly decodable from SynFlowNet embeddings, but an untrained network with the same architecture performs essentially as well as the trained policy (drug-likeness within 0.005 and marginally better molecular-size decoding). Thus, this decodability reflects graph architecture and atom featurization rather than representations acquired through policy training. The surviving conclusions are narrower: the overcomplete autoencoder reconstructs embeddings better than a matched undercomplete baseline at comparable sparsity; chemically enriched substructure detectors, including per-halogen and boron features, emerge in individual runs, although only a small subset of dictionary directions is stable across seeds; and zeroing individual features produces property-specific effects on probe decoding. Beyond SynFlowNet, this study provides a reusable control protocol for molecular-model interpretability, separating learned structure from signals supplied by architecture and input representation. High probe scores alone should not be treated as evidence of learned chemistry.

---

### Solar-GECO: Perovskite Solar Cell Property Prediction with Geometric-Aware Co-Attention

Authors: Lucas Li, Jean-Baptiste Puel, Florence Carton, Dounya Barrit, Jhony H. Giraldo
Published: 2025-11-24
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2511.19263v1

Perovskite solar cells are promising candidates for next-generation photovoltaics. However, their performance as multi-scale devices is determined by complex interactions between their constituent layers. This creates a vast combinatorial space of possible materials and device architectures, making the conventional experimental-based screening process slow and expensive. Machine learning models try to address this problem, but they only focus on individual material properties or neglect the important geometric information of the perovskite crystal. To address this problem, we propose to predict perovskite solar cell power conversion efficiency with a geometric-aware co-attention (Solar-GECO) model. Solar-GECO combines a geometric graph neural network (GNN) - that directly encodes the atomic structure of the perovskite absorber - with language model embeddings that process the textual strings representing the chemical compounds of the transport layers and other device components. Solar-GECO also integrates a co-attention module to capture intra-layer dependencies and inter-layer interactions, while a probabilistic regression head predicts both power conversion efficiency (PCE) and its associated uncertainty. Solar-GECO achieves state-of-the-art performance, significantly outperforming several baselines, reducing the mean absolute error (MAE) for PCE prediction from 3.066 to 2.936 compared to semantic GNN (the previous state-of-the-art model). Solar-GECO demonstrates that integrating geometric and textual information provides a more powerful and accurate framework for PCE prediction.

---

### Psychometric Tests for AI Agents and Their Moduli Space

Authors: Przemyslaw Chojecki
Published: 2025-11-24
Categories: cs.AI, cs.LG, math.ST
arXiv: https://arxiv.org/abs/2511.19262v1

We develop a moduli-theoretic view of psychometric test batteries for AI agents and connect it explicitly to the AAI score developed previously. First, we make precise the notion of an AAI functional on a battery and set out axioms that any reasonable autonomy/general intelligence score should satisfy. Second, we show that the composite index ('AAI-Index') defined previously is a special case of our AAI functional. Third, we introduce the notion of a cognitive core of an agent relative to a battery and define the associated AAI$_{\textrm{core}}$ score as the restriction of an AAI functional to that core. Finally, we use these notions to describe invariants of batteries under evaluation-preserving symmetries and outline how moduli of equivalent batteries are organized.

---

### LAST: LeArning to Think in Space and Time for Generalist Vision-Language Models

Authors: Shuai Wang, Daoan Zhang, Tianyi Bai, Shitong Shao, Jiebo Luo, Jiaheng Wei
Published: 2025-11-24
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.19261v1

Humans can perceive and understand 3D space and long videos from sequential visual observations. But do vision-language models (VLMs) can? Recent work demonstrates that even state-of-the-art VLMs still struggle to understand 3D space and long videos, although they are powerful in typical vision-language tasks. Current methods often rely on specialized architectural designs to improve performance for 3D tasks and video understanding tasks separately. In contrast, we propose LAST, short for LeArn to Think in Space and Time, to jointly improve 3D spatial and long video understanding for general VLMs with only a set of 2D images as inputs. LAST makes VLMs think in space and time rather than only with text before giving the final answer, building visual thinking trajectories in 3D space and temporal dimension. We demonstrate the effectiveness of LAST in two scenarios: 1) zero-shot, where we directly prompt proprietary models; and 2) fine-tuning general VLMs with data that include thinking trajectories in 3D space and time. We show that LAST brings substantial gains in various benchmarks, including 3 spatial understanding, 4 video understanding, and 3 image understanding tasks. Notably, 15.8% gains on EgoSchema with GPT-4o in a zero-shot manner and 8.3 gains on VSI-Bench compared with Qwen2.5-VL-7B.

