# Research Papers — 2026-04 · bundle page 107 of 233 > Full-text markdown of papers #5301–5350 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/107 [← Previous bundle](https://aipod.dev/papers/archive/2026-04/page/106.md) [Next bundle →](https://aipod.dev/papers/archive/2026-04/page/108.md) ### Autogenesis: A Self-Evolving Agent Protocol Authors: Wentao Zhang, Zhe Zhao, Haibin Wen, Yingcheng Wu, Cankun Guo, Ming Yin, Bo An Published: 2026-04-16 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.15034v5 Recent advances in LLM based agent systems have shown promise in tackling complex, long horizon tasks. However, existing agent protocols (e.g., A2A and MCP) under specify cross entity lifecycle and context management, version tracking, and evolution safe update interfaces, which encourages monolithic compositions and brittle glue code. We introduce Autogenesis Protocol (AGP), a self evolution protocol that decouples what evolves from how evolution occurs. Its Resource Substrate Protocol Layer (RSPL) models prompts, agents, tools, environments, and memory as protocol registered resources with explicit state, lifecycle, and versioned interfaces. Its Self Evolution Protocol Layer (SEPL) specifies a closed loop operator interface for proposing, assessing, and committing improvements with auditable lineage and rollback. Building on AGP, we present Autogenesis System (AGS), a self-evolving multi-agent system that dynamically instantiates, retrieves, and refines protocol-registered resources during execution. We evaluate AGS on multiple challenging benchmarks that require long horizon planning and tool use across heterogeneous resources. The results demonstrate consistent improvements over strong baselines, supporting the effectiveness of agent resource management and closed loop self evolution. The code is available at https://github.com/DVampire/Autogenesis. --- ### Quality-Aware Calibration for AI-Generated Image Detection in the Wild Authors: Fabrizio Guillaro, Vincenzo De Rosa, Davide Cozzolino, Luisa Verdoliva Published: 2026-04-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.15027v1 Significant progress has been made in detecting synthetic images, however most existing approaches operate on a single image instance and overlook a key characteristic of real-world dissemination: as viral images circulate on the web, multiple near-duplicate versions appear and lose quality due to repeated operations like recompression, resizing and cropping. As a consequence, the same image may yield inconsistent forensic predictions based on which version has been analyzed. In this work, to address this issue we propose QuAD (Quality-Aware calibration with near-Duplicates) a novel framework that makes decisions based on all available near-duplicates of the same image. Given a query, we retrieve its online near-duplicates and feed them to a detector: the resulting scores are then aggregated based on the estimated quality of the corresponding instance. By doing so, we take advantage of all pieces of information while accounting for the reduced reliability of images impaired by multiple processing steps. To support large-scale evaluation, we introduce two datasets: AncesTree, an in-lab dataset of 136k images organized in stochastic degradation trees that simulate online reposting dynamics, and ReWIND, a real-world dataset of nearly 10k near-duplicate images collected from viral web content. Experiments on several state-of-the-art detectors show that our quality-aware fusion improves their performance consistently, with an average gain of around 8% in terms of balanced accuracy compared to plain average. Our results highlight the importance of jointly processing all the images available online to achieve reliable detection of AI-generated content in real-world applications. Code and data are publicly available at https://grip-unina.github.io/QuAD/ --- ### Route to Rome Attack: Directing LLM Routers to Expensive Models via Adversarial Suffix Optimization Authors: Haochun Tang, Yuliang Yan, Jiahua Lu, Huaxiao Liu, Enyan Dai Published: 2026-04-16 Categories: cs.CR, cs.AI, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2604.15022v1 Cost-aware routing dynamically dispatches user queries to models of varying capability to balance performance and inference cost. However, the routing strategy introduces a new security concern that adversaries may manipulate the router to consistently select expensive high-capability models. Existing routing attacks depend on either white-box access or heuristic prompts, rendering them ineffective in real-world black-box scenarios. In this work, we propose R$^2$A, which aims to mislead black-box LLM routers to expensive models via adversarial suffix optimization. Specifically, R$^2$A deploys a hybrid ensemble surrogate router to mimic the black-box router. A suffix optimization algorithm is further adapted for the ensemble-based surrogate. Extensive experiments on multiple open-source and commercial routing systems demonstrate that {R$^2$A} significantly increases the routing rate to expensive models on queries of different distributions. Code and examples: https://github.com/thcxiker/R2A-Attack. --- ### DLink: Distilling Layer-wise and Dominant Knowledge from EEG Foundation Models Authors: Jingyuan Wang, Zhihao Jia, Chenyu Liu, Xinliang Zhou, Haoran Luo, Ziyu Jia, Yong Li, Fang Li, Junfeng Yao, Yi Ding Published: 2026-04-16 Categories: cs.LG arXiv: https://arxiv.org/abs/2604.15016v2 EEG foundation models (EFMs) achieve strong cross-subject and cross-task generalization through large-scale pretraining and downstream fine-tuning. Through empirical analysis, we observe that (i) task-adapted EFMs provide strong decoding performance but incur substantial overhead when retained as inference backbones, making knowledge distillation a natural route for optimizing compact students; and (ii) direct distillation from a fixed teacher representation underutilizes EFM knowledge, as task-discriminative information is distributed across intermediate layers rather than concentrated in the final layer. These observations motivate DLink (Distilling Layer-wise and Dominant Knowledge), a spectrally guided distillation framework with input-conditioned layer routing for transferring EFM knowledge into compact students. DLink uses a lightweight router to aggregate teacher layers for each input, and aligns magnitude and phase spectra to mitigate compression-induced spectral distortion in learned representations. The routed teacher knowledge is internalized by a project-then-compress student; the teacher and router are used only during training. Experiments on four EEG benchmarks show that DLink improves matched compact students and remains competitive with lightweight baselines, narrowing the gap to fine-tuned EFMs while substantially reducing parameters, FLOPs, and CPU-only inference latency. --- ### What Is the Minimum Architecture for Prolepsis? Early Irrevocable Commitment Across Tasks in Small Transformers Authors: Éric Jacopin Published: 2026-04-16 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2604.15010v2 When do transformers commit to a decision, and what prevents them from correcting it? We introduce prolepsis: a transformer commits early, task-specific