# Research Papers — 2026-03 · bundle page 32 of 243

> Full-text markdown of papers #1551–1600 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/32
[← Previous bundle](https://aipod.dev/papers/archive/2026-03/page/31.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-03/page/33.md)

### Verify Claimed Text-to-Image Models via Boundary-Aware Prompt Optimization

Authors: Zidong Zhao, Yihao Huang, Qing Guo, Tianlin Li, Anran Li, Kailong Wang, Jin Song Dong, Geguang Pu
Published: 2026-03-27
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.26328v1

As Text-to-Image (T2I) generation becomes widespread, third-party platforms increasingly integrate multiple model APIs for convenient image creation. However, false claims of using official models can mislead users and harm model owners' reputations, making model verification essential to confirm whether an API's underlying model matches its claim. Existing methods address this by using verification prompts generated by official model owners, but the generation relies on multiple reference models for optimization, leading to high computational cost and sensitivity to model selection. To address this problem, we propose a reference-free T2I model verification method called Boundary-aware Prompt Optimization (BPO). It directly explores the intrinsic characteristics of the target model. The key insight is that although different T2I models produce similar outputs for normal prompts, their semantic boundaries in the embedding space (transition zones between two concepts such as "corgi" and "bagel") are distinct. Prompts near these boundaries generate unstable outputs (e.g., sometimes a corgi and sometimes a bagel) on the target model but remain stable on other models. By identifying such boundary-adjacent prompts, BPO captures model-specific behaviors that serve as reliable verification cues for distinguishing T2I models. Experiments on five T2I models and four baselines demonstrate that BPO achieves superior verification accuracy.

---

### Making Multi-Axis Models Robust to Multiplicative Noise: How, and Why?

Authors: Bailey Andrew, David R. Westhead, Luisa Cutillo
Published: 2026-03-27
Categories: stat.ME, cs.LG
arXiv: https://arxiv.org/abs/2603.26327v1

In this paper we develop a graph-learning algorithm, MED-MAGMA, to fit multi-axis (Kronecker-sum-structured) models corrupted by multiplicative noise. This type of noise is natural in many application domains, such as that of single-cell RNA sequencing, in which it naturally captures technical biases of RNA sequencing platforms. Our work is evaluated against prior work on each and every public dataset in the Single Cell Expression Atlas under a certain size, demonstrating that our methodology learns networks with better local and global structure. MED-MAGMA is made available as a Python package (MED-MAGMA).

---

### PRISMA: Toward a Normative Information Infrastructure for Responsible Pharmaceutical Knowledge Management

Authors: Eugenio Rodrigo Zimmer Neves, Amanda Vanon Correa, Camila Campioni, Gabielli Pare Guglielmi, Bruno Morelli
Published: 2026-03-27
Categories: cs.DL, cs.AI, cs.CY
arXiv: https://arxiv.org/abs/2603.26324v1

Most existing approaches to AI in pharmacy collapse three epistemologically distinct operations into a single technical layer: document preservation, semantic interpretation, and contextual presentation. This conflation is a root cause of recurring fragilities including loss of provenance, interpretive opacity, alert fatigue, and erosion of accountability. This paper proposes the PATOS--Lector--PRISMA (PLP) infrastructure as a normative information architecture for responsible pharmaceutical knowledge management. PATOS preserves regulatory documents with explicit versioning and provenance; Lector implements machine-assisted reading with human curation, producing typed assertions anchored to primary sources; PRISMA delivers contextual presentation through the RPDA framework (Regulatory, Prescription, Dispensing, Administration), refracting the same informational core into distinct professional views. The architecture introduces the Evidence Pack as a formal unit of accountable assertion (versioned, traceable, epistemically bounded, and curatorially validated), with assertions typified by illocutionary force. A worked example traces dipyrone monohydrate across all three layers using real system data. Developed and validated in Brazil's regulatory context, the architecture is grounded in an operational implementation comprising over 16,000 official documents and 38 curated Evidence Packs spanning five reference medications. The proposal is demonstrated as complementary to operational decision support systems, providing infrastructural conditions that current systems lack: documentary anchoring, interpretive transparency, and institutional accountability.

---

### From Human Cognition to Neural Activations: Probing the Computational Primitives of Spatial Reasoning in LLMs

Authors: Jiyuan An, Liner Yang, Mengyan Wang, Luming Lu, Weihua An, Erhong Yang
Published: 2026-03-27
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2603.26323v1

As spatial intelligence becomes an increasingly important capability for foundation models, it remains unclear whether large language models' (LLMs) performance on spatial reasoning benchmarks reflects structured internal spatial representations or reliance on linguistic heuristics. We address this question from a mechanistic perspective by examining how spatial information is internally represented and used. Drawing on computational theories of human spatial cognition, we decompose spatial reasoning into three primitives, relational composition, representational transformation, and stateful spatial updating, and design controlled task families for each. We evaluate multilingual LLMs in English, Chinese, and Arabic under single pass inference, and analyze internal representations using linear probing, sparse autoencoder based feature analysis, and causal interventions. We find that task relevant spatial information is encoded in intermediate layers and can causally influence behavior, but these representations are transient, fragmented across task families, and weakly integrated into final predictions. Cross linguistic analysis further reveals mechanistic degeneracy, where similar behavioral performance arises from distinct internal pathways. Overall, our results suggest that current LLMs exhibit limited and context dependent spatial representations rather than robust, general purpose spatial reasoning, highlighting the need for mechanistic evaluation beyond benchmark accuracy.

---

### DFM-VLA: Iterative Action Refinement for Robot Manipulation via Discrete Flow Matching

Authors: Jiayi Chen, Wenxuan Song, Jiaxin Fang, Ruiqing Yin, Jingbo Wang, Shuai Chen, Jieyuan Pei, Yikai Qin, Feifan Chen, Haodong Yan, Zhide Zhong, Wen Chen et al.
Published: 2026-03-27
Categories: cs.RO, cs.CV
arXiv: https://arxiv.org/abs/2603.26320v4

Vision-Language-Action (VLA) models that encode actions using a discrete tokenization scheme have been widely adopted for robotic manipulation, but existing decoding paradigms remain fundamentally limited. Whether actions are decoded sequentially by autoregressive VLAs or in parallel by discrete diffusion VLAs, once a token is generated, it is typically fixed and cannot be revised in subsequent iterations. Consequently, early token errors cannot be effectively corrected later. We propose DFM-VLA, a discrete flow matching VLA that iteratively refines action tokens. DFM-VLA models a token-level probability velocity field that dynamically updates the full action sequence across refinement iterations. We investigate two approaches to constructing the velocity field: an auxiliary velocity-head formulation and an embedding-guided formulation. To further improve prediction accuracy, we introduce a metric-aligned action tokenizer (MAAT) tailored to the coarse-to-fine nature of DFM, together with a two-stage decoding strategy. Extensive experiments on CALVIN, LIBERO, LIBERO-Plus, and real-world manipulation tasks demonstrate the effectiveness of our approach. Our project is available at https://chris1220313648.github.io/DFM-VLA/.

---

### STN-GPR: A Singularity Tensor Network Framework for Efficient Option Pricing

Authors: Dominic Gribben, Carolina Allende, Alba Villarino, Aser Cortines, Mazen Ali, Román Orús, Pascal Oswald, Noureddine Lehdili
Published: 2026-03-27
Categories: q-fin.PR, cs.CE, cs.LG, quant-ph
arXiv: https://arxiv.org/abs/2603.26318v1

We develop a tensor-network surrogate for option pricing, targeting large-scale portfolio revaluation problems arising in market risk management (e.g., VaR and Expected Shortfall computations). The method involves representing high-dimensional price surfaces in tensor-train (TT) form using TT-cross approximation, constructing the surrogate directly from black-box price evaluations without materializing the full training tensor. For inference, we use a Laplacian kernel and derive TT representations of the kernel matrix and its closed-form inverse in the noise-free setting, enabling TT-based Gaussian process regression without dense matrix factorization or iterative linear solves. We found that hyperparameter optimization consistently favors a large kernel length-scale and show that in this regime the GPR predictor reduces to multilinear interpolation for off-grid inputs; we also derive a low-rank TT representation for this limit. We evaluate the approach on five-asset basket options over an eight dimensional parameter space (asset spot levels, strike, interest rate, and time to maturity). For European geometric basket puts, the tensor surrogate achieves lower test error at shorter training times than standard GPR by scaling to substantially larger effective training sets. For American arithmetic basket puts trained on LSMC data, the surrogate exhibits more favorable scaling with training-set size while providing millisecond-level evaluation per query, with overall runtime dominated by data generation.

