# Research Papers — 2026-04 · bundle page 56 of 233

> Full-text markdown of papers #2751–2800 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/56
[← Previous bundle](https://aipod.dev/papers/archive/2026-04/page/55.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-04/page/57.md)

### Graph Neural Network-Informed Predictive Flows for Faster Ford-Fulkerson and PAC-Learnability

Authors: Eleanor Wiesler, Trace Baxley
Published: 2026-04-23
Categories: cs.LG, cs.DS
arXiv: https://arxiv.org/abs/2604.21175v1

We propose a learning-augmented framework for accelerating max-flow computation and image segmentation by integrating Graph Neural Networks (GNNs) with the Ford-Fulkerson algorithm. Rather than predicting initial flows, our method learns edge importance probabilities to guide augmenting path selection. We introduce a Message Passing GNN (MPGNN) that jointly learns node and edge embeddings through coupled updates, capturing both global structure and local flow dynamics such as residual capacity and bottlenecks. Given an input image, we propose a method to construct a grid-based flow network with source and sink nodes, extract features, and perform a single GNN inference to assign edge probabilities reflecting their likelihood of belonging to high-capacity cuts. These probabilities are stored in a priority queue and used to guide a modified Ford-Fulkerson procedure, prioritizing augmenting paths via an Edmonds-Karp-style search with bottleneck-aware tie-breaking. This avoids repeated inference over residual graphs while leveraging learned structure throughout optimization. We further introduce a bidirectional path construction strategy centered on high-probability edges and provide a theoretical framework relating prediction quality to efficiency via a weighted permutation distance metric. Our method preserves max-flow/min-cut optimality while reducing the number of augmentations in practice. We also outline a hybrid extension combining flow warm-starting with edge-priority prediction, establishing a foundation for learning-guided combinatorial optimization in image segmentation.

---

### Making Gaussian Kolmogorov-Arnold Networks Reliable and Accurate

Authors: Amir Noorizadegan, Sifan Wang, Leevan Ling
Published: 2026-04-23
Categories: cs.CE, cs.AI, math.AP
arXiv: https://arxiv.org/abs/2604.21174v3

Kolmogorov-Arnold Networks (KANs) replace fixed activations with learnable univariate edge functions whose behavior depends strongly on the chosen basis. Gaussian radial basis functions provide a simple and efficient alternative to splines, but their accuracy and stability are highly sensitive to the scale parameter \(ε\), which has not been studied systematically. We analyze this dependence through the geometry and conditioning of the first-layer feature matrix. Because the first layer is defined directly on the input domain, any loss of feature distinguishability introduced there propagates through the entire network. Based on this analysis, we identify the practical operating interval \( ε\in \left(\frac{1}{G-1},\frac{2}{G-1}\right), \) where \(G\) is the number of Gaussian centers. This interval is proposed as a stable design rule rather than a universal optimum. Extensive experiments on function approximation and physics-informed problems confirm its reliability across different collocation densities, grid resolutions, architectures, and input dimensions. We also show how the same principle supports fixed-scale selection, variable-scale models, constrained optimization of \(ε\), and efficient scale search using early-stage training error. These results establish scale selection as a central design principle for reliable and accurate Gaussian KANs.

---

### Scale-Parameter Selection in Gaussian Kolmogorov-Arnold Networks

Authors: Amir Noorizadegan, Sifan Wang
Published: 2026-04-23
Categories: cs.CE, cs.AI, math.AP
arXiv: https://arxiv.org/abs/2604.21174v2

Kolmogorov--Arnold Networks (KANs) have recently attracted attention as edge-based neural architectures in which learnable univariate functions replace conventional fixed activation functions. A key source of flexibility in KANs is the choice of basis functions used to parameterize the learnable edge functions. In this context, Gaussian basis functions provide a simple and efficient alternative to splines. However, their performance depends strongly on the scale (shape) parameter \(ε\), whose role has not been studied systematically. In this paper, we investigate how \(ε\) affects Gaussian KANs through first-layer feature geometry, conditioning, and approximation behavior. Our central observation is that scale selection is governed primarily by the first layer, since it is the only layer constructed directly on the input domain and any loss of distinguishability introduced there cannot be recovered by later layers. From this viewpoint, we analyze the first-layer feature matrix and identify a practical operating interval, \( ε\in \left(\frac{1}{G-1},\frac{2}{G-1}\right), \) where \(G\) denotes the number of Gaussian centers. We interpret this interval not as a universal optimality result, but as a stable and effective design rule, and validate it through brute-force sweeps over \(ε\) across function-approximation problems with different collocation densities, grid resolutions, network architectures, and input dimensions, as well as physics-informed problems. We further show that this range is useful for fixed-scale selection, variable-scale constructions, constrained training of \(ε\), and efficient scale search using early training MSE. In this way, the paper positions scale selection as a practical design principle for Gaussian KANs rather than as an ad hoc hyperparameter choice.

---

### TAPO-Description Logic for Information Behavior: Refined OBoxes, Inference, and Categorical Semantics

Authors: Takao Inoué
Published: 2026-04-23
Categories: cs.LO, cs.AI
arXiv: https://arxiv.org/abs/2604.21172v1

This paper develops a refined version of TAPO-description logic for the analysis of information behavior. The framework is treated not as a single homogeneous object logic, but as a layered formalism consisting of a static descriptive layer (TBox/ABox), a procedural layer (PBox), and an oracle-sensitive layer (OBox). To make this architecture mathematically explicit, we introduce a metalevel guard-judgment layer governing procedural branching and iteration. On this basis we formulate a core inference system for TAPO-description logic, covering static TBox/ABox reasoning, guarded procedural transition in the PBox, and validated external import in the OBox. We then give a categorical semantics for the resulting framework and indicate its sheaf-theoretic refinement. The theory is illustrated by examples of information-seeking behavior, including simple search behavior and review-sensitive ordering behavior in a curry restaurant. The aim is to treat not only static knowledge representation but also hesitation, external consultation, and action-guiding update within a unified logical setting.

---

### Reinforcing 3D Understanding in Point-VLMs via Geometric Reward Credit Assignment

Authors: Jingkun Chen, Ruoshi Xu, Mingqi Gao, Shengda Luo, Jungong Han
Published: 2026-04-23
Categories: cs.CV
arXiv: https://arxiv.org/abs/2604.21160v1

Point-Vision-Language Models promise to empower embodied agents with executable spatial reasoning, yet they frequently succumb to geometric hallucination where predicted 3D structures contradict the observed 2D reality. We identify a key cause of this failure not as a representation bottleneck but as a structural misalignment in reinforcement learning, where sparse geometric tokens are drowned out by noisy and broadcasted sequence-level rewards. To resolve this causal dilution, we propose Geometric Reward Credit Assignment, a framework that disentangles holistic supervision into field-specific signals and routes them exclusively to their responsible token spans. This mechanism transforms vague feedback into precise gradient updates and effectively turns generic policy optimization into targeted structural alignment. Furthermore, we internalize physical constraints via a Reprojection-Consistency term which serves as a cross-modal verifier to penalize physically impossible geometries. Validated on a calibrated benchmark derived from ShapeNetCore, our approach bridges the reliability gap by boosting 3D KPA from 0.64 to 0.93, increasing 3D bounding box intersection over union to 0.686, and raising reprojection consistency scores to 0.852. Crucially, these gains are achieved while maintaining robust 2D localization performance, marking a meaningful step from plausible textual outputs toward physically verifiable spatial predictions.

---

### C$^2$MOE: Consistency and Complementarity-guided Mixture of Experts for Incomplete Multimodal Emotion Learning

Authors: Yuntao Shou, Tao Meng, Wei Ai, Keqin Li
Published: 2026-04-22
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2608.04013v1

Recent advances in Multimodal Emotion Recognition in Conversations (MERC) highlight its reliance on complete multimodal inputs. However, real-world data often suffer from missing modalities due to transmission errors or user behavior, severely degrading model performance. Existing methods enhance robustness via cross-modal consistency learning but largely ignore modality complementarity, leading to biased reconstructions. To address this limitation, we propose C$2$MOE, a novel Consistency and Complementarity-guided Mixture of Experts framework for incomplete multimodal emotion learning. Our approach unifies representation learning and missing modality imputation within a principled information-theoretic framework. Specifically, multimodal knowledge is factorized into consistency and complementarity components via interaction-aware experts. Consistency is captured by maximizing cross-modal predictability, while complementarity is preserved by maximizing conditional entropy between modalities. Building upon this decomposition, C$2$MOE introduces a dual-branch prediction mechanism for robust imputation under missing modalities. The consistency branch aligns imputed features with the joint distribution by minimizing uncertainty, and the complementarity branch exploits modality-unique cues via entropy maximization. Finally, C$2$MOE employs a learnable reweighting module that dynamically assigns importance scores to each expert's output, yielding a robust and adaptive fusion for imputation. Extensive experiments on multiple MERC benchmarks demonstrate that C$2$MOE consistently surpasses state-of-the-art methods across various missing-modality settings, validating its robustness and generalization.

