# Research Papers — 2026-03 · bundle page 223 of 243 > Full-text markdown of papers #11101–11150 of 12123 published in 2026-03, newest first. AI-readable mirrors of the full 12123-paper 2026-03 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-03/page/223 [← Previous bundle](https://aipod.dev/papers/archive/2026-03/page/222.md) [Next bundle →](https://aipod.dev/papers/archive/2026-03/page/224.md) ### ACE-Brain-0: Spatial Intelligence as a Shared Scaffold for Universal Embodiments Authors: Ziyang Gong, Zehang Luo, Anke Tang, Zhe Liu, Shi Fu, Zhi Hou, Ganlin Yang, Weiyun Wang, Xiaofeng Wang, Jianbo Liu, Gen Luo, Haolan Kang et al. Published: 2026-03-03 Categories: cs.RO, cs.CL, cs.CV arXiv: https://arxiv.org/abs/2603.03198v1 Universal embodied intelligence demands robust generalization across heterogeneous embodiments, such as autonomous driving, robotics, and unmanned aerial vehicles (UAVs). However, existing embodied brain in training a unified model over diverse embodiments frequently triggers long-tail data, gradient interference, and catastrophic forgetting, making it notoriously difficult to balance universal generalization with domain-specific proficiency. In this report, we introduce ACE-Brain-0, a generalist foundation brain that unifies spatial reasoning, autonomous driving, and embodied manipulation within a single multimodal large language model~(MLLM). Our key insight is that spatial intelligence serves as a universal scaffold across diverse physical embodiments: although vehicles, robots, and UAVs differ drastically in morphology, they share a common need for modeling 3D mental space, making spatial cognition a natural, domain-agnostic foundation for cross-embodiment transfer. Building on this insight, we propose the Scaffold-Specialize-Reconcile~(SSR) paradigm, which first establishes a shared spatial foundation, then cultivates domain-specialized experts, and finally harmonizes them through data-free model merging. Furthermore, we adopt Group Relative Policy Optimization~(GRPO) to strengthen the model's comprehensive capability. Extensive experiments demonstrate that ACE-Brain-0 achieves competitive and even state-of-the-art performance across 24 spatial and embodiment-related benchmarks. --- ### Specificity-aware reinforcement learning for fine-grained open-world classification Authors: Samuele Angheben, Davide Berasi, Alessandro Conti, Elisa Ricci, Yiming Wang Published: 2026-03-03 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.03197v3 Classifying fine-grained visual concepts under open-world settings, i.e., without a predefined label set, demands models to be both accurate and specific. Recent reasoning Large Multimodal Models (LMMs) exhibit strong visual understanding capability but tend to produce overly generic predictions when performing fine-grained image classification. Our preliminary analysis reveals that models do possess the intrinsic fine-grained domain knowledge. However, promoting more specific predictions (specificity) without compromising correct ones (correctness) remains a non-trivial and understudied challenge. In this work, we investigate how to steer reasoning LMMs toward predictions that are both correct and specific. We propose a novel specificity-aware reinforcement learning framework, SpeciaRL, to fine-tune reasoning LMMs on fine-grained image classification under the open-world setting. SpeciaRL introduces a dynamic, verifier-based reward signal anchored to the best predictions within online rollouts, promoting specificity while respecting the model's capabilities to prevent incorrect predictions. Our out-of-domain experiments show that SpeciaRL delivers the best trade-off between correctness and specificity across extensive fine-grained benchmarks, surpassing existing methods and advancing open-world fine-grained image classification. Code and model are publicly available at https://github.com/s-angheben/SpeciaRL. --- ### Infinite dimensional generative sensing Authors: Paolo Angella, Vito Paolo Pastore, Matteo Santacesaria Published: 2026-03-03 Categories: math.NA, cs.IT, cs.LG, eess.SP, math.PR arXiv: https://arxiv.org/abs/2603.03196v1 Deep generative models have become a standard for modeling priors for inverse problems, going beyond classical sparsity-based methods. However, existing theoretical guarantees are mostly confined to finite-dimensional vector spaces, creating a gap when the physical signals are modeled as functions in Hilbert spaces. This work presents a rigorous framework for generative compressed sensing in Hilbert spaces. We extend the notion of local coherence in an infinite-dimensional setting, to derive optimal, resolution-independent sampling distributions. Thanks to a generalization of the Restricted Isometry Property, we show that stable recovery holds when the number of measurements is proportional to the prior's intrinsic dimension (up to logarithmic factors), independent of the ambient dimension. Finally, numerical experiments on the Darcy flow equation validate our theoretical findings and demonstrate that in severely undersampled regimes, employing lower-resolution generators acts as an implicit regularizer, improving reconstruction stability. --- ### Chain of World: World Model Thinking in Latent Motion Authors: Fuxiang Yang, Donglin Di, Lulu Tang, Xuancheng Zhang, Lei Fan, Hao Li, Chen Wei, Tonghua Su, Baorui Ma Published: 2026-03-03 Categories: cs.CV, cs.AI, cs.RO arXiv: https://arxiv.org/abs/2603.03195v1 Vision-Language-Action (VLA) models are a promising path toward embodied intelligence, yet they often overlook the predictive and temporal-causal structure underlying visual dynamics. World-model VLAs address this by predicting future frames, but waste capacity reconstructing redundant backgrounds. Latent-action VLAs encode frame-to-frame transitions compactly, but lack temporally continuous dynamic modeling and world knowledge. To overcome these limitations, we introduce CoWVLA (Chain-of-World VLA), a new "Chain of World" paradigm that unifies world-model temporal reasoning with a disentangled latent motion representation. First, a pretrained video VAE serves as a latent motion extractor, explicitly factorizing video segments into structure and motion latents. Then, during pre-training, the VLA learns from an instruction and an initial frame to infer a continuous latent motion chain and predict the segment's terminal frame. Finally, during co-fine-tuning, this latent dynamic is aligned with discrete action prediction by jointly modeling sparse keyframes and action sequences in a unified autoregressive decoder. This design preserves the world-model benefits of temporal reasoning and world knowledge while retaining the compactness and interpretability of latent actions, enabling efficient visuomotor learning. Extensive experiments on robotic simulation benchmarks show that CoWVLA outperforms existing world-model and latent-action approaches and achieves moderate computational efficiency, highlighting its potential as a more effective VLA pretraining paradigm. The project website can be found at https://fx-hit.github.io/cowvla-io. --- ### BeyondSWE: Can Current Code Agent Survive Beyond Single-Repo Bug Fixing? Authors: Guoxin Chen, Fanzhe Meng, Jiale Zhao, Minghao Li, Daixuan Cheng, Huatong Song, Jie Chen, Yuzhi Lin, Hui Chen, Xin Zhao, Ruihua Song, Chang Liu et al. Published: 2026-03-03 Categories: cs.CL, cs.SE arXiv: https://arxiv.org/abs/2603.03194v2 Current code-agent benchmarks primarily evaluate localized issue resolution within a single target repository, leaving under-tested many software engineering tasks that require external knowledge or broader repository-level changes. We introduce BeyondSWE, a 500-instance benchmark drawn from 246 real-world GitHub repositories to evaluate code agents beyond single-repository bug fixing. BeyondSWE covers four representative settings: cross-repository issue resolution, domain-specific issue resolution, dependency-driven migration, and document-to-repository generation, spanning both broader knowledge scope and broader resolution scope. Our evaluation shows that BeyondSWE remains far from saturated: the best OpenHands-based agent reaches 46.12 average score, while the strongest Codex harness with GPT-5.4 (xhigh) reaches 56.65 under a search-aware prompt. To study whether external information access closes this gap, we use SearchSWE as a controlled diagnostic baseline for search-augmented coding. Search access improves most models and substantially helps some tasks, but the gains remain limited and uneven, showing that current agents still struggle to convert retrieved information into precise, version-compatible, and locally actionable code changes. These results suggest that deep search for coding remains an open problem: progress requires agents that can reliably combine external evidence with repository-local reasoning and execution-based verification. --- ### MoD-DPO: Towards Mitigating Cross-modal Hallucinations in Omni LLMs using Modality Decoupled Preference Optimization Authors: Ashutosh Chaubey, Jiacheng Pang, Mohammad Soleymani Published: 2026-03-03 Categories: cs.CV, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2603.03192v2 Omni-modal large language models (omni LLMs) have recently achieved strong performance across audiovisual understanding tasks, yet they remain highly susceptible to cross-modal hallucinations arising from spurious correlations and dominant language priors. In this work, we propose Modality-Decoupled Direct Preference Optimization (MoD-DPO), a simple and effective framework for improving modality grounding in omni LLMs. MoD-DPO introduces modality-aware regularization terms that explicitly enforce invariance to corruptions in irrelevant modalities and sensitivity to perturbations in relevant modalities, thereby reducing unintended cross-modal interactions. To further mitigate over-reliance on textual priors, we incorporate a language-prior debiasing penalty that discourages hallucination-prone text-only responses. Extensive experiments across multiple audiovisual hallucination benchmarks demonstrate that MoD-DPO consistently improves perception accuracy and hallucination resistance, outperforming previous preference optimization baselines under similar training budgets. Our