---

### Label-Free Cross-Task LoRA Merging with Null-Space Compression

Authors: Wonyoung Lee, Wooseong Jeong, Kuk-Jin Yoon
Published: 2026-03-27
Categories: cs.CV, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2603.26317v1

Model merging combines independently fine-tuned checkpoints without joint multi-task training. In the era of foundation-model, fine-tuning with Low-Rank Adaptation (LoRA) is prevalent, making LoRA merging a promising target. Existing approaches can work in homogeneous settings where all target tasks are classification but often fail when tasks span classification and regression. Approaches using entropy-based surrogates do not apply to regression and are costly for large language models due to long token sequences. We introduce Null-Space Compression (NSC) Merging, a label-free, output-agnostic method that sets merge weights from adapter geometry. Our key observation is that during LoRA finetuning the down-projection factor $A$ in $ΔW = BA$ compresses its null space, and the compression correlates with performance. NSC uses this as an optimization signal for merging that can generalize across classification, regression, and sequence generation. NSC achieves state-of-the-art performance across twenty heterogeneous vision tasks with balanced gains where prior methods overfit subsets of tasks. It also outperforms baselines on six NLI benchmarks and on vision-language evaluations for VQA and image captioning, demonstrating scalability and effectiveness.

---

### SALMUBench: A Benchmark for Sensitive Association-Level Multimodal Unlearning

Authors: Cai Selvas-Sala, Lei Kang, Lluis Gomez
Published: 2026-03-27
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2603.26316v1

As multimodal models like CLIP become integral to downstream systems, the need to remove sensitive information is critical. However, machine unlearning for contrastively-trained encoders remains underexplored, and existing evaluations fail to diagnose fine-grained, association-level forgetting. We introduce SALMUBench (Sensitive Association-Level Multimodal Unlearning), a benchmark built upon a synthetic dataset of 60K persona-attribute associations and two foundational models: a Compromised model polluted with this data, and a Clean model without it. To isolate unlearning effects, both are trained from scratch on the same 400M-pair retain base, with the Compromised model additionally trained on the sensitive set. We propose a novel evaluation protocol with structured holdout sets (holdout identity, holdout association) to precisely measure unlearning efficacy and collateral damage. Our benchmark reveals that while utility-efficient deletion is feasible, current methods exhibit distinct failure modes: they either fail to forget effectively or over-generalize by erasing more than intended. SALMUBench sets a new standard for comprehensive unlearning evaluation, and we publicly release our dataset, models, evaluation scripts, and leaderboards to foster future research.

---

### Semi-structured multi-state delinquency model for mortgage default

Authors: Victor Medina-Olivares, Wangzhen Xia, Stefan Lessmann, Nadja Klein
Published: 2026-03-27
Categories: stat.AP, cs.LG, q-fin.RM
arXiv: https://arxiv.org/abs/2603.26309v1

We propose a semi-structured discrete-time multi-state model to analyse mortgage delinquency transitions. This model combines an easy-to-understand structured additive predictor, which includes linear effects and smooth functions of time and covariates, with a flexible neural network component that captures complex nonlinearities and higher-order interactions. To ensure identifiability when covariates are present in both components, we orthogonalise the unstructured part relative to the structured design. For discrete-time competing transitions, we derive exact transformations that map binary logistic models to valid competing transition probabilities, avoiding the need for continuous-time approximations. In simulations, our framework effectively recovers structured baseline and covariate effects while using the neural component to detect interaction patterns. We demonstrate the method using the Freddie Mac Single-Family Loan-Level Dataset, employing an out-of-time test design. Compared with a structured generalised additive benchmark, the semi-structured model provides modest but consistent gains in discrimination across the earliest prediction spans, while maintaining similar Brier scores. Adding macroeconomic indicators provides limited incremental benefit in this out-of-time evaluation and does not materially change the estimated borrower-, loan-, or duration-driven effects. Overall, semi-structured multi-state modelling offers a practical compromise between transparent effect estimates and flexible pattern learning, with potential applications beyond credit-transition forecasting.

---

### D-GATNet: Interpretable Temporal Graph Attention Learning for ADHD Identification Using Dynamic Functional Connectivity

Authors: Qurat Ul Ain, Alptekin Temizel, Soyiba Jawed
Published: 2026-03-27
Categories: cs.LG
arXiv: https://arxiv.org/abs/2603.26308v1

Attention Deficit Hyperactivity Disorder (ADHD) is a prevalent neurodevelopmental disorder whose neuroimaging-based diagnosis remains challenging due to complex time-varying disruptions in brain connectivity. Functional MRI (fMRI) provides a powerful non-invasive modality for identifying functional alterations. Existing deep learning (DL) studies employ diverse neuroimaging features; however, static functional connectivity remains widely used, whereas dynamic connectivity modeling is comparatively underexplored. Moreover, many DL models lack interpretability. In this work, we propose D-GATNet, an interpretable temporal graph-based framework for automated ADHD classification using dynamic functional connectivity (dFC). Sliding-window Pearson correlation constructs sequences of functional brain graphs with regions of interest as nodes and connectivity strengths as edges. Spatial dependencies are learned via a multi-layer Graph Attention Network, while temporal dynamics are modeled using 1D convolution followed by temporal attention. Interpretability is achieved through graph attention weights revealing dominant ROI interactions, ROI importance scores identifying influential regions, and temporal attention emphasizing informative connectivity segments. Experiments on the Peking University site of the ADHD-200 dataset using stratified 10-fold cross-validation with a 5-seed ensemble achieved 85.18% +_5.64 balanced accuracy and 0.881 AUC, outperforming state-of-the-art methods. Attention analysis reveals cerebellar and default mode network disruptions, indicating potential neuroimaging biomarkers.

---

### Complete Causal Identification from Ancestral Graphs under Selection Bias

Authors: Leihao Chen, Joris M. Mooij
Published: 2026-03-27
Categories: stat.ME, math.CO, math.PR, math.ST, stat.ML
arXiv: https://arxiv.org/abs/2603.26301v1

Many causal discovery algorithms, including the celebrated FCI algorithm, output a Partial Ancestral Graph (PAG). PAGs serve as an abstract graphical representation of the underlying causal structure, modeled by directed acyclic graphs with latent and selection variables. This paper develops a characterization of the set of extended-type conditional independence relations that are invariant across all causal models represented by a PAG. This theory allows us to formulate a general measure-theoretic version of Pearl's causal calculus and a sound and complete identification algorithm for PAGs under selection bias. Our results also apply when PAGs are learned by certain algorithms that integrate observational data with experimental data and incorporate background knowledge.

---

### Preference-Aligned LoRA Merging: Preserving Subspace Coverage and Addressing Directional Anisotropy

Authors: Wooseong Jeong, Wonyoung Lee, Kuk-Jin Yoon
Published: 2026-03-27
Categories: cs.CV, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2603.26299v1

Merging multiple Low-Rank Adaptation (LoRA) modules is promising for constructing general-purpose systems, yet challenging because LoRA update directions span different subspaces and contribute unevenly. When merged naively, such mismatches can weaken the directions most critical to certain task losses while overemphasizing relatively less important ones, ultimately reducing the model's ability to represent all tasks faithfully. We revisit this problem through two perspectives: subspace coverage, which captures how broadly LoRA directions cover diverse representational directions, and anisotropy, which reflects the imbalance of influence across those directions. We propose TARA-Merging (Task-Rank Anisotropy Alignment), which aligns merging weights using a preference-weighted cross-entropy pseudo-loss while preserving task-relevant LoRA subspaces. This ensures broad subspace coverage and mitigates anisotropy via direction-wise reweighting. Across eight vision and six NLI benchmarks, TARA-Merging consistently outperforms vanilla and LoRA-aware baselines, demonstrating strong robustness and generalization, and highlighting the importance of addressing both subspace coverage and anisotropy in LoRA merging.