---

### Wrist Photoplethysmography Predicts Dietary Information

Authors: Kyle Verrier, Achille Nazaret, Joseph Futoma, Andrew C. Miller, Guillermo Sapiro
Published: 2025-11-24
Categories: cs.LG, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2511.19260v2

Whether wearable photoplethysmography (PPG) contains dietary information remains unknown. We trained a language model on 1.1M meals to predict meal descriptions from PPG, aligning PPG to text. PPG nontrivially predicts meal content; predictability decreases for PPGs farther from meals. This transfers to dietary tasks: PPG increases AUC by 11% for intake and satiety across held-out and independent cohorts, with gains robust to text degradation. Wearable PPG may enable passive dietary monitoring.

---

### Medusa: Cross-Modal Transferable Adversarial Attacks on Multimodal Medical Retrieval-Augmented Generation

Authors: Yingjia Shang, Yi Liu, Huimin Wang, Furong Li, Wenfang Sun, Wu Chengyu, Yefeng Zheng
Published: 2025-11-24
Categories: cs.CR, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2511.19257v1

With the rapid advancement of retrieval-augmented vision-language models, multimodal medical retrieval-augmented generation (MMed-RAG) systems are increasingly adopted in clinical decision support. These systems enhance medical applications by performing cross-modal retrieval to integrate relevant visual and textual evidence for tasks, e.g., report generation and disease diagnosis. However, their complex architecture also introduces underexplored adversarial vulnerabilities, particularly via visual input perturbations. In this paper, we propose Medusa, a novel framework for crafting cross-modal transferable adversarial attacks on MMed-RAG systems under a black-box setting. Specifically, Medusa formulates the attack as a perturbation optimization problem, leveraging a multi-positive InfoNCE loss (MPIL) to align adversarial visual embeddings with medically plausible but malicious textual targets, thereby hijacking the retrieval process. To enhance transferability, we adopt a surrogate model ensemble and design a dual-loop optimization strategy augmented with invariant risk minimization (IRM). Extensive experiments on two real-world medical tasks, including medical report generation and disease diagnosis, demonstrate that Medusa achieves over 90% average attack success rate across various generation models and retrievers under appropriate parameter configuration, while remaining robust against four mainstream defenses, outperforming state-of-the-art baselines. Our results reveal critical vulnerabilities in the MMed-RAG systems and highlight the necessity of robustness benchmarking in safety-critical medical applications. The code and data are available at https://anonymous.4open.science/r/MMed-RAG-Attack-F05A.

---

### SimDiff: Simpler Yet Better Diffusion Model for Time Series Point Forecasting

Authors: Hang Ding, Xue Wang, Tian Zhou, Tao Yao
Published: 2025-11-24
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2511.19256v1

Diffusion models have recently shown promise in time series forecasting, particularly for probabilistic predictions. However, they often fail to achieve state-of-the-art point estimation performance compared to regression-based methods. This limitation stems from difficulties in providing sufficient contextual bias to track distribution shifts and in balancing output diversity with the stability and precision required for point forecasts. Existing diffusion-based approaches mainly focus on full-distribution modeling under probabilistic frameworks, often with likelihood maximization objectives, while paying little attention to dedicated strategies for high-accuracy point estimation. Moreover, other existing point prediction diffusion methods frequently rely on pre-trained or jointly trained mature models for contextual bias, sacrificing the generative flexibility of diffusion models. To address these challenges, we propose SimDiff, a single-stage, end-to-end framework. SimDiff employs a single unified Transformer network carefully tailored to serve as both denoiser and predictor, eliminating the need for external pre-trained or jointly trained regressors. It achieves state-of-the-art point estimation performance by leveraging intrinsic output diversity and improving mean squared error accuracy through multiple inference ensembling. Key innovations, including normalization independence and the median-of-means estimator, further enhance adaptability and stability. Extensive experiments demonstrate that SimDiff significantly outperforms existing methods in time series point forecasting.