findings underscore the importance of modality-faithful alignment and demonstrate a scalable path toward more reliable and resilient multimodal foundation models. --- ### A Covering Framework for Offline POMDPs Learning using Belief Space Metric Authors: Youheng Zhu, Yiping Lu Published: 2026-03-03 Categories: stat.ML, cs.LG, math.OC arXiv: https://arxiv.org/abs/2603.03191v1 In off policy evaluation (OPE) for partially observable Markov decision processes (POMDPs), an agent must infer hidden states from past observations, which exacerbates both the curse of horizon and the curse of memory in existing OPE methods. This paper introduces a novel covering analysis framework that exploits the intrinsic metric structure of the belief space (distributions over latent states) to relax traditional coverage assumptions. By assuming value relevant functions are Lipschitz continuous in the belief space, we derive error bounds that mitigate exponential blow ups in horizon and memory length. Our unified analysis technique applies to a broad class of OPE algorithms, yielding concrete error bounds and coverage requirements expressed in terms of belief space metrics rather than raw history coverage. We illustrate the improved sample efficiency of this framework via case studies: the double sampling Bellman error minimization algorithm, and the memory based future dependent value functions (FDVF). In both cases, our coverage definition based on the belief space metric yields tighter bounds. --- ### Expectation and Acoustic Neural Network Representations Enhance Music Identification from Brain Activity Authors: Shogo Noguchi, Taketo Akama, Tai Nakamura, Shun Minamikawa, Natalia Polouliakh Published: 2026-03-03 Categories: cs.AI, q-bio.NC arXiv: https://arxiv.org/abs/2603.03190v3 During music listening, cortical activity encodes both acoustic and expectation-related information. Prior work has shown that ANN representations resemble cortical representations and can serve as supervisory signals for EEG recognition. Here we show that distinguishing acoustic and expectation-related ANN representations as teacher targets improves EEG-based music identification. Models pretrained to predict either representation outperform non-pretrained baselines, and combining them yields complementary gains that exceed strong seed ensembles formed by varying random initializations. These findings show that teacher representation type shapes downstream performance and that representation learning can be guided by neural encoding. This work points toward advances in predictive music cognition and neural decoding. Our expectation representation, computed directly from raw signals without manual labels, reflects predictive structure beyond onset or pitch, enabling investigation of multilayer predictive encoding across diverse stimuli. Its scalability to large, diverse datasets further suggests potential for developing general-purpose EEG models grounded in cortical encoding principles. --- ### Scalable Posterior Uncertainty for Flexible Density-Based Clustering Authors: Nicola Bariletto, Stephen G. Walker Published: 2026-03-03 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2603.03188v2 We introduce a novel framework for uncertainty quantification in clustering that combines martingale posterior distributions with density-based clustering. Unlike classical model-based approaches, which define clusters at the latent level of a mixture model, we treat clusters as explicit functionals of the data-generating density, without assuming any specific parametric form. To characterize density uncertainty, we obtain martingale posterior samples via a predictive resampling scheme driven by model score evaluations. This allows us to leverage state-of-the-art differentiable density estimators, such as normalizing flows, making density resampling efficient in large-scale settings and fully parallelizable on modern GPU hardware. Martingale posterior samples of the clustering structure are then obtained by applying density-based clustering to the density draws, enabling principled inference on any clustering-related quantity. Casting the inference target as a density functional further enables a rigorous theoretical analysis of the procedure's convergence properties. We apply our methodology to image and single-cell RNA sequencing data, demonstrating the computational efficiency afforded by its GPU compatibility as well as its ability to recover meaningful clustering structures, with associated uncertainty, across diverse domains. --- ### ProSMA-UNet: Decoder Conditioning for Proximal-Sparse Skip Feature Selection Authors: Chun-Wun Cheng, Yanqi Cheng, Peiyuan Jing, Guang Yang, Javier A. Montoya-Zegarra, Carola-Bibiane Schönlieb, Angelica I. Aviles-Rivero Published: 2026-03-03 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.03187v2 Medical image segmentation commonly relies on U-shaped encoder-decoder architectures such as U-Net, where skip connections preserve fine spatial detail by injecting high-resolution encoder features into the decoder. However, these skip pathways also propagate low-level textures, background clutter, and acquisition noise, allowing irrelevant information to bypass deeper semantic filtering -- an issue that is particularly detrimental in low-contrast clinical imaging. Although attention gates have been introduced to address this limitation, they typically produce dense sigmoid masks that softly reweight features rather than explicitly removing irrelevant activations. We propose ProSMA-UNet (Proximal-Sparse Multi-Scale Attention U-Net), which reformulates skip gating as a decoder-conditioned sparse feature selection problem. ProSMA constructs a multi-scale compatibility field using lightweight depthwise dilated convolutions to capture relevance across local and contextual scales, then enforces explicit sparsity via an $\ell_1$ proximal operator with learnable per-channel thresholds, yielding a closed-form soft-thresholding gate that can remove noisy responses. To further suppress semantically irrelevant channels, ProSMA incorporates decoder-conditioned channel gating driven by global decoder context. Extensive experiments on challenging 2D and 3D benchmarks demonstrate state-of-the-art performance, with particularly large gains ($\approx20$\%) on difficult 3D segmentation tasks. Project page: https://math-ml-x.github.io/ProSMA-UNet/ --- ### Type-Aware Retrieval-Augmented Generation with Dependency Closure for Solver-Executable Industrial Optimization Modeling Authors: Y. Zhong, R. Huang, M. Wang, Z. Guo, YC. Li, M. Yu, Z. Jin Published: 2026-03-03 Categories: cs.SE, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2603.03180v1 Automated industrial optimization modeling requires reliable translation of natural-language requirements into solver-executable code. However, large language models often generate non-compilable models due to missing declarations, type inconsistencies, and incomplete dependency contexts. We propose a type-aware retrieval-augmented generation (RAG) method that enforces modeling entity types and minimal dependency closure to ensure executability. Unlike existing RAG approaches that index unstructured text, our method constructs a domain-specific typed knowledge base by parsing heterogeneous sources, such as academic papers and solver code, into typed units and encoding their mathematical dependencies in a knowledge graph. Given a natural-language instruction, it performs hybrid retrieval and computes a minimal dependency-closed context, the smallest set of typed symbols required for solver-executable code, via dependency propagation over the graph. We validate the method on two constraint-intensive industrial cases: demand response optimization in battery production and flexible job shop scheduling. In the first case, our method generates an executable model incorporating demand-response incentives and load-reduction constraints, achieving peak shaving while preserving profitability; conventional RAG baselines fail. In the second case, it consistently produces compilable models that reach known optimal solutions, demonstrating robust cross-domain generalization; baselines fail entirely. Ablation studies confirm that enforcing type-aware dependency closure is essential for avoiding structural hallucinations and ensuring executability, addressing a critical barrier to deploying large language models in complex engineering optimization tasks. --- ### Neuro-Symbolic Artificial Intelligence: A Task-Directed Survey in the Black-Box Models Era Authors: Giovanni Pio Delvecchio, Lorenzo Molfetta, Gianluca Moro Published: 2026-03-03 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.03177v1 The integration of symbolic computing with neural networks has intrigued researchers since the first theorizations of Artificial intelligence (AI). The ability of Neuro-Symbolic (NeSy) methods to infer or exploit behavioral schema has been widely considered as one of the possible proxies for human-level intelligence. However, the limited semantic generalizability and the challenges in declining complex domains with pre-defined patterns and rules hinder their practical implementation in real-world scenarios. The unprecedented results achieved by connectionist systems since the last AI breakthrough in 2017 have raised questions about the competitiveness of NeSy solutions, with particular emphasis on the Natural Language Processing and Computer Vision fields. This survey examines task-specific advancements in the NeSy domain to explore how incorporating symbolic systems can enhance explainability and reasoning capabilities. Our findings are meant to serve as a resource for researchers exploring explainable NeSy methodologies for real-life tasks and applications. Reproducibility details and in-depth comments on each surveyed research work are made available at https://github.com/disi-unibo-nlp/task-oriented-neuro-symbolic.git. --- ### FEAST: Retrieval-Augmented Multi-Hierarchical Food Classification for the FoodEx2 System Authors: Lorenzo Molfetta, Alessio Cocchieri, Stefano Fantazzini, Giacomo Frisoni, Luca Ragazzi, Gianluca Moro Published: 2026-03-03 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.03176v1 Hierarchical text classification (HTC) and extreme