---

### findsylls: A Language-Agnostic Toolkit for Syllable-Level Speech Tokenization and Embedding

Authors: Héctor Javier Vázquez Martínez
Published: 2026-03-27
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2603.26292v2

Syllable-level units offer compact and linguistically meaningful representations for spoken language modeling and unsupervised word discovery, but research on syllabification remains fragmented across disparate implementations, datasets, and evaluation protocols. We introduce findsylls, a modular, language-agnostic toolkit that unifies classical syllable detectors and end-to-end syllabifiers under a common interface for syllable segmentation, embedding extraction, and multi-granular evaluation. The toolkit implements and standardizes widely used methods (e.g., Sylber, VG-HuBERT) and allows their components to be recombined, enabling controlled comparisons of representations, algorithms, and token rates. We demonstrate findsylls on English and Spanish corpora and on new hand-annotated data from Kono, an underdocumented Central Mande language, illustrating how a single framework can support reproducible syllable-level experiments across both high-resource and under-resourced settings.

---

### PhysVid: Physics Aware Local Conditioning for Generative Video Models

Authors: Saurabh Pathak, Elahe Arani, Mykola Pechenizkiy, Bahram Zonooz
Published: 2026-03-27
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2603.26285v2

Generative video models achieve high visual fidelity but often violate basic physical principles, limiting reliability in real-world settings. Prior attempts to inject physics rely on conditioning: frame-level signals are domain-specific and short-horizon, while global text prompts are coarse and noisy, missing fine-grained dynamics. We present PhysVid, a physics-aware local conditioning scheme that operates over temporally contiguous chunks of frames. Each chunk is annotated with physics-grounded descriptions of states, interactions, and constraints, which are fused with the global prompt via chunk-aware cross-attention during training. At inference, we introduce negative physics prompts (descriptions of locally relevant law violations) to steer generation away from implausible trajectories. On VideoPhy, PhysVid improves physical commonsense scores by $\approx 33\%$ over baseline video generators, and by up to $\approx 8\%$ on VideoPhy2. These results show that local, physics-aware guidance substantially increases physical plausibility in generative video and marks a step toward physics-grounded video models.

---

### Knowdit: Agentic Smart Contract Vulnerability Detection with Auditing Knowledge Summarization

Authors: Ziqiao Kong, Wanxu Xia, Chong Wang, Yue Xue, Yi Lu, Pan Li, Shaohua Li, Zong Cao, Yang Liu
Published: 2026-03-27
Categories: cs.CR, cs.AI, cs.SE
arXiv: https://arxiv.org/abs/2603.26270v2

Smart contracts govern billions of dollars in decentralized finance (DeFi), yet automated vulnerability detection remains challenging because many vulnerabilities are tightly coupled with project-specific business logic. We observe that recurring vulnerabilities across diverse DeFi business models often share the same underlying economic mechanisms, which we term DeFi semantics, and that capturing these shared abstractions can enable more systematic auditing. Building on this insight, we propose Knowdit, a knowledge-driven, agentic workflow for smart contract vulnerability detection. Knowdit first constructs an auditing knowledge graph from historical human audit reports, linking fine-grained DeFi semantics with recurring vulnerability patterns. Given a new project, a multi-agent pipeline leverages this knowledge through an iterative loop of specification generation, Proof-of-Concept (PoC) synthesis, PoC execution, and finding reflection, driven by a shared repository index. We evaluate Knowdit on 11 recent Code4rena projects with 84 ground-truth vulnerabilities. Knowdit detects all 21 high-severity and 90% of medium-severity vulnerabilities without false positives, fully covering eight projects, significantly outperforming all baselines. Applied to seven real-world projects, Knowdit further discovers 9 high- and 36 medium-severity previously unknown vulnerabilities, securing millions in liquidity and proving its outstanding performance.

---

### GUIDE: Resolving Domain Bias in GUI Agents through Real-Time Web Video Retrieval and Plug-and-Play Annotation

Authors: Rui Xie, Zhi Gao, Chenrui Shi, Zirui Shang, Lu Chen, Qing Li
Published: 2026-03-27
Categories: cs.AI, cs.CV
arXiv: https://arxiv.org/abs/2603.26266v3

Large vision-language models have endowed GUI agents with strong general capabilities for interface understanding and interaction. However, due to insufficient exposure to domain-specific software operation data during training, these agents exhibit significant domain bias - they lack familiarity with the specific operation workflows (planning) and UI element layouts (grounding) of particular applications, limiting their real-world task performance. In this paper, we present GUIDE (GUI Unbiasing via Instructional-Video Driven Expertise), a training-free, plug-and-play framework that resolves GUI agent domain bias by autonomously acquiring domain-specific expertise from web tutorial videos through a retrieval-augmented automated annotation pipeline. GUIDE introduces two key innovations. First, a subtitle-driven Video-RAG pipeline unlocks video semantics through subtitle analysis, performing progressive three-stage retrieval - domain classification, topic extraction, and relevance matching - to identify task-relevant tutorial videos. Second, a fully automated annotation pipeline built on an inverse dynamics paradigm feeds consecutive keyframes enhanced with UI element detection into VLMs, inferring the required planning and grounding knowledge that are injected into the agent's corresponding modules to address both manifestations of domain bias. Extensive experiments on OSWorld demonstrate GUIDE's generality as a plug-and-play component for both multi-agent systems and single-model agents. It consistently yields over 5% improvements and reduces execution steps - without modifying any model parameters or architecture - validating GUIDE as an architecture-agnostic enhancement to bridge GUI agent domain bias.

---

### Topology-Aware Graph Reinforcement Learning for Energy Storage Systems Optimal Dispatch in Distribution Networks

Authors: Shuyi Gao, Stavros Orfanoudakis, Shengren Hou, Peter Palensky, Pedro P. Vergara
Published: 2026-03-27
Categories: cs.LG, eess.SY
arXiv: https://arxiv.org/abs/2603.26264v1

Optimal dispatch of energy storage systems (ESSs) in distribution networks involves jointly improving operating economy and voltage security under time-varying conditions and possible topology changes. To support fast online decision making, we develop a topology-aware Reinforcement Learning architecture based on Twin Delayed Deep Deterministic Policy Gradient (TD3), which integrates graph neural networks (GNNs) as graph feature encoders for ESS dispatch. We conduct a systematic investigation of three GNN variants: graph convolutional networks (GCNs), topology adaptive graph convolutional networks (TAGConv), and graph attention networks (GATs) on the 34-bus and 69-bus systems, and evaluate robustness under multiple topology reconfiguration cases as well as cross-system transfer between networks with different system sizes. Results show that GNN-based controllers consistently reduce the number and magnitude of voltage violations, with clearer benefits on the 69-bus system and under reconfiguration; on the 69-bus system, TD3-GCN and TD3-TAGConv also achieve lower saved cost relative to the NLP benchmark than the NN baseline. We also highlight that transfer gains are case-dependent, and zero-shot transfer between fundamentally different systems results in notable performance degradation and increased voltage magnitude violations. This work is available at: https://github.com/ShuyiGao/GNNs_RL_ESSs and https://github.com/distributionnetworksTUDelft/GNNs_RL_ESSs.

---

### DRUM: Diffusion-based Raydrop-aware Unpaired Mapping for Sim2Real LiDAR Segmentation

Authors: Tomoya Miyawaki, Kazuto Nakashima, Yumi Iwashita, Ryo Kurazume
Published: 2026-03-27
Categories: cs.CV, cs.RO
arXiv: https://arxiv.org/abs/2603.26263v1

LiDAR-based semantic segmentation is a key component for autonomous mobile robots, yet large-scale annotation of LiDAR point clouds is prohibitively expensive and time-consuming. Although simulators can provide labeled synthetic data, models trained on synthetic data often underperform on real-world data due to a data-level domain gap. To address this issue, we propose DRUM, a novel Sim2Real translation framework. We leverage a diffusion model pre-trained on unlabeled real-world data as a generative prior and translate synthetic data by reproducing two key measurement characteristics: reflectance intensity and raydrop noise. To improve sample fidelity, we introduce a raydrop-aware masked guidance mechanism that selectively enforces consistency with the input synthetic data while preserving realistic raydrop noise induced by the diffusion prior. Experimental results demonstrate that DRUM consistently improves Sim2Real performance across multiple representations of LiDAR data. The project page is available at https://miya-tomoya.github.io/drum.