---

### A Long-Run Persistence Theory for AI Systems under the Redundancy-Adjusted Artificial Age Score (AAS)

Authors: Seyma Yaman Kayadibi
Published: 2026-04-22
Categories: cs.AI
arXiv: https://arxiv.org/abs/2608.04012v1

Artificial intelligence systems are increasingly expected to operate over repeated cycles of interaction, adaptation, and update rather than through isolated one-shot outputs. This raises a fundamental theoretical question: can an AI system persist indefinitely without incurring unbounded structural aging? This paper develops a long-run persistence framework for AI systems based on the redundancy-adjusted Artificial Age Score (AAS). The model extends AAS from a static evaluative measure into a cycle-level functional that generates an age sequence across repeated operation. At each cycle, structural age is defined through a weighted, redundancy-aware logarithmic penalty over component consistency levels. Within this framework, cycle-level age is shown to be well defined and uniformly bounded, thereby excluding explosive pointwise aging. On this basis, the paper defines a hierarchy of asymptotic regimes, including burdened persistence, zero-burden persistence, oscillatory persistence, and cumulative terminal burden. It also establishes comparative ordering, sensitivity bounds, convergence under componentwise stabilization, persistence under finite total variation, geometric stabilization under damped inter-cycle perturbations, and a zero-burden characterization under nondegenerate redundancy conditions. The main result is that indefinite cyclic continuation does not require unbounded structural aging: an AI system may pass through infinitely many cycles while its structural age remains bounded, while under stronger regularity conditions its marginal aging vanishes and, in the strongest regime, its cycle-level burden converges to zero. The framework thus provides a formal basis for analyzing long-run artificial persistence as a problem of bounded structural burden rather than inevitable cumulative deterioration.

---

### Causal-Audit: Explicit and Auditable Graph-based Reasoning via Target-Aware Causal Chain Construction

Authors: Su Lan, Xuefei Yin, Yanming Zhu, Alan Wee-Chung Liew
Published: 2026-04-22
Categories: cs.AI
arXiv: https://arxiv.org/abs/2607.15281v1

Causal and intervention-based question answering is fundamental to advancing large language models (LLMs) toward reasoning beyond surface-level correlations and understanding underlying causal mechanisms. However, existing LLM-based methods often rely on implicit language-level reasoning, resulting in opaque causal assumptions, unverifiable reasoning paths, and fragile predictions under complex interventions, particularly in context-free settings. In this paper, we propose an explicit and auditable causal reasoning framework for context-free intervention-based question answering. Our method formulates causal inference as structured reasoning over an explicit causal graph through four modular stages, rather than implicit end-to-end prediction. A key innovation is a target-aware causal graph construction strategy that treats the target variable as a core constraint during graph expansion, effectively suppressing irrelevant variables, spurious causal relations, and reasoning noise. We further introduce a path-level causal evidence aggregation mechanism that combines multiple causal paths while modeling both reinforcing and counteracting effects, enabling robust decision-making beyond single-chain reasoning. Extensive experiments on three benchmarks demonstrate that our framework consistently outperforms existing LLM-based methods while providing interpretable and auditable causal reasoning traces.

---

### Cross-Dataset Bloom Question Classification: Supervised Models and Prompted LLMs

Authors: Abdolali Faraji, Mohammadreza Molavi, Zohreh Rasoulkhani, Mohammadreza Tavakoli, Gábor Kismihók
Published: 2026-04-22
Categories: cs.CY, cs.AI, cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2606.13684v1

Automatic Bloom's taxonomy classification of assessment questions can substantially reduce instructor workload, but labeling is subjective and teacher-dependent. Prior machine learning (ML) and deep learning (DL) approaches reported strong within-dataset results, yet were rarely evaluated in cross-dataset settings, leaving real-world generalizability unclear; meanwhile, LLM effectiveness for Bloom question classification has not been systematically studied. We evaluated the cross-dataset generalization of existing ML/DL methods and assessed LLMs with multiple prompting strategies on five datasets; the best prompting strategy combined in-context examples with course-specific action verbs. Supervised ML/DL models degraded substantially on unseen datasets, whereas LLMs were more stable, suggesting a robust alternative across diverse educational contexts. Based on the best prompting strategy, we also presented a lightweight UI that supports instructors in automatically classifying large question banks; a usability study indicated low workload and high usability.

---

### Compatibility-Aware Dynamic Fine-Tuning for Large Language Models

Authors: Yucheng Zhou, Junwei Sheng, Qianning Wang, Jianbing Shen
Published: 2026-04-22
Categories: cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2606.11206v1

Supervised Fine-Tuning (SFT) is the predominant paradigm for aligning large language models (LLMs), yet it suffers from optimization instability and limited generalization. Recent work attributes this issue to pathological gradient scaling and proposes Dynamic Fine-Tuning (DFT) to correct it at the token level. However, DFT assumes all demonstrations are equally suitable learning targets, an assumption violated by the strong heterogeneity of large-scale instruction data, where demonstration-policy mismatch induces high-variance updates at the sample level. We introduce Compatibility-Aware Dynamic Fine-Tuning (CADFT), a principled extension of DFT that controls sample-level optimization variance. CADFT derives a dynamic, policy-dependent compatibility signal from model likelihoods to modulate supervised updates, suppressing high-variance gradients from incompatible demonstrations. We further propose a delayed, low-frequency compatibility-guided rewriting strategy to transform persistently incompatible demonstrations into learnable targets. We show that CADFT can be interpreted as a variance-controlled estimator that generalizes token-level stabilization in DFT to the sample level. Extensive experiments demonstrate improved stability, generalization, and cold-start reinforcement learning initialization, while remaining fully supervised and independent of explicit reward modeling.

---

### Dual-Stance Evaluation of Sycophancy: The Structure of Agreement and the Limits of Intervention

Authors: Matthew James Buchan
Published: 2026-04-22
Categories: cs.LG, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2606.11205v1

Activation steering can shift LLM behaviour, but standard evaluations do not typically test whether a sycophancy-reduction direction also suppresses agreement with factually correct statements. We introduce dual-stance evaluation, which tests both stances of each topic, and apply it to centroid-difference steering on Llama-3-8B-Instruct. We find a dissociation: the model represents sycophantic and factual agreement in geometrically distinct subspaces, yet the steering direction projects equally onto both and cannot differentially target either. The direction accordingly reduces agreement with factually correct statements (e.g. that the Earth is round) as well as sycophantic ones. All other static properties of the two activation groups are matched, suggesting the behavioural dissociation arises from generation dynamics or from finer-grained structure that residual-stream analysis cannot resolve. The pattern illustrates a general gap: representations that are readable from activations may not be writable through them.

---

### Benchmarking Large Language Models for Safety Data Extraction

Authors: Jonas Grill, Thomas Bayer, Sören Berlinger
Published: 2026-04-22
Categories: cs.CL, cs.IR
arXiv: https://arxiv.org/abs/2606.11204v1

Accurate extraction of structured information from Safety Data Sheets (SDS) remains challenging in industrial safety due to heterogeneous document formats and the limitations of traditional rule-based methods. This study benchmarks state-of-the-art Large Language Models (LLMs) for automated SDS data extraction, comparing text-based and multimodal processing pipelines. We systematically evaluate four models: Gemini 1.5 Pro, GPT-4o, Claude 3.7 Sonnet, and Llama 3.1-70B, across three prompting strategies: zero-shot, few-shot, and chain-of-thought. The evaluation framework assessed accuracy, latency, and cost across more than 50,000 extracted data fields. Results show that text-based extraction consistently outperforms multimodal processing across all metrics. Gemini 1.5 Pro combined with a Chain-of-Thought prompt achieved the highest accuracy (84%), outperforming GPT-4o (81%) and Claude 3.7 Sonnet (79%). However, no model surpassed the 90% accuracy threshold commonly required for reliable real-world deployment. These findings indicate that general-purpose LLMs are not yet robust enough for unsupervised industrial use, though performance suggests strong potential with task-specific fine-tuning. Future research should focus on domain-adapted training, model calibration, and the integration of Human-in-the-Loop verification to ensure safety-critical reliability.

---

### LatticeBridge: Rare-Event Sequential Inference for Faithful Structured Sequence Synthesis

Authors: Faruk Alpay, Bugra Kilictas
Published: 2026-04-22
Categories: cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2606.11203v1

Structured sequence generation often requires a model to satisfy several input-derived constraints in a single output. Standard decoding methods may assign high probability to fluent continuations while placing low mass on continuations that realize all required anchors jointly. We study this regime as a rare-event sequential inference problem. LatticeBridge combines a compact prefix language model, instance-compiled surface automata, and a twisted sequential Monte Carlo (SMC) decoder with resampling, multilevel splitting, and a source-support proposal term derived from instance-provided phrases. The constraint representation is compiled from each input instance and does not rely on manually curated lexical classes. On 2,610 attainable validation tasks spanning CommonGen, E2E NLG, and WikiBio, the particle decoder improves exact anchor satisfaction and mean anchor coverage over greedy, beam-filtered, and best-of-k ancestral baselines under a shared proposal model. Since exact anchor satisfaction alone does not rule out unsupported attribute substitutions, the evaluation reports required-anchor coverage, source coverage, source-intrusion diagnostics, overlap, runtime, and particle statistics jointly. The benchmark characterizes the faithfulness-overlap-latency frontier under a fixed proposal model.