---

### Adversarial Patch Attacks on Vision-Based Cargo Occupancy Estimation via Differentiable 3D Simulation

Authors: Mohamed Rissal Hedna, Sesugh Samuel Nder
Published: 2025-11-24
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2511.19254v1

Computer vision systems are increasingly adopted in modern logistics operations, including the estimation of trailer occupancy for planning, routing, and billing. Although effective, such systems may be vulnerable to physical adversarial attacks, particularly adversarial patches that can be printed and placed on interior surfaces. In this work, we study the feasibility of such attacks on a convolutional cargo-occupancy classifier using fully simulated 3D environments. Using Mitsuba 3 for differentiable rendering, we optimize patch textures across variations in geometry, lighting, and viewpoint, and compare their effectiveness to a 2D compositing baseline. Our experiments demonstrate that 3D-optimized patches achieve high attack success rates, especially in a denial-of-service scenario (empty to full), where success reaches 84.94 percent. Concealment attacks (full to empty) prove more challenging but still reach 30.32 percent. We analyze the factors influencing attack success, discuss implications for the security of automated logistics pipelines, and highlight directions for strengthening physical robustness. To our knowledge, this is the first study to investigate adversarial patch attacks for cargo-occupancy estimation in physically realistic, fully simulated 3D scenes.

---

### MAESTRO: Multi-Agent Environment Shaping through Task and Reward Optimization

Authors: Boyuan Wu
Published: 2025-11-24
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2511.19253v2

Cooperative Multi-Agent Reinforcement Learning (MARL) faces two major design bottlenecks: crafting dense reward functions and constructing curricula that avoid local optima in high-dimensional, non-stationary environments. Existing approaches rely on fixed heuristics or use Large Language Models (LLMs) directly in the control loop, which is costly and unsuitable for real-time systems. We propose MAESTRO (Multi-Agent Environment Shaping through Task and Reward Optimization), a framework that moves the LLM outside the execution loop and uses it as an offline training architect. MAESTRO introduces two generative components: (i) a semantic curriculum generator that creates diverse, performance-driven traffic scenarios, and (ii) an automated reward synthesizer that produces executable Python reward functions adapted to evolving curriculum difficulty. These components guide a standard MARL backbone (MADDPG) without increasing inference cost at deployment. We evaluate MAESTRO on large-scale traffic signal control (Hangzhou, 16 intersections) and conduct controlled ablations. Results show that combining LLM-generated curricula with LLM-generated reward shaping yields improved performance and stability. Across four seeds, the full system achieves +4.0% higher mean return (163.26 vs. 156.93) and 2.2% better risk-adjusted performance (Sharpe 1.53 vs. 0.70) over a strong curriculum baseline. These findings highlight LLMs as effective high-level designers for cooperative MARL training.

---

### FedPoisonTTP: A Threat Model and Poisoning Attack for Federated Test-Time Personalization

Authors: Md Akil Raihan Iftee, Syed Md. Ahnaf Hasan, Amin Ahsan Ali, AKM Mahbubur Rahman, Sajib Mistry, Aneesh Krishna
Published: 2025-11-24
Categories: cs.CR, cs.CV
arXiv: https://arxiv.org/abs/2511.19248v1

Test-time personalization in federated learning enables models at clients to adjust online to local domain shifts, enhancing robustness and personalization in deployment. Yet, existing federated learning work largely overlooks the security risks that arise when local adaptation occurs at test time. Heterogeneous domain arrivals, diverse adaptation algorithms, and limited cross-client visibility create vulnerabilities where compromised participants can craft poisoned inputs and submit adversarial updates that undermine both global and per-client performance. To address this threat, we introduce FedPoisonTTP, a realistic grey-box attack framework that explores test-time data poisoning in the federated adaptation setting. FedPoisonTTP distills a surrogate model from adversarial queries, synthesizes in-distribution poisons using feature-consistency, and optimizes attack objectives to generate high-entropy or class-confident poisons that evade common adaptation filters. These poisons are injected during local adaptation and spread through collaborative updates, leading to broad degradation. Extensive experiments on corrupted vision benchmarks show that compromised participants can substantially diminish overall test-time performance.