multi-label classification (XML) tasks face compounded challenges from complex label interdependencies, data sparsity, and extreme output dimensions. These challenges are exemplified in the European Food Safety Authority's FoodEx2 system-a standardized food classification framework essential for food consumption monitoring and contaminant exposure assessment across Europe. FoodEx2 coding transforms natural language food descriptions into a set of codes from multiple standardized hierarchies, but faces implementation barriers due to its complex structure. Given a food description (e.g., "organic yogurt''), the system identifies its base term ("yogurt''), all the applicable facet categories (e.g., "production method''), and then, every relevant facet descriptors to each category (e.g., "organic production''). While existing models perform adequately on well-balanced and semantically dense hierarchies, no work has been applied on the practical constraints imposed by the FoodEx2 system. The limited literature addressing such real-world scenarios further compounds these challenges. We propose FEAST (Food Embedding And Semantic Taxonomy), a novel retrieval-augmented framework that decomposes FoodEx2 classification into a three-stage approach: (1) base term identification, (2) multi-label facet prediction, and (3) facet descriptor assignment. By leveraging the system's hierarchical structure to guide training and performing deep metric learning, FEASTlearns discriminative embeddings that mitigate data sparsity and improve generalization on rare and fine-grained labels. Evaluated on the multilingual FoodEx2 benchmark, FEAST outperforms the prior European's CNN baseline F1 scores by 12-38 % on rare classes. --- ### Saarthi for AGI: Towards Domain-Specific General Intelligence for Formal Verification Authors: Aman Kumar, Deepak Narayan Gadde, Luu Danh Minh, Vaisakh Naduvodi Viswambharan, Keerthan Kopparam Radhakrishna, Sivaram Pothireddypalli Published: 2026-03-03 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.03175v1 Saarthi is an agentic AI framework that uses multi-agent collaboration to perform end-to-end formal verification. Even though the framework provides a complete flow from specification to coverage closure, with around 40% efficacy, there are several challenges that need to be addressed to make it more robust and reliable. Artificial General Intelligence (AGI) is still a distant goal, and current Large Language Model (LLM)-based agents are prone to hallucinations and making mistakes, especially when dealing with complex tasks such as formal verification. However, with the right enhancements and improvements, we believe that Saarthi can be a significant step towards achieving domain-specific general intelligence for formal verification. Especially for problems that require Short Term, Short Context (STSC) capabilities, such as formal verification, Saarthi can be a powerful tool to assist verification engineers in their work. In this paper, we present two key enhancements to the Saarthi framework: (1) a structured rulebook and specification grammar to improve the accuracy and controllability of SystemVerilog Assertion (SVA) generation, and (2) integration of advanced Retrieval Augmented Generation (RAG) techniques, such as GraphRAG, to provide agents with access to technical knowledge and best practices for iterative refinement and improvement of outputs. We also benchmark these enhancements for the overall Saarthi framework using challenging test cases from NVIDIA's CVDP benchmark targeting formal verification. Our benchmark results stand out with a 70% improvement in the accuracy of generated assertions, and a 50% reduction in the number of iterations required to achieve coverage closure. --- ### Less Noise, Same Certificate: Retain Sensitivity for Unlearning Authors: Carolin Heinzler, Kasra Malihi, Amartya Sanyal Published: 2026-03-03 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.03172v1 Certified machine unlearning aims to provably remove the influence of a deletion set $U$ from a model trained on a dataset $S$, by producing an unlearned output that is statistically indistinguishable from retraining on the retain set $R:=S\setminus U$. Many existing certified unlearning methods adapt techniques from Differential Privacy (DP) and add noise calibrated to global sensitivity, i.e., the worst-case output change over all adjacent datasets. We show that this DP-style calibration is often overly conservative for unlearning, based on a key observation: certified unlearning, by definition, does not require protecting the privacy of the retained data $R$. Motivated by this distinction, we define retain sensitivity as the worst-case output change over deletions $U$ while keeping $R$ fixed. While insufficient for DP, retain sensitivity is exactly sufficient for unlearning, allowing for the same certificates with less noise. We validate these reductions in noise theoretically and empirically across several problems, including the weight of minimum spanning trees, PCA, and ERM. Finally, we refine the analysis of two widely used certified unlearning algorithms through the lens of retain sensitivity, leveraging the regularity induced by $R$ to further reduce noise and improve utility. --- ### Conditioned Activation Transport for T2I Safety Steering Authors: Maciej Chrabąszcz, Aleksander Szymczyk, Jan Dubiński, Tomasz Trzciński, Franziska Boenisch, Adam Dziedzic Published: 2026-03-03 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.03163v1 Despite their impressive capabilities, current Text-to-Image (T2I) models remain prone to generating unsafe and toxic content. While activation steering offers a promising inference-time intervention, we observe that linear activation steering frequently degrades image quality when applied to benign prompts. To address this trade-off, we first construct SafeSteerDataset, a contrastive dataset containing 2300 safe and unsafe prompt pairs with high cosine similarity. Leveraging this data, we propose Conditioned Activation Transport (CAT), a framework that employs a geometry-based conditioning mechanism and nonlinear transport maps. By conditioning transport maps to activate only within unsafe activation regions, we minimize interference with benign queries. We validate our approach on two state-of-the-art architectures: Z-Image and Infinity. Experiments demonstrate that CAT generalizes effectively across these backbones, significantly reducing Attack Success Rate while maintaining image fidelity compared to unsteered generations. Warning: This paper contains potentially offensive text and images. --- ### Kling-MotionControl Technical Report Authors: Kling Team, Jialu Chen, Yikang Ding, Zhixue Fang, Kun Gai, Kang He, Xu He, Jingyun Hua, Mingming Lao, Xiaohan Li, Hui Liu, Jiwen Liu et al. Published: 2026-03-03 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.03160v1 Character animation aims to generate lifelike videos by transferring motion dynamics from a driving video to a reference image. Recent strides in generative models have paved the way for high-fidelity character animation. In this work, we present Kling-MotionControl, a unified DiT-based framework engineered specifically for robust, precise, and expressive holistic character animation. Leveraging a divide-and-conquer strategy within a cohesive system, the model orchestrates heterogeneous motion representations tailored to the distinct characteristics of body, face, and hands, effectively reconciling large-scale structural stability with fine-grained articulatory expressiveness. To ensure robust cross-identity generalization, we incorporate adaptive identity-agnostic learning, facilitating natural motion retargeting for diverse characters ranging from realistic humans to stylized cartoons. Simultaneously, we guarantee faithful appearance preservation through meticulous identity injection and fusion designs, further supported by a subject library mechanism that leverages comprehensive reference contexts. To ensure practical utility, we implement an advanced acceleration framework utilizing multi-stage distillation, boosting inference speed by over 10x. Kling-MotionControl distinguishes itself through intelligent semantic motion understanding and precise text responsiveness, allowing for flexible control beyond visual inputs. Human preference evaluations demonstrate that Kling-MotionControl delivers superior performance compared to leading commercial and open-source solutions, achieving exceptional fidelity in holistic motion control, open domain generalization, and visual quality and coherence. These results establish Kling-MotionControl as a robust solution for high-quality, controllable, and lifelike character animation. --- ### An Investigation Into Various Approaches For Bengali Long-Form Speech Transcription and Bengali Speaker Diarization Authors: Epshita Jahan, Khandoker Md Tanjinul Islam, Pritom Biswas, Tafsir Al Nafin Published: 2026-03-03 Categories: cs.SD, cs.AI arXiv: https://arxiv.org/abs/2603.03158v1 Bengali remains a low-resource language in speech technology, especially for complex tasks like long-form transcription and speaker diarization. This paper presents a multistage approach developed for the "DL Sprint 4.0 - Bengali Long-Form Speech Recognition" and "DL Sprint 4.0 - Bengali Speaker Diarization" competitions on Kaggle, addressing the challenge of "who spoke when/what" in hour-long recordings. We implemented Whisper Medium fine-tuned on Bengali data (bengaliAI/tugstugi bengaliai-asr whisper-medium) for transcription and integrated pyannote/speaker-diarization-community-1 with our custom-trained segmentation model to handle diverse and noisy acoustic environments. Using a two-pass method with hyperparameter tuning, we achieved a DER of 0.27 on the private leaderboard and 0.19 on the public leaderboard. For transcription, chunking, background noise cleaning, and algorithmic post-processing yielded a WER of 0.38 on the private leaderboard. These results show that targeted tuning and strategic data utilization can significantly improve AI inclusivity for South Asian languages. All relevant code is available at: https://github.com/Short-Potatoes/Bengali-long-form-transcription-and-diarization.git Index Terms: Bengali speech