---

### GLASS: Geometry-aware Local Alignment and Structure Synchronization Network for 2D-3D Registration

Authors: Zhixin Cheng, Jiacheng Deng, Xinjun Li, Bohao Liao, Li Liu, Xiaotian Yin, Baoqun Yin, Tianzhu Zhang
Published: 2026-03-27
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2603.26262v1

Image-to-point cloud registration methods typically follow a coarse-to-fine pipeline, extracting patch-level correspondences and refining them into dense pixel-to-point matches. However, in scenes with repetitive patterns, images often lack sufficient 3D structural cues and alignment with point clouds, leading to incorrect matches. Moreover, prior methods usually overlook structural consistency, limiting the full exploitation of correspondences. To address these issues, we propose two novel modules: the Local Geometry Enhancement (LGE) module and the Graph Distribution Consistency (GDC) module. LGE enhances both image and point cloud features with normal vectors, injecting geometric structure into image features to reduce mismatches. GDC constructs a graph from matched points to update features and explicitly constrain similarity distributions. Extensive experiments and ablations on two benchmarks, RGB-D Scenes v2 and 7-Scenes, demonstrate that our approach achieves state-of-the-art performance in image-to-point cloud registration.

---

### Contrastive Conformal Sets

Authors: Yahya Alkhatib, Wee Peng Tay
Published: 2026-03-27
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2603.26261v2

Contrastive learning produces coherent semantic feature embeddings by encouraging positive samples to cluster closely while separating negative samples. However, existing contrastive learning methods lack a principled construction of geometric sets in the semantic feature space with distribution-free guarantees at any user-specified coverage level. We extend conformal prediction to this setting by introducing covering sets equipped with learnable generalized hyper-ball constraints. We propose a method that constructs conformal sets guaranteeing user-specified coverage of positive samples while maximizing negative sample exclusion. We theoretically motivate volume minimization as a proxy for negative exclusion, enabling our approach to operate effectively even when negative pairs are unavailable. The positive inclusion guarantee inherits the distribution-free coverage property of conformal prediction, while negative exclusion is maximized through learned set geometry optimized on a held-out training split. Experiments on simulated and real-world image datasets demonstrate improved inclusion-exclusion trade-offs compared to standard distance-based conformal baselines.

---

### GeoGuide: Hierarchical Geometric Guidance for Open-Vocabulary 3D Semantic Segmentation

Authors: Xujing Tao, Chuxin Wang, Yubo Ai, Zhixin Cheng, Zhuoyuan Li, Liangsheng Liu, Yujia Chen, Xinjun Li, Qiao Li, Wenfei Yang, Tianzhu Zhang
Published: 2026-03-27
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2603.26260v1

Open-vocabulary 3D semantic segmentation aims to segment arbitrary categories beyond the training set. Existing methods predominantly rely on distilling knowledge from 2D open-vocabulary models. However, aligning 3D features to the 2D representation space restricts intrinsic 3D geometric learning and inherits errors from 2D predictions. To address these limitations, we propose GeoGuide, a novel framework that leverages pretrained 3D models to integrate hierarchical geometry-semantic consistency for open-vocabulary 3D segmentation. Specifically, we introduce an Uncertainty-based Superpoint Distillation module to fuse geometric and semantic features for estimating per-point uncertainty, adaptively weighting 2D features within superpoints to suppress noise while preserving discriminative information to enhance local semantic consistency. Furthermore, our Instance-level Mask Reconstruction module leverages geometric priors to enforce semantic consistency within instances by reconstructing complete instance masks. Additionally, our Inter-Instance Relation Consistency module aligns geometric and semantic similarity matrices to calibrate cross-instance consistency for same-category objects, mitigating viewpoint-induced semantic drift. Extensive experiments on ScanNet v2, Matterport3D, and nuScenes demonstrate the superior performance of GeoGuide.

---

### Working Notes on Late Interaction Dynamics: Analyzing Targeted Behaviors of Late Interaction Models

Authors: Antoine Edy, Max Conti, Quentin Macé
Published: 2026-03-27
Categories: cs.IR, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2603.26259v2

While Late Interaction models exhibit strong retrieval performance, many of their underlying dynamics remain understudied, potentially hiding performance bottlenecks. In this work, we focus on two topics in Late Interaction retrieval: a length bias that arises when using multi-vector scoring, and the similarity distribution beyond the best scores pooled by the MaxSim operator. We analyze these behaviors for state-of-the-art models on the NanoBEIR benchmark. Results show that while the theoretical length bias of causal Late Interaction models holds in practice, bi-directional models can also suffer from it in extreme cases. We also note that no significant similarity trend lies beyond the top-1 document token, validating that the MaxSim operator efficiently exploits the token-level similarity scores.

---

### ARTA: Adaptive Mixed-Resolution Token Allocation for Efficient Dense Feature Extraction

Authors: David Hagerman, Roman Naeem, Erik Brorsson, Fredrik Kahl, Lennart Svensson
Published: 2026-03-27
Categories: cs.CV, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2603.26258v1

We present ARTA, a mixed-resolution coarse-to-fine vision transformer for efficient dense feature extraction. Unlike models that begin with dense high-resolution (fine) tokens, ARTA starts with low-resolution (coarse) tokens and uses a lightweight allocator to predict which regions require more fine tokens. The allocator iteratively predicts a semantic (class) boundary score and allocates additional tokens to patches above a low threshold, concentrating token density near boundaries while maintaining high sensitivity to weak boundary evidence. This targeted allocation encourages tokens to represent a single semantic class rather than a mixture of classes. Mixed-resolution attention enables interaction between coarse and fine tokens, focusing computation on semantically complex areas while avoiding redundant processing in homogeneous regions. Experiments demonstrate that ARTA achieves state-of-the-art results on ADE20K and COCO-Stuff with substantially fewer FLOPs, and delivers competitive performance on Cityscapes at markedly lower compute. For example, ARTA-Base attains 54.6 mIoU on ADE20K in the ~100M-parameter class while using fewer FLOPs and less memory than comparable backbones.

---

### Improving Risk Stratification in Hypertrophic Cardiomyopathy: A Novel Score Combining Echocardiography, Clinical, and Medication Data

Authors: Marion Taconné, Valentina D. A. Corino, Annamaria Del Franco, Sara Giovani, Iacopo Olivotto, Adrien Al Wazzan, Erwan Donal, Pietro Cerveri, Luca Mainardi
Published: 2026-03-27
Categories: cs.LG
arXiv: https://arxiv.org/abs/2603.26254v1

Hypertrophic cardiomyopathy (HCM) requires accurate risk stratification to inform decisions regarding ICD therapy and follow-up management. Current established models, such as the European Society of Cardiology (ESC) score, exhibit moderate discriminative performance. This study develops a robust, explainable machine learning (ML) risk score leveraging routinely collected echocardiographic, clinical, and medication data, typically contained within Electronic Health Records (EHRs), to predict a 5-year composite cardiovascular outcome in HCM patients. The model was trained and internally validated using a large cohort (N=1,201) from the SHARE registry (Florence Hospital) and externally validated on an independent cohort (N=382) from Rennes Hospital. The final Random Forest ensemble model achieved a high internal Area Under the Curve (AUC) of 0.85 +- 0.02, significantly outperforming the ESC score (0.56 +- 0.03). Critically, survival curve analysis on the external validation set showed superior risk separation for the ML score (Log-rank p = 8.62 x 10^(-4) compared to the ESC score (p = 0.0559). Furthermore, longitudinal analyses demonstrate that the proposed risk score remains stable over time in event-free patients. The model high interpretability and its capacity for longitudinal risk monitoring represent promising tools for the personalized clinical management of HCM.

---

### SocialX: A Modular Platform for Multi-Source Big Data Research in Indonesia

Authors: Muhammad Apriandito Arya Saputra, Andry Alamsyah, Dian Puteri Ramadhani, Thomhert Suprapto Siadari, Hanif Fakhrurroja
Published: 2026-03-27
Categories: cs.CL
arXiv: https://arxiv.org/abs/2603.26253v1

Big data research in Indonesia is constrained by a fundamental fragmentation: relevant data is scattered across social media, news portals, e-commerce platforms, review sites, and academic databases, each with different formats, access methods, and noise characteristics. Researchers must independently build collection pipelines, clean heterogeneous data, and assemble separate analysis tools, a process that often overshadows the research itself. We present SocialX, a modular platform for multi-source big data research that integrates heterogeneous data collection, language-aware preprocessing, and pluggable analysis into a unified, source-agnostic pipeline. The platform separates concerns into three independent layers (collection, preprocessing, and analysis) connected by a lightweight job-coordination mechanism. This modularity allows each layer to grow independently: new data sources, preprocessing methods, or analysis tools can be added without modifying the existing pipeline. We describe the design principles that enable this extensibility, detail the preprocessing methodology that addresses challenges specific to Indonesian text across registers, and demonstrate the platform's utility through a walkthrough of a typical research workflow. SocialX is publicly accessible as a web-based platform at https://www.socialx.id.