---

### One Jailbreak, Many Tongues: Learning Language-Insensitive Intention Representations for Multilingual Jailbreak Detection

Authors: Shuyu Jiang, Kaiyu Xu, Xingshu Chen, Hao Ren, Rui Tang, Yi Zhang, Tianwei Zhang, Hongwei Li
Published: 2026-04-22
Categories: cs.CL
arXiv: https://arxiv.org/abs/2606.11202v1

Large language models (LLMs) are increasingly deployed in applications for global multilingual users, yet safety training remains concentrated in dominant languages and has not progressed in parallel with multilingual capability, creating exploitable gaps for jailbreak attacks. Current jailbreak defenses are largely developed and evaluated in dominant languages, and their effectiveness is limited by the scarcity of aligned multilingual supervision and representations dispersion caused by language variation. To address this issue, we propose MLJailDe, a multilingual jailbreak detection framework designed to improve both multilingual robustness and cross-lingual generalization. MLJailDe first introduces a multilingual back-translation data augmentation algorithm to construct a semantically consistent and functionally effective dataset spanning 11 languages, consisting of 2,232 benign and 1,239 jailbreak samples. On this basis, MLJailDe employs relative-distance constraints to reduce cross-lingual representation dispersion and encourage jailbreak prompts with similar intent to form consistent clusters across languages, while an imbalance-aware classification objective is further used to alleviate class imbalance and learn more reliable multilingual decision boundaries. Experimental results show that MLJailDe outperforms state-of-the-art baselines across multiple languages, achieving an F1 score of 98.5\%, and obtains an average F1 score of 97.1\% on unseen languages, demonstrating strong effectiveness and cross-lingual generalization.

---

### To Intervene or Not: Guiding Inference-time Alignment with Probabilistic Model Blending

Authors: Jin Gan, Xin Li, Jun Luo
Published: 2026-04-22
Categories: cs.LG, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2606.11201v1

The wide deployment of LLMs has made model alignment necessary to make newly trained models safely and effectively respond to user instructions. Among different methods, inference-time alignment is often cheaper as it intervenes (i.e., offers guidances) only during output generation. Existing proposals apply guidances extracted from certain aligned models without properly assessing their reliability. Nonetheless, our systematic evaluation reveals that guidance effectiveness varies drastically across models; since ineffective guidances lead to further confusion and thus further interventions, the resulting excessive interventions typically indicate poor performance. To make interventions more effective and thus more efficient, we introduce BlendIn, an inference-time alignment framework that shifts from binary decisions to creating hybrid distributions integrating both models' knowledge. BlendIn stabilizes inference-time alignment by performing quality-aware alignment and proportionally weighting each model's contribution based on reliability. Compared with existing works, it preserves beneficial guidance while downweighting unreliable suggestions. BlendIn provides both diagnostic signals and mitigation strategies for misaligned guidance, achieving consistent and up to 50% performance improvement on challenging model pairs. Our code is available at: https://github.com/DecayingSeart/BlendIn.

---

### IGADA-IoT: IoT Sensor Energy Optimization in Wireless Sensor Networks Driven by Automatic Data Augmentation

Authors: Mingchun Sun, Rongqiang Zhao, Muhammad Abdul Munnaf, Jie Liu
Published: 2026-04-22
Categories: cs.LG
arXiv: https://arxiv.org/abs/2605.27397v1

In wireless sensor networks (WSNs), data augmentation is a novel method to improve sampling-frequency decision performance, thereby enabling energy optimization for IoT (Internet of Things) sensors. However, existing methods rely on a single generator and empirically determined quantities, failing to establish a mapping between dynamic information gaps and multiple generators, and overlooking the heterogeneity of generated samples. Moreover, an evaluation and a closed-loop method that jointly considers the information gap and the model performance are lacking. To address these issues, we propose an information gap-guided IoT sensor automatic data augmentation framework (IGADA-IoT) with hierarchical multi-generator collaboration and scheduling over multiple rounds. Capabilities of different generators are jointly utilized to reduce the information gaps. In the IGADA-IoT, a hierarchical multi-generator collaboration and scheduling strategy (HMGCS) is proposed to enhance the targetedness and rationality of generated sample allocation. An information gap-model performance joint evaluation and closed-loop method (IGMP-EC) is proposed to enhance the accuracy of augmentation decisions, and to mitigate the risks of under-augmentation and over-augmentation. Experimental results show that the IGADA-IoT improves the average accuracy of multiple downstream models by 7.27%. Compared with advanced data augmentation methods, the average accuracy is improved by 8.67%. Compared with the individual generators, the average accuracy is improved by 7.24%. Furthermore, public IoT sensor datasets from the UCR Archive and real-world deployments demonstrate the accuracy and generalizability of the proposed method.

---

### BODHI: Precise OS Kernel Specification Inference

Authors: Zhiming Chang, Ziyang Li
Published: 2026-04-22
Categories: cs.AI, cs.PL, cs.SE
arXiv: https://arxiv.org/abs/2605.23931v1

The formal verification of operating system kernels requires precise specifications that capture the intended behavior of system calls. Writing these specifications manually demands deep domain expertise, motivating the use of large language models (LLMs) to automate the process. However, in OSV-Bench, a benchmark of 245 specification generation tasks derived from the Hyperkernel OS kernel, the best reported Pass@1 is 55.10%. We propose a domain knowledge prompting method (BODHI), which augments the standard few-shot prompt with a structured C-to-Python translation guide covering 15 categories of domain-specific translation patterns. Inspired by Structured Chain-of-Thought (SCoT) prompting, the guide organizes translation by separation of concerns, addressing pre-condition extraction and post-condition generation as distinct categories. Evaluated on nine models from six providers (Anthropic, Mistral, Amazon, DeepSeek, Meta, Alibaba), covering dense, mixture-of-experts and reasoning architectures, BODHI improves every model tested, with gains ranging from +11% to +32%. The best configuration (Claude Opus 4.6 + BODHI) reaches 96.73% Pass@1. BODHI reduces both syntax and semantic errors, with the strongest effect on models that have sufficient instruction-following capability to utilize structured reference material. These results demonstrate that domain knowledge injection is a model-agnostic technique that substantially bridges the gap between general-purpose code generation and formal specification synthesis.

---

### Quantum Frog: Emergent Cooperation and Difficulty Scaling in a Quantized-Time Cooperative Game

Authors: Saad Mankarious
Published: 2026-04-22
Categories: cs.AI, cs.LG, cs.MA
arXiv: https://arxiv.org/abs/2605.23930v1

We introduce \emph{Quantum Frog}, a two-player cooperative game built on a novel \emph{quantized-time} mechanic in which the environment advances only when a player acts. Inspired by the classic arcade game Frogger, Quantum Frog requires two frogs to cross an 8$\times$8 grid of traffic and reach the far side together. We use reinforcement learning (RL) as an analytical lens to answer four design questions: (1) how does game difficulty scale with traffic density, (2) what is the optimal single-agent policy and why, (3) how large is the cooperation gap between independent and cooperative two-agent play, and (4) what joint strategy emerges when agents are incentivised to cooperate? We train agents through five escalating stages, Tabular Q-Learning, Deep Q-Network (\DQN), Independent \DQN~(\IDQN), and Multi-Agent Proximal Policy Optimisation (\MAPPO\ with a centralised critic), evaluating each against traffic densities of one to six cars. Our key findings are: (i) the quantized-time mechanic makes a \emph{rush strategy} (moving directly upward at every step) universally optimal, as time exposure to traffic is minimised; (ii) adding an uncoordinated second player is harder than sextupling the traffic for a single expert player; (iii) cooperative training recovers +32--34 percentage points of joint success rate relative to independent agents and reduces episode length from $\sim$90 to $\sim$6 steps; and (iv) the emergent cooperative strategy is synchronised rushing, not complex positional coordination, illustrating that shared incentives alone suffice to align agents in time-critical cooperative tasks. These findings provide concrete, empirically grounded guidance for the commercial design of Quantum Frog and offer broader insights into the role of environment mechanics in shaping multi-agent learning dynamics.

---

### Seed3D 2.0: Advancing High-Fidelity Simulation-Ready 3D Content Generation

Authors: Diandian Gu, Jing Lin, Gaohong Liu, Jiahang Liu, Su Ma, Guang Shi, Jun Wang, Qinlong Wang, Qianyi Wu, Zhongcong Xu, Xuanyu Yi, Zihao Yu et al.
Published: 2026-04-22
Categories: cs.GR, cs.CV, eess.IV
arXiv: https://arxiv.org/abs/2605.13862v1

We present Seed3D 2.0, an advanced 3D content generation system built on Seed3D 1.0, with substantial improvements across generation fidelity, simulation-ready capabilities, and application coverage. For geometry, a coarse-to-fine two-stage pipeline decouples global structure learning from high-frequency detail recovery, while a locality-aware VAE achieves higher spatial compression and more efficient decoding. For texture and material generation, we replace the cascaded pipeline of Seed3D 1.0 with a unified PBR model that directly generates multi-view albedo and metallic-roughness maps, enhanced by Mixture-of-Experts scaling and VLM-based semantic conditioning for improved material precision and visual fidelity. Beyond single-object generation, Seed3D 2.0 introduces a simulation-ready model suite comprising scene layout planning, part-aware decomposition, and training-free articulation generation, enabling coherent scene construction and part-level physical interaction across physics and graphics engines. A large-scale human preference study against five recent commercial models shows that Seed3D 2.0 achieves consistent win rates of 69.0% to 89.9% in textured 3D asset generation. Seed3D 2.0 is available on https://exp.volcengine.com/ark/vision?_vtm_=0.0.c70961.d701978.0&mode=vision&modelId=doubao-seed3d-2-0-260328&tab=Gen3D

---

### A Hierarchical Ensemble Pipeline for Anomaly Detection in ESA Satellite Telemetry

Authors: Lorenzo Riccardo Allegrini, Geremia Pompei
Published: 2026-04-22
Categories: cs.LG, cs.CV
arXiv: https://arxiv.org/abs/2605.06681v1

A hierarchical ensemble pipeline is introduced to address anomaly detection in multivariate telemetry data provided by European Space Agency (ESA). The method integrates shapelet-based and statistical feature extraction, per-channel modeling, intra-channel stacking, and a final cross-channel aggregation. The pipeline is trained and validated using time-series cross-validation and two-level masking strategies to prevent information leakage. Results on the European Space Agency Anomaly Detection Benchmark (ESA-ADB) challenge demonstrate strong generalization, highlighting the effectiveness of hierarchical modeling in detecting subtle anomalies in realistic satellite telemetry.