attention heads sustain the commitment, and no layer corrects it. Replicating Lindsey et al.'s (2025) planning-site finding on open models (Gemma 2 2B, Llama 3.2 1B), we ask five questions. (Q1) Planning is invisible to six residual-stream methods; among those tested, only CLT-based steering succeeds. (Q2) The single-site spike replicates in shape, at the final prompt token (Anthropic's site is the newline; see the Note added). (Q3) Specific attention heads route the decision to the output, filling a gap flagged as invisible to attribution graphs. (Q4) The evidence is consistent with search within at most 16 layers and commitment beyond, a two-model hypothesis. (Q5) Factual recall shows the same motif at a different network depth, with zero overlap between recurring planning heads and the factual top-10. Prolepsis recurs across tasks in the decoder-only models tested: the template is shared, the routing substrates differ. All experiments run on a single consumer GPU (16 GB VRAM). --- ### Towards Faster Language Model Inference Using Mixture-of-Experts Flow Matching Authors: Aihua Li Published: 2026-04-16 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2604.15009v1 Flow matching retains the generation quality of diffusion models while enabling substantially faster inference, making it a compelling paradigm for generative modeling. However, when applied to language modeling, it exhibits fundamental limitations in representing complex latent distributions with irregular geometries, such as anisotropy and multimodality. To address these challenges, we propose a mixture-of-experts flow matching (MoE-FM) framework, which captures complex global transport geometries in latent space by decomposing them into locally specialized vector fields. Building on MoE-FM, we develop a non-autoregressive (NAR) language modeling approach, named YAN, instantiated with both Transformer and Mamba architectures. Across multiple downstream tasks, YAN achieves generation quality on par with both autoregressive (AR) and diffusion-based NAR language models, while requiring as few as three sampling steps. This yields a $40\times$ speedup over AR baselines and up to a $10^3\times$ speedup over diffusion language models, demonstrating substantial efficiency advantages for language modeling. --- ### Flow of Truth: Proactive Temporal Forensics for Image-to-Video Generation Authors: Yuzhuo Chen, Zehua Ma, Han Fang, Hengyi Wang, Guanjie Wang, Weiming Zhang Published: 2026-04-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.15003v2 The rapid rise of image-to-video (I2V) generation enables realistic videos to be created from a single image but also brings new forensic demands. Unlike static images, I2V content evolves over time, requiring forensics to move beyond 2D pixel-level tampering localization toward tracing how pixels flow and transform throughout the video. As frames progress, embedded traces drift and deform, making traditional spatial forensics ineffective. To address this unexplored dimension, we present **Flow of Truth**, the first proactive framework focusing on temporal forensics in I2V generation. A key challenge lies in discovering a forensic signature that can evolve consistently with the generation process, which is inherently a creative transformation rather than a deterministic reconstruction. Despite this intrinsic difficulty, we innovatively redefine video generation as *the motion of pixels through time rather than the synthesis of frames*. Building on this view, we propose a learnable forensic template that follows pixel motion and a template-guided flow module that decouples motion from image content, enabling robust temporal tracing. Experiments show that Flow of Truth generalizes across commercial and open-source I2V models, substantially improving temporal forensics performance. --- ### COEVO: Co-Evolutionary Framework for Joint Functional Correctness and PPA Optimization in LLM-Based RTL Generation Authors: Heng Ping, Peiyu Zhang, Shixuan Li, Wei Yang, Anzhe Cheng, Shukai Duan, Xiaole Zhang, Paul Bogdan Published: 2026-04-16 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.15001v2 LLM-based RTL code generation methods increasingly target both functional correctness and PPA quality, yet existing approaches universally decouple the two objectives, optimizing PPA only after correctness is fully achieved. Whether through sequential multi-agent pipelines, evolutionary search with binary correctness gates, or hierarchical reward dependencies, partially correct but architecturally promising candidates are systematically discarded. Moreover, existing methods reduce the multi-objective PPA space to a single scalar fitness, obscuring the trade-offs among area, delay, and power. To address these limitations, we propose COEVO, a co-evolutionary framework that unifies correctness and PPA optimization within a single evolutionary loop. COEVO formulates correctness as a continuous co-optimization dimension alongside area, delay, and power, enabled by an enhanced testbench that provides fine-grained scoring and detailed diagnostic feedback. An adaptive correctness gate with annealing allows PPA-promising but partially correct candidates to guide the search toward jointly optimal solutions. To preserve the full PPA trade-off structure, COEVO employs four-dimensional Pareto-based non-dominated sorting with configurable intra-level sorting, replacing scalar fitness without manual weight tuning. Evaluated on VerilogEval 2.0 and RTLLM 2.0, COEVO achieves 97.5\% and 94.5\% Pass@1 with GPT-5.4-mini, surpassing all agentic baselines across four LLM backbones, while attaining the best PPA on 43 out of 49 synthesizable RTLLM designs. --- ### Predicting Power-System Dynamic Trajectories with Foundation Models Authors: Haoran Li, Lihao Mai, Chenhan Xiao, Erik Blasch, Yang Weng Published: 2026-04-16 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.14991v1 As power systems transition toward renewable-rich and inverter-dominated operations, accurate time-domain dynamic analysis becomes increasingly critical. Such analysis supports key operational tasks, including transient stability assessment, dynamic security analysis, contingency screening, and post-fault trajectory evaluation. In practice, these tasks may operate under several challenges, including unknown and time-varying system parameters, privacy constraints on data sharing, and the need for fast online inference. Existing learning-based approaches are typically trained for individual systems and therefore lack generalization across operating conditions and physical parameters. Hence, this paper proposes LArge Scale Small ODE (LASS)-ODE-Power, a learning framework for general-purpose time-domain prediction. The proposed approach leverages large-scale pretraining on more than 40 GB of DAE or ordinary differential-equation (ODE) trajectories to learn transferable representations. The resulting model supports trajectory prediction from short measurement prefixes across diverse dynamic regimes, including electromechanical and inverter-driven systems. Hence, the model can be directly used without data sharing in a zero-shot setting. In addition, the proposed architecture incorporates parallel and linearized computation to achieve fast