---

### Channelling, Coordinating, Collaborating: A Three-Layer Framework for Disability-Centered Human-Agent Collaboration

Authors: Lan Xiao, Catherine Holloway
Published: 2026-03-27
Categories: cs.HC, cs.AI
arXiv: https://arxiv.org/abs/2603.26252v1

AI accessibility tools have mostly been designed for individual use, helping one person overcome a specific functional barrier. But for many people with disabilities, complex tasks are accomplished through collaboration with others who bring complementary abilities, not solitary effort. We propose a three-layer framework, Channelling, Coordinating, and Co-Creating, that rethinks AI's role in ability-diverse collaboration: establishing shared informational ground across abilities, mediating workflows between collaborators with different abilities, and contributing as a bounded partner toward shared goals. Grounded in the Ability-Diverse Collaboration framework, grounding theory, and Carlile's 3T framework, it extends the ``agents as remote collaborators'' vision by centring the collaborative, interdependent ways people with disabilities already work.

---

### Real-Time Branch-to-Tool Distance Estimation for Autonomous UAV Pruning: Benchmarking Five DEFOM-Stereo Variants from Simulation to Jetson Deployment

Authors: Yida Lin, Bing Xue, Mengjie Zhang, Sam Schofield, Richard Green
Published: 2026-03-27
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.26250v1

Autonomous tree pruning with unmanned aerial vehicles (UAVs) is a safety-critical real-world task: the onboard perception system must estimate the metric distance from a cutting tool to thin tree branches in real time so that the UAV can approach, align, and actuate the pruner without collision. We address this problem by training five variants of DEFOM-Stereo - a recent foundation-model-based stereo matcher - on a task-specific synthetic dataset and deploying the checkpoints on an NVIDIA Jetson Orin Super 16 GB. The training corpus is built in Unreal Engine 5 with a simulated ZED Mini stereo camera capturing 5,520 stereo pairs across 115 tree instances from three viewpoints at 2m distance; dense EXR depth maps provide exact, spatially complete supervision for thin branches. On the synthetic test set, DEFOM-Stereo ViT-S achieves the best depth-domain accuracy (EPE 1.74 px, D1-all 5.81%, delta-1 95.90%, depth MAE 23.40 cm) but its Jetson inference speed of ~2.2 FPS (~450 ms per frame) remains too slow for responsive closed-loop tool control. A newly introduced balanced variant, DEFOM-PrunePlus (~21M backbone, ~3.3 FPS on Jetson), offers the best deployable accuracy-speed trade-off (EPE 5.87 px, depth MAE 64.26 cm, delta-1 87.59%): its frame rate is sufficient for real-time guidance and its depth accuracy supports safe branch approach planning at the 2m operating range. The lightweight DEFOM-PruneStereo (~6.9 FPS) and DEFOM-PruneNano (~8.5 FPS) run fast but sacrifice substantial accuracy (depth MAE > 57 cm), making estimates too unreliable for safe actuation. Zero-shot inference on real photographs confirms that full-capacity models preserve branch geometry, validating the sim-to-real transfer. We conclude that DEFOM-PrunePlus provides the most practical accuracy-latency balance for onboard distance estimation, while ViT-S serves as the reference for future hardware.

---

### Knowledge Distillation for Efficient Transformer-Based Reinforcement Learning in Hardware-Constrained Energy Management Systems

Authors: Pascal Henrich, Jonas Sievers, Maximilian Beichter, Thomas Blank, Ralf Mikut, Veit Hagenmeyer
Published: 2026-03-27
Categories: cs.LG
arXiv: https://arxiv.org/abs/2603.26249v1

Transformer-based reinforcement learning has emerged as a strong candidate for sequential control in residential energy management. In particular, the Decision Transformer can learn effective battery dispatch policies from historical data, thereby increasing photovoltaic self-consumption and reducing electricity costs. However, transformer models are typically too computationally demanding for deployment on resource-constrained residential controllers, where memory and latency constraints are critical. This paper investigates knowledge distillation to transfer the decision-making behaviour of high-capacity Decision Transformer policies to compact models that are more suitable for embedded deployment. Using the Ausgrid dataset, we train teacher models in an offline sequence-based Decision Transformer framework on heterogeneous multi-building data. We then distil smaller student models by matching the teachers' actions, thereby preserving control quality while reducing model size. Across a broad set of teacher-student configurations, distillation largely preserves control performance and even yields small improvements of up to 1%, while reducing the parameter count by up to 96%, the inference memory by up to 90%, and the inference time by up to 63%. Beyond these compression effects, comparable cost improvements are also observed when distilling into a student model of identical architectural capacity. Overall, our results show that knowledge distillation makes Decision Transformer control more applicable for residential energy management on resource-limited hardware.

---

### Automatic Speech Recognition for Documenting Endangered Languages: Case Study of Ikema Miyakoan

Authors: Chihiro Taguchi, Yukinori Takubo, David Chiang
Published: 2026-03-27
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2603.26248v2

Language endangerment poses a major challenge to linguistic diversity worldwide, and technological advances have opened new avenues for documentation and revitalization. Among these, automatic speech recognition (ASR) has shown increasing potential to assist in the transcription of endangered language data. This study focuses on Ikema, a severely endangered Ryukyuan language spoken in Okinawa, Japan, with approximately 1,300 remaining speakers, most of whom are over 60 years old. We present an ongoing effort to develop an ASR system for Ikema based on field recordings. Specifically, we (1) construct a 6.33-hour speech corpus from field recordings, (2) train an ASR model that achieves a character error rate as low as 15%, and (3) evaluate the impact of ASR assistance on the efficiency of speech transcription. Our results demonstrate that ASR integration can substantially reduce transcription time and cognitive load, offering a practical pathway toward scalable, technology-supported documentation of endangered languages.

---

### Distilling Conversations: Abstract Compression of Conversational Audio Context for LLM-based ASR

Authors: Shashi Kumar, Esaú Villatoro-Tello, Sergio Burdisso, Kadri Hacioglu, Thibault Bañeras-Roux, Hasindri Watawana, Dairazalia Sanchez-Cortes, Srikanth Madikeri, Petr Motlicek, Andreas Stolcke
Published: 2026-03-27
Categories: cs.CL, cs.AI, cs.LG, eess.AS
arXiv: https://arxiv.org/abs/2603.26246v1

Standard LLM-based speech recognition systems typically process utterances in isolation, limiting their ability to leverage conversational context. In this work, we study whether multimodal context from prior turns improves LLM-based ASR and how to represent that context efficiently. We find that, after supervised multi-turn training, conversational context mainly helps with the recognition of contextual entities. However, conditioning on raw context is expensive because the prior-turn audio token sequence grows rapidly with conversation length. To address this, we propose Abstract Compression, which replaces the audio portion of prior turns with a fixed number of learned latent tokens while retaining corresponding transcripts explicitly. On both in-domain and out-of-domain test sets, the compressed model recovers part of the gains of raw-context conditioning with a smaller prior-turn audio footprint. We also provide targeted analyses of the compression setup and its trade-offs.

---

### Physics-Informed Neural Networks and Sequence Encoder: Application to heating and early cooling of thermo-stamping process

Authors: Mouad Elaarabi, Domenico Borzacchiello, Philippe Le Bot, Nathan Lauzeral, Sebastien Comas-Cardona
Published: 2026-03-27
Categories: cs.CE, cs.AI
arXiv: https://arxiv.org/abs/2603.26245v1

In a previous work (Elaarabi et al., 2025b), the Sequence Encoder for online dynamical system identification (Elaarabi et al., 2025a) and its combination with PINN (PINN-SE) were introduced and tested on both synthetic and real data case scenarios. The sequence encoder is able to effectively encode time series into feature vectors, which the PINN then uses to map to dynamical behavior, predicting system response under changes in parameters, ICs and BCs. Previously (Elaarabi et al., 2025b), the tests on real data were limited to simple 1D problems and only 1D time series inputs of the Sequence Encoder. In this work, the possibility of applying PINN-SE to a more realistic case is investigated: heating and early cooling of the thermo-stamping process, which is a critical stage in the forming process of continuous fiber reinforced composite materials with thermoplastic polymer. The possibility of extending the PINN-SE inputs to multimodal data, such as sequences of temporal 2D images and to scenarios involving variable geometries, is also explored. The results show that combining multiple encoders with the previously proposed method (Elaarabi et al., 2025b) is feasible, we also show that training the model on synthetic data generated based on experimental data can help the model to generalize well for real experimental data, unseen during the training phase.