---

### Neural Architecture Search for Quantum Autoencoders

Authors: Hibah Agha, Samuel Yen-Chi Chen, Huan-Hsin Tseng, Shinjae Yoo
Published: 2025-11-24
Categories: quant-ph, cs.AI, cs.LG, cs.NE
arXiv: https://arxiv.org/abs/2511.19246v1

In recent years, machine learning and deep learning have driven advances in domains such as image classification, speech recognition, and anomaly detection by leveraging multi-layer neural networks to model complex data. Simultaneously, quantum computing (QC) promises to address classically intractable problems via quantum parallelism, motivating research in quantum machine learning (QML). Among QML techniques, quantum autoencoders show promise for compressing high-dimensional quantum and classical data. However, designing effective quantum circuit architectures for quantum autoencoders remains challenging due to the complexity of selecting gates, arranging circuit layers, and tuning parameters. This paper proposes a neural architecture search (NAS) framework that automates the design of quantum autoencoders using a genetic algorithm (GA). By systematically evolving variational quantum circuit (VQC) configurations, our method seeks to identify high-performing hybrid quantum-classical autoencoders for data reconstruction without becoming trapped in local minima. We demonstrate effectiveness on image datasets, highlighting the potential of quantum autoencoders for efficient feature extraction within a noise-prone, near-term quantum era. Our approach lays a foundation for broader application of genetic algorithms to quantum architecture search, aiming for a robust, automated method that can adapt to varied data and hardware constraints.

---

### Local Entropy Search over Descent Sequences for Bayesian Optimization

Authors: David Stenger, Armin Lindicke, Alexander von Rohr, Sebastian Trimpe
Published: 2025-11-24
Categories: cs.LG, cs.AI, stat.ML
arXiv: https://arxiv.org/abs/2511.19241v1

Searching large and complex design spaces for a global optimum can be infeasible and unnecessary. A practical alternative is to iteratively refine the neighborhood of an initial design using local optimization methods such as gradient descent. We propose local entropy search (LES), a Bayesian optimization paradigm that explicitly targets the solutions reachable by the descent sequences of iterative optimizers. The algorithm propagates the posterior belief over the objective through the optimizer, resulting in a probability distribution over descent sequences. It then selects the next evaluation by maximizing mutual information with that distribution, using a combination of analytic entropy calculations and Monte-Carlo sampling of descent sequences. Empirical results on high-complexity synthetic objectives and benchmark problems show that LES achieves strong sample efficiency compared to existing local and global Bayesian optimization methods.

---

### Empirical Comparison of Forgetting Mechanisms for UCB-based Algorithms on a Data-Driven Simulation Platform

Authors: Minxin Chen
Published: 2025-11-24
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.19240v1

Many real-world bandit problems involve non-stationary reward distributions, where the optimal decision may shift due to evolving environments. However, the performance of some typical Multi-Armed Bandit (MAB) models such as Upper Confidence Bound (UCB) algorithms degrades significantly in non-stationary environments where reward distributions change over time. To address this limitation, this paper introduces and evaluates FDSW-UCB, a novel dual-view algorithm that integrates a discount-based long-term perspective with a sliding-window-based short-term view. A data-driven semi-synthetic simulation platform, built upon the MovieLens-1M and Open Bandit datasets, is developed to test algorithm adaptability under abrupt and gradual drift scenarios. Experimental results demonstrate that a well-configured sliding-window mechanism (SW-UCB) is robust, while the widely used discounting method (D-UCB) suffers from a fundamental learning failure, leading to linear regret. Crucially, the proposed FDSW-UCB, when employing an optimistic aggregation strategy, achieves superior performance in dynamic settings, highlighting that the ensemble strategy itself is a decisive factor for success.

