# Research Papers — 2026-04 · bundle page 61 of 233

> Full-text markdown of papers #3001–3050 of 11612 published in 2026-04, newest first. AI-readable mirrors of the full 11612-paper 2026-04 archive (50 papers per file).

Canonical page: https://aipod.dev/papers/archive/2026-04/page/61
[← Previous bundle](https://aipod.dev/papers/archive/2026-04/page/60.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-04/page/62.md)

### LLM StructCore: Schema-Guided Reasoning Condensation and Deterministic Compilation

Authors: Serhii Zabolotnii
Published: 2026-04-22
Categories: cs.CL
arXiv: https://arxiv.org/abs/2604.20560v1

Automatically filling Case Report Forms (CRFs) from clinical notes is challenging due to noisy language, strict output contracts, and the high cost of false positives. We describe our CL4Health 2026 submission for Dyspnea CRF filling (134 items) using a contract-driven two-stage design grounded in Schema-Guided Reasoning (SGR). The key task property is extreme sparsity: the majority of fields are unknown, and official scoring penalizes both empty values and unsupported predictions. We shift from a single-step "LLM predicts 134 fields" approach to a decomposition where (i) Stage 1 produces a stable SGR-style JSON summary with exactly 9 domain keys, and (ii) Stage 2 is a fully deterministic, 0-LLM compiler that parses the Stage 1 summary, canonicalizes item names, normalizes predictions to the official controlled vocabulary, applies evidence-gated false-positive filters, and expands the output into the required 134-item format. On the dev80 split, the best teacher configuration achieves macro-F1 0.6543 (EN) and 0.6905 (IT); on the hidden test200, the submitted English variant scores 0.63 on Codabench. The pipeline is language-agnostic: Italian results match or exceed English with no language-specific engineering.

---

### LayerTracer: A Joint Task-Particle and Vulnerable-Layer Analysis framework for Arbitrary Large Language Model Architectures

Authors: Yuhang Wu, Qinyuan Liu, Qiuyang Zhao, Qingwei Chong
Published: 2026-04-22
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2604.20556v1

Currently, Large Language Models (LLMs) feature a diversified architectural landscape, including traditional Transformer, GateDeltaNet, and Mamba. However, the evolutionary laws of hierarchical representations, task knowledge formation positions, and network robustness bottleneck mechanisms in various LLM architectures remain unclear, posing core challenges for hybrid architecture design and model optimization. This paper proposes LayerTracer, an architecture-agnostic end-to-end analysis framework compatible with any LLM architecture. By extracting hidden states layer-by-layer and mapping them to vocabulary probability distributions, it achieves joint analysis of task particle localization and layer vulnerability quantification. We define the task particle as the key layer where the target token probability first rises significantly, representing the model's task execution starting point, and the vulnerable layer is defined as the layer with the maximum Jensen-Shannon (JS) divergence between output distributions before and after mask perturbation, reflecting its sensitivity to disturbances. Experiments on models of different parameter scales show that task particles mainly appear in the deep layers of the model regardless of parameter size, while larger-parameter models exhibit stronger hierarchical robustness. LayerTracer provides a scientific basis for layer division, module ratio, and gating switching of hybrid architectures, effectively optimizing model performance. It accurately locates task-effective layers and stability bottlenecks, offering universal support for LLM structure design and interpretability research.

---

### On Bayesian Softmax-Gated Mixture-of-Experts Models

Authors: Nicola Bariletto, Huy Nguyen, Nhat Ho, Alessandro Rinaldo
Published: 2026-04-22
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2604.20551v1

Mixture-of-experts models provide a flexible framework for learning complex probabilistic input-output relationships by combining multiple expert models through an input-dependent gating mechanism. These models have become increasingly prominent in modern machine learning, yet their theoretical properties in the Bayesian framework remain largely unexplored. In this paper, we study Bayesian mixture-of-experts models, focusing on the ubiquitous softmax-based gating mechanism. Specifically, we investigate the asymptotic behavior of the posterior distribution for three fundamental statistical tasks: density estimation, parameter estimation, and model selection. First, we establish posterior contraction rates for density estimation, both in the regimes with a fixed, known number of experts and with a random learnable number of experts. We then analyze parameter estimation and derive convergence guarantees based on tailored Voronoi-type losses, which account for the complex identifiability structure of mixture-of-experts models. Finally, we propose and analyze two complementary strategies for selecting the number of experts. Taken together, these results provide one of the first systematic theoretical analyses of Bayesian mixture-of-experts models with softmax gating, and yield several theory-grounded insights for practical model design.

---

### Toward Cross-Lingual Quality Classifiers for Multilingual Pretraining Data Selection

Authors: Yassine Turki, Vinko Sabolčec, Bettina Messmer, Martin Jaggi
Published: 2026-04-22
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2604.20549v1

As Large Language Models (LLMs) scale, data curation has shifted from maximizing volume to optimizing the signal-to-noise ratio by performing quality filtering. However, for many languages, native high quality data is insufficient to train robust quality classifiers. This work investigates the idea that quality markers in embedding space may show cross-lingual consistency, which would allow high-resource languages to subsidize the filtering of low-resource ones. We evaluate various filtering strategies, including cross-lingual transfer, third quartile sampling (Q3), and retention rate tuning. Our results demonstrate that massive multilingual pooling frequently outperforms monolingual baselines in both rank stability and aggregate accuracy for a 1B model trained on 103B tokens, delivering gains for high resource languages (1.2% increase in aggregate normalized accuracy for French) and matching or exceeding monolingual baselines for low-resource languages. However, we find that scale alone does not guarantee stability. Furthermore, for high-resource languages like French, we show that refining the decision boundary through third quartile sampling (Q3) or tuning the retention rate is necessary to fully leverage the multilingual signal.

---

### Enhancing Research Idea Generation through Combinatorial Innovation and Multi-Agent Iterative Search Strategies

Authors: Shuai Chen, Chengzhi Zhang
Published: 2026-04-22
Categories: cs.CL, cs.AI, cs.DL, cs.IR
arXiv: https://arxiv.org/abs/2604.20548v1

Scientific progress depends on the continual generation of innovative re-search ideas. However, the rapid growth of scientific literature has greatly increased the cost of knowledge filtering, making it harder for researchers to identify novel directions. Although existing large language model (LLM)-based methods show promise in research idea generation, the ideas they produce are often repetitive and lack depth. To address this issue, this study proposes a multi-agent iterative planning search strategy inspired by com-binatorial innovation theory. The framework combines iterative knowledge search with an LLM-based multi-agent system to generate, evaluate, and re-fine research ideas through repeated interaction, with the goal of improving idea diversity and novelty. Experiments in the natural language processing domain show that the proposed method outperforms state-of-the-art base-lines in both diversity and novelty. Further comparison with ideas derived from top-tier machine learning conference papers indicates that the quality of the generated ideas falls between that of accepted and rejected papers. These results suggest that the proposed framework is a promising approach for supporting high-quality research idea generation. The source code and dataset used in this paper are publicly available on Github repository: https://github.com/ChenShuai00/MAGenIdeas. The demo is available at https://huggingface.co/spaces/cshuai20/MAGenIdeas.

---

### Measuring the Machine: Evaluating Generative AI as Pluralist Sociotechical Systems

Authors: Rebecca L. Johnson
Published: 2026-04-22
Categories: cs.AI
arXiv: https://arxiv.org/abs/2604.20545v1

In measurement theory, instruments do not simply record reality; they help constitute what is observed. The same holds for generative AI evaluation: benchmarks do not just measure, they shape what models appear to be. Functionalist benchmarks treat models as isolated predictors, while prescriptive approaches assess what systems ought to be. Both obscure the sociotechnical processes through which meaning and values are enacted, risking the reification of narrow cultural perspectives in pluralist contexts. This thesis advances a descriptive alternative. It argues that generative AI must be evaluated as a pluralist sociotechnical system and develops Machine-Society-Human (MaSH) Loops, a framework for tracing how models, users, and institutions recursively co-construct meaning and values. Evaluation shifts from judging outputs to examining how values are enacted in interaction. Three contributions follow. Conceptually, MaSH Loops reframes evaluation as recursive, enactive process. Methodologically, the World Values Benchmark introduces a distributional approach grounded in World Values Survey data, structured prompt sets, and anchor-aware scoring. Empirically, the thesis demonstrates these through two cases: value drift in early GPT-3 and sociotechnical evaluation in real estate. A final chapter draws on participatory realism to argue that prompting and evaluation are constitutive interventions, not neutral observations. The thesis argues that static benchmarks are insufficient for generative AI. Responsible evaluation requires pluralist, process-oriented frameworks that make visible whose values are enacted. Evaluation is therefore a site of governance, shaping how AI systems are understood, deployed, and trusted.