---

### Automating Domain-Driven Design: Experience with a Prompting Framework

Authors: Tobias Eisenreich, Husein Jusic, Stefan Wagner
Published: 2026-03-27
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2603.26244v1

Domain-driven design (DDD) is a powerful design technique for architecting complex software systems. This paper introduces a prompting framework that automates core DDD activities through structured large language model (LLM) interactions. We decompose DDD into five sequential steps: (1) establishing an ubiquitous language, (2) simulating event storming, (3) identifying bounded contexts, (4) designing aggregates, and (5) mapping to technical architecture. In a case study, we validated the prompting framework against real-world requirements from FTAPI's enterprise platform. While the first steps consistently generate valuable and usable artifacts, later steps show how minor errors or inaccuracies can propagate and accumulate. Overall, the framework excels as a collaborative sparring partner for building actionable documentation, such as glossaries and context maps, but not for full automation. This allows the experts to concentrate their discussion on the critical trade-offs. In our evaluation, Steps 1 to 3 worked well, but the accumulated errors rendered the artifacts generated from Steps 4 and 5 impractical. Our findings show that LLMs can enhance, but not replace, architectural expertise, offering a practical tool to reduce the effort and overhead of DDD while preserving human-centric decision-making.

---

### SwarmCoDe: A Scalable Co-Design Framework for Heterogeneous Robot Swarms via Dynamic Speciation

Authors: Andrew Wilhelm, Josie Hughes
Published: 2026-03-27
Categories: cs.RO, cs.MA, cs.NE
arXiv: https://arxiv.org/abs/2603.26240v2

Robot swarms offer inherent robustness and the capacity to execute complex, collaborative tasks surpassing the capabilities of single-agent systems. Co-designing these systems is critical, as marginal improvements in individual performance or unit cost compound significantly at scale. However, under traditional frameworks, this scale renders co-design intractable due to exponentially large, non-intuitive design spaces. To address this, we propose SwarmCoDe, a novel Collaborative Co-Evolutionary Algorithm (CCEA) that utilizes dynamic speciation to automatically scale swarm heterogeneity to match task complexity. Inspired by biological signaling mechanisms for inter-species cooperation, the algorithm uses evolved genetic tags and a selectivity gene to facilitate the emergent identification of symbiotically beneficial partners without predefined species boundaries. Additionally, an evolved dominance gene dictates the relative swarm composition, decoupling the physical swarm size from the evolutionary population. We apply SwarmCoDe to simultaneously optimize task planning and hardware morphology under fabrication budgets, successfully evolving specialized swarms of up to 200 agents -- four times the size of the evolutionary population. This framework provides a scalable, computationally viable pathway for the holistic co-design of large-scale, heterogeneous robot swarms.

---

### A Universal Vibe? Finding and Controlling Language-Agnostic Informal Register with SAEs

Authors: Uri Z. Kialy, Avi Shtarkberg, Ayal Klein
Published: 2026-03-27
Categories: cs.CL
arXiv: https://arxiv.org/abs/2603.26236v2

While multilingual language models successfully transfer factual and syntactic knowledge across languages, it remains unclear whether they process culture-specific pragmatic registers, such as slang, as isolated language-specific memorizations or as unified, abstract concepts. We study this by probing the internal representations of Gemma-2-9B-IT using Sparse Autoencoders (SAEs) across three typologically diverse source languages: English, Hebrew, and Russian. To definitively isolate pragmatic register processing from trivial lexical sensitivity, we introduce a novel dataset in which every target term is polysemous, appearing in both literal and informal contexts. We find that while much of the informal-register signal is distributed across language-specific features, a small but highly robust cross-linguistic core consistently emerges. This shared core forms a geometrically coherent ``informal register subspace'' that sharpens in the model's deeper layers. Crucially, these shared representations are not merely correlational: activation steering with these features causally shifts output formality across all source languages and transfers zero-shot to six unseen languages spanning diverse language families and scripts. Together, these results provide the first mechanistic evidence that multilingual LLMs internalize informal register not just as surface-level heuristics, but as a portable, language-agnostic pragmatic abstraction.

---

### A Universal Vibe? Finding and Controlling Language-Agnostic Informal Register with SAEs

Authors: Uri Z. Kialy, Avi Shtarkberg, Ayal Klein
Published: 2026-03-27
Categories: cs.CL
arXiv: https://arxiv.org/abs/2603.26236v1

While multilingual language models successfully transfer factual and syntactic knowledge across languages, it remains unclear whether they process culture-specific pragmatic registers, such as slang, as isolated language-specific memorizations or as unified, abstract concepts. We study this by probing the internal representations of Gemma-2-9B-IT using Sparse Autoencoders (SAEs) across three typologically diverse source languages: English, Hebrew, and Russian. To definitively isolate pragmatic register processing from trivial lexical sensitivity, we introduce a novel dataset in which every target term is polysemous, appearing in both literal and informal contexts. We find that while much of the informal-register signal is distributed across language-specific features, a small but highly robust cross-linguistic core consistently emerges. This shared core forms a geometrically coherent ``informal register subspace'' that sharpens in the model's deeper layers. Crucially, these shared representations are not merely correlational: activation steering with these features causally shifts output formality across all source languages and transfers zero-shot to six unseen languages spanning diverse language families and scripts. Together, these results provide the first mechanistic evidence that multilingual LLMs internalize informal register not just as surface-level heuristics, but as a portable, language-agnostic pragmatic abstraction.

---

### GS-BrainText: A Multi-Site Brain Imaging Report Dataset from Generation Scotland for Clinical Natural Language Processing Development and Validation

Authors: Beatrice Alex, Claire Grover, Arlene Casey, Richard Tobin, Heather Whalley, William Whiteley
Published: 2026-03-27
Categories: cs.CL
arXiv: https://arxiv.org/abs/2603.26235v1

We present GS-BrainText, a curated dataset of 8,511 brain radiology reports from the Generation Scotland cohort, of which 2,431 are annotated for 24 brain disease phenotypes. This multi-site dataset spans five Scottish NHS health boards and includes broad age representation (mean age 58, median age 53), making it uniquely valuable for developing and evaluating generalisable clinical natural language processing (NLP) algorithms and tools. Expert annotations were performed by a multidisciplinary clinical team using an annotation schema, with 10-100% double annotation per NHS health board and rigorous quality assurance. Benchmark evaluation using EdIE-R, an existing rule-based NLP system developed in conjunction with the annotation schema, revealed some performance variation across health boards (F1: 86.13-98.13), phenotypes (F1: 22.22-100) and age groups (F1: 87.01-98.13), highlighting critical challenges in generalisation of NLP tools. The GS-BrainText dataset addresses a significant gap in available UK clinical text resources and provides a valuable resource for the study of linguistic variation, diagnostic uncertainty expression and the impact of data characteristics on NLP system performance.

---

### Ask or Assume? Uncertainty-Aware Clarification-Seeking in Coding Agents

Authors: Nicholas Edwards, Sebastian Schuster
Published: 2026-03-27
Categories: cs.CL
arXiv: https://arxiv.org/abs/2603.26233v3

As Large Language Model (LLM) agents are increasingly deployed in open-ended domains like software engineering, they frequently encounter underspecified instructions that lack crucial context. While human developers naturally resolve underspecification by asking clarifying questions, current agents are largely optimized for autonomous execution. In this work, we systematically evaluate the clarification-seeking abilities of LLM agents on an underspecified variant of SWE-bench Verified. We propose an uncertainty-aware multi-agent scaffold that decouples underspecification detection from code execution. Across both proprietary and open-weight frontier LLMs, our scaffold achieves a 69.40% task resolve rate, significantly outperforming a standard single-agent setup and closing the performance gap with agents operating on fully specified instructions. Furthermore, we find that the multi-agent system exhibits well-calibrated information-seeking behavior, conserving queries on simple tasks while proactively seeking information on more complex issues. These findings indicate that current models can be turned into proactive collaborators, where agents independently recognize when to ask questions to elicit missing information in real-world, underspecified tasks.