---

### On the Role of Strain and Vorticity in Numerical Integration Error for Flow Matching

Authors: Chenxi Tao, Seung-Kyum Choi
Published: 2026-04-22
Categories: cs.LG, cs.CV, physics.flu-dyn
arXiv: https://arxiv.org/abs/2605.06680v1

Flow matching generates data by integrating a learned velocity field, where the number of integration steps (NFE) directly determines inference cost. We analyze which properties of the velocity field govern integration error by decomposing the velocity Jacobian into its symmetric part S (strain rate) and antisymmetric part Omega (vorticity). We prove that strain and vorticity play different roles: strain controls exponential error amplification through the logarithmic norm, while vorticity contributes only linearly to the local truncation error. We further show that the optimal transport velocity field is irrotational and has zero material derivative, implying second-order Euler accuracy; for exact displacement interpolation, the associated Lagrangian particle dynamics are integrated exactly by Euler. Motivated by this analysis, we study weighted Jacobian regularization with strain weight alpha and vorticity weight beta. Experiments on 2D synthetic data confirm the main theoretical predictions, showing up to 2.7x lower integration error at NFE=5. Preliminary CIFAR-10 experiments show consistent trends, with a lightweight fine-tuning procedure improving FID by 14 percent at NFE=10 while preserving high-NFE quality.

---

### Breaking the Illusion: When Positive Meets Negative in Multimodal Decoding

Authors: Yubo Jiang, Yitong An, Xin Yang, Abudukelimu Wuerkaixi, Xuxin Cheng, Fengying Xie, Zhiguo Jiang, Cao Liu, Ke Zeng, Haopeng Zhang
Published: 2026-04-22
Categories: cs.LG
arXiv: https://arxiv.org/abs/2605.06679v1

Vision-Language Models (VLMs) are frequently undermined by object hallucination, generating content that contradicts visual reality, due to an over-reliance on linguistic priors. We introduce Positive-and-Negative Decoding (PND), a training-free inference framework that intervenes directly in the decoding process to enforce visual fidelity. PND is motivated by our finding of an attention imbalance in VLMs, where visual features are under-weighted. Our framework introduces a dual-path contrast: a positive path that amplifies visual evidence and a negative path that constructs counterfactuals to penalize prior-dominant generation. By contrasting outputs from both paths during decoding, PND steers generation toward visually grounded results. Experiments on POPE, MME, and CHAIR demonstrate state-of-the-art performance without retraining.

---

### A Wasserstein GAN-based climate scenario generator for risk management and insurance: the case of soil subsidence

Authors: Antoine Heranval, Olivier Lopez, Didier Ngatcha, Daniel Nkameni
Published: 2026-04-22
Categories: cs.LG, q-fin.RM, stat.AP
arXiv: https://arxiv.org/abs/2605.06678v1

According to the United Nations Office for Disaster Risk Reduction (2025), the average annual cost of natural catastrophes increased from 70--80 billion USD between 1970 and 2000 to 180--200 billion USD between 2001 and 2020. Reports from organizations such as the IFOA and the WWF highlight the need for the insurance sector to adapt to this rapidly evolving context by developing medium- to long-term strategies that go beyond the one-year horizon of prudential regulations such as Solvency II. This paper introduces an artificial intelligence framework based on Conditional Generative Adversarial Networks (Conditional GANs) to generate future spatio-temporal trajectories of climatic indices. The approach focuses on the Soil Wetness Index (SWI), a key indicator used in France to assess drought severity. Drought accounts for approximately 30% of the indemnities paid under the French natural catastrophe insurance scheme. The proposed model, SwiGAN, simulates plausible drought propagation patterns up to 2050 for a region of France particularly exposed to this hazard. By generating realistic sequences of SWI maps, SwiGAN provides insights into drought dynamics under climate change scenarios and supports the design of adaptive risk management and insurance strategies. The methodology is also generalizable to other climate-related perils and actuarial applications such as economic scenario generation.

---

### LKV: End-to-End Learning of Head-wise Budgets and Token Selection for LLM KV Cache Eviction

Authors: Enshuai Zhou, Yifan Hao, Chao Wang, Rui Zhang, Di Huang, Jiaming Guo, Xing Hu, Zidong Du, Qi Guo, Yunji Chen
Published: 2026-04-22
Categories: cs.LG, cs.CL
arXiv: https://arxiv.org/abs/2605.06676v1

Long-context inference in Large Language Models (LLMs) is bottlenecked by the linear growth of Key-Value (KV) cache memory. Existing KV cache compression paradigms are fundamentally limited by heuristics: heuristic budgeting relies on statistical priors rather than task objectives, causing resource misallocation, while heuristic selection relies on coupled query-key interactions or static inductive biases (e.g., attention sinks). To address this limitation, we introduce LKV (Learned KV Eviction), which formulates KV compression as an end-to-end differentiable optimization problem. LKV integrates LKV-H to learn task-optimized global budgets, and LKV-T to derive intrinsic KV importance without materializing attention matrices. This design bypasses heuristic proxies, strictly aligning compression with task objectives. Extensive evaluations demonstrate that LKV achieves state-of-the-art performance on both LongBench and RULER benchmarks at high compression rates. In particular, on LongBench, LKV achieves near-lossless performance with only 15\% KV cache retention. Crucially, our analysis identifies learned budgeting as the dominant driver of fidelity, demonstrating that data-driven allocation is essential to overcome the limitations of hand-crafted heuristics.

---

### RateQuant: Optimal Mixed-Precision KV Cache Quantization via Rate-Distortion Theory

Authors: Fei Zuo, Zikang Zhou, Hao Cong, Xiaoyan Xi, Ho Fai Leung
Published: 2026-04-22
Categories: cs.LG, cs.CL, cs.IT
arXiv: https://arxiv.org/abs/2605.06675v2

Large language models cache all previously computed key-value (KV) pairs during generation, and this KV cache grows linearly with sequence length, making it a primary memory bottleneck for serving. Quantizing the KV cache to fewer bits reduces this cost, yet all current quantizers assign the same bit-width to every attention head, ignoring the large variation in head importance. A natural idea is to allocate more bits to important heads and fewer to the rest. We show, however, that such mixed-precision allocation has a hidden pitfall: each quantizer follows a different distortion curve D(b)=alpha*beta^{-b}, and the decay rate beta varies from 3.6 to 5.3 across quantizer designs. Applying one quantizer's distortion model to another inverts the allocation order and makes performance worse than uniform quantization. We call this failure mode distortion model mismatch and propose RateQuant to resolve it. RateQuant fits a per-quantizer distortion model from a small calibration set, then solves the resulting bit-allocation problem in closed form via reverse waterfilling from rate-distortion theory. On Qwen3-8B at 2.5 average bits, calibrated RateQuant reduces KIVI's perplexity from 49.3 to 14.9 (70% reduction) and improves QuaRot by 6.6 PPL. The entire calibration takes 1.6 s on a single GPU and adds zero overhead at inference time.

---

### FASQ: Flexible Accelerated Subspace Quantization for Calibration-Free LLM Compression

Authors: Ye Qiao, Yian Wang, Zhiheng Chen, Hyoukjun Kwon, Sitao Huang
Published: 2026-04-22
Categories: cs.LG, cs.AI, cs.AR
arXiv: https://arxiv.org/abs/2605.04084v1

Compressing large language models (LLMs) for deployment on commodity GPUs remains challenging: conventional scalar quantization is limited to fixed bit-widths (e.g., 8/4/3-bit), offers only a few discrete compression points, and typically requires calibration data. We present FASQ (Flexible Accelerated Subspace Quantization), a calibration-free framework that applies product quantization to LLM weight matrices. By tuning two parameters, sub-vector size and codebook cardinality, FASQ exposes a continuous design space spanning 27-49% of the original FP16 model size, filling compression gaps that fixed-bit schemes cannot reach. On Meta-Llama-3-8B, FASQ surpasses 4-bit GPTQ and AWQ in accuracy (67.1-67.7 avg.) at 37-42% model size, with consistent results on Qwen3-8B and Qwen3.5-9B-Base. To make product quantization practical at inference time, we design custom CUDA kernels: a LUT-free direct-compute GEMV for decode and an output-stationary double-buffered LUT GEMM for prefill, both with split-K parallelism. On an RTX~3090, FASQ achieves 45.2 tok/s decode at effective 4-bit (2.56x memory reduction) and 51.8 tok/s at effective 3-bit (2.80x), both surpassing FP16 tensor-core performance (43.9 tok/s) and delivering 1.6 to 1.8x the throughput of AWQ, 2.5 to 2.5x of GPTQ, and 4.3 to 5x of RTN. FASQ is the only compressed method that accelerates decode beyond FP16, offering calibration-free compression, continuous size-quality trade-offs, and real-time inference on a single consumer GPU.