---

### Evian: Towards Explainable Visual Instruction-tuning Data Auditing

Authors: Zimu Jia, Mingjie Xu, Andrew Estornell, Jiaheng Wei
Published: 2026-04-22
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2604.20544v1

The efficacy of Large Vision-Language Models (LVLMs) is critically dependent on the quality of their training data, requiring a precise balance between visual fidelity and instruction-following capability. Existing datasets, however, are plagued by inconsistent quality, and current data filtering methods rely on coarse-grained scores that lack the granularity to identify nuanced semantic flaws like logical fallacies or factual errors. This creates a fundamental bottleneck in developing more reliable models. To address this, we make three core contributions. First, we construct a large-scale, 300K-sample benchmark by systematically injecting diverse, subtle defects to provide a challenging testbed for data auditing. Second, we introduce a novel "Decomposition-then-Evaluation" paradigm that breaks model responses into constituent cognitive components: visual description, subjective inference, and factual claim, enabling targeted analysis. Third, we instantiate this paradigm via EVIAN (Explainable Visual Instruction-tuning Data AuditiNg), an automated framework that evaluates these components along the orthogonal axes of Image-Text Consistency, Logical Coherence, and Factual Accuracy. Our empirical findings challenge the prevailing scale-centric paradigm: a model fine-tuned on a compact, high-quality subset curated by EVIAN consistently surpassed models trained on orders-of-magnitude larger datasets. We also reveal that dividing complex auditing into verifiable subtasks enables robust curation, and that Logical Coherence is the most critical factor in data quality evaluation.

---

### RefAerial: A Benchmark and Approach for Referring Detection in Aerial Images

Authors: Guyue Hu, Hao Song, Yuxing Tong, Duzhi Yuan, Dengdi Sun, Aihua Zheng, Chenglong Li, Jin Tang
Published: 2026-04-22
Categories: cs.CV
arXiv: https://arxiv.org/abs/2604.20543v2

Referring detection refers to locate the target referred by natural languages, which has recently attracted growing research interests. However, existing datasets are limited to ground images with large object centered in relative small scenes. This paper introduces a large-scale challenging dataset for referring detection in aerial images, termed as RefAerial. It distinguishes from conventional ground referring detection datasets by 4 characteristics: (1) low but diverse object-to-scene ratios, (2) numerous targets and distractors, (3)complex and fine-grained referring descriptions, (4) diverse and broad scenes in the aerial view. We also develop a human-in-the-loop referring expansion and annotation engine (REA-Engine) for efficient semi-automated referring pair annotation. Besides, we observe that existing ground referring detection approaches exhibiting serious performance degradation on our aerial dataset since the intrinsic scale variety issue within or across aerial images. Therefore, we further propose a novel scale-comprehensive and sensitive (SCS) framework for referring detection in aerial images. It consists of a mixture-of-granularity (MoG) attention and a two-stage comprehensive-to-sensitive (CtS) decoding strategy. Specifically, the mixture-of-granularity attention is developed for scale-comprehensive target understanding. In addition, the two-stage comprehensive-to-sensitive decoding strategy is designed for coarse-to-fine referring target decoding. Eventually, the proposed SCS framework achieves remarkable performance on our aerial referring detection dataset and even promising performance boost on conventional ground referring detection datasets.

---

### Aligning Stuttered-Speech Research with End-User Needs: Scoping Review, Survey, and Guidelines

Authors: Hawau Olamide Toyin, Mutiah Apampa, Toluwani Aremu, Humaid Alblooshi, Ana Rita Valente, Gonçalo Leal, Zhengjun Yue, Zeerak Talat, Hanan Aldarmaki
Published: 2026-04-22
Categories: cs.CL, cs.HC
arXiv: https://arxiv.org/abs/2604.20535v1

Atypical speech is receiving greater attention in speech technology research, but much of this work unfolds with limited interdisciplinary dialogue. For stuttered speech in particular, it is widely recognised that current speech recognition systems fall short in practice, and current evaluation methods and research priorities are not systematically grounded in end-user experiences and needs. In this work, we analyse these gaps through 1) a scoping review of papers that deal with stuttered speech and 2) a survey of 70 stakeholders, including adults who stutter and speech-language pathologists. By analysing these two perspectives, we propose a taxonomy of stuttered-speech research, identify where current research directions diverge from the needs articulated by stakeholders, and conclude by outlining concrete guidelines and directions towards addressing the real needs of the stuttering community.

---

### Effects of Cross-lingual Evidence in Multilingual Medical Question Answering

Authors: Anar Yeginbergen, Maite Oronoz, Rodrigo Agerri
Published: 2026-04-22
Categories: cs.CL
arXiv: https://arxiv.org/abs/2604.20531v1

This paper investigates Multilingual Medical Question Answering across high-resource (English, Spanish, French, Italian) and low-resource (Basque, Kazakh) languages. We evaluate three types of external evidence sources across models of varying size: curated repositories of specialized medical knowledge, web-retrieved content, and explanations from LLM's parametric knowledge. Moreover, we conduct experiments with multilingual, monolingual and cross-lingual retrieval. Our results demonstrate that larger models consistently achieve superior performance in English across baseline evaluations. When incorporating external knowledge, web-retrieved data in English proves most beneficial for high-resource languages. Conversely, for low-resource languages, the most effective strategy combines retrieval in both English and the target language, achieving comparable accuracy to high-resource language results. These findings challenge the assumption that external knowledge systematically improves performance and reveal that effective strategies depend on both the source of language resources and on model scale. Furthermore, specialized medical knowledge sources such as PubMed are limited: while they provide authoritative expert knowledge, they lack adequate multilingual coverage

---

### Response time of lateral predictive coding and benefits of modular structures

Authors: Guanghui Cai, Zhen-Ye Huang, Weikang Wang, Hai-Jun Zhou
Published: 2026-04-22
Categories: q-bio.NC, cond-mat.dis-nn, cs.NE
arXiv: https://arxiv.org/abs/2604.20524v1

Lateral predictive coding (LPC) is a simple theoretical framework to appreciate feature detection in biological neural circuits. Recent theoretical work (Huang et al., Phys.Rev.E 112, 034304 (2025)) has successfully constructed optimal LPC networks capable of extracting non-Gaussian hidden input features by imposing the tradeoff between energetic cost and information robustness, but the resulting dynamical systems of recurrent interactions can be very slow in responding to external inputs. We investigate response-time reduction in the present paper. We find that the characteristic response time of the LPC system can be minimized to closely approaching the lower-bound value without compromising the mean predictive error (energetic cost) and the information robustness of signal transmission. We further demonstrate that optimal LPC networks taking a modular structural organization with extensively reduced number of lateral interactions are equally excellent as all-to-all completely connected networks, in terms of feature detection performance, response time, energetic cost and information robustness.

---

### Early-Stage Product Line Validation Using LLMs: A Study on Semi-Formal Blueprint Analysis

Authors: Viet-Man Le, Thi Ngoc Trang Tran, Sebastian Lubos, Alexander Felfernig, Damian Garber
Published: 2026-04-22
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2604.20523v1

We study whether Large Language Models (LLMs) can perform feature model analysis operations (AOs) directly on semi-formal textual blueprints, i.e., concise constrained-language descriptions of feature hierarchies and constraints, enabling early validation in Software Product Line scoping. Using 12 state-of-the-art LLMs and 16 standard AOs, we compare their outputs against the solver-based oracle FLAMA. Results show that reasoning-optimized models (e.g., Grok 4 Fast Reasoning, Gemini 2.5 Pro) achieve 88-89% average accuracy across all evaluated blueprints and operations, approaching solver correctness. We identify systematic errors in structural parsing and constraint reasoning, and highlight accuracy-cost trade-offs that inform model selection. These findings position LLMs as lightweight assistants for early variability validation.