---

### SENTINEL: A Fully End-to-End Language-Action Model for Humanoid Whole Body Control

Authors: Yuxuan Wang, Haobin Jiang, Shiqing Yao, Ziluo Ding, Zongqing Lu
Published: 2025-11-24
Categories: cs.RO, cs.AI
arXiv: https://arxiv.org/abs/2511.19236v1

Existing humanoid control systems often rely on teleoperation or modular generation pipelines that separate language understanding from physical execution. However, the former is entirely human-driven, and the latter lacks tight alignment between language commands and physical behaviors. In this paper, we present SENTINEL, a fully end-to-end language-action model for humanoid whole-body control. We construct a large-scale dataset by tracking human motions in simulation using a pretrained whole body controller, combined with their text annotations. The model directly maps language commands and proprioceptive inputs to low-level actions without any intermediate representation. The model generates action chunks using flow matching, which can be subsequently refined by a residual action head for real-world deployment. Our method exhibits strong semantic understanding and stable execution on humanoid robots in both simulation and real-world deployment, and also supports multi-modal extensions by converting inputs into texts.

---

### IDSplat: Instance-Decomposed 3D Gaussian Splatting for Driving Scenes

Authors: Carl Lindström, Mahan Rafidashti, Maryam Fatemi, Lars Hammarstrand, Martin R. Oswald, Lennart Svensson
Published: 2025-11-24
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.19235v2

Reconstructing dynamic driving scenes is essential for developing autonomous systems through sensor-realistic simulation. Although recent methods achieve high-fidelity reconstructions, they either rely on costly human annotations for object trajectories or use time-varying representations without explicit object-level decomposition, leading to intertwined static and dynamic elements that hinder scene separation. We present IDSplat, a self-supervised 3D Gaussian Splatting framework that reconstructs dynamic scenes with explicit instance decomposition and learnable motion trajectories, without requiring human annotations. Our key insight is to model dynamic objects as coherent instances undergoing rigid transformations, rather than unstructured time-varying primitives. For instance decomposition, we employ zero-shot, language-grounded video tracking anchored to 3D using lidar, and estimate consistent poses via feature correspondences. We introduce a coordinated-turn smoothing scheme to obtain temporally and physically consistent motion trajectories, mitigating pose misalignments and tracking failures, followed by joint optimization of object poses and Gaussian parameters. Experiments on the Waymo Open Dataset demonstrate that our method achieves competitive reconstruction quality while maintaining instance-level decomposition and generalizes across diverse sequences and view densities without retraining, making it practical for large-scale autonomous driving applications. Code will be released.

---

### In Machina N400: Pinpointing Where a Causal Language Model Detects Semantic Violations

Authors: Christos-Nikolaos Zacharopoulos, Revekka Kyriakoglou
Published: 2025-11-24
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2511.19232v1

How and where does a transformer notice that a sentence has gone semantically off the rails? To explore this question, we evaluated the causal language model (phi-2) using a carefully curated corpus, with sentences that concluded plausibly or implausibly. Our analysis focused on the hidden states sampled at each model layer. To investigate how violations are encoded, we utilized two complementary probes. First, we conducted a per-layer detection using a linear probe. Our findings revealed that a simple linear decoder struggled to distinguish between plausible and implausible endings in the lowest third of the model's layers. However, its accuracy sharply increased in the middle blocks, reaching a peak just before the top layers. Second, we examined the effective dimensionality of the encoded violation. Initially, the violation widens the representational subspace, followed by a collapse after a mid-stack bottleneck. This might indicate an exploratory phase that transitions into rapid consolidation. Taken together, these results contemplate the idea of alignment with classical psycholinguistic findings in human reading, where semantic anomalies are detected only after syntactic resolution, occurring later in the online processing sequence.