---

### Ask or Assume? Uncertainty-Aware Clarification-Seeking in Coding Agents

Authors: Nicholas Edwards, Sebastian Schuster
Published: 2026-03-27
Categories: cs.CL
arXiv: https://arxiv.org/abs/2603.26233v2

As Large Language Model (LLM) agents are increasingly deployed in open-ended domains like software engineering, they frequently encounter underspecified instructions that lack crucial context. While human developers naturally resolve underspecification by asking clarifying questions, current agents are largely optimized for autonomous execution. In this work, we systematically evaluate the clarification-seeking abilities of LLM agents on an underspecified variant of SWE-bench Verified. We propose an uncertainty-aware multi-agent scaffold that decouples underspecification detection from code execution. Across both proprietary and open-weight frontier LLMs, our scaffold achieves a 69.40% task resolve rate, significantly outperforming a standard single-agent setup and closing the performance gap with agents operating on fully specified instructions. Furthermore, we find that the multi-agent system exhibits well-calibrated information-seeking behavior, conserving queries on simple tasks while proactively seeking information on more complex issues. These findings indicate that current models can be turned into proactive collaborators, where agents independently recognize when to ask questions to elicit missing information in real-world, underspecified tasks.

---

### Optimization Trade-offs in Asynchronous Federated Learning: A Stochastic Networks Approach

Authors: Abdelkrim Alahyane, Céline Comte, Matthieu Jonckheere
Published: 2026-03-27
Categories: cs.LG, cs.PF, math.OC, math.PR
arXiv: https://arxiv.org/abs/2603.26231v1

Synchronous federated learning scales poorly due to the straggler effect. Asynchronous algorithms increase the update throughput by processing updates upon arrival, but they introduce two fundamental challenges: gradient staleness, which degrades convergence, and bias toward faster clients under heterogeneous data distributions. Although algorithms such as AsyncSGD and Generalized AsyncSGD mitigate this bias via client-side task queues, most existing analyses neglect the underlying queueing dynamics and lack closed-form characterizations of the update throughput and gradient staleness. To close this gap, we develop a stochastic queueing-network framework for Generalized AsyncSGD that jointly models random computation times at the clients and the central server, as well as random uplink and downlink communication delays. Leveraging product-form network theory, we derive a closed-form expression for the update throughput, alongside closed-form upper bounds for both the communication round complexity and the expected wall-clock time required to reach an $ε$-stationary point. These results formally characterize the trade-off between gradient staleness and wall-clock convergence speed. We further extend the framework to quantify energy consumption under stochastic timing, revealing an additional trade-off between convergence speed and energy efficiency. Building on these analytical results, we propose gradient-based optimization strategies to jointly optimize routing and concurrency. Experiments on EMNIST demonstrate reductions of 29%--46% in convergence time and 36%--49% in energy consumption compared to AsyncSGD.

---

### Privacy-Accuracy Trade-offs in High-Dimensional LASSO under Perturbation Mechanisms

Authors: Ayaka Sakata, Haruka Tanzawa
Published: 2026-03-27
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2603.26227v2

We study privacy-preserving sparse linear regression in the high-dimensional regime, focusing on the LASSO estimator. We analyze two widely used mechanisms for differential privacy: output perturbation, which injects noise into the estimator, and objective perturbation, which adds a random linear term to the loss function. Using approximate message passing (AMP), we characterize the typical behavior of these estimators under random design and privacy noise. To quantify privacy, we adopt typical-case measures, including the on-average KL divergence, which admits a hypothesis-testing interpretation in terms of distinguishability between neighboring datasets. Our analysis reveals that sparsity plays a central role in shaping the privacy-accuracy trade-off: stronger regularization can improve privacy by stabilizing the estimator against single-point data changes. We further show that the two mechanisms exhibit qualitatively different behaviors. In particular, for objective perturbation, increasing the noise level can have non-monotonic effects, and excessive noise may destabilize the estimator, leading to increased sensitivity to data perturbations. Our results demonstrate that AMP provides a powerful framework for analyzing privacy-accuracy trade-offs in high-dimensional sparse models.

---

### Clawed and Dangerous: Can We Trust Open Agentic Systems?

Authors: Shiping Chen, Qin Wang, Guangsheng Yu, Xu Wang, Liming Zhu
Published: 2026-03-27
Categories: cs.CR, cs.AI, cs.ET, cs.SE
arXiv: https://arxiv.org/abs/2603.26221v1

Open agentic systems combine LLM-based planning with external capabilities, persistent memory, and privileged execution. They are used in coding assistants, browser copilots, and enterprise automation. OpenClaw is a visible instance of this broader class. Without much attention yet, their security challenge is fundamentally different from that of traditional software that relies on predictable execution and well-defined control flow. In open agentic systems, everything is ''probabilistic'': plans are generated at runtime, key decisions may be shaped by untrusted natural-language inputs and tool outputs, execution unfolds in uncertain environments, and actions are taken under authority delegated by human users. The central challenge is therefore not merely robustness against individual attacks, but the governance of agentic behavior under persistent uncertainty. This paper systematizes the area through a software engineering lens. We introduce a six-dimensional analytical taxonomy and synthesize 50 papers spanning attacks, benchmarks, defenses, audits, and adjacent engineering foundations. From this synthesis, we derive a reference doctrine for secure-by-construction agent platforms, together with an evaluation scorecard for assessing platform security posture. Our review shows that the literature is relatively mature in attack characterization and benchmark construction, but remains weak in deployment controls, operational governance, persistent-memory integrity, and capability revocation. These gaps define a concrete engineering agenda for building agent ecosystems that are governable, auditable, and resilient under compromise.

---

### On associative neural networks for sparse patterns with huge capacities

Authors: Matthias Löwe, Franck Vermet
Published: 2026-03-27
Categories: math.PR, cs.LG
arXiv: https://arxiv.org/abs/2603.26217v2

Generalized Hopfield models with higher-order or exponential interaction terms are known to have substantially larger storage capacities than the classical quadratic model. On the other hand, associative memories for sparse patterns, such as the Willshaw and Amari models, already exhibit enhanced storage capacities in the sparse regime. In this paper we combine these two mechanisms. We introduce higher-order versions of sparse associative memory models and study their storage capacities in the sense of fixed-pattern stability. For the Amari and Willshaw models with fixed interaction order $n$, we obtain storage scales of order $\frac{N^n}{(\log N)^n}$. When the interaction order grows logarithmically with the number of neurons, the resulting storage scale becomes super-polynomial. We also study higher-order interactions in the block-structured Gripon--Berrou architecture, where the natural storage scale is of order $c^n$. Our results show that the capacity increase caused by higher-order interactions persists in the sparse setting, while the precise storage scale depends on the underlying architecture.

---

### On associative neural networks for sparse patterns with huge capacities

Authors: Matthias Löwe, Franck Vermet
Published: 2026-03-27
Categories: math.PR, cs.LG
arXiv: https://arxiv.org/abs/2603.26217v1

Generalized Hopfield models with higher-order or exponential interaction terms are known to have substantially larger storage capacities than the classical quadratic model. On the other hand, associative memories for sparse patterns, such as the Willshaw and Amari models, already outperform the classical Hopfield model in the sparse regime. In this paper we combine these two mechanisms. We introduce higher-order versions of sparse associative memory models and study their storage capacities. For fixed interaction order $n$, we obtain storage capacities of polynomial order in the system size. When the interaction order is allowed to grow logarithmically with the number of neurons, this yields super-polynomial capacities. We also discuss an analogue in the Gripon--Berrou architecture which was formulated for non-sparse messages (see \cite{griponc}). Our results show that the capacity increase caused by higher-order interactions persists in the sparse setting, although the precise storage scale depends on the underlying architecture.

---

### Towards GUI Agents: Vision-Language Diffusion Models for GUI Grounding

Authors: Shrinidhi Kumbhar, Haofu Liao, Srikar Appalaraju, Kunwar Yashraj Singh
Published: 2026-03-27
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2603.26211v1

Autoregressive (AR) vision-language models (VLMs) have long dominated multimodal understanding, reasoning, and graphical user interface (GUI) grounding. Recently, discrete diffusion vision-language models (DVLMs) have shown strong performance in multimodal reasoning, offering bidirectional attention, parallel token generation, and iterative refinement. However, their potential for GUI grounding remains unexplored. In this work, we evaluate whether discrete DVLMs can serve as a viable alternative to AR models for GUI grounding. We adapt LLaDA-V for single-turn action and bounding-box prediction, framing the task as text generation from multimodal input. To better capture the hierarchical structure of bounding-box geometry, we propose a hybrid masking schedule that combines linear and deterministic masking, improving grounding accuracy by up to 6.1 points in Step Success Rate (SSR) over the GUI-adapted LLaDA-V trained with linear masking. Evaluations on four datasets spanning web, desktop, and mobile interfaces show that the adapted diffusion model with hybrid masking consistently outperforms the linear-masked variant and performs competitively with autoregressive counterparts despite limited pretraining. Systematic ablations reveal that increasing diffusion steps, generation length, and block length improves accuracy but also increases latency, with accuracy plateauing beyond a certain number of diffusion steps. Expanding the training data with diverse GUI domains further reduces latency by about 1.3 seconds and improves grounding accuracy by an average of 20 points across benchmarks. These results demonstrate that discrete DVLMs are a promising modeling framework for GUI grounding and represent an important step toward diffusion-based GUI agents.