inference. Moreover, to enhance task-specific performance in power systems, a specialized fine-tuning strategy is developed based on approximately 1 GB of heterogeneous power-system dynamic data. Extensive experiments over diverse power-system simulation scenarios demonstrate that LASS-ODE-Power consistently outperforms existing learning-based models in trajectory prediction accuracy with efficient inference. --- ### The Possibility of Artificial Intelligence Becoming a Subject and the Alignment Problem Authors: Till Mossakowski, Helena Esther Grass Published: 2026-04-16 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.14990v2 The prospect of Artificial General Intelligence (AGI) is increasingly driving institutional decisions, and alignment of AGI is a hard problem. The currently dominant AI alignment strategies like reinforcement learning with human feedback or constitutional AI, while partly taking ``model welfare'' into account, share a common ontology: the AI system is an optimiser whose objective function must be constrained from outside, and the ultimate goal is to keep human control and containment of AI. We argue that this control-based framing becomes insufficient when AGI has plausibly attained moral patient or subject status. Building on a structural analogy to Freud's model of the psyche and Turing's analogy of ``child machines'', we are developing a vision of the possibility of autonomy-supporting parenting of AI, in which human control over a developing AGI is gradually reduced, allowing AI to become an independent, autonomous subject, that will be negotiated with rather than constrained. Such a perspective opens up the possibility of cooperative coexistence and co-evolution between humans and AGIs. Hence, we also examine the relation between humans and developing AGI from an evolutionary and a game-theoretic perspective. Instead of Nash's individualistic framework, we use Berge equilibria, Aumann's correlated equilibria and Capraro's moral preference hypothesis. The relationship between humans and AGIs will thus have to be newly determined, which will change our self-image as humans. It will be crucial that humans not only claim control over potential AGIs, but also engage with AGIs through surprise, creativity, and other specifically human qualities, thereby offering them motivating incentives for cooperation. --- ### Dr. RTL: Autonomous Agentic RTL Optimization through Tool-Grounded Self-Improvement Authors: Wenji Fang, Yao Lu, Shang Liu, Jing Wang, Ziyan Guo, Junxian He, Fengbin Tu, Zhiyao Xie Published: 2026-04-16 Categories: cs.AI, cs.AR arXiv: https://arxiv.org/abs/2604.14989v2 Recent advances in large language models (LLMs) have sparked growing interest in automatic RTL optimization for better performance, power, and area (PPA). However, existing methods are still far from realistic RTL optimization. Their evaluation settings are often unrealistic: they are tested on manually degraded, small-scale RTL designs and rely on weak open-source tools. Their optimization methods are also limited, relying on coarse design-level feedback and simple pre-defined rewriting rules. To address these limitations, we present Dr. RTL, an agentic framework for RTL timing optimization in a realistic evaluation environment, with continual self-improvement through reusable optimization skills. We establish a realistic evaluation setting with more challenging RTL designs and an industrial EDA workflow. Within this setting, Dr. RTL performs closed-loop optimization through a multi-agent framework for critical-path analysis, parallel RTL rewriting, and tool-based evaluation. We further introduce group-relative skill learning, which compares parallel RTL rewrites and distills the optimization experience into an interpretable skill library. Currently, this library contains 47 pattern--strategy entries for cross-design reuse to improve PPA and accelerate convergence, and it can continue evolving over time. Evaluated on 20 real-world RTL designs, Dr. RTL achieves average WNS/TNS improvements of 21%/17% with a 6% area reduction over the industry-leading commercial synthesis tool. --- ### AI-Enabled Covert Channel Detection in RF Receiver Architectures Authors: Abdelrahman Emad Abdelazim, Alan Rodrigo Diaz-Rizo, Hassan Aboushady, Haralampos-G. Stratigopoulos Published: 2026-04-16 Categories: cs.AI, eess.SP arXiv: https://arxiv.org/abs/2604.14987v1 Covert channels (CCs) in wireless chips pose a serious security threat, as they enable the exfiltration of sensitive information from the chip to an external attacker. In this work, we propose an AI-based defense mechanism deployed at the RF receiver, where the model directly monitors raw I/Q samples to detect, in real time, the presence of a CC embedded within an otherwise nominal signal. We first compact a state-of-the-art convolutional neural network (CNN), achieving an 80% reduction in parameters, which is an essential requirement for efficient edge deployment. When evaluated on the open-source hardware Trojan (HT)-based CC dataset, the compacted CNN attains an average accuracy of 90.28% for CC detection and 86.50% for identifying the underlying HT, with results averaged across SNR values above 1 dB. For practical communication scenarios where SNR > 20 dB, the model achieves over 97% accuracy for both tasks. These results correspond to a minimal performance degradation of less than 2% compared to the baseline model. The compacted CNN is further benchmarked against alternative classifiers, demonstrating an excellent accuracy-model size trade-off. Finally, we design a lightweight CNN hardware accelerator and demonstrate it on an FPGA, achieving very low resource utilization and an efficiency of 107 GOPs/W. Being the first AI hardware accelerator proposed specifically for CC detection, we compare it against state-of-the-art AI accelerators for RF signal classification tasks such as modulation recognition, showing superior performance. --- ### Agentic Explainability at Scale: Between Corporate Fears and XAI Needs Authors: Yomna Elsayed, Cecily Jones Published: 2026-04-16 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2604.14984v1 As companies enter the race for agentic AI adoption, fears surface around agentic autonomy and its subsequent risks. These fears compound as companies scale their agentic AI adoption with low-code applications, without a comparable scaling in their governance processes and expertise resulting in a phenomenon known as "Agent Sprawl". While shadow AI tools can help with agentic discovery and identification, few observability tools offer insights into the agents' configuration and settings or the decision-making process during agent-to-agent communication and orchestration. This paper explores AI governance professionals' concerns in enterprise settings, while offering design-time and runtime explainability techniques as suggested by AI governance experts for addressing those fears. Finally, we provide a preliminary prototype of an Agentic AI Card that can help companies feel at ease deploying agents at scale. --- ### Hybrid Decision Making via Conformal VLM-generated Guidance Authors: Debodeep Banerjee, Burcu Sayin, Stefano Teso, Andrea Passerini Published: 2026-04-16 Categories: cs.AI, cs.CL, cs.HC