---

### From Image to Music Language: A Two-Stage Structure Decoding Approach for Complex Polyphonic OMR

Authors: Nan Xu, Shiheng Li, Shengchao Hou
Published: 2026-04-22
Categories: cs.SD, cs.CV
arXiv: https://arxiv.org/abs/2604.20522v3

We propose a new approach for a practical two-stage Optical Music Recognition (OMR) pipeline, with a particular focus on its second stage. Given symbol and event candidates from the visual pipeline, we decode them into an editable, verifiable, and exportable score structure. We focus on complex polyphonic staff notation, especially piano scores, where voice separation and intra-measure timing are the main bottlenecks. Our approach formulates second-stage decoding as a structure decoding problem and uses topology recognition with probability-guided search (BeadSolver) as its core method. We also describe a data strategy that combines procedural generation with recognition-feedback annotations. The result is a practical decoding component for real OMR systems and a path to accumulate structured score data for future end-to-end, multimodal, and RL-style methods.

---

### Efficient Symbolic Computations for Identifying Causal Effects

Authors: Benjamin Hollering, Pratik Misra, Nils Sturma
Published: 2026-04-22
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2604.20516v1

Determining identifiability of causal effects from observational data under latent confounding is a central challenge in causal inference. For linear structural causal models, identifiability of causal effects is decidable through symbolic computation. However, standard approaches based on Gröbner bases become computationally infeasible beyond small settings due to their doubly exponential complexity. In this work, we study how to practically use symbolic computation for deciding rational identifiability. In particular, we present an efficient algorithm that provably finds the lowest degree identifying formulas. For a causal effect of interest, if there exists an identification formula of a prespecified maximal degree, our algorithm returns such a formula in quasi-polynomial time.

---

### CHASM: Unveiling Covert Advertisements on Chinese Social Media

Authors: Jingyi Zheng, Tianyi Hu, Yule Liu, Zhen Sun, Zongmin Zhang, Zifan Peng, Wenhan Dong, Xinlei He
Published: 2026-04-22
Categories: cs.LG, cs.AI, cs.CL, cs.CV, cs.CY
arXiv: https://arxiv.org/abs/2604.20511v1

Current benchmarks for evaluating large language models (LLMs) in social media moderation completely overlook a serious threat: covert advertisements, which disguise themselves as regular posts to deceive and mislead consumers into making purchases, leading to significant ethical and legal concerns. In this paper, we present the CHASM, a first-of-its-kind dataset designed to evaluate the capability of Multimodal Large Language Models (MLLMs) in detecting covert advertisements on social media. CHASM is a high-quality, anonymized, manually curated dataset consisting of 4,992 instances, based on real-world scenarios from the Chinese social media platform Rednote. The dataset was collected and annotated under strict privacy protection and quality control protocols. It includes many product experience sharing posts that closely resemble covert advertisements, making the dataset particularly challenging.The results show that under both zero-shot and in-context learning settings, none of the current MLLMs are sufficiently reliable for detecting covert advertisements.Our further experiments revealed that fine-tuning open-source MLLMs on our dataset yielded noticeable performance gains. However, significant challenges persist, such as detecting subtle cues in comments and differences in visual and textual structures.We provide in-depth error analysis and outline future research directions. We hope our study can serve as a call for the research community and platform moderators to develop more precise defenses against this emerging threat.

---

### Explicit Dropout: Deterministic Regularization for Transformer Architectures

Authors: Vidhi Agrawal, Illia Oleksiienko, Alexandros Iosifidis
Published: 2026-04-22
Categories: cs.LG
arXiv: https://arxiv.org/abs/2604.20505v1

Dropout is a widely used regularization technique in deep learning, but its effects are typically realized through stochastic masking rather than explicit optimization objectives. We propose a deterministic formulation that expresses dropout as an additive regularizer directly incorporated into the training loss. The framework derives explicit regularization terms for Transformer architectures, covering attention query, key, value, and feed-forward components with independently controllable strengths. This formulation removes reliance on stochastic perturbations while providing clearer and fine-grained control over regularization strength. Experiments across image classification, temporal action detection, and audio classification show that explicit dropout matches or outperforms conventional implicit methods, with consistent gains when applied to attention and feed-forward network layers. Ablation studies demonstrate stable performance and controllable regularization through regularization coefficients and dropout rates. Overall, explicit dropout offers a practical and interpretable alternative to stochastic regularization while maintaining architectural flexibility across diverse tasks.

---

### Efficient Test-Time Inference via Deterministic Exploration of Truncated Decoding Trees

Authors: Xueyan Li, Johannes Zenn, Ekaterina Fadeeva, Guinan Su, Mrinmaya Sachan, Jonas Geiping
Published: 2026-04-22
Categories: cs.LG
arXiv: https://arxiv.org/abs/2604.20500v1

Self-consistency boosts inference-time performance by sampling multiple reasoning traces in parallel and voting. However, in constrained domains like math and code, this strategy is compute-inefficient because it samples with replacement, repeatedly revisiting the same high-probability prefixes and duplicate completions. We propose Distinct Leaf Enumeration (DLE), a deterministic decoding method that treats truncated sampling as traversal of a pruned decoding tree and systematically enumerates distinct leaves instead of sampling with replacement. This strategy improves inference efficiency in two ways. Algorithmically, it increases coverage of the truncated search space under a fixed budget by exploring previously unvisited high-probability branches. Systemically, it reuses shared prefixes and reduces redundant token generation. Empirically, DLE explores higher-quality reasoning traces than stochastic self-consistency, yielding better performance on math, coding, and general reasoning tasks.

---

### Mythos and the Unverified Cage: Z3-Based Pre-Deployment Verification for Frontier-Model Sandbox Infrastructure

Authors: Dominik Blain
Published: 2026-04-22
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2604.20496v1

The April 2026 Claude Mythos sandbox escape exposed a critical weakness in frontier AI containment: the infrastructure surrounding advanced models remains susceptible to formally characterizable arithmetic vulnerabilities. Anthropic has not publicly characterized the escape vector; some secondary accounts hypothesize a CWE-190 arithmetic vulnerability in sandbox networking code. We treat this as unverified and analyze the vulnerability class rather than the specific escape. This paper presents COBALT, a Z3 SMT-based formal verification engine for identifying CWE-190/191/195 arithmetic vulnerability patterns in C/C++ infrastructure prior to deployment. We distinguish two classes of contribution. Validated: COBALT detects arithmetic vulnerability patterns in production codebases, producing SAT verdicts with concrete witnesses and UNSAT guarantees under explicit safety bounds. We demonstrate this on four production case studies: NASA cFE, wolfSSL, Eclipse Mosquitto, and NASA F Prime, with reproducible encodings, verified solver output, and acknowledged security outcomes. Proposed: a four-layer containment framework consisting of COBALT, VERDICT, DIRECTIVE-4, and SENTINEL, mapping pre-deployment verification, pre-execution constraints, output control, and runtime monitoring to the failure modes exposed by the Mythos incident. Under explicit assumptions, we further argue that the publicly reported Mythos escape class is consistent with a Z3-expressible CWE-190 arithmetic formulation and that pre-deployment formal analysis would have been capable of surfacing the relevant pattern. The broader claim is infrastructural: frontier-model safety cannot depend on behavioral safeguards alone; the containment stack itself must be subjected to formal verification.

---

### Towards Certified Malware Detection: Provable Guarantees Against Evasion Attacks

Authors: Nandakrishna Giri, Asmitha K. A., Serena Nicolazzo, Antonino Nocera, Vinod P
Published: 2026-04-22
Categories: cs.CR, cs.LG
arXiv: https://arxiv.org/abs/2604.20495v1

Machine learning-based static malware detectors remain vulnerable to adversarial evasion techniques, such as metamorphic engine mutations. To address this vulnerability, we propose a certifiably robust malware detection framework based on randomized smoothing through feature ablation and targeted noise injection. During evaluation, our system analyzes an executable by generating multiple ablated variants, classifies them by using a smoothed classifier, and identifies the final label based on the majority vote. By analyzing the top-class voting distribution and the Wilson score interval, we derive a formal certificate that guarantees robustness within a specific radius against feature-space perturbations. We evaluate our approach by comparing the performance of the base classifier and the smoothed classifier on both clean executables and ablated variants generated using PyMetaEngine. Our results demonstrate that the proposed smoothed classifier successfully provides certifiable robustness against metamorphic evasion attacks without requiring modifications to the underlying machine learning architecture.