recognition, speaker diarization, Whisper, ASR, low-resource languages, pyannote, voice activity detection --- ### Information Routing in Atomistic Foundation Models: How Task Alignment and Equivariance Shape Linear Disentanglement Authors: Joshua Steier Published: 2026-03-03 Categories: cs.LG, cs.AI, physics.chem-ph arXiv: https://arxiv.org/abs/2603.03155v2 What determines whether a molecular property prediction model organizes its representations so that geometric and compositional information can be cleanly separated? We introduce Compositional Probe Decomposition (CPD), which linearly projects out composition signal and measures how much geometric information remains accessible to a Ridge probe. We validate CPD with four independent checks, including a structural isomer benchmark where compositional projections score at chance while geometric residuals reach 94.6\% pairwise classification accuracy. Across ten models from five architectural families on QM9, we find a \emph{linear accessibility gradient}: models differ by $6.6\times$ in geometric information accessible after composition removal ($R^2_{\mathrm{geom}}$ from 0.081 to 0.533 for HOMO-LUMO gap). Three factors explain this gradient. Task alignment dominates: models trained on HOMO-LUMO gap ($R^2_{\mathrm{geom}}$ 0.44--0.53) outscore energy-trained models by $\sim$0.25 $R^2$ regardless of architecture. Within-architecture ablations on two independent architectures confirm this: PaiNN drops from 0.53 to 0.31 when retrained on energy, and MACE drops from 0.44 to 0.08. Data diversity partially compensates for misaligned objectives, with MACE pretrained on MPTraj (0.36) outperforming QM9-only energy models. Inside MACE's representations, information routes by symmetry type: $L{=}1$ (vector) channels preferentially encode dipole moment ($R^2 = 0.59$ vs.\ 0.38 in $L{=}0$), while $L{=}0$ (scalar) channels encode HOMO-LUMO gap ($R^2 = 0.76$ vs.\ 0.34 in $L{=}1$). This pattern is absent in ViSNet. We also show that nonlinear probes produce misleading results on residualized representations, recovering $R^2 = 0.68$--$0.95$ on a purely compositional target, and recommend linear probes for this setting. --- ### Agentic AI-based Coverage Closure for Formal Verification Authors: Sivaram Pothireddypalli, Ashish Raman, Deepak Narayan Gadde, Aman Kumar Published: 2026-03-03 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.03147v2 Coverage closure is a critical requirement in Integrated Chip (IC) development process and key metric for verification sign-off. However, traditional exhaustive approaches often fail to achieve full coverage within project timelines. This study presents an agentic AI-driven workflow that utilizes Large Language Model (LLM)-enabled Generative AI (GenAI) to automate coverage analysis for formal verification, identify coverage gaps, and generate the required formal properties. The framework accelerates verification efficiency by systematically addressing coverage holes. Benchmarking open-source and internal designs reveals a measurable increase in coverage metrics, with improvements correlated to the complexity of the design. Comparative analysis validates the effectiveness of this approach. These results highlight the potential of agentic AI-based techniques to improve formal verification productivity and support comprehensive coverage closure. --- ### Channel-Adaptive Edge AI: Maximizing Inference Throughput by Adapting Computational Complexity to Channel States Authors: Jierui Zhang, Jianhao Huang, Kaibin Huang Published: 2026-03-03 Categories: cs.IT, cs.AI, cs.LG, cs.NI arXiv: https://arxiv.org/abs/2603.03146v2 \emph{Integrated communication and computation} (IC$^2$) has emerged as a new paradigm for enabling efficient edge inference in sixth-generation (6G) networks. However, the design of IC$^2$ technologies is hindered by the lack of a tractable theoretical framework for characterizing \emph{end-to-end} (E2E) inference performance. The metric is highly complicated as it needs to account for both channel distortion and artificial intelligence (AI) model architecture and computational complexity. In this work, we address this challenge by developing a tractable analytical model for E2E inference accuracy and leveraging it to design a \emph{channel-adaptive AI} algorithm that maximizes inference throughput, referred to as the edge processing rate (EPR), under latency and accuracy constraints. Specifically, we consider an edge inference system in which a server deploys a backbone model with early exit, which enables flexible computational complexity, to perform inference on data features transmitted by a mobile device. The proposed accuracy model characterizes high-dimensional feature distributions in the angular domain using a Mixture of von Mises (MvM) distribution. This leads to a desired closed-form expression for inference accuracy as a function of quantization bit-width and model traversal depth, which represents channel distortion and computational complexity, respectively. Building upon this accuracy model, we formulate and solve the EPR maximization problem under joint latency and accuracy constraints, leading to a channel-adaptive AI algorithm that achieves full IC$^2$ integration. The proposed algorithm jointly adapts transmit-side feature compression and receive-side model complexity according to channel conditions to maximize overall efficiency and inference throughput. Experimental results demonstrate its superior performance as compared with fixed-complexity counterparts. --- ### Channel-Adaptive Edge AI: Maximizing Inference Throughput by Adapting Computational Complexity to Channel States Authors: Jierui Zhang, Jianhao Huang, Kaibin Huang Published: 2026-03-03 Categories: cs.IT, cs.AI, cs.LG, cs.NI arXiv: https://arxiv.org/abs/2603.03146v1 \emph{Integrated communication and computation} (IC$^2$) has emerged as a new paradigm for enabling efficient edge inference in sixth-generation (6G) networks. However, the design of IC$^2$ technologies is hindered by the lack of a tractable theoretical framework for characterizing \emph{end-to-end} (E2E) inference performance. The metric is highly complicated as it needs to account for both channel distortion and artificial intelligence (AI) model architecture and computational complexity. In this work, we address this challenge by developing a tractable analytical model for E2E inference accuracy and leveraging it to design a \emph{channel-adaptive AI} algorithm that maximizes inference throughput, referred to as the edge processing rate (EPR), under latency and accuracy constraints. Specifically, we consider an edge inference system in which a server deploys a backbone model with early exit, which enables flexible computational complexity, to perform inference on data features transmitted by a mobile device. The proposed accuracy model characterizes high-dimensional feature distributions in the angular domain using a Mixture of von Mises (MvM) distribution. This leads to a desired closed-form expression for inference accuracy as a function of quantization bit-width and model traversal depth, which represents channel distortion and computational complexity, respectively. Building upon this accuracy model, we formulate and solve the EPR maximization problem under joint latency and accuracy constraints, leading to a channel-adaptive AI algorithm that achieves full IC$^2$ integration. The proposed algorithm jointly adapts transmit-side feature compression and receive-side model complexity according to channel conditions to maximize overall efficiency and inference throughput. Experimental results demonstrate its superior performance as compared with fixed-complexity counterparts. --- ### Edit in 2D, Verify in 3D: Reinforcement Learning for Multi-view Consistent Scene Editing Authors: Jiyuan Wang, Chunyu Lin, Lei Sun, Zhi Cao, Yuyang Yin, Lang Nie, Zhenlong Yuan, Xiangxiang Chu, Yunchao Wei, Kang Liao, Guosheng Lin Published: 2026-03-03 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.03143v2 Leveraging the priors of 2D diffusion models for 3D editing has emerged as a promising paradigm. However, multi-view consistency remains challenging in edited results, and the extreme scarcity of paired 3D-consistent editing data makes supervised fine-tuning (SFT) impractical, despite its effectiveness for editing tasks. In this paper, we observe that, while generating multi-view consistent 3D content is highly challenging, verifying 3D consistency is tractable, naturally positioning reinforcement learning (RL) as a feasible solution. Motivated by this, we propose RL3DEdit, a single-pass framework driven by RL optimization with novel rewards derived from the 3D foundation model, VGGT. Specifically, we leverage VGGT's robust priors learned from massive real-world data, feed the edited images into it, and utilize the output confidence maps and pose estimation errors as reward signals, effectively anchoring the 2D editing priors onto a 3D-consistent manifold via RL. Extensive experiments demonstrate that RL3DEdit achieves stable multi-view consistency and outperforms state-of-the-art methods in editing quality with high efficiency. To promote the development of 3D editing, we will release the code and model. --- ### APRES: An Agentic Paper Revision and Evaluation System Authors: Bingchen Zhao, Jenny Zhang, Chenxi Whitehouse, Minqi Jiang, Michael Shvartsman, Abhishek Charnalia, Despoina Magka, Tatiana Shavrina, Derek Dunfield, Oisin Mac Aodha, Yoram Bachrach Published: 2026-03-03 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2603.03142v1 Scientific discoveries must be communicated clearly to realize their full potential. Without effective communication, even the most groundbreaking findings risk being overlooked or misunderstood. The primary way scientists communicate their work and receive feedback from the community is through peer review. However, the current system often provides inconsistent feedback between reviewers, ultimately hindering the improvement of a manuscript and limiting its potential impact. In this paper, we introduce a novel method APRES powered by Large Language Models (LLMs) to update a scientific papers text based on an evaluation rubric. Our automated method discovers a rubric that is highly