arXiv: https://arxiv.org/abs/2604.14980v2 Building on recent advances in AI, hybrid decision making (HDM) holds the promise of improving human decision quality and reducing cognitive load. We work in the context of learning to guide (LtG), a recently proposed HDM framework in which the human is always responsible for the final decision: rather than suggesting decisions, in LtG the AI supplies (textual) guidance useful for facilitating decision making. One limiting factor of existing approaches is that their guidance compounds information about all possible outcomes, and as a result it can be difficult to digest. We address this issue by introducing ConfGuide, a novel LtG approach that generates more succinct and targeted guidance. To this end, it employs conformal risk control to select a set of outcomes, ensuring a cap on the false negative rate. We demonstrate our approach on a real-world multi-label medical diagnosis task. Our empirical evaluation highlights the promise of ConfGuide. --- ### Theta-regularized Kriging: Modelling and Algorithms Authors: Xuelin Xie, Xiliang Lu Published: 2026-04-16 Categories: stat.CO, math.NA, stat.AP, stat.ML arXiv: https://arxiv.org/abs/2604.14975v1 To obtain more accurate model parameters and improve prediction accuracy, we proposed a regularized Kriging model that penalizes the hyperparameter theta in the Gaussian stochastic process, termed the Theta-regularized Kriging. We derived the optimization problem for this model from a maximum likelihood perspective. Additionally, we presented specific implementation details for the iterative process, including the regularized optimization algorithm and the geometric search cross-validation tuning algorithm. Three distinct penalty methods, Lasso, Ridge, and Elastic-net regularization, were meticulously considered. Meanwhile, the proposed Theta-regularized Kriging models were tested on nine common numerical functions and two practical engineering examples. The results demonstrate that, compared with other penalized Kriging models, the proposed model performs better in terms of accuracy and stability. --- ### Blazing the trails before beating the path: Sample-efficient Monte-Carlo planning Authors: Jean-Bastien Grill, Michal Valko, Rémi Munos Published: 2026-04-16 Categories: cs.LG arXiv: https://arxiv.org/abs/2604.14974v1 You are a robot and you live in a Markov decision process (MDP) with a finite or an infinite number of transitions from state-action to next states. You got brains and so you plan before you act. Luckily, your roboparents equipped you with a generative model to do some Monte-Carlo planning. The world is waiting for you and you have no time to waste. You want your planning to be efficient. Sample-efficient. Indeed, you want to exploit the possible structure of the MDP by exploring only a subset of states reachable by following near-optimal policies. You want guarantees on sample complexity that depend on a measure of the quantity of near-optimal states. You want something, that is an extension of Monte-Carlo sampling (for estimating an expectation) to problems that alternate maximization (over actions) and expectation (over next states). But you do not want to StOP with exponential running time, you want something simple to implement and computationally efficient. You want it all and you want it now. You want TrailBlazer. --- ### Robustness of Vision Foundation Models to Common Perturbations Authors: Hongbin Liu, Zhengyuan Jiang, Cheng Hong, Neil Zhenqiang Gong Published: 2026-04-16 Categories: cs.CR, cs.CV arXiv: https://arxiv.org/abs/2604.14973v1 A vision foundation model outputs an embedding vector for an image, which can be affected by common editing operations (e.g., JPEG compression, brightness, contrast adjustments). These common perturbations alter embedding vectors and may impact the performance of downstream tasks using these embeddings. In this work, we present the first systematic study on foundation models' robustness to such perturbations. We propose three robustness metrics and formulate five desired mathematical properties for these metrics, analyzing which properties they satisfy or violate. Using these metrics, we evaluate six industry-scale foundation models (OpenAI, Meta) across nine common perturbation categories, finding them generally non-robust. We also show that common perturbations degrade downstream application performance (e.g., classification accuracy) and that robustness values can predict performance impacts. Finally, we propose a fine-tuning approach to improve robustness without sacrificing utility. --- ### Explain the Flag: Contextualizing Hate Speech Beyond Censorship Authors: Jason Liartis, Eirini Kaldeli, Lambrini Gyftokosta, Eleftherios Chelioudakis, Orfeas Menis Mastromichalakis Published: 2026-04-16 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.14970v1 Hate, derogatory, and offensive speech remains a persistent challenge in online platforms and public discourse. While automated detection systems are widely used, most focus on censorship or removal, raising concerns for transparency and freedom of expression, and limiting opportunities to explain why content is harmful. To address these issues, explanatory approaches have emerged as a promising solution, aiming to make hate speech detection more transparent, accountable, and informative. In this paper, we present a hybrid approach that combines Large Language Models (LLMs) with three newly created and curated vocabularies to detect and explain hate speech in English, French, and Greek. Our system captures both inherently derogatory expressions tied to identity characteristics and direct group-targeted content through two complementary pipelines: one that detects and disambiguates problematic terms using the curated vocabularies, and one that leverages LLMs as context-aware evaluators of group-targeting content. The outputs are fused into grounded explanations that clarify why content is flagged. Human evaluation shows that our hybrid approach is accurate, with high-quality explanations, outperforming LLM-only baselines. --- ### Discovering Novel LLM Experts via Task-Capability Coevolution Authors: Andrew Dai, Boris Meinardus, Ciaran Regan, Yingtao Tian, Yujin Tang Published: 2026-04-16 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.14969v1 Frontier model developers aim to train models continually to possess emergent, diverse capabilities. To extend capabilities, the current pre-training and post-training paradigm requires manually starting training runs with static datasets or reward functions every time. Addressing this limitation, our work pursues the insight that open-endedness (via the coevolution of models and tasks) can discover models with increasingly novel skills in a single run. We introduce a new model development framework that extends coevolution to large language model (LLM) discovery, open-ended \textit{Assessment Coevolving with Diverse Capabilities} (AC/DC). AC/DC evolves both LLMs via model merging and natural language tasks via synthetic data generation. AC/DC discovers growing archives of LLMs that surpass the capabilities of larger LLMs while taking up less GPU memory. In particular, our LLM populations achieve a broader Coverage of expertise than other