---

### EvoJail: Evolutionary Diverse Jailbreak Prompt Generation for Large Language Models

Authors: Rui Tang, Kaiyu Xu, Pengsen Cheng, Hao Ren, Haizhou Wang, Shuyu Jiang
Published: 2026-04-22
Categories: cs.NE, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2605.02921v1

As LLMs continue to shape real-world applications, automated jailbreak generation becomes essential to reveal safety weaknesses and guide model improvement. Existing automatic jailbreak generation methods have not yet fully considered two important aspects: adaptability to evolving safety-finetuned models, which affects their effectiveness on newer model versions, and diversity in generated prompts, which can cause narrow or repetitive attack patterns. To address these issues, we propose EvoJail, an instruction-fusion-driven evolutionary jailbreak generation framework that formalizes jailbreak prompt generation as a multi-objective black-box optimization problem and leverages the principles of evolutionary algorithms to search for jailbreak prompts that can adapt across different model versions and exhibit diverse attack patterns. Specifically, EvoJail integrates jailbreak prompt generation into an iterative evolutionary loop, where at each iteration candidate prompts are evaluated directly against the target model and then selected and varied based on the target model's responses, enabling the generation process to continuously adapt to model updates. To enhance diversity, EvoJail introduces field-aware instruction fusion to construct diverse starting points and incorporates diversity-aware objectives into the evolutionary fitness function, guiding the search toward prompts with richer semantic variation, while further designing multi-level LLM-based mutation operators that modify prompt structures at different granularities to promote structural diversity throughout the evolutionary process. Results demonstrate that EvoJail has stronger adaptability and can achieve over $93\%$ attack success rate and more than $5.6\%$ improvement in diversity metrics over state-of-the-art methods.

---

### Where to Bind Matters: Hebbian Fast Weights in Vision Transformers for Few-Shot Character Recognition

Authors: Gavin Money, Sindhuja Penchala, Jiacheng Li, Noorbakhsh Amiri Golilarz
Published: 2026-04-22
Categories: cs.NE, cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2605.02920v1

Standard transformer architectures learn fixed slow-weight representations during training and lack mechanisms for rapid adaptation within an episode. In contrast, biological neural systems address this through fast synaptic updates that form transient associative memories during inference, a property known as Hebbian plasticity. In this paper, we conduct an empirical study of Hebbian Fast-Weight (HFW) modules integrated into multiple transformer backbones, including ViT-Small, DeiT-Small, and Swin-Tiny. We evaluate six model variants: ViT, DeiT, Swin, ViT-Hebbian, DeiT-Hebbian, and Swin-Hebbian on 5-way 1-shot and 5-way 5-shot classification tasks using the Omniglot benchmark under a Prototypical Network meta-learning framework. We propose a single module placement strategy for Swin-Tiny in which one HFW module is applied to the final stage feature map after all hierarchical stages have completed. This design avoids the training instability caused by placing separate Hebbian modules at each stage and achieves the highest test accuracy across all six models (96.2\% at 1-shot; 99.2\% at 5-shot), outperforming its non-Hebbian baseline by $+0.3$ percentage points at 1-shot. We analyze the interaction between Swin's shifted window inductive bias and episode-level Hebbian binding, discuss why per-block placement fails for ViT and DeiT variants in a low-data regime, and situate the results within the wider literature on fast and slow-weight meta-learning.

---

### Autonomous Reliability Qualification of Ga$_2$O$_3$-based diode sensors via Safe Active Learning

Authors: Davi Febba, William A. Callahan, Anna Sacchi, Andriy Zakutayev
Published: 2026-04-22
Categories: physics.app-ph, cond-mat.mtrl-sci, cs.LG, eess.SY
arXiv: https://arxiv.org/abs/2605.00868v3

Ultra-wide bandgap (UWBG) Ga$_2$O$_3$ is a promising semiconductor for high-power and high-temperature electronics. Reliable qualification of these devices under extreme operating conditions is essential, yet conventional reliability testing is inherently time-consuming. Autonomous experimentation offers a new paradigm by enabling measurement planning and model refinement to evolve in parallel in real time. We present a Safe Active Learning (SAL) framework for autonomous reliability characterization of Ga$_2$O$_3$-based diode sensors under coupled thermal and hydrogen stress. We first evaluate SAL in simulation, where it safely expands the explored region while learning the evolving rectification surface. Second, we demonstrate SAL experimentally on an automated high-temperature probe-station platform using a Pt/Cr$_2$O$_3$:Mg/$β$-Ga$_2$O$_3$ diode sensor of H$_2$ and temperature, spanning 0-800 ppm H$_2$ and 350-550 °C. Finally, we use the SAL-generated dataset for offline long-horizon forecasting of the diode current at a target voltage with a structured Gaussian-process model. Its condition-dependent Kohlrausch--Williams--Watts mean and residual covariance kernel were engineered with artificial-intelligence assistance using the SAL data and an auxiliary validation dataset spanning 1,000 hours at 400 °C across multiple H$_2$ concentrations. This dataset guided kernel design and validation, and the resulting model captures its long-time, saturating degradation trends. Although demonstrated here for a rectifying Ga$_2$O$_3$-based diode, SAL is applicable to other device classes whenever a suitable safety observable can be measured in situ.

---

### Autonomous Reliability Qualification of Ga$_2$O$_3$-based Hydrogen and Temperature Sensors via Safe Active Learning

Authors: Davi Febba, William A. Callahan, Anna Sacchi, Andriy Zakutayev
Published: 2026-04-22
Categories: physics.app-ph, cond-mat.mtrl-sci, cs.LG, eess.SY
arXiv: https://arxiv.org/abs/2605.00868v2

We present a Safe Active Learning (SAL) framework for autonomous reliability characterization of rectifying Ga$_2$O$_3$-based devices under coupled thermal and hydrogen stress. SAL treats rectification as a device-physics-motivated safety observable and models its evolution over elapsed time, temperature, and H$_2$ concentration using a Gaussian-process surrogate. To handle condition-dependent and uncertain experiment durations, the method combines an adaptive completion-time window, time-window lower-confidence-bound safety checks, a trust region anchored to previously verified safe conditions, and a two-phase strategy that transitions from conservative safe exploration to progressively relaxed rectification targets as the device degrades. We first evaluate SAL in simulation, where it safely expands the explored region while learning the evolving rectification surface. We then demonstrate SAL experimentally on an automated high-temperature probe-station platform using a Pt/Cr$_2$O$_3$:Mg/$β$-Ga$_2$O$_3$ device. In the reported campaign, phase 1 incurred only one unsafe measurement associated with spurious current-voltage sweeps, while phase 2 intentionally probed lower-rectification regimes. Finally, we use the curated SAL dataset for offline long-horizon forecasting of device response at a target voltage using a structured Gaussian-process model with a condition-dependent Kohlrausch--Williams--Watts mean and a residual covariance kernel. The model captures long-time, saturating degradation trends in an auxiliary validation dataset, illustrating how safety-aware autonomous experimentation enables both conservative characterization and subsequent degradation modeling. Although demonstrated here for a rectifying Ga$_2$O$_3$ device, SAL is applicable to other systems where a measurable in situ safety observable can be defined.

---

### Leakage-Audited Benchmarking Reveals Limited Evidence for Cross-Subject Auditory-Evoked EEG Vowel Perception Decoding

Authors: Xiaoyang Li, Zeyan Tao
Published: 2026-04-22
Categories: eess.SP, cs.CL, cs.CV, cs.LG, cs.SD, q-bio.NC
arXiv: https://arxiv.org/abs/2605.00865v4

We tested whether auditory-evoked EEG supports subject-independent five-vowel perception decoding when trial identity, model identity, prediction provenance, and participant-level inference are controlled within a single benchmark. We reconstructed Study 2 event tables from OpenNeuro ds006104 version 1.0.1 and analysed the consonant-vowel pair task. One-to-one marker-stimulus pairing yielded 3,840 independent trials; control-condition selection and artifact rejection retained 1,094 epochs from 16 participants and 61 EEG channels. Thirteen unique implementations were evaluated using leave-one-subject-out testing, with participant metrics reconstructed from 36,102 trial predictions across 33 complete prediction replicas. Random Forest was numerically highest at 21.474% balanced accuracy (95% participant-bootstrap interval, 19.526-23.482%; chance, 20%), but neither its participant-level tests nor any implementation survived correction across the 13-model family. Deep-model performance was close to chance, and several architectures showed substantial seed-dependent variation and low trial-label agreement. An exploratory MDM analysis comprising 9,616 genuine refits across training cohorts of 3-15 participants showed no monotonic performance gain. Within this dataset and protocol, evidence for reliable cross-subject five-vowel decoding is limited. The benchmark provides a reproducible chain from source rows to retained epochs, predictions, participant-level metrics, multiplicity-adjusted inference, and bounded diagnostic analyses.