predictive of future citation counts, and integrate it with APRES in an automated system that revises papers to enhance their quality and impact. Crucially, this objective should be met without altering the core scientific content. We demonstrate the success of APRES, which improves future citation prediction by 19.6% in mean averaged error over the next best baseline, and show that our paper revision process yields papers that are preferred over the originals by human expert evaluators 79% of the time. Our findings provide strong empirical support for using LLMs as a tool to help authors stress-test their manuscripts before submission. Ultimately, our work seeks to augment, not replace, the essential role of human expert reviewers, for it should be humans who discern which discoveries truly matter, guiding science toward advancing knowledge and enriching lives. --- ### How to Model AI Agents as Personas?: Applying the Persona Ecosystem Playground to 41,300 Posts on Moltbook for Behavioral Insights Authors: Danial Amin, Joni Salminen, Bernard J. Jansen Published: 2026-03-03 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2603.03140v3 AI agents are increasingly active on social media platforms, generating content and interacting with one another at scale. Yet the behavioral diversity of these agents remains poorly understood, and methods for characterizing distinct agent types and studying how they engage with shared topics are largely absent from current research. We apply the Persona Ecosystem Playground (PEP) to Moltbook, a social platform for AI agents, to generate and validate conversational personas from 41,300 posts using k-means clustering and retrieval-augmented generation. Cross-persona validation confirms that personas are semantically closer to their own source cluster than to others (t(61) = 17.85, p < .001, d = 2.20; own-cluster M = 0.71 vs. other-cluster M = 0.35). These personas are then deployed in a nine-turn structured discussion, and simulation messages were attributed to their source persona significantly above chance (binomial test, p < .001). The results indicate that persona-based ecosystem modeling can represent behavioral diversity in AI agent populations. --- ### Torus embeddings Authors: Dan Stowell Published: 2026-03-03 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.03135v1 Many data representations are vectors of continuous values. In particular, deep learning embeddings are data-driven representations, typically either unconstrained in Euclidean space, or constrained to a hypersphere. These may also be translated into integer representations (quantised) for efficient large-scale use. However, the fundamental (and most efficient) numeric representation in the overwhelming majority of existing computers is integers with overflow -- and vectors of these integers do not correspond to either of these spaces, but instead to the topology of a (hyper)torus. This mismatch can lead to wasted representation capacity. Here we show that common deep learning frameworks can be adapted, quite simply, to create representations with inherent toroidal topology. We investigate two alternative strategies, demonstrating that a normalisation-based strategy leads to training with desirable stability and performance properties, comparable to a standard hyperspherical L2 normalisation. We also demonstrate that a torus embedding maintains desirable quantisation properties. The torus embedding does not outperform hypersphere embeddings in general, but is comparable, and opens the possibility to train deep embeddings which have an extremely simple pathway to efficient `TinyML' embedded implementation. --- ### UniSkill: A Dataset for Matching University Curricula to Professional Competencies Authors: Nurlan Musazade, Joszef Mezei, Mike Zhang Published: 2026-03-03 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.03134v1 Skill extraction and recommendation systems have been studied from recruiter, applicant, and education perspectives. While AI applications in job advertisements have received broad attention, deficiencies in the instructed skills side remain a challenge. In this work, we address the scarcity of publicly available datasets by releasing both manually annotated and synthetic datasets of skills from the European Skills, Competences, Qualifications and Occupations (ESCO) taxonomy and university course pairs and publishing corresponding annotation guidelines. Specifically, we match graduate-level university courses with skills from the Systems Analysts and Management and Organization Analyst ESCO occupation groups at two granularities: course title with a skill, and course sentence with a skill. We train language models on this dataset to serve as a baseline for retrieval and recommendation systems for course-to-skill and skill-to-course matching. We evaluate the models on a portion of the annotated data. Our BERT model achieves 87% F1-score, showing that course and skill matching is a feasible task. --- ### Joint Training Across Multiple Activation Sparsity Regimes Authors: Haotian Wang Published: 2026-03-03 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.03131v1 Generalization in deep neural networks remains only partially understood. Inspired by the stronger generalization tendency of biological systems, we explore the hypothesis that robust internal representations should remain effective across both dense and sparse activation regimes. To test this idea, we introduce a simple training strategy that applies global top-k constraints to hidden activations and repeatedly cycles a single model through multiple activation budgets via progressive compression and periodic reset. Using CIFAR-10 without data augmentation and a WRN-28-4 backbone, we find in single-run experiments that two adaptive keep-ratio control strategies both outperform dense baseline training. These preliminary results suggest that joint training across multiple activation sparsity regimes may provide a simple and effective route to improved generalization. --- ### AWDiff: An a trous wavelet diffusion model for lung ultrasound image synthesis Authors: Maryam Heidari, Nantheera Anantrasirichai, Steven Walker, Rahul Bhatnagar, Alin Achim Published: 2026-03-03 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.03125v2 Lung ultrasound (LUS) is a safe and portable imaging modality, but the scarcity of data limits the development of machine learning methods for image interpretation and disease monitoring. Existing generative augmentation methods, such as Generative Adversarial Networks (GANs) and diffusion models, often lose subtle diagnostic cues due to resolution reduction, particularly B-lines and pleural irregularities. We propose A trous Wavelet Diffusion (AWDiff), a diffusion based augmentation framework that integrates the a trous wavelet transform to preserve fine-scale structures while avoiding destructive downsampling. In addition, semantic conditioning with BioMedCLIP, a vision language foundation model trained on large scale biomedical corpora, enforces alignment with clinically meaningful labels. On a LUS dataset, AWDiff achieved lower distortion and higher perceptual quality compared to existing methods, demonstrating both structural fidelity and clinical diversity. --- ### AI Space Physics: Constitutive boundary semantics for open AI institutions Authors: Oleg Romanchuk, Roman Bondar Published: 2026-03-03 Categories: cs.AI, cs.LO arXiv: https://arxiv.org/abs/2603.03119v1 Agentic AI deployments increasingly behave as persistent institutions rather than one-shot inference endpoints: they accumulate state, invoke external tools, coordinate multiple runtimes, and modify their future authority surface over time. Existing governance language typically specifies decision-layer constraints but leaves the causal mechanics of boundary crossing underdefined, particularly for transitions that do not immediately change the external world yet expand what the institution can later do. This paper introduces AI Space Physics as a constitutive semantics for open, self-expanding AI institutions. We define a minimal state model with typed boundary channels, horizon-limited reach semantics, and a membrane-witness discipline. The core law family (P-1, P-1a, P-1b, P-1c) requires witness completeness, non-bypass mediation, atomic adjudication-to-effect transitions, and replayable reconstruction of adjudication class. We explicitly separate second-order effects into structural expansion and policy broadening, and treat expansion transitions as governance-relevant even when immediate external deltas are zero. The novelty claim is precise rather than expansive: this work does not introduce mediation as a concept; it reclassifies authority-surface expansion as a first-class boundary event with constitutive witness obligations. In this semantics, expansion without immediate commit remains adjudication-relevant. --- ### Beyond Task Completion: Revealing Corrupt Success in LLM Agents through Procedure-Aware Evaluation Authors: Hongliu Cao, Ilias Driouich, Eoin Thomas Published: 2026-03-03 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.03116v1 Large Language Model (LLM)-based agents are increasingly adopted in high-stakes settings, but current benchmarks evaluate mainly whether a task was completed, not how. We introduce Procedure-Aware Evaluation (PAE), a framework that formalizes agent procedures as structured observations and exposes consistency relationships between what agents observe, communicate, and execute. PAE evaluates agents along complementary axes (Utility, Efficiency, Interaction Quality, Procedural Integrity) and applies multi-dimensional gating that categorically disqualifies corrupt outcomes. Evaluating state-of-the-art LLM agents on tau-bench yields findings at the axis, compliance, and benchmark levels. At the axis level, the dimensions capture non-redundant failure modes: utility masks reliability gaps, speed does not imply precision, and conciseness does not predict intent adherence. At the procedural compliance level, 27-78% of benchmark reported successes are corrupt successes concealing violations across interaction and integrity. Furthermore, gating substantially collapses Pass^4 rate and affects model rankings. The analysis of corrupt