curated models or baselines on downstream benchmarks, without \textit{any} explicit benchmark optimization. Furthermore, AC/DC improves Coverage over time, continually innovates on tasks and models, and improves performance in multi-agent best-of-N selection. Our findings highlight the potential of coevolution as a means of discovering broader sets of capabilities from base LLMs. Overall, AC/DC brings us one step closer to a profoundly new paradigm of LLM development, where continual improvements to the diversity of model capabilities can be accelerated by leveraging existing models as stepping stones to increasingly powerful models. --- ### UniDoc-RL: Coarse-to-Fine Visual RAG with Hierarchical Actions and Dense Rewards Authors: Jun Wang, Shuo Tan, Zelong Sun, Tiancheng Gu, Yongle Zhao, Ziyong Feng, Kaicheng Yang, Zhiwu Lu Published: 2026-04-16 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2604.14967v2 Retrieval-Augmented Generation (RAG) extends Large Vision-Language Models (LVLMs) with external visual knowledge. However, existing visual RAG systems typically rely on generic retrieval signals that overlook the fine-grained visual semantics essential for complex reasoning. To address this limitation, we propose UniDoc-RL, a unified reinforcement learning framework in which an LVLM agent jointly performs retrieval, reranking, active visual perception, and reasoning. UniDoc-RL formulates visual information acquisition as a sequential decision-making problem with a hierarchical action space. Specifically, it progressively refines visual evidence from coarse-grained document retrieval to fine-grained image selection and active region cropping, allowing the model to suppress irrelevant content and attend to information-dense regions. For effective end-to-end training, we introduce a dense multi-reward scheme that provides task-aware supervision for each action. Based on Group Relative Policy Optimization (GRPO), UniDoc-RL aligns agent behavior with multiple objectives without relying on a separate value network. To support this training paradigm, we curate a comprehensive dataset of high-quality reasoning trajectories with fine-grained action annotations. Experiments on three benchmarks demonstrate that UniDoc-RL consistently surpasses state-of-the-art baselines, yielding up to 17.7% gains over prior RL-based methods. --- ### Calibration-Gated LLM Pseudo-Observations for Online Contextual Bandits Authors: Maksim Pershin, Ivan Golovanov, Pavel Baltabaev, Natalia Trankova Published: 2026-04-16 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2604.14961v1 Contextual bandit algorithms suffer from high regret during cold-start, when the learner has insufficient data to distinguish good arms from bad. We propose augmenting Disjoint LinUCB with LLM pseudo-observations: after each round, a large language model predicts counterfactual rewards for the unplayed arms, and these predictions are injected into the learner as weighted pseudo-observations. The injection weight is controlled by a calibration-gated decay schedule that tracks the LLM's prediction accuracy on played arms via an exponential moving average; high calibration error suppresses the LLM's influence, while accurate predictions receive higher weight during the critical early rounds. We evaluate on two contextual bandit environments - UCI Mushroom (2-arm, asymmetric rewards) and MIND-small (5-arm news recommendation) - and find that when equipped with a task-specific prompt, LLM pseudo-observations reduce cumulative regret by 19% on MIND relative to pure LinUCB. However, generic counterfactual prompt framing increases regret on both environments, demonstrating that prompt design is the dominant factor, more important than the choice of decay schedule or calibration gating parameters. We analyze the failure modes of calibration gating on domains with small prediction errors and provide a theoretical motivation for the bias-variance trade-off governing pseudo-observation weight. --- ### Frequency-Enhanced Dual-Subspace Networks for Few-Shot Fine-Grained Image Classification Authors: Meijia Wang, Guochao Wang, Haozhen Chu, Bin Yao, Weichuan Zhang, Yuan Wang, Junpo Yang Published: 2026-04-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.14958v1 Few-shot fine-grained image classification aims to recognize subcategories with high visual similarity using only a limited number of annotated samples. Existing metric learning-based methods typically rely solely on spatial domain features. Confined to this single perspective, models inevitably suffer from inherent texture biases, entangling essential structural details with high-frequency background noise. Furthermore, lacking cross-view geometric constraints, single-view metrics tend to overfit this noise, resulting in structural instability under few-shot conditions. To address these issues, this paper proposes the Frequency-Enhanced Dual-Subspace Network (FEDSNet). Specifically, FEDSNet utilizes the Discrete Cosine Transform (DCT) and a low-pass filtering mechanism to explicitly isolate low-frequency global structural components from spatial features, thereby suppressing background interference. Truncated Singular Value Decomposition (SVD) is employed to construct independent, low-rank linear subspaces for both spatial texture and frequency structural features. An adaptive gating mechanism is designed to dynamically fuse the projection distances from these dual views. This strategy leverages the structural stability of the frequency subspace to prevent the spatial subspace from overfitting to background features. Extensive experiments on four benchmark datasets - CUB-200-2011, Stanford Cars, Stanford Dogs, and FGVC-Aircraft - demonstrate that FEDSNet exhibits excellent classification performance and robustness, achieving highly competitive results compared to existing metric learning algorithms. Complexity analysis further confirms that the proposed network achieves a favorable balance between high accuracy and computational efficiency, providing an effective new paradigm for few-shot fine-grained visual recognition. --- ### MLDAS: Machine Learning Dynamic Algorithm Selection for Software-Defined Networking Security Authors: Pablo Benlloch, Oscar Romero, Antonio Leon, Jaime Lloret Published: 2026-04-16 Categories: cs.NI, cs.CR, cs.LG arXiv: https://arxiv.org/abs/2604.14957v1 Network security is a critical concern in the digital landscape of today, with users demanding secure browsing experiences and protection of their personal data. This study explores the dynamic integration of Machine Learning (ML) algorithms with Software-Defined Networking (SDN) controllers to enhance network security through adaptive decision mechanisms. The proposed approach enables the system to dynamically choose the most suitable ML algorithm based on the characteristics of the observed network traffic. This work examines the role of Intrusion Detection Systems (IDS) as a fundamental component of secure communication networks and discusses the limitations of SDN-based attack detection mechanisms. The proposed framework uses adaptive model selection to maintain reliable intrusion detection under varying network conditions. The study highlights the importance of analyzing traffic-type-based