---

### Decentralized Machine Learning with Centralized Performance Guarantees via Gibbs Algorithms

Authors: Yaiza Bermudez, Samir M. Perlaza, Iñaki Esnaola
Published: 2026-04-22
Categories: stat.ML, cs.IT, cs.LG
arXiv: https://arxiv.org/abs/2604.20492v1

In this paper, it is shown, for the first time, that centralized performance is achievable in decentralized learning without sharing the local datasets. Specifically, when clients adopt an empirical risk minimization with relative-entropy regularization (ERM-RER) learning framework and a forward-backward communication between clients is established, it suffices to share the locally obtained Gibbs measures to achieve the same performance as that of a centralized ERM-RER with access to all the datasets. The core idea is that the Gibbs measure produced by client~$k$ is used, as reference measure, by client~$k+1$. This effectively establishes a principled way to encode prior information through a reference measure. In particular, achieving centralized performance in the decentralized setting requires a specific scaling of the regularization factors with the local sample sizes. Overall, this result opens the door to novel decentralized learning paradigms that shift the collaboration strategy from sharing data to sharing the local inductive bias via the reference measures over the set of models.

---

### Knowledge Capsules: Structured Nonparametric Memory Units for LLMs

Authors: Bin Ju, Shenfeng Weng, Danying Zhou, Rongkai Xu, Kunkai Su
Published: 2026-04-22
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2604.20487v2

Large language models (LLMs) encode knowledge in parametric weights, making it costly to update or extend without retraining. Retrieval-augmented generation (RAG) mitigates this limitation by appending retrieved text to the input, but operates purely through context expansion, where external knowledge competes as tokens within the attention mechanism. As a result, its influence is indirect and often unstable, particularly in long context and multi hop reasoning scenarios. We propose Knowledge Capsules, structured nonparametric memory units that represent normalized relational knowledge and can be constructed directly from document corpora using a frozen base model. Instead of injecting knowledge as text, we introduce an External Key Value Injection (KVI) framework that compiles capsules into attention-compatible key value representations, enabling external knowledge to directly participate in the model's attention computation. By shifting knowledge integration from context-level augmentation to memory level interaction, the proposed framework consistently outperforms RAG and GraphRAG across multiple QA benchmarks, with improved stability and accuracy in long context and multi hop reasoning, while requiring no parameter updates.

---

### ProMMSearchAgent: A Generalizable Multimodal Search Agent Trained with Process-Oriented Rewards

Authors: Wentao Yan, Shengqin Wang, Huichi Zhou, Yihang Chen, Kun Shao, Yuan Xie, Zhizhong Zhang
Published: 2026-04-22
Categories: cs.CV
arXiv: https://arxiv.org/abs/2604.20486v1

Training multimodal agents via reinforcement learning for knowledge-intensive visual reasoning is fundamentally hindered by the extreme sparsity of outcome-based supervision and the unpredictability of live web environments. To resolve these algorithmic and environmental bottlenecks, we introduce ProMMSearchAgent, establishing a novel Sim-to-Real training paradigm for multimodal search. We decouple policy learning into a deterministic, local static sandbox. Crucially, to learn effectively within this constrained environment, we propose an introspective process-oriented reward. By probing the agent's own parametric knowledge boundaries, we generate dense behavioral metadata that explicitly rewards the correct cognitive decision, initiating a multimodal or text search only when visually or factually uncertain. Extensive experiments demonstrate that our locally-trained policy transfers zero-shot to the live Google Search API. ProMMSearchAgent achieves new SOTA performance, outperforming MMSearch-R1 by +5.1% on FVQA-test, +6.3% on InfoSeek, and +11.3% on MMSearch.

---

### Forecasting Individual NetFlows using a Predictive Masked Graph Autoencoder

Authors: Georgios Anyfantis, Pere Barlet-Ros
Published: 2026-04-22
Categories: cs.NI, cs.LG
arXiv: https://arxiv.org/abs/2604.20483v3

In this paper, we propose a proof-of-concept Graph Neural Network model that can successfully predict network flow-level traffic (NetFlow) by accurately modelling the graph structure and the connection features. We use sliding-windows to split the network traffic in equal-sized heterogeneous bidirectional graphs containing IP, Port, and Connection nodes. We then use the GNN to model the evolution of the graph structure and the connection features. Our approach shows superior results when identifying the Port and IP to which connections attach, while feature reconstruction remains competitive with strong forecasting baselines. Overall, our work showcases the use of GNNs for per-flow NetFlow prediction.

---

### Forecasting Individual NetFlows using a Predictive Masked Graph Autoencoder

Authors: Georgios Anyfantis, Pere Barlet-Ros
Published: 2026-04-22
Categories: cs.NI, cs.LG
arXiv: https://arxiv.org/abs/2604.20483v2

In this paper, we propose a proof-of-concept Graph Neural Network model that can successfully predict network flow-level traffic (NetFlow) by accurately modelling the graph structure and the connection features. We use sliding-windows to split the network traffic in equal-sized heterogeneous bidirectional graphs containing IP, Port, and Connection nodes. We then use the GNN to model the evolution of the graph structure and the connection features. Our approach shows superior results when identifying the Port and IP to which connections attach, while feature reconstruction remains competitive with strong forecasting baselines. Overall, our work showcases the use of GNNs for per-flow NetFlow prediction.

---

### Random Walk on Point Clouds for Feature Detection

Authors: Yuhe Zhang, Zhikun Tu, Zhi Li, Jian Gao, Bao Guo, Shunli Zhang
Published: 2026-04-22
Categories: cs.CV
arXiv: https://arxiv.org/abs/2604.20474v1

The points on the point clouds that can entirely outline the shape of the model are of critical importance, as they serve as the foundation for numerous point cloud processing tasks and are widely utilized in computer graphics and computer-aided design. This study introduces a novel method, RWoDSN, for extracting such feature points, incorporating considerations of sharp-to-smooth transitions, large-to-small scales, and textural-to-detailed features. We approach feature extraction as a two-stage context-dependent analysis problem. In the first stage, we propose a novel neighborhood descriptor, termed the Disk Sampling Neighborhood (DSN), which, unlike traditional spatially and geometrically invariant approaches, preserves a matrix structure while maintaining normal neighborhood relationships. In the second stage, a random walk is performed on the DSN (RWoDSN), yielding a graph-based DSN that simultaneously accounts for the spatial distribution, topological properties, and geometric characteristics of the local surface surrounding each point. This enables the effective extraction of feature points. Experimental results demonstrate that the proposed RWoDSN method achieves a recall of 0.769-22% higher than the current state-of-the-art-alongside a precision of 0.784. Furthermore, it significantly outperforms several traditional and deep-learning techniques across eight evaluation metrics.

---

### Video-ToC: Video Tree-of-Cue Reasoning

Authors: Qizhong Tan, Zhuotao Tian, Guangming Lu, Jun Yu, Wenjie Pei
Published: 2026-04-22
Categories: cs.CV
arXiv: https://arxiv.org/abs/2604.20473v1

Existing Video Large Language Models (Video LLMs) struggle with complex video understanding, exhibiting limited reasoning capabilities and potential hallucinations. In particular, these methods tend to perform reasoning solely relying on the pretrained inherent reasoning rationales whilst lacking perception-aware adaptation to the input video content. To address this, we propose \textbf{Video-ToC}, a novel video reasoning framework that enhances video understanding through tree-of-cue reasoning. Specifically, our approach introduces three key innovations: (1) A tree-guided visual cue localization mechanism, which endows the model with enhanced fine-grained perceptual capabilities through structured reasoning patterns; (2) A reasoning-demand reward mechanism, which dynamically adjusts the reward value for reinforcement learning (RL) based on the estimation of reasoning demands, enabling on-demand incentives for more effective reasoning strategies; and (3) An automated annotation pipeline that constructs the Video-ToC-SFT-1k and Video-ToC-RL-2k datasets for supervised fine-tuning (SFT) and RL training, respectively. Extensive evaluations on six video understanding benchmarks and a video hallucination benchmark demonstrate the superiority of Video-ToC over baselines and recent methods. Code is available at https://github.com/qizhongtan/Video-ToC.