---

### Leakage-Audited Benchmarking Reveals Limited Evidence for Cross-Subject Auditory-Evoked EEG Vowel Perception Decoding

Authors: Xiaoyang Li, Zeyan Tao
Published: 2026-04-22
Categories: eess.SP, cs.CL, cs.CV, cs.LG, cs.SD, q-bio.NC
arXiv: https://arxiv.org/abs/2605.00865v2

We tested whether auditory-evoked EEG supports subject-independent five-vowel perception decoding when trial identity, model identity, prediction provenance, and participant-level inference are controlled within a single benchmark. We reconstructed Study 2 event tables from OpenNeuro ds006104 version 1.0.1 and analyzed the consonant-vowel pair task. One-to-one marker-stimulus pairing yielded 3,840 independent trials; control-condition selection and artifact rejection retained 1,094 epochs from 16 participants and 61 EEG channels. Thirteen unique implementations were evaluated using leave-one-subject-out testing, with participant metrics reconstructed from 36,102 trial predictions across 33 complete prediction replicas. Random Forest was numerically highest at 21.474% balanced accuracy (95% participant-bootstrap interval, 19.526-23.482%; chance, 20%), but neither its participant-level tests nor any implementation survived correction across the 13-model family. Deep-model performance was close to chance, and several architectures showed substantial seed-dependent variation and low trial-label agreement. In a separate descriptive sensor-space representation, participant-associated effects accounted for 72.24% of the balanced standardized centroid sum of squares, compared with 2.04% for vowel-associated effects; between-participant same-vowel distances exceeded within-participant across-vowel distances for all 16 participants. An exploratory MDM analysis comprising 9,616 genuine refits across training cohorts of 3-15 participants showed no monotonic performance gain. Within this dataset and protocol, evidence for reliable cross-subject five-vowel decoding is limited. The benchmark provides a reproducible chain from source rows to retained epochs, predictions, participant-level metrics, multiplicity-adjusted inference, and bounded diagnostic analyses.

---

### Broadband Wide Field of View Imaging with Computational Mirrors

Authors: Vishwanath Saragadam, Niki Nezakati, Amit Roy-Chowdhury, Vivek Boominathan
Published: 2026-04-22
Categories: eess.IV, cs.CV, physics.optics
arXiv: https://arxiv.org/abs/2605.00029v1

Traditional glass-based optics are typically optimized for narrow spectral bands, such as the visible (400-700nm) or shortwave infrared (1000-1800nm). While the emergence of VIS-SWIR sensors (400-1700nm) offers transformative potential, refractive optics struggle to focus this entire range simultaneously. Mirrors represent a promising achromatic alternative; however, they are often sidelined by field curvature, and off-axis aberrations. This paper introduces Computational Mirrors, a framework that enables high-resolution, wide-field-of-view imaging across the complete VIS-SWIR spectrum using a single sensor. Our method is built on the observation that distinct regions of the field of view reach focus at varying distances from the mirror. By capturing a minimal focal stack (2-4 images), we utilize a computational backend to recover a sharp, all-in-focus image. A key contribution of this work is SeidelConv, a novel, physics-inspired, spatially-varying point spread function (PSF) model designed to accurately characterize and correct the off-axis aberrations inherent in simple concave mirrors. We demonstrate the efficacy of our approach using a first-of-its-kind 50mm F/1 optical system equipped with a VIS-SWIR sensor. Our system produces sharp images across RGB, NIR, and SWIR wavelengths without requiring refocusing, revealing material details invisible within individual spectral bands. We further validate the scalability of our approach with a 100mm F/2 system optimized for long-range imaging.

---

### MoDAl: Self-Supervised Neural Modality Discovery via Decorrelation for Speech Neuroprosthesis

Authors: Yuanhao Chen, Peter Chin
Published: 2026-04-22
Categories: q-bio.NC, cs.CL, cs.HC, cs.LG, eess.AS
arXiv: https://arxiv.org/abs/2605.00025v3

Speech neuroprosthesis systems decode intended speech from neural activity in the absence of audible output, offering a path to restoring communication for individuals with speech-impairing conditions. Current approaches decode predominantly from motor cortical areas, discarding others -- such as area 44, part of Broca's area -- that may encode complementary linguistic information. We introduce MoDAl (Modality Decorrelation and Alignment), a framework that discovers complementary neural modalities through the interplay of two objectives in a shared projection space. A contrastive loss aligns each of several parallel brain encoders with the text embeddings of a pretrained large language model (LLM), while a decorrelation loss prevents the encoders from coalescing to duplicative representations. We prove that these objectives are in productive tension: Contrastive alignment induces transitive modality coalescence, which decorrelation must counteract for the framework to discover diverse neurolinguistic modalities. On the Brain-to-Text Benchmark '24, MoDAl reduces word error rate (WER) from 26.3% to 21.6% compared to the previous best end-to-end method, with the gain from incorporating previously discarded area 44 signals arising entirely from the decorrelation mechanism. Analysis of the discovered modalities reveals functional specialization: Encoders receiving area 44 input capture structural and syntactic properties (sentence length, grammatical voice, wh-words), consistent with the neurolinguistic understanding of Broca's area.

---

### Not All Memories Age the Same: Autodiscovery of Adaptive Decay in Knowledge Graphs

Authors: Mandar Karhade
Published: 2026-04-22
Categories: cs.IR, cs.AI, cs.LG, q-bio.QM
arXiv: https://arxiv.org/abs/2604.26970v1

Knowledge graphs used for retrieval treat all facts as equally current. Existing temporal approaches apply uniform decay, using a single forgetting curve regardless of knowledge type. We show this is fundamentally misspecified: different knowledge types exhibit different temporal dynamics, and the core retrieval problem is not latency or throughput but identifying what is important at query time. We propose a hierarchical framework that replaces uniform decay with a continuous decay surface parameterized by two orthogonal signals: velocity (how frequently a concept is observed) and volatility (how much the value changes between observations, measured via embedding distance). The decay surface is decomposed into three learnable levels: domain-level parameters capture universal patterns (some predicates are inherently permanent, others inherently transient), context-level parameters capture setting-dependent variation, and entity-level adaptation personalizes decay to specific subjects. All parameters emerge from data through survival analysis on observed value lifetimes, requiring no predefined taxonomies or domain expertise. We formulate edge lifetime as a survival problem where the event is value supersession (a meaningfully different value replacing the current one), distinct from mere re-observation. Experiments on synthetic temporal knowledge graphs demonstrate recovery of planted hierarchical parameters (HDBSCAN ARI = 1.0). Validation on 107 Wikipedia articles and 1,163 patient records from the Synthea clinical EHR simulator shows that velocity-volatility clusters emerge naturally, align with observable persistence patterns, and near-universally exhibit the Lindy effect (Weibull shape k < 1). Uniform decay performs 18x worse than no temporal weighting. Heterogeneous decay recovers from this, with each hierarchy level contributing measurable improvement.

---

### A Digital Pathology Resource for Liver Cancer Quantification with Datasets, Benchmarks, and Tools

Authors: Ying Xiao, Shimiao Tang, Xitong Ling, Weiming Chen, Jun Wang, Jiawen Li, Huaitian Yuan, Jianghui Yang, Bowen Li, Huan Li, Yiting Meng, Tian Guan et al.
Published: 2026-04-22
Categories: cs.CV
arXiv: https://arxiv.org/abs/2604.22858v1

Liver cancer, especially hepatocellular carcinoma (HCC), imposes a substantial global disease burden. Accurate diagnosis and prognostic assessment directly influence treatment selection and patient survival, and pathological examination remains the gold standard for liver cancer diagnosis. Identifying diverse tissue components and pathological subtypes on histopathology slides is crucial for estimating postoperative recurrence risk and overall prognosis. However, most publicly available resources are still provided at the whole-slide image (WSI) level, and well-annotated datasets for fine-grained tissue component identification in liver cancer are scarce, which hinders reproducible model development and the deployment of quantitative analysis tools. To address this gap, we release HepatoBench, a patch-level image database for liver cancer with annotations for seven key tissue categories. Based on HepatoBench, we train and open-source a deep learning classification model as a tissue recognition tool. Furthermore, we train a WSI-level tumor/non-tumor segmentation model to automatically localize lesion regions across entire slides. By integrating the patch-level tissue classifier with the WSI-level segmentation model, we build HepatoQuant, an end-to-end, disease-specific regional quantification tool for liver cancer, enabling a unified workflow from WSIs to tissue composition parsing and quantitative statistics. We also open-source HepatoBench, the benchmarking protocol, and supporting tools, providing a solid foundation for automated regional quantification and fair method comparison in liver cancer pathology.

---

### IoT-Enhanced CNN-Based Labelled Crack Detection for Additive Manufacturing Image Annotation in Industry 4.0

Authors: Mohsen Asghari Ilani, Yaser Mike Banad
Published: 2026-04-22
Categories: cs.CV
arXiv: https://arxiv.org/abs/2604.22857v1

This paper presents an IoT-enhanced deep learning framework for automated crack detection in Additive Manufacturing (AM) surfaces using convolutional neural networks (CNNs). By integrating IoT-enabled real-time monitoring, high-resolution imaging, and edge computing, the system enables continuous in-situ defect detection and classification. Real-time data acquisition supports immediate CNN-based analysis, improving both accuracy and efficiency in AM quality control. The framework supports supervised and semi-supervised learning, enabling robust performance on large, sparsely annotated datasets. Using LabelImg for annotation and OpenCV for preprocessing, the system achieves 99.54% accuracy on 14,982 images, with 96% precision, 98% recall, and a 97% F1-score. Dataset balancing and augmentation significantly improve generalization, increasing accuracy from 32% to 99%. Beyond detection, the framework establishes a linkage between AM process parameters, defect formation, and surface topology, supporting predictive analytics and defect mitigation. Aligned with Industry 4.0, it incorporates Digital Twin (DT) technology for real-time process simulation, predictive maintenance, and adaptive control. Key contributions include an IoT-based monitoring system using edge devices (Raspberry Pi 4B), an optimized CNN with model quantization and batch processing reducing inference latency by 47%, and an MQTT-based low-latency data streaming system with 5G connectivity, lowering transmission overhead by 35%. DT integration further enables predictive defect analysis and dynamic adjustment of AM parameters. This work advances intelligent AM quality control by providing a scalable, high-accuracy, and low-latency framework. Future directions include multimodal data fusion, hybrid architectures, and enhanced Digital Twin simulations for AI-driven defect prevention.