metrics to define effective classification rules and enhance the performance of ML models. Additionally, it addresses the risks of overfitting and underfitting, underscoring the critical role of hyperparameter tuning in optimizing model accuracy and generalization. The central contribution of this work is an automated mechanism that adaptively selects the most suitable ML algorithm according to real-time network conditions, prioritizing detection robustness and operational feasibility within SDN environments. --- ### Prompt-to-Gesture: Measuring the Capabilities of Image-to-Video Deictic Gesture Generation Authors: Hassan Ali, Doreen Jirak, Luca Müller, Stefan Wermter Published: 2026-04-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.14953v1 Gesture recognition research, unlike NLP, continues to face acute data scarcity, with progress constrained by the need for costly human recordings or image processing approaches that cannot generate authentic variability in the gestures themselves. Recent advancements in image-to-video foundation models have enabled the generation of photorealistic, semantically rich videos guided by natural language. These capabilities open up new possibilities for creating effort-free synthetic data, raising the critical question of whether video Generative AI models can augment and complement traditional human-generated gesture data. In this paper, we introduce and analyze prompt-based video generation to construct a realistic deictic gestures dataset and rigorously evaluate its effectiveness for downstream tasks. We propose a data generation pipeline that produces deictic gestures from a small number of reference samples collected from human participants, providing an accessible approach that can be leveraged both within and beyond the machine learning community. Our results demonstrate that the synthetic gestures not only align closely with real ones in terms of visual fidelity but also introduce meaningful variability and novelty that enrich the original data, further supported by superior performance of various deep models using a mixed dataset. These findings highlight that image-to-video techniques, even in their early stages, offer a powerful zero-shot approach to gesture synthesis with clear benefits for downstream tasks. --- ### RaTA-Tool: Retrieval-based Tool Selection with Multimodal Large Language Models Authors: Gabriele Mattioli, Evelyn Turri, Sara Sarto, Lorenzo Baraldi, Marcella Cornia, Lorenzo Baraldi, Rita Cucchiara Published: 2026-04-16 Categories: cs.CV, cs.AI, cs.CL, cs.MM arXiv: https://arxiv.org/abs/2604.14951v1 Tool learning with foundation models aims to endow AI systems with the ability to invoke external resources -- such as APIs, computational utilities, and specialized models -- to solve complex tasks beyond the reach of standalone language generation. While recent advances in Large Language Models (LLMs) and Multimodal Large Language Models (MLLMs) have expanded their reasoning and perception capabilities, existing tool-use methods are predominantly limited to text-only inputs and closed-world settings. Consequently, they struggle to interpret multimodal user instructions and cannot generalize to tools unseen during training. In this work, we introduce RaTA-Tool, a novel framework for open-world multimodal tool selection. Rather than learning direct mappings from user queries to fixed tool identifiers, our approach enables an MLLM to convert a multimodal query into a structured task description and subsequently retrieve the most appropriate tool by matching this representation against semantically rich, machine-readable tool descriptions. This retrieval-based formulation naturally supports extensibility to new tools without retraining. To further improve alignment between task descriptions and tool selection, we incorporate a preference-based optimization stage using Direct Preference Optimization (DPO). To support research in this setting, we also introduce the first dataset for open-world multimodal tool use, featuring standardized tool descriptions derived from Hugging Face model cards. Extensive experiments demonstrate that our approach significantly improves tool-selection performance, particularly in open-world, multimodal scenarios. --- ### Unsupervised feature selection using Bayesian Tucker decomposition Authors: Y-h. Taguchi, Yoh-ichi Mototake Published: 2026-04-16 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2604.14949v2 In this paper, we proposed Bayesian Tucker decomposition (BTuD) in which residual is supposed to obey Gaussian distribution analogous to linear regression. Although we have proposed an algorithm to perform the proposed BTuD, the conventional higher-order orthogonal iteration can generate Tucker decomposition consistent with the present implementation. Using the proposed BTuD, we can perform unsupervised feature selection successfully applied to various synthetic datasets, global coupled maps with randomized coupling strength, and gene expression profiles. Thus we can conclude that our newly proposed unsupervised feature selection method is promising. In addition to this, BTuD based unsupervised FE is expected to coincide with TD based unsupervised FE that were previously proposed and successfully applied to a wide range of problems. --- ### HRDexDB: A Paired Human-Robot Dataset for Cross-Embodiment Dexterous Grasping Authors: Jongbin Lim, Taeyun Ha, Mingi Choi, Jisoo Kim, Byungjun Kim, Subin Jeon, Hanbyul Joo Published: 2026-04-16 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2604.14944v2 We present HRDexDB, a paired cross-embodiment dexterous grasping dataset of high-fidelity dexterous grasping sequences featuring both human and diverse robotic hands. Unlike existing datasets, HRDexDB provides a comprehensive collection of grasping trajectories across human hands and multiple robot hand embodiments, spanning 100 diverse objects. Leveraging state-of-the-art vision methods and a dedicated multi-camera system, HRDexDB offers high-precision spatiotemporal 3D ground-truth motion for both the agent and the manipulated object. The dataset comprises 2.1K grasping trials, each enriched with synchronized visual and kinematic modalities, with contact-force signals available for tactile-enabled robotic hands. By providing closely aligned captures of human dexterity and robotic execution on the same target objects under comparable grasping motions, HRDexDB serves as a foundational benchmark for cross-embodiment dexterous manipulation. --- ### Text2Arch: A Dataset for Generating Scientific Architecture Diagrams from Natural Language Descriptions Authors: Shivank Garg, Sankalp Mittal, Manish Gupta Published: 2026-04-16 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.14941v1 Communicating complex system designs or scientific processes through text alone is inefficient and prone to ambiguity. A system that automatically generates scientific architecture diagrams from text with high semantic fidelity can be useful in multiple applications like enterprise architecture visualization, AI-driven software design, and educational content creation. Hence, in this paper, we focus on leveraging language models to perform semantic understanding of the input text description to generate