---

### Temporal Difference Calibration in Sequential Tasks: Application to Vision-Language-Action Models

Authors: Shelly Francis-Meretzki, Mirco Mutti, Yaniv Romano, Aviv Tamar
Published: 2026-04-22
Categories: cs.RO, cs.LG
arXiv: https://arxiv.org/abs/2604.20472v1

Recent advances in vision-language-action (VLA) models for robotics have highlighted the importance of reliable uncertainty quantification in sequential tasks. However, assessing and improving calibration in such settings remains mostly unexplored, especially when only partial trajectories are observed. In this work, we formulate sequential calibration for episodic tasks, where task-success confidence is produced along an episode, while success is determined at the end of it. We introduce a sequential extension of the Brier score and show that, for binary outcomes, its risk minimizer coincides with the VLA policy's value function. This connection bridges uncertainty calibration and reinforcement learning, enabling the use of temporal-difference (TD) value estimation as a principled calibration mechanism over time. We empirically show that TD calibration improves performance relative to the state-of-the-art on simulated and real-robot data. Interestingly, we show that when calibrated using TD, the VLA's single-step action probabilities can yield competitive uncertainty estimates, in contrast to recent findings that employed different calibration techniques.

---

### DynamicRad: Content-Adaptive Sparse Attention for Long Video Diffusion

Authors: Yongji Long, Shijun Liang, Jintao Li, Yun Li
Published: 2026-04-22
Categories: cs.CV
arXiv: https://arxiv.org/abs/2604.20470v1

Leveraging the natural spatiotemporal energy decay in video diffusion offers a path to efficiency, yet relying solely on rigid static masks risks losing critical long-range information in complex dynamics. To address this issue, we propose \textbf{DynamicRad}, a unified sparse-attention paradigm that grounds adaptive selection within a radial locality prior. DynamicRad introduces a \textbf{dual-mode} strategy: \textit{static-ratio} for speed-optimized execution and \textit{dynamic-threshold} for quality-first filtering. To ensure robustness without online search overhead, we integrate an offline Bayesian Optimization (BO) pipeline coupled with a \textbf{semantic motion router}. This lightweight projection module maps prompt embeddings to optimal sparsity regimes with \textbf{minimal runtime overhead}. Unlike online profiling methods, our offline BO optimizes attention reconstruction error (MSE) on a physics-based proxy task, ensuring rapid convergence. Experiments on HunyuanVideo and Wan2.1-14B demonstrate that DynamicRad pushes the efficiency--quality Pareto frontier, achieving \textbf{1.7$\times$--2.5$\times$ inference speedups} with \textbf{over 80\% effective sparsity}. In some long-sequence settings, the dynamic mode even matches or exceeds the dense baseline, while mask-aware LoRA further improves long-horizon coherence. Code is available at https://github.com/Adamlong3/DynamicRad.

---

### MOMO: A framework for seamless physical, verbal, and graphical robot skill learning and adaptation

Authors: Markus Knauer, Edoardo Fiorini, Maximilian Mühlbauer, Stefan Schneyer, Promwat Angsuratanawech, Florian Samuel Lay, Timo Bachmann, Samuel Bustamante, Korbinian Nottensteiner, Freek Stulp, Alin Albu-Schäffer, João Silvério et al.
Published: 2026-04-22
Categories: cs.RO, cs.AI, cs.CL, cs.HC, cs.LG
arXiv: https://arxiv.org/abs/2604.20468v3

Industrial robot applications require increasingly flexible systems that non-expert users can easily adapt for varying tasks and environments. However, different adaptations benefit from different interaction modalities. We present an interactive framework that enables robot skill adaptation through three complementary modalities: kinesthetic touch for precise spatial corrections, natural language for high-level semantic modifications, and a graphical web interface for visualizing geometric relations and trajectories, inspecting and adjusting parameters, and editing via-points by drag-and-drop. The framework integrates five components: energy-based human-intention detection, a tool-based LLM architecture (where the LLM selects and parameterizes predefined functions rather than generating code) for safe natural language adaptation, Kernelized Movement Primitives (KMPs) for motion encoding, probabilistic Virtual Fixtures for guided demonstration recording, and ergodic control for surface finishing. We demonstrate that this tool-based LLM architecture generalizes skill adaptation from KMPs to ergodic control, enabling voice-commanded surface finishing. Validation on a 7-DoF torque-controlled robot at the Automatica 2025 trade fair demonstrates the practical applicability of our approach in industrial settings.

---

### MOMO: A framework for seamless physical, verbal, and graphical robot skill learning and adaptation

Authors: Markus Knauer, Edoardo Fiorini, Maximilian Mühlbauer, Stefan Schneyer, Promwat Angsuratanawech, Florian Samuel Lay, Timo Bachmann, Samuel Bustamante, Korbinian Nottensteiner, Freek Stulp, Alin Albu-Schäffer, João Silvério et al.
Published: 2026-04-22
Categories: cs.RO, cs.AI, cs.CL, cs.HC, cs.LG
arXiv: https://arxiv.org/abs/2604.20468v2

Industrial robot applications require increasingly flexible systems that non-expert users can easily adapt for varying tasks and environments. However, different adaptations benefit from different interaction modalities. We present an interactive framework that enables robot skill adaptation through three complementary modalities: kinesthetic touch for precise spatial corrections, natural language for high-level semantic modifications, and a graphical web interface for visualizing geometric relations and trajectories, inspecting and adjusting parameters, and editing via-points by drag-and-drop. The framework integrates five components: energy-based human-intention detection, a tool-based LLM architecture (where the LLM selects and parameterizes predefined functions rather than generating code) for safe natural language adaptation, Kernelized Movement Primitives (KMPs) for motion encoding, probabilistic Virtual Fixtures for guided demonstration recording, and ergodic control for surface finishing. We demonstrate that this tool-based LLM architecture generalizes skill adaptation from KMPs to ergodic control, enabling voice-commanded surface finishing. Validation on a 7-DoF torque-controlled robot at the Automatica 2025 trade fair demonstrates the practical applicability of our approach in industrial settings.

---

### Mechanistic Interpretability Tool for AI Weather Models

Authors: Kirsten I. Tempest, Matthias Beylich, George C. Craig
Published: 2026-04-22
Categories: physics.ao-ph, cs.LG, physics.comp-ph
arXiv: https://arxiv.org/abs/2604.20467v1

Artificial Intelligence (AI) weather models are improving rapidly, and their forecasts are already competitive with long-established traditional Numerical Weather Prediction (NWP). To build confidence in this new methodology, it is critical that we understand how these predictions are generated. This is a huge challenge as these AI weather models remain largely black boxes. In other areas of Machine Learning (ML), mechanistic interpretability has emerged as a framework for understanding ML predictions by analysing the building blocks responsible for them. Here we present an open-source, highly adaptable tool which incorporates concepts from mechanistic interpretability. The tool organises internal latent representations from the model processor and allows for initial analyses, including cosine similarity and Principal Component Analysis (PCA), enabling the user to identify directions in latent space potentially associated with meteorological features. Applying our tool to the graph neural network GraphCast, we present preliminary case studies for mid-latitude synoptic-scale waves and specific humidity. These demonstrate the tool's ability to identify linear combinations of latent channels that appear to correspond to interpretable features.

---

### Deja Vu at Scale: Paraphrase-Robust Detection of Duplicate Gherkin Steps in Behaviour-Driven Software Testing with Sentence-Transformer Embeddings and a 1.1M-Step Open Benchmark

Authors: Ali Hassaan Mughal, Noor Fatima, Muhammad Bilal
Published: 2026-04-22
Categories: cs.SE, cs.CL, cs.IR
arXiv: https://arxiv.org/abs/2604.20462v3

Context. Behaviour-Driven Development (BDD) suites in Gherkin accumulate step-text duplication with documented maintenance cost. Prior detectors either require runnable tests or are single-organisation, leaving a gap: a static, paraphrase-robust, step-level detector and a public benchmark to calibrate it. Objective. We release (i) the largest cross-organisational BDD step corpus to date, (ii) a labelled pair-level calibration benchmark, and (iii) a four-strategy detector with a consolidation-savings model linking clusters to ISO/IEC 25010 maintainability sub-characteristics. Method. The corpus contains 347 public GitHub repositories, 23,667 .feature files, and 1,113,616 Gherkin steps, SPDX-tagged. The detector layers exact hashing, normalised Levenshtein, sentence-transformer cosine, and a Levenshtein-banded hybrid. Calibration uses 1,020 manually labelled step pairs under a released rubric (60-pair overlap, Fleiss kappa = 0.84). We report precision, recall, and F1 with bootstrap 95% CIs under the primary rubric and a score-free relabelling, and benchmark against SourcererCC-style and NiCad-style lexical baselines. Results. Step-weighted exact-duplicate rate is 80.2%; median-repository rate is 58.6% (Spearman rho = 0.51). The top hybrid cluster has 20,737 occurrences across 2,245 files. Near-exact reaches F1 = 0.822 on score-free labels; semantic F1 = 0.906 under the primary rubric reflects a disclosed stratification artefact. Lexical baselines reach F1 = 0.761 and 0.799. The savings model estimates 893,357 corpus-wide eliminable step occurrences; on the median repository 62.5% of step lines are eliminable.