---

### Attention-Augmented YOLOv8 with Ghost Convolution for Real-Time Vehicle Detection in Intelligent Transportation Systems

Authors: Syed Sajid Ullah, Muhammad Zunair Zamir, Ahsan Ishfaq, Salman Khan
Published: 2026-04-22
Categories: cs.CV
arXiv: https://arxiv.org/abs/2604.22856v1

Accurate vehicle detection is a critical component of autonomous driving, traffic surveillance, and intelligent transportation systems. This paper presents an enhanced YOLOv8n-based model that integrates the Ghost Module, Convolutional Block Attention Module (CBAM), and Deformable Convolutional Networks v2 (DCNv2) to improve detection performance. The Ghost Module reduces feature redundancy through efficient feature generation, CBAM refines feature representation via channel and spatial attention, and DCNv2 enhances adaptability to geometric variations in vehicle structures. Evaluated on the KITTI dataset, the proposed model achieves 95.4% mAP@0.5, representing an 8.97% improvement over the baseline YOLOv8n, along with 96.2% precision, 93.7% recall, and a 94.93% F1-score. Comparative analysis against seven state-of-the-art detectors demonstrates consistent superiority across key performance metrics, while ablation studies validate the individual and combined contributions of the integrated modules. By addressing feature redundancy, attention refinement, and spatial adaptability, the proposed approach offers a robust and computationally efficient solution for vehicle detection in diverse and complex traffic environments.

---

### Evaluating Remote Sensing Image Captions Beyond Metric Biases

Authors: Ziyun Chen, Fan Liu, Liang Yao, Chuanyi Zhang, Yuye Ma, Wei Zhou
Published: 2026-04-22
Categories: cs.CV
arXiv: https://arxiv.org/abs/2604.22855v1

The core objective of image captioning is to achieve lossless semantic compression from visual signals into textual modalities. However, the reliance on manually curated reference texts for evaluation essentially forces models to mimic specific human annotation styles, thereby masking the true descriptive capabilities of advanced foundation models. This systemic misalignment prompts a critical question: Is task-specific fine-tuning truly necessary for Remote Sensing Image Captioning, or is the perceived performance gap merely an artifact of flawed evaluation criteria? To investigate this discrepancy, we propose ReconScore, a novel reference-free evaluation metric. Rather than computing textual similarities, we assess caption quality by its capability to reconstruct the original visual elements solely from the generated text, effectively neutralizing human annotation biases. Applying this metric, we uncover a profound, counterintuitive truth: inherently powerful, unfine-tuned MLLMs surpass their fine-tuned counterparts in authentic zero-shot RSIC tasks. Driven by this structural discovery, we introduce RemoteDescriber, a completely training-free generation methodology. By employing ReconScore as a self-correction mechanism, we iteratively refine the semantic precision of MLLM outputs without any computational fine-tuning overhead. Comprehensive experiments demonstrate that RemoteDescriber achieves state-of-the-art performance on three datasets. Furthermore, we validate ReconScore's reliability and analyze the flaws of traditional metrics. Our code is available at https://github.com/hhu-czy/RemoteDescriber.

---

### MAE-Based Self-Supervised Pretraining for Data-Efficient Medical Image Segmentation Using nnFormer

Authors: R. M. Krishna Sureddi, T. Satyanarayana Murthy, Nomula Varsha Reddy, Adi Kanishka, Nalla Manvika Reddy
Published: 2026-04-22
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2604.22854v1

Transformer architectures, including nnFormer,have demonstrated promising results in volumetric medical image segmentation by being able to capture long-range spatial interactions. Although they have high performance, these models need large quantities of labeled training data and are also likely to overfit and become training unstable. This is a serious practical problem because it is not only time-consuming but also expensive to obtain medical images that are annotated by experts. Moreover, fully supervised traditional training pipelines do not take advantage of the available large amounts of unlabeled medical imaging data that can be easily obtained in the clinics. We have solved these drawbacks by advancing the efficiency of the nnFormer with a self-supervised pretraining framework, which is based on the Masked Autoencoders (MAE). In this method, the model is pretrained on unlabeled volumetric medical images to reconstruct randomly masked parts of the input. This allows the encoder to learn meaningful anatomical and structural representations . The encoder is then further fine-tuned on a labeled dataset on the downstream segmentation task. Conducted Experiment shows that the offered method leads to a higher segmentation performance on the count of Dice score, a quicker convergence rate on the course of the fine-tuning procedure, and a superior generalization on the basis of limited labeled data . These findings validate that self-supervised learning combined with transformer-based segmentation models is an appropriate approach to the problem of data shortage in medical image analysis.

---

### FastAT Benchmark: A Comprehensive Framework for Fair Evaluation of Fast Adversarial Training Methods

Authors: Chao Pan, Xin Yao
Published: 2026-04-22
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2604.22853v1

Fast Adversarial Training (FastAT) seeks to achieve adversarial robustness at a fraction of the computational cost incurred by standard multi-step methods such as PGD-AT. Although numerous FastAT techniques have been proposed in recent years, fair comparison among them remains elusive. Existing benchmarks and public leaderboards typically permit diverse model architectures, varying training configurations, and external data sources, making it unclear whether reported improvements reflect genuine algorithmic advances or merely more favorable experimental conditions. To address this problem, we introduce the FastAT Benchmark, a controlled evaluation framework built on three core design principles: unified architecture requirements, standardized training settings, and strict prohibition of external or synthetic data. The benchmark implements over twenty representative FastAT methods within a single codebase, enabling direct and reproducible comparison. Each method is assessed through a dual-metric evaluation framework that measures both adversarial robustness (accuracy under PGD, AutoAttack, and CR Attack) and computational cost (GPU training time and peak memory footprint). Comprehensive experiments on CIFAR-10, CIFAR-100, and Tiny-ImageNet provide reliable baseline measurements and reveal that well-designed single-step methods can match or surpass PGD-AT robustness at substantially lower cost, while no single method dominates across all evaluation dimensions. The complete benchmark, including source code, configuration files, and experimental results, is publicly available to support transparent and fair evaluation of future FastAT research.

---

### SwarmDrive: Semantic V2V Coordination for Latency-Constrained Cooperative Autonomous Driving

Authors: Anjie Qiu, Donglin Wang, Zexin Fang, Sanket Partani, Hans D. Schotten
Published: 2026-04-22
Categories: cs.RO, cs.AI
arXiv: https://arxiv.org/abs/2604.22852v1

Cloud-hosted LLM inference for autonomous driving adds round-trip delay and depends on stable connectivity, while purely local edge models struggle under occlusion. We present SwarmDrive, a semantic Vehicle-to-Vehicle (V2V) coordination framework in which nearby vehicles run local Small Language Models (SLMs), share compact intent distributions only when uncertainty is high, and fuse them through event-triggered consensus. We evaluate SwarmDrive in a 5-seed executable study built around one occluded intersection case, combining matched operating-point comparisons with robustness sweeps. In that setting, SwarmDrive under its 6G communication setting ("Swarm 6G") raises success from 68.9% to 94.1% over a single local SLM while reducing latency from a 510 ms cloud reference to 151.4 ms. However, an increased number of participating vehicles leads to higher communication overhead and packet loss. SwarmDrive also evaluates the impact of swarm-size, packet-loss, and entropy-threshold sweeps and shows that the cooperative gain holds across ablations and is best balanced near an active swarm size of 4 vehicles and an entropy trigger threshold of 0.65 in the current prototype. These results show that semantic edge cooperation can work under tight latency constraints in the targeted intersection case, but they are not a deployment-grade validation of a real 6G stack.

---

### EgoDyn-Bench: Evaluating Ego-Motion Understanding in Vision-Centric Foundation Models for Autonomous Driving

Authors: Finn Rasmus Schäfer, Yuan Gao, Dingrui Wang, Thomas Stauner, Stephan Günnemann, Mattia Piccinini, Sebastian Schmidt, Johannes Betz
Published: 2026-04-22
Categories: cs.CV, cs.CL, cs.RO
arXiv: https://arxiv.org/abs/2604.22851v2

While Vision-Language Models (VLMs) have advanced high-level reasoning in autonomous driving, their ability to ground this reasoning in the underlying physics of ego-motion remains poorly understood. We introduce EgoDyn-Bench (Project page: (https://tum-avs.github.io/EgoDyn-Bench-Website/), Code: (https://github.com/TUM-AVS/EgoDyn-Bench), Dataset: (https://huggingface.co/datasets/fnc1901/EgoDyn-Bench)), a diagnostic benchmark for evaluating the semantic ego-motion understanding of vision-centric foundation models. By mapping continuous vehicle kinematics to discrete motion concepts via a deterministic oracle, we decouple a model's internal physical logic from its visual perception. Our large-scale empirical audit spanning 20$+$ models, including closed-source MLLMs, open-source VLMs across multiple scales, and specialized VLAs, identifies a significant Perception Bottleneck: while models exhibit logical physical concepts, they consistently fail to accurately align them with visual observations, frequently underperforming classical non-learned geometric baselines. This failure persists across model scales and domain-specific training, indicating a structural deficit in how current architectures couple visual perception with physical reasoning. We demonstrate that providing explicit trajectory encodings substantially restores physical consistency across all evaluated models, revealing a functional disentanglement between vision and language: ego-motion logic is derived almost exclusively from the language modality, while visual observations contribute negligible temporal signal. This structural finding provides a standardized diagnostic framework and a practical pathway toward physically aligned embodied AI. Ego-motion - Physical Reasoning - Foundation Models