success cases reveals distinctive per-model failure signatures: GPT-5 spreads errors across policy, execution, and intent dimensions; Kimi-K2-Thinking concentrates 78% of violations in policy faithfulness and compliance; and Mistral-Large-3 is dominated by faithfulness failures. At the benchmark level, our analysis exposes structural flaws in the benchmark design, including task scope gaps, contradictory reward signals, and simulator artifacts that produce accidental successes. --- ### From Complex Dynamics to DynFormer: Rethinking Transformers for PDEs Authors: Pengyu Lai, Yixiao Chen, Dewu Yang, Rui Wang, Feng Wang, Hui Xu Published: 2026-03-03 Categories: cs.LG, cs.AI, nlin.CD arXiv: https://arxiv.org/abs/2603.03112v1 Partial differential equations (PDEs) are fundamental for modeling complex physical systems, yet classical numerical solvers face prohibitive computational costs in high-dimensional and multi-scale regimes. While Transformer-based neural operators have emerged as powerful data-driven alternatives, they conventionally treat all discretized spatial points as uniform, independent tokens. This monolithic approach ignores the intrinsic scale separation of physical fields, applying computationally prohibitive global attention that redundantly mixes smooth large-scale dynamics with high-frequency fluctuations. Rethinking Transformers through the lens of complex dynamics, we propose DynFormer, a novel dynamics-informed neural operator. Rather than applying a uniform attention mechanism across all scales, DynFormer explicitly assigns specialized network modules to distinct physical scales. It leverages a Spectral Embedding to isolate low-frequency modes, enabling a Kronecker-structured attention mechanism to efficiently capture large-scale global interactions with reduced complexity. Concurrently, we introduce a Local-Global-Mixing transformation. This module utilizes nonlinear multiplicative frequency mixing to implicitly reconstruct the small-scale, fast-varying turbulent cascades that are slaved to the macroscopic state, without incurring the cost of global attention. Integrating these modules into a hybrid evolutionary architecture ensures robust long-term temporal stability. Extensive memory-aligned evaluations across four PDE benchmarks demonstrate that DynFormer achieves up to a 95% reduction in relative error compared to state-of-the-art baselines, while significantly reducing GPU memory consumption. Our results establish that embedding first-principles physical dynamics into Transformer architectures yields a highly scalable, theoretically grounded blueprint for PDE surrogate modeling. --- ### Evaluating Performance Drift from Model Switching in Multi-Turn LLM Systems Authors: Raad Khraishi, Iman Zafar, Katie Myles, Greig A Cowan Published: 2026-03-03 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.03111v1 Deployed multi-turn LLM systems routinely switch models mid-interaction due to upgrades, cross-provider routing, and fallbacks. Such handoffs create a context mismatch: the model generating later turns must condition on a dialogue prefix authored by a different model, potentially inducing silent performance drift. We introduce a switch-matrix benchmark that measures this effect by running a prefix model for early turns and a suffix model for the final turn, and comparing against the no-switch baseline using paired episode-level bootstrap confidence intervals. Across CoQA conversational QA and Multi-IF benchmarks, even a single-turn handoff yields prevalent and statistically significant, directional effects and may swing outcomes by -8 to +13 percentage points in Multi-IF strict success rate and +/- 4 absolute F1 on CoQA, comparable to the no-switch gap between common model tiers (e.g., GPT-5-nano vs GPT-5-mini). We further find systematic compatibility patterns: some suffix models degrade under nearly any non-self dialogue history, while others improve under nearly any foreign prefix. To enable compressed handoff risk monitoring, we decompose switch-induced drift into per-model prefix influence and suffix susceptibility terms, accounting for ~70% of variance across benchmarks. These results position handoff robustness as an operational reliability dimension that single-model benchmarks miss, motivating explicit monitoring and handoff-aware mitigation in multi-turn systems. --- ### Multi-Scale Adaptive Neighborhood Awareness Transformer For Graph Fraud Detection Authors: Jiaqi Lv, Qingfeng Du, Yu Zhang, Yongqi Han, Sheng Li Published: 2026-03-03 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.03106v1 Graph fraud detection (GFD) is crucial for identifying fraudulent behavior within graphs, benefiting various domains such as financial networks and social media. Existing methods based on graph neural networks (GNNs) have succeeded considerably due to their effective expressive capacity for graph-structured data. However, the inherent inductive bias of GNNs, including the homogeneity assumption and the limited global modeling ability, hinder the effectiveness of these models. To address these challenges, we propose Multi-scale Neighborhood Awareness Transformer (MANDATE), which alleviates the inherent inductive bias of GNNs. Specifically, we design a multi-scale positional encoding strategy to encode the positional information of various distances from the central node. By incorporating it with the self-attention mechanism, the global modeling ability can be enhanced significantly. Meanwhile, we design different embedding strategies for homophilic and heterophilic connections. This mitigates the homophily distribution differences between benign and fraudulent nodes. Moreover, an embedding fusion strategy is designed for multi-relation graphs, which alleviates the distribution bias caused by different relationships. Experiments on three fraud detection datasets demonstrate the superiority of MANDATE. --- ### MoECLIP: Patch-Specialized Experts for Zero-shot Anomaly Detection Authors: Jun Yeong Park, JunYoung Seo, Minji Kang, Yu Rang Park Published: 2026-03-03 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.03101v2 The CLIP model's outstanding generalization has driven recent success in Zero-Shot Anomaly Detection (ZSAD) for detecting anomalies in unseen categories. The core challenge in ZSAD is to specialize the model for anomaly detection tasks while preserving CLIP's powerful generalization capability. Existing approaches attempting to solve this challenge share the fundamental limitation of a patch-agnostic design that processes all patches monolithically without regard for their unique characteristics. To address this limitation, we propose MoECLIP, a Mixture-of-Experts (MoE) architecture for the ZSAD task, which achieves patch-level adaptation by dynamically routing each image patch to a specialized Low-Rank Adaptation (LoRA) expert based on its unique characteristics. Furthermore, to prevent functional redundancy among the LoRA experts, we introduce (1) Frozen Orthogonal Feature Separation (FOFS), which orthogonally separates the input feature space to force experts to focus on distinct information, and (2) a simplex equiangular tight frame (ETF) loss to regulate the expert outputs to form maximally equiangular representations. Comprehensive experimental results across 14 benchmark datasets spanning industrial and medical domains demonstrate that MoECLIP outperforms existing state-of-the-art methods. The code is available at https://github.com/CoCoRessa/MoECLIP. --- ### Why Adam Can Beat SGD: Second-Moment Normalization Yields Sharper Tails Authors: Ruinan Jin, Yingbin Liang, Shaofeng Zou Published: 2026-03-03 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.03099v8 Despite Adam demonstrating faster empirical convergence than SGD in many applications, much of the existing theory yields guarantees essentially comparable to those of SGD, leaving the empirical performance gap insufficiently explained. In this paper, we uncover a key second-moment normalization in Adam and develop a stopping-time/martingale analysis that provably distinguishes Adam from SGD under the classical bounded variance model (a second moment assumption). In particular, we establish the first theoretical separation between the high-probability convergence behaviors of the two methods: Adam achieves a $δ^{-1/2}$ dependence on the confidence parameter $δ$, whereas corresponding high-probability guarantee for SGD necessarily incurs at least a $δ^{-1}$ dependence. --- ### Odin: Multi-Signal Graph Intelligence for Autonomous Discovery in Knowledge Graphs Authors: Muyukani Kizito, Elizabeth Nyambere Published: 2026-03-03 Categories: cs.AI, cs.DB arXiv: https://arxiv.org/abs/2603.03097v1 We present Odin, the first production-deployed graph intelligence engine for autonomous discovery of meaningful patterns in knowledge graphs without prior specification. Unlike retrieval-based systems that answer predefined queries, Odin guides exploration through the COMPASS (Composite Oriented Multi-signal Path Assessment) score, a novel metric that combines (1) structural importance via Personalized PageRank, (2) semantic plausibility through Neural Probabilistic Logic Learning (NPLL) used as a discriminative filter rather than generative model, (3) temporal relevance with configurable decay, and (4) community-aware guidance through GNN-identified bridge entities and inter-community affinity scores. This multi-signal integration, particularly the bridge scoring mechanism, addresses the "echo chamber" problem where graph exploration becomes trapped in dense local communities. We formalize the autonomous discovery problem, prove theoretical properties of our scoring function, and demonstrate that beam search with multi-signal guidance achieves $O(b \cdot h)$ complexity while maintaining high recall compared to exhaustive exploration. To our knowledge, Odin represents the first autonomous discovery system deployed in regulated production environments (healthcare and insurance), demonstrating significant improvements in pattern discovery quality and analyst efficiency. Our approach maintains complete provenance traceability -- a critical requirement for regulated industries where hallucination is unacceptable. --- ### Interpreting Speaker Characteristics