---

### Sparse Auto-Encoders and Holism about Large Language Models

Authors: Jumbly Grindrod
Published: 2026-03-27
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2603.26207v1

Does Large Language Model (LLM) technology suggest a meta-semantic picture i.e. a picture of how words and complex expressions come to have the meaning that they do? One modest approach explores the assumptions that seem to be built into how LLMs capture the meanings of linguistic expressions as a way of considering their plausibility (Grindrod, 2026a, 2026b). It has previously been argued that LLMs, in employing a form of distributional semantics, adopt a form of holism about meaning (Grindrod, 2023; Grindrod et al., forthcoming). However, recent work in mechanistic interpretability presents a challenge to these arguments. Specifically, the discovery of a vast array of interpretable latent features within the high dimensional spaces used by LLMs potentially challenges the holistic interpretation. In this paper, I will present the original reasons for thinking that LLMs embody a form of holism (section 1), before introducing recent work on features generated through sparse auto-encoders, and explaining how the discovery of such features suggests an alternative decompositional picture of meaning (section 2). I will then respond to this challenge by considering in greater detail the nature of such features (section 3). Finally, I will return to the holistic picture defended by Grindrod et al. and argue that the picture still stands provided that the features are countable (section 4).

---

### 4DRaL: Bridging 4D Radar with LiDAR for Place Recognition using Knowledge Distillation

Authors: Ningyuan Huang, Zhiheng Li, Zheng Fang
Published: 2026-03-27
Categories: cs.CV, cs.RO
arXiv: https://arxiv.org/abs/2603.26206v1

Place recognition is crucial for loop closure detection and global localization in robotics. Although mainstream algorithms typically rely on cameras and LiDAR, these sensors are susceptible to adverse weather conditions. Fortunately, the recently developed 4D millimeter-wave radar (4D radar) offers a promising solution for all-weather place recognition. However, the inherent noise and sparsity in 4D radar data significantly limit its performance. Thus, in this paper, we propose a novel framework called 4DRaL that leverages knowledge distillation (KD) to enhance the place recognition performance of 4D radar. Its core is to adopt a high-performance LiDAR-to-LiDAR (L2L) place recognition model as a teacher to guide the training of a 4D radar-to-4D radar (R2R) place recognition model. 4DRaL comprises three key KD modules: a local image enhancement module to handle the sparsity of raw 4D radar points, a feature distribution distillation module that ensures the student model generates more discriminative features, and a response distillation module to maintain consistency in feature space between the teacher and student models. More importantly, 4DRaL can also be trained for 4D radar-to-LiDAR (R2L) place recognition through different module configurations. Experimental results prove that 4DRaL achieves state-of-the-art performance in both R2R and R2L tasks regardless of normal or adverse weather.

---

### An Object Web Seminar: A Retrospective on a Technical Dialogue Still Reverberating

Authors: James J. Cusick
Published: 2026-03-27
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2603.26203v2

Technology change happens quickly such that new trends tend to crowd out the focus on what was new just yesterday. In this paper the peak popularity of the confluence of Object Technologies with early Web adoption is explored through the content of a seminar held in 1999. Distributed architectures were undergoing significant change at this point, and deeper software capabilities were just beginning to be broadly accessible over the Internet. The Object Web arose and was infused with new development tools reflecting these capabilities and allowing design of applications for deployment during the early days of the World Wide Web. This conference discussed the history, evolution, and use of these tools, architectures, and their future possibilities. The continued dominance of these approaches although under different names is demonstrated even though the term Object Web has receded in use. Favored newer offerings such as Kubernetes and microservices still model the core design attributes of the Object Web for example. Aside from connecting this seminar to relevance in the software world of today this paper also touches on the early AI tools demonstrated in this seminar a quarter century ago and how the popularity wave of any given technology might affect the current focus on AI technology offerings.

---

### SAFT: Sensitivity-Aware Filtering and Transmission for Adaptive 3D Point Cloud Communication over Wireless Channels

Authors: Huda Adam Sirag Mekki, Hui Yuan, Mohanad M. G. Hassan, Zejia Chen, Guanghui Zhang
Published: 2026-03-27
Categories: cs.IT, cs.CV
arXiv: https://arxiv.org/abs/2603.26197v1

Reliable transmission of 3D point clouds over wireless channels is challenging due to time-varying signal-to-noise ratio (SNR) and limited bandwidth. This paper introduces sensitivity-aware filtering and transmission (SAFT), a learned transmission framework that integrates a Point-BERT-inspired encoder, a sensitivity-guided token filtering (STF) unit, a quantization block, and an SNR-aware decoder for adaptive reconstruction. Specifically, the STF module assigns token-wise importance scores based on the reconstruction sensitivity of each token under channel perturbation. We further employ a training-only symbol-usage penalty to stabilize the discrete representation, without affecting the transmitted payload. Experiments on ShapeNet, ModelNet40, and 8iVFB show that SAFT improves geometric fidelity (D1/D2 PSNR) compared with a separate source--channel coding pipeline (G-PCC combined with LDPC and QAM) and existing learned baselines, with the largest gains observed in low-SNR regimes, highlighting improved robustness under limited bandwidth.

---

### MemCam: Memory-Augmented Camera Control for Consistent Video Generation

Authors: Xinhang Gao, Junlin Guan, Shuhan Luo, Wenzhuo Li, Guanghuan Tan, Jiacheng Wang
Published: 2026-03-27
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2603.26193v1

Interactive video generation has significant potential for scene simulation and video creation. However, existing methods often struggle with maintaining scene consistency during long video generation under dynamic camera control due to limited contextual information. To address this challenge, we propose MemCam, a memory-augmented interactive video generation approach that treats previously generated frames as external memory and leverages them as contextual conditioning to achieve controllable camera viewpoints with high scene consistency. To enable longer and more relevant context, we design a context compression module that encodes memory frames into compact representations and employs co-visibility-based selection to dynamically retrieve the most relevant historical frames, thereby reducing computational overhead while enriching contextual information. Experiments on interactive video generation tasks show that MemCam significantly outperforms existing baseline methods as well as open-source state-of-the-art approaches in terms of scene consistency, particularly in long video scenarios with large camera rotations.

---

### HAD: Heterogeneity-Aware Distillation for Lifelong Heterogeneous Learning

Authors: Xuerui Zhang, Xuehao Wang, Zhan Zhuang, Linglan Zhao, Ziyue Li, Xinmin Zhang, Zhihuan Song, Yu Zhang
Published: 2026-03-27
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.26192v1

Lifelong learning aims to preserve knowledge acquired from previous tasks while incorporating knowledge from a sequence of new tasks. However, most prior work explores only streams of homogeneous tasks (\textit{e.g.}, only classification tasks) and neglects the scenario of learning across heterogeneous tasks that possess different structures of outputs. In this work, we formalize this broader setting as lifelong heterogeneous learning (LHL). Departing from conventional lifelong learning, the task sequence of LHL spans different task types, and the learner needs to retain heterogeneous knowledge for different output space structures. To instantiate the LHL, we focus on LHL in the context of dense prediction (LHL4DP), a realistic and challenging scenario. To this end, we propose the Heterogeneity-Aware Distillation (HAD) method, an exemplar-free approach that preserves previously gained heterogeneous knowledge by self-distillation in each training phase. The proposed HAD comprises two complementary components, including a distribution-balanced heterogeneity-aware distillation loss to alleviate the global imbalance of prediction distribution and a salience-guided heterogeneity-aware distillation loss that concentrates learning on informative edge pixels extracted with the Sobel operator. Extensive experiments demonstrate that the proposed HAD method significantly outperforms existing methods in this new scenario.

---