---

### CCTVBench: Contrastive Consistency Traffic VideoQA Benchmark for Multimodal LLMs

Authors: Xingcheng Zhou, Hao Guo, Rui Song, Walter Zimmer, Mingyu Liu, André Schamschurko, Hu Cao, Alois Knoll
Published: 2026-04-22
Categories: cs.CV
arXiv: https://arxiv.org/abs/2604.20460v1

Safety-critical traffic reasoning requires contrastive consistency: models must detect true hazards when an accident occurs, and reliably reject plausible-but-false hypotheses under near-identical counterfactual scenes. We present CCTVBench, a Contrastive Consistency Traffic VideoQA Benchmark built on paired real accident videos and world-model-generated counterfactual counterparts, together with minimally different, mutually exclusive hypothesis questions. CCTVBench enforces a single structured decision pattern over each video question quadruple and provides actionable diagnostics that decompose failures into positive omission, positive swap, negative hallucination, and mutual-exclusivity violation, while separating video versus question consistency. Experiments across open-source and proprietary video LLMs reveal a large and persistent gap between standard per-instance QA metrics and quadruple-level contrastive consistency, with unreliable none-of-the-above rejection as a key bottleneck. Finally, we introduce C-TCD, a contrastive decoding approach leveraging a semantically exclusive counterpart video as the contrast input at inference time, improving both instance-level QA and contrastive consistency.

---

### Surrogate Functionals for Machine-Learned Orbital-Free Density Functional Theory

Authors: Roman Remme, Fred A. Hamprecht
Published: 2026-04-22
Categories: cs.LG, physics.chem-ph
arXiv: https://arxiv.org/abs/2604.20458v1

We introduce surrogate functionals: machine-learned energy functionals for orbital-free density functional theory (OF-DFT) which are defined not by universal fidelity to a physical reference, but merely by the requirement that density optimization with a fixed procedure yields the true ground-state density. Helpfully, training surrogate functionals requires only ground-state densities, no energies or gradients away from the ground state. We here propose a gradient-descent-improvement loss that guarantees exponential convergence of the density to the ground state, and combine it with an adaptive sampling scheme that concentrates learning around the optimization trajectories actually visited during inference. On the QM9 and QMugs benchmarks, surrogate functionals achieve density errors competitive with or improving upon the state of the art for fully supervised machine-learned OF-DFT, while eliminating the need for the $O(N^3)$ orthononormalization step required by prior work, yielding improved runtime scaling for larger systems.

---

### Not all ANIMALs are equal: metaphorical framing through source domains and semantic frames

Authors: Yulia Otmakhova, Matteo Guida, Lea Frermann
Published: 2026-04-22
Categories: cs.CL
arXiv: https://arxiv.org/abs/2604.20454v1

Metaphors are powerful framing devices, yet their source domains alone do not fully explain the specific associations they evoke. We argue that the interplay between source domains and semantic frames determines how metaphors shape understanding of complex issues, and present a computational framework that allows to derive salient discourse metaphors through their source domains and semantic frames. Applying this framework to climate change news, we uncover not only well-known source domains but also reveal nuanced frame-level associations that distinguish how the issue is portrayed. In analyzing immigration discourse across political ideologies, we demonstrate that liberals and conservatives systematically employ different semantic frames within the same source domains, with conservatives favoring frames emphasizing uncontrollability and liberals choosing neutral or more ``victimizing'' semantic frames. Our work bridges conceptual metaphor theory and linguistics, providing the first NLP approach for discovery of discourse metaphors and fine-grained analysis of differences in metaphorical framing. Code, data and statistical scripts are available at https://github.com/julia-nixie/ConceptFrameMet.

---

### HaS: Accelerating RAG through Homology-Aware Speculative Retrieval

Authors: Peng Peng, Weiwei Lin, Wentai Wu, Xinyang Wang, Yongheng Liu
Published: 2026-04-22
Categories: cs.IR, cs.CL
arXiv: https://arxiv.org/abs/2604.20452v1

Retrieval-Augmented Generation (RAG) expands the knowledge boundary of large language models (LLMs) at inference by retrieving external documents as context. However, retrieval becomes increasingly time-consuming as the knowledge databases grow in size. Existing acceleration strategies either compromise accuracy through approximate retrieval, or achieve marginal gains by reusing results of strictly identical queries. We propose HaS, a homology-aware speculative retrieval framework that performs low-latency speculative retrieval over restricted scopes to obtain candidate documents, followed by validating whether they contain the required knowledge. The validation, grounded in the homology relation between queries, is formulated as a homologous query re-identification task: once a previously observed query is identified as a homologous re-encounter of the incoming query, the draft is deemed acceptable, allowing the system to bypass slow full-database retrieval. Benefiting from the prevalence of homologous queries under real-world popularity patterns, HaS achieves substantial efficiency gains. Extensive experiments demonstrate that HaS reduces retrieval latency by 23.74% and 36.99% across datasets with only a 1-2% marginal accuracy drop. As a plug-and-play solution, HaS also significantly accelerates complex multi-hop queries in modern agentic RAG pipelines. Source code is available at: https://github.com/ErrEqualsNil/HaS.

---

### Decoding Text Spans for Efficient and Accurate Named-Entity Recognition

Authors: Andrea Maracani, Savas Ozkan, Junyi Zhu, Sinan Mutlu, Mete Ozay
Published: 2026-04-22
Categories: cs.CL
arXiv: https://arxiv.org/abs/2604.20447v1

Named Entity Recognition (NER) is a key component in industrial information extraction pipelines, where systems must satisfy strict latency and throughput constraints in addition to strong accuracy. State-of-the-art NER accuracy is often achieved by span-based frameworks, which construct span representations from token encodings and classify candidate spans. However, many span-based methods enumerate large numbers of candidates and process each candidate with marker-augmented inputs, substantially increasing inference cost and limiting scalability in large-scale deployments. In this work, we propose SpanDec, an efficient span-based NER framework that targets this bottleneck. Our main insight is that span representation interactions can be computed effectively at the final transformer stage, avoiding redundant computation in earlier layers via a lightweight decoder dedicated to span representations. We further introduce a span filtering mechanism during enumeration to prune unlikely candidates before expensive processing. Across multiple benchmarks, SpanDec matches competitive span-based baselines while improving throughput and reducing computational cost, yielding a better accuracy-efficiency trade-off suitable for high-volume serving and on-device applications.

---

### The Origin of Edge of Stability

Authors: Elon Litman
Published: 2026-04-22
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2604.20446v1

Full-batch gradient descent on neural networks drives the largest Hessian eigenvalue to the threshold $2/η$, where $η$ is the learning rate. This phenomenon, the Edge of Stability, has resisted a unified explanation: existing accounts establish self-regulation near the edge but do not explain why the trajectory is forced toward $2/η$ from arbitrary initialization. We introduce the edge coupling, a functional on consecutive iterate pairs whose coefficient is uniquely fixed by the gradient-descent update. Differencing its criticality condition yields a step recurrence with stability boundary $2/η$, and a second-order expansion yields a loss-change formula whose telescoping sum forces curvature toward $2/η$. The two formulas involve different Hessian averages, but the mean value theorem localizes each to the true Hessian at an interior point of the step segment, yielding exact forcing of the Hessian eigenvalue with no gap. Setting both gradients of the edge coupling to zero classifies fixed points and period-two orbits; near a fixed point, the problem reduces to a function of the half-amplitude alone, which determines which directions support period-two orbits and on which side of the critical learning rate they appear.