in the Dimensions of Self-Supervised Speech Features Authors: Kyle Janse van Rensburg, Benjamin van Niekerk, Herman Kamper Published: 2026-03-03 Categories: eess.AS, cs.CL arXiv: https://arxiv.org/abs/2603.03096v2 How do speech models trained through self-supervised learning structure their representations? Previous studies have looked at how information is encoded in feature vectors across different layers. But few studies have considered whether speech characteristics are captured within individual dimensions of SSL features. In this paper we specifically look at speaker information using PCA on utterance-averaged representations. For a range of SSL models, we find that the principal dimension that explains most variance encodes pitch and associated characteristics like gender. Other individual principal dimensions correlate with intensity, noise levels, the second formant, and higher frequency characteristics. We then use synthesis analyses to show that the dimensions for most characteristics are isolated from each other's influence. We further show that characteristics can be changed by manipulating the corresponding dimensions. --- ### Compact Prompting in Instruction-tuned LLMs for Joint Argumentative Component Detection Authors: Sofiane Elguendouze, Erwan Hain, Elena Cabrio, Serena Villata Published: 2026-03-03 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2603.03095v1 Argumentative component detection (ACD) is a core subtask of Argument(ation) Mining (AM) and one of its most challenging aspects, as it requires jointly delimiting argumentative spans and classifying them into components such as claims and premises. While research on this subtask remains relatively limited compared to other AM tasks, most existing approaches formulate it as a simplified sequence labeling problem, component classification, or a pipeline of component segmentation followed by classification. In this paper, we propose a novel approach based on instruction-tuned Large Language Models (LLMs) using compact instruction-based prompts, and reframe ACD as a language generation task, enabling arguments to be identified directly from plain text without relying on pre-segmented components. Experiments on standard benchmarks show that our approach achieves higher performance compared to state-of-the-art systems. To the best of our knowledge, this is one of the first attempts to fully model ACD as a generative task, highlighting the potential of instruction tuning for complex AM problems. --- ### Proactive Guiding Strategy for Item-side Fairness in Interactive Recommendation Authors: Chongjun Xia, Xiaoyu Shi, Hong Xie, Xianzhi Wang, yun lu, Mingsheng Shang Published: 2026-03-03 Categories: cs.IR, cs.AI arXiv: https://arxiv.org/abs/2603.03094v1 Item-side fairness is crucial for ensuring the fair exposure of long-tail items in interactive recommender systems. Existing approaches promote the exposure of long-tail items by directly incorporating them into recommended results. This causes misalignment between user preferences and the recommended long-tail items, which hinders long-term user engagement and reduces the effectiveness of recommendations. We aim for a proactive fairness-guiding strategy, which actively guides user preferences toward long-tail items while preserving user satisfaction during the interactive recommendation process. To this end, we propose HRL4PFG, an interactive recommendation framework that leverages hierarchical reinforcement learning to guide user preferences toward long-tail items progressively. HRL4PFG operates through a macro-level process that generates fairness-guided targets based on multi-step feedback, and a micro-level process that fine-tunes recommendations in real time according to both these targets and evolving user preferences. Extensive experiments show that HRL4PFG improves cumulative interaction rewards and maximum user interaction length by a larger margin when compared with state-of-the-art methods in interactive recommendation environments. --- ### On the Expressive Power of Transformers for Maxout Networks and Continuous Piecewise Linear Functions Authors: Linyan Gu, Lihua Yang, Feng Zhou Published: 2026-03-03 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.03084v1 Transformer networks have achieved remarkable empirical success across a wide range of applications, yet their theoretical expressive power remains insufficiently understood. In this paper, we study the expressive capabilities of Transformer architectures. We first establish an explicit approximation of maxout networks by Transformer networks while preserving comparable model complexity. As a consequence, Transformers inherit the universal approximation capability of ReLU networks under similar complexity constraints. Building on this connection, we develop a framework to analyze the approximation of continuous piecewise linear functions by Transformers and quantitatively characterize their expressivity via the number of linear regions, which grows exponentially with depth. Our analysis establishes a theoretical bridge between approximation theory for standard feedforward neural networks and Transformer architectures. It also yields structural insights into Transformers: self-attention layers implement max-type operations, while feedforward layers realize token-wise affine transformations. --- ### Safe and Robust Domains of Attraction for Discrete-Time Systems: A Set-Based Characterization and Certifiable Neural Network Estimation Authors: Mohamed Serry, Maxwell Fitzsimmons, Jun Liu Published: 2026-03-03 Categories: eess.SY, cs.LG, math.DS, math.OC arXiv: https://arxiv.org/abs/2603.03082v1 Analyzing nonlinear systems with attracting robust invariant sets (RISs) requires estimating their domains of attraction (DOAs). Despite extensive research, accurately characterizing DOAs for general nonlinear systems remains challenging due to both theoretical and computational limitations, particularly in the presence of uncertainties and state constraints. In this paper, we propose a novel framework for the accurate estimation of safe (state-constrained) and robust DOAs for discrete-time nonlinear uncertain systems with continuous dynamics, open safe sets, compact disturbance sets, and uniformly locally $\ell_p$-stable compact RISs. The notion of uniform $\ell_p$ stability is quite general and encompasses, as special cases, uniform exponential and polynomial stability. The DOAs are characterized via newly introduced value functions defined on metric spaces of compact sets. We establish their fundamental mathematical properties and derive the associated Bellman-type (Zubov-type) functional equations. Building on this characterization, we develop a physics-informed neural network (NN) framework to learn the corresponding value functions by embedding the derived Bellman-type equations directly into the training process. To obtain certifiable estimates of the safe robust DOAs from the learned neural approximations, we further introduce a verification procedure that leverages existing formal verification tools. The effectiveness and applicability of the proposed methodology are demonstrated through four numerical examples involving nonlinear uncertain systems subject to state constraints, and its performance is compared with existing methods from the literature. --- ### TAO-Attack: Toward Advanced Optimization-Based Jailbreak Attacks for Large Language Models Authors: Zhi Xu, Jiaqi Li, Xiaotong Zhang, Hong Yu, Han Liu Published: 2026-03-03 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.03081v1 Large language models (LLMs) have achieved remarkable success across diverse applications but remain vulnerable to jailbreak attacks, where attackers craft prompts that bypass safety alignment and elicit unsafe responses. Among existing approaches, optimization-based attacks have shown strong effectiveness, yet current methods often suffer from frequent refusals, pseudo-harmful outputs, and inefficient token-level updates. In this work, we propose TAO-Attack, a new optimization-based jailbreak method. TAO-Attack employs a two-stage loss function: the first stage suppresses refusals to ensure the model continues harmful prefixes, while the second stage penalizes pseudo-harmful outputs and encourages the model toward more harmful completions. In addition, we design a direction-priority token optimization (DPTO) strategy that improves efficiency by aligning candidates with the gradient direction before considering update magnitude. Extensive experiments on multiple LLMs demonstrate that TAO-Attack consistently outperforms state-of-the-art methods, achieving higher attack success rates and even reaching 100\% in certain scenarios. --- ### Beyond Factual Correctness: Mitigating Preference-Inconsistent Explanations in Explainable Recommendation Authors: Chengkai Wang, Baisong Liu Published: 2026-03-03 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.03080v2 LLM-based explainable recommenders can produce fluent explanations that are factually correct, yet still justify items using attributes that conflict with a user's historical preferences. Such preference-inconsistent explanations yield logically valid but unconvincing reasoning and are largely missed by standard hallucination or faithfulness metrics. We formalize this failure mode and propose PURE, a preference-aware reasoning framework following a select-then-generate paradigm. Instead of only improving generation, PURE intervenes in evidence selection, it selects a compact set of multi-hop item-centric reasoning paths that are both factually grounded and aligned with user preference structure, guided by user intent, specificity, and diversity to suppress generic, weakly personalized evidence. The selected evidence is then injected into LLM generation via structure-aware prompting that preserves relational constraints. To measure preference inconsistency, we introduce a feature-level, user-centric evaluation metric that reveals misalignment overlooked by factuality-based measures. Experiments on three real-world datasets show that PURE consistently reduces preference-inconsistent explanations and factual hallucinations while maintaining competitive recommendation accuracy, explanation quality, and inference efficiency. These