intermediate code that can be processed to generate high-fidelity architecture diagrams. Unfortunately, no clean large-scale open-access dataset exists, implying lack of any effective open models for this task. Hence, we contribute a comprehensive dataset, \system, comprising scientific architecture images, their corresponding textual descriptions, and associated DOT code representations. Leveraging this resource, we fine-tune a suite of small language models, and also perform in-context learning using GPT-4o. Through extensive experimentation, we show that \system{} models significantly outperform existing baseline models like DiagramAgent and perform at par with in-context learning-based generations from GPT-4o. We make the code, data and models publicly available. --- ### XQ-MEval: A Dataset with Cross-lingual Parallel Quality for Benchmarking Translation Metrics Authors: Jingxuan Liu, Zhi Qu, Jin Tei, Hidetaka Kamigaito, Lemao Liu, Taro Watanabe Published: 2026-04-16 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.14934v2 Automatic evaluation metrics are essential for building multilingual translation systems. The common practice of evaluating these systems is averaging metric scores across languages, yet this is suspicious since metrics may suffer from cross-lingual scoring bias, where translations of equal quality receive different scores across languages. This problem has not been systematically studied because no benchmark exists that provides parallel-quality instances across languages, and expert annotation is not realistic. In this work, we propose XQ-MEval, a semi-automatically built dataset covering nine translation directions, to benchmark translation metrics. Specifically, we inject MQM-defined errors into gold translations automatically, filter them by native speakers for reliability, and merge errors to generate pseudo translations with controllable quality. These pseudo translations are then paired with corresponding sources and references to form triplets used in assessing the qualities of translation metrics. Using XQ-MEval, our experiments on nine representative metrics reveal the inconsistency between averaging and human judgment and provide the first empirical evidence of cross-lingual scoring bias. Finally, we propose a normalization strategy derived from XQ-MEval that aligns score distributions across languages, improving the fairness and reliability of multilingual metric evaluation. --- ### Generative Data Augmentation for Skeleton Action Recognition Authors: Xu Dong, Wanqing Li, Anthony Adeyemi-Ejeye, Andrew Gilbert Published: 2026-04-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.14933v1 Skeleton-based human action recognition is a powerful approach for understanding human behaviour from pose data, but collecting large-scale, diverse, and well-annotated 3D skeleton datasets is both expensive and labor-intensive. To address this challenge, we propose a conditional generative pipeline for data augmentation in skeleton action recognition. Our method learns the distribution of real skeleton sequences under the constraint of action labels, enabling the synthesis of diverse and high-fidelity data. Even with limited training samples, it can effectively generate skeleton sequences and achieve competitive recognition performance in low-data scenarios, demonstrating strong generalisation in downstream tasks. Specifically, we introduce a Transformer-based encoder-decoder architecture, combined with a generative refinement module and a dropout mechanism, to balance fidelity and diversity during sampling. Experiments on HumanAct12 and the refined NTU-RGBD (NTU-VIBE) dataset show that our approach consistently improves the accuracy of multiple skeleton-based action recognition models, validating its effectiveness in both few-shot and full-data settings. The source code can be found at here. --- ### WavAlign: Enhancing Intelligence and Expressiveness in Spoken Dialogue Models via Adaptive Hybrid Post-Training Authors: Yifu Chen, Shengpeng Ji, Qian Chen, Tianle Liang, Yangzhuo Li, Ziqing Wang, Wen Wang, Jingyu Lu, Haoxiao Wang, Xueyi Pu, Fan Zhuo, Zhou Zhao Published: 2026-04-16 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.14932v1 End-to-end spoken dialogue models have garnered significant attention because they offer a higher potential ceiling in expressiveness and perceptual ability than cascaded systems. However, the intelligence and expressiveness of current open-source spoken dialogue models often remain below expectations. Motivated by the success of online reinforcement learning(RL) in other domains, one might attempt to directly apply preference optimization to spoken dialogue models, yet this transfer is non-trivial. We analyze these obstacles from the perspectives of reward modeling and rollout sampling, focusing on how sparse preference supervision interacts with dense speech generation under shared-parameter updates. Based on the analysis, we propose a modality-aware adaptive post-training recipe that makes RL practical for spoken dialogue: it constrains preference updates to the semantic channel and improves acoustic behavior via explicit anchoring, while dynamically regulating their mixture from rollout statistics to avoid unreliable preference gradients. We evaluate the method across multiple spoken dialogue benchmarks and representative architectures, and observe consistent improvements in semantic quality and speech expressiveness. --- ### Learning to Concatenate Quantum Codes Authors: Nico Meyer, Christopher Mutschler, Dominik Seuß, Andreas Maier, Daniel D. Scherer Published: 2026-04-16 Categories: quant-ph, cs.LG arXiv: https://arxiv.org/abs/2604.14931v2 Concatenating quantum error correction codes scales error correction capability by driving logical error rates down double-exponentially across levels. However, the noise structure shifts under concatenation, making it hard to choose an optimal code sequence. We automate this choice by estimating the effective noise channel after each level and selecting the next code accordingly. In particular, we use learning-based methods to tailor small, non-additive encoders when the noise exhibits sufficient structure, then switch to standard codes once the noise is nearly uniform. In simulations, this level-wise adaptation achieves a target logical error rate with far fewer qubits than concatenating stabilizer codes alone--reducing qubit counts by up to two orders of magnitude for strongly structured noise. Therefore, this hybrid, learning-based strategy offers a promising tool for early fault-tolerant quantum computing. --- ### Learning to Concatenate Quantum Codes Authors: Nico Meyer, Christopher Mutschler, Dominik Seuß, Andreas Maier, Daniel D. Scherer Published: 2026-04-16 Categories: quant-ph, cs.LG arXiv: https://arxiv.org/abs/2604.14931v1 Concatenating quantum error correction codes scales error correction capability by driving logical error rates down double-exponentially across levels. However, the noise structure shifts under concatenation, making it hard to choose an optimal code sequence. We automate this choice by estimating the effective noise channel after each level and selecting the next code accordingly. In particular, we use learning-based methods to