---

### VTouch++: A Multimodal Dataset with Vision-Based Tactile Enhancement for Bimanual Manipulation

Authors: Qianxi Hua, Xinyue Li, Zheng Yan, Yang Li, Chi Zhang, Yongyao Li, Yufei Liu
Published: 2026-04-22
Categories: cs.RO, cs.AI, cs.DB, cs.LG
arXiv: https://arxiv.org/abs/2604.20444v1

Embodied intelligence has advanced rapidly in recent years; however, bimanual manipulation-especially in contact-rich tasks remains challenging. This is largely due to the lack of datasets with rich physical interaction signals, systematic task organization, and sufficient scale. To address these limitations, we introduce the VTOUCH dataset. It leverages vision based tactile sensing to provide high-fidelity physical interaction signals, adopts a matrix-style task design to enable systematic learning, and employs automated data collection pipelines covering real-world, demand-driven scenarios to ensure scalability. To further validate the effectiveness of the dataset, we conduct extensive quantitative experiments on cross-modal retrieval as well as real-robot evaluation. Finally, we demonstrate real-world performance through generalizable inference across multiple robots, policies, and tasks.

---

### DialToM: A Theory of Mind Benchmark for Forecasting State-Driven Dialogue Trajectories

Authors: Neemesh Yadav, Palakorn Achananuparp, Jing Jiang, Ee-Peng Lim
Published: 2026-04-22
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2604.20443v3

We introduce DialToM, an annotated Theory of Mind (ToM) benchmark built from naturalistic human-human dialogues using a multiple-choice evaluation framework. Concurrent with recent work showing a gap between explicit mental-state inference and applied ToM in synthetic settings~\cite{gu2024simpletom}, we establish a stricter \emph{State-Driven Diagnostic Probe} in which models must forecast state-consistent dialogue trajectories solely from isolated mental-state profiles without dialogue context. Our evaluation reveals a systematic reasoning asymmetry -- LLMs excel at inferring mental states (Literal ToM) but struggle to leverage them for social forecasting (Functional ToM). Crucially, a domain expert achieves 100\% accuracy on this task, proving its validity and establishing a stark human-AI capability gap. Further, a teacher-student reasoning injection probe shows that Gemini 3 Pro -- which establishes the leading baseline -- possesses robust Functional ToM capabilities for context-free forecasting that are transferable to weaker models. DialToM, its evaluation code, and dataset are publicly available at https://github.com/Stealth-py/DialToM.

---

### DialToM: A Theory of Mind Benchmark for Forecasting State-Driven Dialogue Trajectories

Authors: Neemesh Yadav, Palakorn Achananuparp, Jing Jiang, Ee-Peng Lim
Published: 2026-04-22
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2604.20443v2

We introduce DialToM, an annotated Theory of Mind (ToM) benchmark built from naturalistic human-human dialogues using a multiple-choice evaluation framework. Concurrent with recent work showing a gap between explicit mental-state inference and applied ToM in synthetic settings~\cite{gu2024simpletom}, we establish a stricter \emph{State-Driven Diagnostic Probe} in which models must forecast state-consistent dialogue trajectories solely from isolated mental-state profiles without dialogue context. Our evaluation reveals a systematic reasoning asymmetry -- LLMs excel at inferring mental states (Literal ToM) but struggle to leverage them for social forecasting (Functional ToM). Crucially, a domain expert achieves 100\% accuracy on this task, proving its validity and establishing a stark human-AI capability gap. Further, a teacher-student reasoning injection probe shows that Gemini 3 Pro -- which establishes the leading baseline -- possesses robust Functional ToM capabilities for context-free forecasting that are transferable to weaker models. DialToM, its evaluation code, and dataset are publicly available at https://github.com/Stealth-py/DialToM.

---

### MedSkillAudit: A Domain-Specific Audit Framework for Medical Research Agent Skills

Authors: Yingyong Hou, Xinyuan Lao, Huimei Wang, Qianyu Yao, Wei Chen, Bocheng Huang, Fei Sun, Yuxian Lv, Weiqi Lei, Xueqian Wen, Pengfei Xia, Zhujun Tan et al.
Published: 2026-04-22
Categories: cs.AI
arXiv: https://arxiv.org/abs/2604.20441v1

Background: Agent skills are increasingly deployed as modular, reusable capability units in AI agent systems. Medical research agent skills require safeguards beyond general-purpose evaluation, including scientific integrity, methodological validity, reproducibility, and boundary safety. This study developed and preliminarily evaluated a domain-specific audit framework for medical research agent skills, with a focus on reliability against expert review. Methods: We developed MedSkillAudit (skill-auditor@1.0), a layered framework assessing skill release readiness before deployment. We evaluated 75 skills across five medical research categories (15 per category). Two experts independently assigned a quality score (0-100), an ordinal release disposition (Production Ready / Limited Release / Beta Only / Reject), and a high-risk failure flag. System-expert agreement was quantified using ICC(2,1) and linearly weighted Cohen's kappa, benchmarked against the human inter-rater baseline. Results: The mean consensus quality score was 72.4 (SD = 13.0); 57.3% of skills fell below the Limited Release threshold. MedSkillAudit achieved ICC(2,1) = 0.449 (95% CI: 0.250-0.610), exceeding the human inter-rater ICC of 0.300. System-consensus score divergence (SD = 9.5) was smaller than inter-expert divergence (SD = 12.4), with no directional bias (Wilcoxon p = 0.613). Protocol Design showed the strongest category-level agreement (ICC = 0.551); Academic Writing showed a negative ICC (-0.567), reflecting a structural rubric-expert mismatch. Conclusions: Domain-specific pre-deployment audit may provide a practical foundation for governing medical research agent skills, complementing general-purpose quality checks with structured audit workflows tailored to scientific use cases.

---

### Shift-Up: A Framework for Software Engineering Guardrails in AI-native Software Development -- Initial Findings

Authors: Petrus Lipsanen, Liisa Rannikko, François Christophe, Konsta Kalliokoski, Vlad Stirbu, Tommi Mikkonen
Published: 2026-04-22
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2604.20436v1

Generative AI (GenAI) is reshaping software engineering by shifting development from manual coding toward agent-driven implementation. While vibe coding promises rapid prototyping, it often suffers from architectural drift, limited traceability, and reduced maintainability. Applying the design science research (DSR) methodology, this paper proposes Shift-Up, a framework that reinterprets established software engineering practices, like executable requirements (BDD), architectural modeling (C4), and architecture decision records (ADRs), as structural guardrails for GenAI-native development. Preliminary findings from our exploratory evaluation compare unstructured vibe coding, structured prompt engineering, and the Shift-Up approach in the development of a web application. These findings indicate that embedding machine-readable requirements and architectural artifacts stabilizes agent behavior, reduces implementation drift, and shifts human effort toward higher-level design and validation activities. The results suggest that traditional software engineering artifacts can serve as effective control mechanisms in AI-assisted development.

---

### Fast-then-Fine: A Two-Stage Framework with Multi-Granular Representation for Cross-Modal Retrieval in Remote Sensing

Authors: Xi Chen, Xu Chen, Xiangyang Jia, Xu Zhang, Shuquan Wei, Wei Wang
Published: 2026-04-22
Categories: cs.CV
arXiv: https://arxiv.org/abs/2604.20429v1

Remote sensing (RS) image-text retrieval plays a critical role in understanding massive RS imagery. However, the dense multi-object distribution and complex backgrounds in RS imagery make it difficult to simultaneously achieve fine-grained cross-modal alignment and efficient retrieval. Existing methods either rely on complex cross-modal interactions that lead to low retrieval efficiency, or depend on large-scale vision-language model pre-training, which requires massive data and computational resources. To address these issues, we propose a fast-then-fine (FTF) two-stage retrieval framework that decomposes retrieval into a text-agnostic recall stage for efficient candidate selection and a text-guided rerank stage for fine-grained alignment. Specifically, in the recall stage, text-agnostic coarse-grained representations are employed for efficient candidate selection; in the rerank stage, a parameter-free balanced text-guided interaction block enhances fine-grained alignment without introducing additional learnable parameters. Furthermore, an inter- and intra-modal loss is designed to jointly optimize cross-modal alignment across multi-granular representations. Extensive experiments on public benchmarks demonstrate that the FTF achieves competitive retrieval accuracy while significantly improving retrieval efficiency compared with existing methods.