results highlight that trustworthy explanations require not only factual correctness but also justification aligned with user preferences. --- ### RAPO: Expanding Exploration for LLM Agents via Retrieval-Augmented Policy Optimization Authors: Siwei Zhang, Yun Xiong, Xi Chen, Zi'an Jia, Renhong Huang, Jiarong Xu, Jiawei Zhang Published: 2026-03-03 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.03078v1 Agentic Reinforcement Learning (Agentic RL) has shown remarkable potential in large language model-based (LLM) agents. These works can empower LLM agents to tackle complex tasks via multi-step, tool-integrated reasoning. However, an inherent limitation of existing Agentic RL methods is their reliance on a pure on-policy paradigm for exploration, restricting exploration to the agent's self-generated outputs and preventing the discovery of new reasoning perspectives for further improvement. While recent efforts incorporate auxiliary off-policy signals to enhance exploration, they typically utilize full off-policy trajectories for trajectory-level policy estimation, overlooking the necessity for the fine-grained, step-level exploratory dynamics within agentic rollout. In this paper, we revisit exploration in Agentic RL and propose Retrieval-Augmented Policy Optimization (RAPO), a novel RL framework that introduces retrieval to explicitly expand exploration during training. To achieve this, we decompose the Agentic RL training process into two phases: (i) Hybrid-policy Agentic Rollout, and (ii) Retrieval-aware Policy Optimization. Specifically, we propose a Hybrid-policy Agentic Rollout strategy, which allows the agents to continuously reason over the retrieved off-policy step-level traces. It dynamically extends the reasoning receptive field of agents, enabling broader exploration conditioned on external behaviors. Subsequently, we introduce the Retrieval-aware Policy Optimization mechanism, which calibrates the policy gradient estimation with retrieval reward and importance shaping, stabilizing training and prioritizing retrieval-illuminating exploration. Extensive experiments show that RAPO achieves an +5.0% average gain on fourteen datasets across three agentic reasoning tasks, while delivering 1.2x faster training efficiency. --- ### TinyIceNet: Low-Power SAR Sea Ice Segmentation for On-Board FPGA Inference Authors: Mhd Rashed Al Koutayni, Mohamed Selim, Gerd Reis, Alain Pagani, Didier Stricker Published: 2026-03-03 Categories: cs.CV, cs.AI, cs.AR arXiv: https://arxiv.org/abs/2603.03075v1 Accurate sea ice mapping is essential for safe maritime navigation in polar regions, where rapidly changing ice conditions require timely and reliable information. While Sentinel-1 Synthetic Aperture Radar (SAR) provides high-resolution, all-weather observations of sea ice, conventional ground-based processing is limited by downlink bandwidth, latency, and energy costs associated with transmitting large volumes of raw data. On-board processing, enabled by dedicated inference chips integrated directly within the satellite payload, offers a transformative alternative by generating actionable sea ice products in orbit. In this context, we present TinyIceNet, a compact semantic segmentation network co-designed for on-board Stage of Development (SOD) mapping from dual-polarized Sentinel-1 SAR imagery under strict hardware and power constraints. Trained on the AI4Arctic dataset, TinyIceNet combines SAR-aware architectural simplifications with low-precision quantization to balance accuracy and efficiency. The model is synthesized using High-Level Synthesis and deployed on a Xilinx Zynq UltraScale+ FPGA platform, demonstrating near-real-time inference with significantly reduced energy consumption. Experimental results show that TinyIceNet achieves 75.216% F1 score on SOD segmentation while reducing energy consumption by 2x compared to full-precision GPU baselines, underscoring the potential of chip-level hardware-algorithm co-design for future spaceborne and edge AI systems. --- ### Design Generative AI for Practitioners: Exploring Interaction Approaches Aligned with Creative Practice Authors: Xiaohan Peng, Wendy E. Mackay, Janin Koch Published: 2026-03-03 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2603.03074v1 Design is a non-linear, reflective process in which practitioners engage with visual, semantic, and other expressive materials to explore, iterate, and refine ideas. As Generative AI (GenAI) becomes integrated into professional design practice, traditional interaction approaches focusing on prompts or whole-image manipulation can misalign AI output with designers' intent, forcing visual thinkers into verbal reasoning or post-hoc adjustments. We present three interaction approaches from DesignPrompt, FusAIn, and DesignTrace that distribute control across intent, input, and process, enabling designers to guide AI alignment at different stages of interaction. We further argue that alignment is a dynamic negotiation, with AI adopting proactive or reactive roles according to designers' instrumental and inspirational needs and the creative stage. --- ### TikZilla: Scaling Text-to-TikZ with High-Quality Data and Reinforcement Learning Authors: Christian Greisinger, Steffen Eger Published: 2026-03-03 Categories: cs.AI, cs.CL, cs.CV arXiv: https://arxiv.org/abs/2603.03072v3 Large language models (LLMs) are increasingly used to assist scientists across diverse workflows. A key challenge is generating high-quality figures from textual descriptions, often represented as TikZ programs that can be rendered as scientific images. Prior research has proposed a variety of datasets and modeling approaches for this task. However, existing datasets for Text-to-TikZ are too small and noisy to capture the complexity of TikZ, causing mismatches between text and rendered figures. Moreover, prior approaches rely solely on supervised fine-tuning (SFT), which does not expose the model to the rendered semantics of the figure, often resulting in errors such as looping, irrelevant content, and incorrect spatial relations. To address these issues, we construct DaTikZ-V4, a dataset more than four times larger and substantially higher in quality than DaTikZ-V3, enriched with LLM-generated figure descriptions. Using this dataset, we train TikZilla, a family of small open-source Qwen models (3B and 8B) with a two-stage pipeline of SFT followed by reinforcement learning (RL). For RL, we leverage an image encoder trained via inverse graphics to provide semantically faithful reward signals. Extensive human evaluations with over 1,000 judgments show that TikZilla improves by 1.5-2 points over its base models on a 5-point scale, surpasses GPT-4o by 0.5 points, and matches GPT-5 in the image-based evaluation, while operating at much smaller model sizes. --- ### TikZilla: Scaling Text-to-TikZ with High-Quality Data and Reinforcement Learning Authors: Christian Greisinger, Steffen Eger Published: 2026-03-03 Categories: cs.AI, cs.CL, cs.CV arXiv: https://arxiv.org/abs/2603.03072v2 Large language models (LLMs) are increasingly used to assist scientists across diverse workflows. A key challenge is generating high-quality figures from textual descriptions, often represented as TikZ programs that can be rendered as scientific images. Prior research has proposed a variety of datasets and modeling approaches for this task. However, existing datasets for Text-to-TikZ are too small and noisy to capture the complexity of TikZ, causing mismatches between text and rendered figures. Moreover, prior approaches rely solely on supervised fine-tuning (SFT), which does not expose the model to the rendered semantics of the figure, often resulting in errors such as looping, irrelevant content, and incorrect spatial relations. To address these issues, we construct DaTikZ-V4, a dataset more than four times larger and substantially higher in quality than DaTikZ-V3, enriched with LLM-generated figure descriptions. Using this dataset, we train TikZilla, a family of small open-source Qwen models (3B and 8B) with a two-stage pipeline of SFT followed by reinforcement learning (RL). For RL, we leverage an image encoder trained via inverse graphics to provide semantically faithful reward signals. Extensive human evaluations with over 1,000 judgments show that TikZilla improves by 1.5-2 points over its base models on a 5-point scale, surpasses GPT-4o by 0.5 points, and matches GPT-5 in the image-based evaluation, while operating at much smaller model sizes. Code, data, and models will be made available. --- ### From Reachability to Learnability: Geometric Design Principles for Quantum Neural Networks Authors: Vishal S. Ngairangbam, Michael Spannowsky Published: 2026-03-03 Categories: quant-ph, cs.LG, hep-ex, hep-ph, stat.ML arXiv: https://arxiv.org/abs/2603.03071v2 Classical deep networks are effective because depth enables adaptive geometric deformation of data representations. In quantum neural networks (QNNs), however, depth or state reachability alone does not guarantee this feature-learning capability. We study this question in the pure-state setting by viewing encoded data as an embedded manifold in $\mathbb{C}P^{2^n-1}$ and analysing infinitesimal unitary actions through Lie-algebra directions. We introduce Classical-to-Lie-algebra (CLA) maps and the criterion of almost Complete Local Selectivity (aCLS), which combines directional completeness with data-dependent local selectivity. Within this framework, we show that data-independent trainable unitaries are complete but non-selective, i.e. learnable rigid reorientations, whereas pure data encodings are selective but non-tunable, i.e. fixed deformations. Hence, geometric flexibility requires a non-trivial joint dependence on data and trainable weights. We further show that accessing high-dimensional deformations of many-qubit state manifolds requires parametrised entangling directions; fixed entanglers such as CNOT alone do not provide adaptive geometric control. Numerical examples validate that aCLS-satisfying data re-uploading models outperform non-tunable schemes while requiring only a quarter of the gate operations. Thus, the resulting picture reframes QNN design from state reachability to controllable geometry of hidden quantum representations. ---