---

### Learning Plug-and-play Memory for Guiding Video Diffusion Models

Authors: Selena Song, Ziming Xu, Zijun Zhang, Kun Zhou, Jiaxian Guo, Lianhui Qin, Biwei Huang
Published: 2025-11-24
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2511.19229v2

Diffusion Transformer(DiT) based video generation models have recently achieved impressive visual quality and temporal coherence, but they still frequently violate basic physical laws and commonsense dynamics, revealing a lack of explicit world knowledge. In this work, we explore how to equip them with a plug-and-play memory that injects useful world knowledge. Motivated by in-context memory in Transformer-based LLMs, we conduct empirical studies to show that DiT can be steered via interventions on its hidden states, and simple low-pass and high-pass filters in the embedding space naturally disentangle low-level appearance and high-level physical/semantic cues, enabling targeted guidance. Building on these observations, we propose a learnable memory encoder DiT-Mem, composed of stacked 3D CNNs, low-/high-pass filters, and self-attention layers. The encoder maps reference videos into a compact set of memory tokens, which are concatenated as the memory within the DiT self-attention layers. During training, we keep the diffusion backbone frozen, and only optimize the memory encoder. It yields a rather efficient training process on few training parameters (150M) and 10K data samples, and enables plug-and-play usage at inference time. Extensive experiments on state-of-the-art models demonstrate the effectiveness of our method in improving physical rule following and video fidelity. Our code and data are publicly released here: https://thrcle421.github.io/DiT-Mem-Web/.

---

### Percept-WAM: Perception-Enhanced World-Awareness-Action Model for Robust End-to-End Autonomous Driving

Authors: Jianhua Han, Meng Tian, Jiangtong Zhu, Fan He, Huixin Zhang, Sitong Guo, Dechang Zhu, Hao Tang, Pei Xu, Yuze Guo, Minzhe Niu, Haojie Zhu et al.
Published: 2025-11-24
Categories: cs.CV, cs.RO
arXiv: https://arxiv.org/abs/2511.19221v1

Autonomous driving heavily relies on accurate and robust spatial perception. Many failures arise from inaccuracies and instability, especially in long-tail scenarios and complex interactions. However, current vision-language models are weak at spatial grounding and understanding, and VLA systems built on them therefore show limited perception and localization ability. To address these challenges, we introduce Percept-WAM, a perception-enhanced World-Awareness-Action Model that is the first to implicitly integrate 2D/3D scene understanding abilities within a single vision-language model (VLM). Instead of relying on QA-style spatial reasoning, Percept-WAM unifies 2D/3D perception tasks into World-PV and World-BEV tokens, which encode both spatial coordinates and confidence. We propose a grid-conditioned prediction mechanism for dense object perception, incorporating IoU-aware scoring and parallel autoregressive decoding, improving stability in long-tail, far-range, and small-object scenarios. Additionally, Percept-WAM leverages pretrained VLM parameters to retain general intelligence (e.g., logical reasoning) and can output perception results and trajectory control outputs directly. Experiments show that Percept-WAM matches or surpasses classical detectors and segmenters on downstream perception benchmarks, achieving 51.7/58.9 mAP on COCO 2D detection and nuScenes BEV 3D detection. When integrated with trajectory decoders, it further improves planning performance on nuScenes and NAVSIM, e.g., surpassing DiffusionDrive by 2.1 in PMDS on NAVSIM. Qualitative results further highlight its strong open-vocabulary and long-tail generalization.

---

### Are Large Vision Language Models Truly Grounded in Medical Images? Evidence from Italian Clinical Visual Question Answering

Authors: Federico Felizzi, Olivia Riccomi, Michele Ferramola, Francesco Andrea Causio, Manuel Del Medico, Vittorio De Vita, Lorenzo De Mori, Alessandra Piscitelli, Pietro Eric Risuleo, Bianca Destro Castaniti, Antonio Cristiano, Alessia Longo et al.
Published: 2025-11-24
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2511.19220v2

Large vision language models (VLMs) have achieved impressive performance on medical visual question answering benchmarks, yet their reliance on visual information remains unclear. We investigate whether frontier VLMs demonstrate genuine visual grounding when answering Italian medical questions by testing four state-of-the-art models: Claude Sonnet 4.5, GPT-4o, GPT-5-mini, and Gemini 2.0 flash exp. Using 60 questions from the EuropeMedQA Italian dataset that explicitly require image interpretation, we substitute correct medical images with blank placeholders to test whether models truly integrate visual and textual information. Our results reveal striking variability in visual dependency: GPT-4o shows the strongest visual grounding with a 27.9pp accuracy drop (83.2% (74.6%, 91.7%) to 55.3% (44.1%, 66.6%)), while GPT-5-mini, Gemini, and Claude maintain high accuracy with modest drops of 8.5pp, 2.4pp, and 5.6pp respectively. Analysis of model-generated reasoning reveals confident explanations for fabricated visual interpretations across all models, suggesting varying degrees of reliance on textual shortcuts versus genuine visual analysis. These findings highlight critical differences in model robustness and the need for rigorous evaluation before clinical deployment.