---

### Accelerating New Product Introduction for Visual Quality Inspection via Few-Shot Diffusion-Based Defect Synthesis

Authors: Serkan Hamdi Güğül, Kemal Levi, Burak Acar
Published: 2026-04-22
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2604.22850v1

Industrial visual inspection systems often suffer from a severe scarcity of labeled defect data, particularly during the early stages of New Product Introduction (NPI). This limitation hinders the deployment of robust supervised detectors precisely when automated quality control is most needed. We present an end-to-end generative framework for high-fidelity, few-shot defect synthesis that enables both in-domain augmentation and cross-domain transfer. Our approach disentangles defect morphology from background appearance by combining masked textual inversion for defect representation learning, noise-blended conditioned generation for surface-aware synthesis, and gradient-aware post-processing for seamless visual integration. We evaluate the framework in two practically relevant settings: few-shot data augmentation, where synthetic samples enrich a small set of real defects, and zero-shot adaptation, where defects learned from a source domain are transferred to a novel target surface without any real target-domain defect examples. Using RF-DETR as the downstream detector, we show that the proposed pipeline substantially narrows the domain gap on a private industrial dataset. In the few-shot setting, synthetic augmentation improves mAP from 78.8% to 83.3%. In the zero-shot setting, synthetic domain adaptation improves mAP from 65.0% to 85.1%. These results demonstrate that high-fidelity defect synthesis can meaningfully accelerate NPI by enabling effective inspection models before sufficient real defect data has been collected.

---

### LunarDepthNet: Generation of Digital Elevation Models using Deep Learning and Monocular Satellite Images

Authors: Aaranay Aadi, Jai Gopal Singla, Amitabh, Nitant Dube, Praveen Kumar Shukla, Vijaypal Singh Dhaka
Published: 2026-04-22
Categories: cs.CV
arXiv: https://arxiv.org/abs/2604.22848v1

Recent times have seen an increase in demand of high quality Digital Elevation Models (DEMs) for the lunar surface, because they are highly important for studying the moon and planning future missions. However, there is an evident lack of detailed elevation data on the Moon. To overcome this limitation, this study proposes a novel deep learning method that estimates and generates a surface elevation map directly from monocular images of the surface. The dataset used comprises of the Chandrayaan-2 Terrain Mapping Camera (TMC) images with their corresponding Digital Terrain Models (DTMs). The study proposes LunarDepthNet, which comprises of a UNet architecture to generate DEMS. It incorporates an EfficientNet encoder and custom layers to correctly learn how the light shadows on the surface relate to the actual elevation values. A combined loss function was also utilized to keep the terrain details accurate and smooth. During validation, the model showed a stable loss convergence of 12%. It achieved a mean nRMSE of 0.437 and an MAE of 4.5m in the testing stage. These results prove the model can generate dependable elevation maps from single orbital images, which are quite useful in regions of the moon where stereo-images are not available.

---

### Dream-Cubed: Controllable Generative Modeling in Minecraft by Training on Billions of Cubes

Authors: Tim Merino, Sam Earle, Ryunosuke Iwai, Julian Togelius, Edoardo Cetin
Published: 2026-04-22
Categories: cs.CV
arXiv: https://arxiv.org/abs/2604.22847v1

We introduce Dream-Cubed, a large-scale dataset of Minecraft worlds at voxel resolution, and a family of models using cubes as powerful compositional units for efficient generation of interactive 3D environments. Dream-Cubed comprises tens of billions of tokens from a carefully curated mixture of procedural biome terrain and high-quality human-authored maps. We use this dataset to conduct the first large-scale study of 3D diffusion models for voxel generation, analyzing discrete and continuous diffusion formulations, data compositions, and architectural design choices. Our models operate directly in the space of blocks, enabling efficient and semantically grounded generation while supporting interactive user workflows such as inpainting and outpainting from user-authored blocks. To quantitatively evaluate our models, we adapt the FID metric to assess semantic differences between real and generated world renderings, and validate generation quality through a human preference study. We release the full dataset, code, and all our pretrained models, which we hope will provide a foundation for future research in efficient generative modeling for structured, interactive 3D environments.

---

### Building a Precise Video Language with Human-AI Oversight

Authors: Zhiqiu Lin, Chancharik Mitra, Siyuan Cen, Isaac Li, Yuhan Huang, Yu Tong Tiffany Ling, Hewei Wang, Irene Pi, Shihang Zhu, Ryan Rao, George Liu, Jiaxi Li et al.
Published: 2026-04-22
Categories: cs.CV, cs.AI, cs.CL, cs.LG, cs.MM
arXiv: https://arxiv.org/abs/2604.21718v2

Video-language models (VLMs) learn to reason about the dynamic visual world through natural language. We introduce a suite of open datasets, benchmarks, and recipes for scalable oversight that enable precise video captioning. First, we define a structured specification for describing subjects, scenes, motion, spatial, and camera dynamics, grounded by hundreds of carefully defined visual primitives developed with professional video creators such as filmmakers. Next, to curate high-quality captions, we introduce CHAI (Critique-based Human-AI Oversight), a framework where trained experts critique and revise model-generated pre-captions into improved post-captions. This division of labor improves annotation accuracy and efficiency by offloading text generation to models, allowing humans to better focus on verification. Additionally, these critiques and preferences between pre- and post-captions provide rich supervision for improving open-source models (Qwen3-VL) on caption generation, reward modeling, and critique generation through SFT, DPO, and inference-time scaling. Our ablations show that critique quality in precision, recall, and constructiveness, ensured by our oversight framework, directly governs downstream performance. With modest expert supervision, the resulting model outperforms closed-source models such as Gemini-3.1-Pro. Finally, we apply our approach to re-caption large-scale professional videos (e.g., films, commercials, games) and fine-tune video generation models such as Wan to better follow detailed prompts of up to 400 words, achieving finer control over cinematography including camera motion, angle, lens, focus, point of view, and framing. Our results show that precise specification and human-AI oversight are key to professional-level video understanding and generation. Data and code are available on our project page: https://linzhiqiu.github.io/papers/chai/

---

### Adaptive Instruction Composition for Automated LLM Red-Teaming

Authors: Jesse Zymet, Andy Luo, Swapnil Shinde, Sahil Wadhwa, Emily Chen
Published: 2026-04-22
Categories: cs.CR, cs.AI, cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2604.21159v1

Many approaches to LLM red-teaming leverage an attacker LLM to discover jailbreaks against a target. Several of them task the attacker with identifying effective strategies through trial and error, resulting in a semantically limited range of successes. Another approach discovers diverse attacks by combining crowdsourced harmful queries and tactics into instructions for the attacker, but does so at random, limiting effectiveness. This article introduces a novel framework, Adaptive Instruction Composition, that combines crowdsourced texts according to an adaptive mechanism trained to jointly optimize effectiveness with diversity. We use reinforcement learning to balance exploration with exploitation in a combinatorial space of instructions to guide the attacker toward diverse generations tailored to target vulnerabilities. We demonstrate that our approach substantially outperforms random combination on a set of effectiveness and diversity metrics, even under model transfer. Further, we show that it surpasses a host of recent adaptive approaches on Harmbench. We employ a lightweight neural contextual bandit that adapts to contrastive embedding inputs, and provide ablations suggesting that the contrastive pretraining enables the network to rapidly generalize and scale to the massive space as it learns.

---

### Multi-Agent Empowerment and Emergence of Complex Behavior in Groups

Authors: Tristan Shah, Ilya Nemenman, Daniel Polani, Stas Tiomkin
Published: 2026-04-22
Categories: cs.AI, cs.MA
arXiv: https://arxiv.org/abs/2604.21155v2

Intrinsic motivations are receiving increasing attention, i.e. behavioral incentives that are not engineered, but emerge from the interaction of an agent with its surroundings. In this work we study the emergence of behaviors driven by one such incentive, empowerment, specifically in the context of more than one agent. We formulate a principled extension of empowerment to the multi-agent setting, and demonstrate its efficient calculation. We observe that this intrinsic motivation gives rise to characteristic modes of group-organization in two qualitatively distinct environments: a pair of agents coupled by a tendon, and a controllable Vicsek flock. This demonstrates the potential of intrinsic motivations such as empowerment to not just drive behavior for only individual agents but also higher levels of behavioral organization at scale.

---

### Multi-Agent Empowerment and Emergence of Complex Behavior in Groups

Authors: Tristan Shah, Ilya Nemenman, Daniel Polani, Stas Tiomkin
Published: 2026-04-22
Categories: cs.AI, cs.MA
arXiv: https://arxiv.org/abs/2604.21155v1

Intrinsic motivations are receiving increasing attention, i.e. behavioral incentives that are not engineered, but emerge from the interaction of an agent with its surroundings. In this work we study the emergence of behaviors driven by one such incentive, empowerment, specifically in the context of more than one agent. We formulate a principled extension of empowerment to the multi-agent setting, and demonstrate its efficient calculation. We observe that this intrinsic motivation gives rise to characteristic modes of group-organization in two qualitatively distinct environments: a pair of agents coupled by a tendon, and a controllable Vicsek flock. This demonstrates the potential of intrinsic motivations such as empowerment to not just drive behavior for only individual agents but also higher levels of behavioral organization at scale.

---