---

### Unlocking the Forecasting Economy: A Suite of Datasets for the Full Lifecycle of Prediction Market: (Experiments \& Analysis)

Authors: Huaiyu Jia, Luofeng Zhou, Wentao Zhang, Lin William Cong, Siguang Li, Shuo Sun
Published: 2026-04-22
Categories: cs.LG
arXiv: https://arxiv.org/abs/2604.20421v2

Prediction markets are markets for trading claims on universal future events (e.g., presidential elections). Fueled by a meteoric surge with over \$50 billion trading volume, they have emerged as a promising forecasting mechanism, where their prices provide continuously updated signals of collective beliefs. In decentralized platforms (e.g., Polymarket), the prediction market lifecycle include six stages: market creation, token registration, trading, oracle interaction, dispute, and final settlement. However, comprehensively tracking this complete pipeline remains a major challenge, as the underlying data are severely fragmented across heterogeneous on-chain smart contracts and off-chain sources. To fill this critical gap, we present the first continuously synchronized dataset suite for the full-lifecycle of decentralized prediction markets. To achieve large-scale cross-source integration, incomplete linkage, and continuous synchronization, we build a unified relational data system that integrates three canonical layers: i) market metadata, ii) fill-level trading records, iii) oracle-resolution events, through identifier resolution, on-chain recovery, and incremental updates. The resulting dataset spans from October 2020 to update-to-date and comprise more than 3.29 million market records, over 1.90 billion order execution records, and nearly 21 million oracle events. We describe the data model, collection pipeline, and consistency mechanisms that make the datasets reproducible and extensible. We further demonstrate its utility for multiple communities through NBA outcome calibration for sport traders, CPI expectation reconstruction for economists, and oracle-risk analysis for blockchain researchers. A public website with dataset access, interactive visualizations, and lightweight LLM-assisted exploration tools are publicly available at https://www.polymonitor.club.

---

### Unlocking the Forecasting Economy: A Suite of Datasets for the Full Lifecycle of Prediction Market: (Experiments \& Analysis)

Authors: Huaiyu Jia, Luofeng Zhou, Wentao Zhang, Lin William Cong, Siguang Li, Shuo Sun
Published: 2026-04-22
Categories: cs.LG
arXiv: https://arxiv.org/abs/2604.20421v1

Prediction markets are markets for trading claims on future events, such as presidential elections, and their prices provide continuously updated signals of collective beliefs. In decentralized platforms such as Polymarket, the market lifecycle spans market creation, token registration, trading, oracle interaction, dispute, and final settlement, yet the corresponding data are fragmented across heterogeneous off-chain and on-chain sources. We present the first continuously maintained dataset suite for the full lifecycle of decentralized prediction markets, built on Polymarket. To address the challenges of large-scale cross-source integration, incomplete linkage, and continuous synchronization, we build a unified relational data system that integrates three canonical layers: market metadata, fill-level trading records, and oracle-resolution events, through identifier resolution, on-chain recovery, and incremental updates. The resulting dataset spans October 2020 to March 2026 and comprises more than 770 thousand market records, over 943 million fill records, and nearly 2 million oracle events. We describe the data model, collection pipeline, and consistency mechanisms that make the dataset reproducible and extensible, and we demonstrate its utility through descriptive analyses of market activity and two downstream case studies: NBA outcome calibration and CPI expectation reconstruction.

---

### Scalable AI Inference: Performance Analysis and Optimization of AI Model Serving

Authors: Hung Cuong Pham, Fatih Gedikli
Published: 2026-04-22
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2604.20420v1

AI research often emphasizes model design and algorithmic performance, while deployment and inference remain comparatively underexplored despite being critical for real-world use. This study addresses that gap by investigating the performance and optimization of a BentoML-based AI inference system for scalable model serving developed in collaboration with graphworks.ai. The evaluation first establishes baseline performance under three realistic workload scenarios. To ensure a fair and reproducible assessment, a pre-trained RoBERTa sentiment analysis model is used throughout the experiments. The system is subjected to traffic patterns following gamma and exponential distributions in order to emulate real-world usage conditions, including steady, bursty, and high-intensity workloads. Key performance metrics, such as latency percentiles and throughput, are collected and analyzed to identify bottlenecks in the inference pipeline. Based on the baseline results, optimization strategies are introduced at multiple levels of the serving stack to improve efficiency and scalability. The optimized system is then reevaluated under the same workload conditions, and the results are compared with the baseline using statistical analysis to quantify the impact of the applied improvements. The findings demonstrate practical strategies for achieving efficient and scalable AI inference with BentoML. The study examines how latency and throughput scale under varying workloads, how optimizations at the runtime, service, and deployment levels affect response time, and how deployment in a single-node K3s cluster influences resilience during disruptions.

---

### Semantic Recall for Vector Search

Authors: Leonardo Kuffo, Ioanna Tsakalidou, Roberta De Viti, Albert Angel, Jiří Iša, Rastislav Lenhardt
Published: 2026-04-22
Categories: cs.IR, cs.AI
arXiv: https://arxiv.org/abs/2604.20417v1

We introduce Semantic Recall, a novel metric to assess the quality of approximate nearest neighbor search algorithms by considering only semantically relevant objects that are theoretically retrievable via exact nearest neighbor search. Unlike traditional recall, semantic recall does not penalize algorithms for failing to retrieve objects that are semantically irrelevant to the query, even if those objects are among their nearest neighbors. We demonstrate that semantic recall is particularly useful for assessing retrieval quality on queries that have few relevant results among their nearest neighbors-a scenario we uncover to be common within embedding datasets. Additionally, we introduce Tolerant Recall, a proxy metric that approximates semantic recall when semantically relevant objects cannot be identified. We empirically show that our metrics are more effective indicators of retrieval quality, and that optimizing search algorithms for these metrics can lead to improved cost-quality tradeoffs.

---

### Fast and Provably Accurate Sequential Designs using Hilbert Space Gaussian Processes

Authors: Huanyan Zhu, Cheng Li
Published: 2026-04-22
Categories: math.ST, stat.ME, stat.ML
arXiv: https://arxiv.org/abs/2604.20414v1

Gaussian processes are widely used for accurate emulation of unknown surfaces in sequential design of expensive simulation experiments. Integrated mean squared error (IMSE) is an effective acquisition function for sequential designs based on Gaussian processes. However, existing approaches struggle with its implementation because the required integrals often lack closed-form expressions for most kernel functions. We propose a novel and computationally efficient Hilbert space Gaussian process approximation for the IMSE acquisition function, where a truncated eigenbasis representation of the integral enables closed-form evaluation. We establish sharp global non-asymptotic bounds for both the approximation error of isotropic kernels and the resulting error in the acquisition function. In a series of numerical experiments with $γ$-stabilizing, the proposed method achieves substantially lower prediction error and reduced computation time compared to existing benchmarks. These results demonstrate that the proposed Hilbert space Gaussian process framework provides an accurate and computationally efficient approach for Gaussian process based sequential design.

---

### Self-Awareness before Action: Mitigating Logical Inertia via Proactive Cognitive Awareness

Authors: Fulong Fan, Peilin Liu, Fengzhe Liu, Shuyan Yang, Gang Yan
Published: 2026-04-22
Categories: cs.AI
arXiv: https://arxiv.org/abs/2604.20413v1

Large language models perform well on many reasoning tasks, yet they often lack awareness of whether their current knowledge or reasoning state is complete. In non-interactive puzzle settings, the narrative is fixed and the underlying structure is hidden; once a model forms an early hypothesis under incomplete premises, it can propagate that error throughout the reasoning process, leading to unstable conclusions. To address this issue, we propose SABA, a reasoning framework that explicitly introduces self-awareness of missing premises before making the final decision. SABA formulates reasoning as a recursive process that alternates between structured state construction and obstacle resolution: it first applies Information Fusion to consolidate the narrative into a verifiable base state, and then uses Query-driven Structured Reasoning to identify and resolve missing or underspecified premises by turning them into queries and progressively completing the reasoning state through hypothesis construction and state refinement. Across multiple evaluation metrics, SABA achieves the best performance on all three difficulty splits of the non-interactive Detective Puzzle benchmark, and it also maintains leading results on multiple public benchmarks.

---