---

### Adversarial Attack-Defense Co-Evolution for LLM Safety Alignment via Tree-Group Dual-Aware Search and Optimization

Authors: Xurui Li, Kaisong Song, Rui Zhu, Pin-Yu Chen, Haixu Tang
Published: 2025-11-24
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2511.19218v2

Large Language Models (LLMs) have developed rapidly in web services, delivering unprecedented capabilities while amplifying societal risks. Existing works tend to focus on either isolated jailbreak attacks or static defenses, neglecting the dynamic interplay between evolving threats and safeguards in real-world web contexts. To mitigate these challenges, we propose ACE-Safety (Adversarial Co-Evolution for LLM Safety), a novel framework that jointly optimize attack and defense models by seamlessly integrating two key innovative procedures: (1) Group-aware Strategy-guided Monte Carlo Tree Search (GS-MCTS), which efficiently explores jailbreak strategies to uncover vulnerabilities and generate diverse adversarial samples; (2) Adversarial Curriculum Tree-aware Group Policy Optimization (AC-TGPO), which jointly trains attack and defense LLMs with challenging samples via curriculum reinforcement learning, enabling robust mutual improvement. Evaluations across multiple benchmarks demonstrate that our method outperforms existing attack and defense approaches, and provides a feasible pathway for developing LLMs that can sustainably support responsible AI ecosystems.

---

### ReAlign: Text-to-Motion Generation via Step-Aware Reward-Guided Alignment

Authors: Wanjiang Weng, Xiaofeng Tan, Junbo Wang, Guo-Sen Xie, Pan Zhou, Hongsong Wang
Published: 2025-11-24
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.19217v1

Text-to-motion generation, which synthesizes 3D human motions from text inputs, holds immense potential for applications in gaming, film, and robotics. Recently, diffusion-based methods have been shown to generate more diversity and realistic motion. However, there exists a misalignment between text and motion distributions in diffusion models, which leads to semantically inconsistent or low-quality motions. To address this limitation, we propose Reward-guided sampling Alignment (ReAlign), comprising a step-aware reward model to assess alignment quality during the denoising sampling and a reward-guided strategy that directs the diffusion process toward an optimally aligned distribution. This reward model integrates step-aware tokens and combines a text-aligned module for semantic consistency and a motion-aligned module for realism, refining noisy motions at each timestep to balance probability density and alignment. Extensive experiments of both motion generation and retrieval tasks demonstrate that our approach significantly improves text-motion alignment and motion quality compared to existing state-of-the-art methods.

---

### NVGS: Neural Visibility for Occlusion Culling in 3D Gaussian Splatting

Authors: Brent Zoomers, Florian Hahlbohm, Joni Vanherck, Lode Jorissen, Marcus Magnor, Nick Michiels
Published: 2025-11-24
Categories: cs.CV, cs.GR
arXiv: https://arxiv.org/abs/2511.19202v2

3D Gaussian Splatting can exploit frustum culling and level-of-detail strategies to accelerate rendering of scenes containing a large number of primitives. However, the semi-transparent nature of Gaussians prevents the application of another highly effective technique: occlusion culling. We address this limitation by proposing a novel method to learn the viewpoint-dependent visibility function of all Gaussians in a trained model using a small, shared MLP across instances of an asset in a scene. By querying it for Gaussians within the viewing frustum prior to rasterization, our method can discard occluded primitives during rendering. Leveraging Tensor Cores for efficient computation, we integrate these neural queries directly into a novel instanced software rasterizer. Our approach outperforms the current state of the art for composed scenes in terms of VRAM usage and image quality, utilizing a combination of our instanced rasterizer and occlusion culling MLP, and exhibits complementary properties to existing LoD techniques.

---