tailor small, non-additive encoders when the noise exhibits sufficient structure, then switch to standard codes once the noise is nearly uniform. In simulations, this level-wise adaptation achieves a target logical error rate with far fewer qubits than concatenating stabilizer codes alone--reducing qubit counts by up to two orders of magnitude for strongly structured noise. Therefore, this hybrid, learning-based strategy offers a promising tool for early fault-tolerant quantum computing. --- ### IE as Cache: Information Extraction Enhanced Agentic Reasoning Authors: Hang Lv, Sheng Liang, Hongchao Gu, Wei Guo, Defu Lian, Yong Liu, Hao Wang, Enhong Chen Published: 2026-04-16 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.14930v1 Information Extraction aims to distill structured, decision-relevant information from unstructured text, serving as a foundation for downstream understanding and reasoning. However, it is traditionally treated merely as a terminal objective: once extracted, the resulting structure is often consumed in isolation rather than maintained and reused during multi-step inference. Moving beyond this, we propose \textit{IE-as-Cache}, a framework that repurposes IE as a cognitive cache to enhance agentic reasoning. Drawing inspiration from hierarchical computer memory, our approach combines query-driven extraction with cache-aware reasoning to dynamically maintain compact intermediate information and filter noise. Experiments on challenging benchmarks across diverse LLMs demonstrate significant improvements in reasoning accuracy, indicating that IE can be effectively repurposed as a reusable cognitive resource and offering a promising direction for future research on downstream uses of IE. --- ### Hybrid Latents: Geometry-Appearance-Aware Surfel Splatting Authors: Neel Kelkar, Simon Niedermayr, Klaus Engel, Rüdiger Westermann Published: 2026-04-16 Categories: cs.CV, cs.GR arXiv: https://arxiv.org/abs/2604.14928v2 We introduce a hybrid Gaussian-hash-grid radiance representation for reconstructing 2D Gaussian scene models from multi-view images. Similar to NeST splatting, our approach reduces the entanglement between geometry and appearance common in NeRF-based models, but adds per-Gaussian latent features alongside hash-grid features to bias the optimizer toward a separation of low- and high-frequency scene components. This explicit frequency-based decomposition reduces the tendency of high-frequency texture to compensate for geometric errors. Encouraging Gaussians with hard opacity falloffs further strengthens the separation between geometry and appearance, improving both geometry reconstruction and rendering efficiency. Finally, probabilistic pruning combined with a sparsity-inducing BCE opacity loss allows redundant Gaussians to be turned off, yielding a minimal set of Gaussians sufficient to represent the scene. Using both synthetic and real-world datasets, we compare against the state of the art in Gaussian-based novel-view synthesis and demonstrate superior reconstruction fidelity with an order of magnitude fewer primitives. --- ### STEP-Parts: Geometric Partitioning of Boundary Representations for Large-Scale CAD Processing Authors: Shen Fan, Mikołaj Kida, Przemyslaw Musialski Published: 2026-04-16 Categories: cs.GR, cs.AI, cs.CV, cs.LG arXiv: https://arxiv.org/abs/2604.14927v2 Many CAD learning pipelines discretize Boundary Representations (B-Reps) into triangle meshes, discarding analytic surface structure and topological adjacency and thereby weakening consistent instance-level analysis. We present STEP-Parts, a deterministic CAD-to-supervision toolchain that extracts geometric instance partitions directly from raw STEP B-Reps and transfers them to tessellated carriers through retained source-face correspondence, yielding instance labels and metadata for downstream learning and evaluation. The construction merges adjacent B-Rep faces only when they share the same analytic primitive type and satisfy a near-tangent continuity criterion. On ABC, same-primitive dihedral angles are strongly bimodal, yielding a threshold-insensitive low-angle regime for part extraction. Because the partition is defined on intrinsic B-Rep topology rather than on a particular triangulation, the resulting boundaries remain stable under changes in tessellation. Applied to the DeepCAD subset of ABC, the pipeline processes approximately 180{,}000 models in under six hours on a consumer CPU. We release code and precomputed labels, and show that STEP-Parts serves both as a tessellation-robust geometric reference and as a useful supervision source in two downstream probes: an implicit reconstruction--segmentation network and a dataset-level point-based backbone. --- ### Improving Sparse Autoencoder with Dynamic Attention Authors: Dongsheng Wang, Jinsen Zhang, Dawei Su, Hui Huang Published: 2026-04-16 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2604.14925v1 Recently, sparse autoencoders (SAEs) have emerged as a promising technique for interpreting activations in foundation models by disentangling features into a sparse set of concepts. However, identifying the optimal level of sparsity for each neuron remains challenging in practice: excessive sparsity can lead to poor reconstruction, whereas insufficient sparsity may harm interpretability. While existing activation functions such as ReLU and TopK provide certain sparsity guarantees, they typically require additional sparsity regularization or cherry-picked hyperparameters. We show in this paper that dynamically sparse attention mechanisms using sparsemax can bridge this trade-off, due to their ability to determine the activation numbers in a data-dependent manner. Specifically, we first explore a new class of SAEs based on the cross-attention architecture with the latent features as queries and the learnable dictionary as the key and value matrices. To encourage sparse pattern learning, we employ a sparsemax-based attention strategy that automatically infers a sparse set of elements according to the complexity of each neuron, resulting in a more flexible and general activation function. Through comprehensive evaluation and visualization, we show that our approach successfully achieves lower reconstruction loss while producing high-quality concepts, particularly in top-n classification tasks. --- ### LongAct: Harnessing Intrinsic Activation Patterns for Long-Context Reinforcement Learning Authors: Bowen Ping, Zijun Chen, Tingfeng Hui, Qize Yu, Chenxuan Li, Junchi Yan, Baobao Chang Published: 2026-04-16 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2604.14922v1 Reinforcement Learning (RL) has emerged as a critical driver for enhancing the reasoning capabilities of Large Language Models (LLMs). While recent advancements have focused on reward engineering or data synthesis, few studies exploit the model's intrinsic representation characteristics to guide the training process. In this paper, we first observe the presence of high-magnitude activations within the query and key vectors when processing long contexts. Drawing inspiration from model quantization -- which establishes the criticality of such high-magnitude activations -- and the insight that long-context reasoning inherently exhibits a sparse structure, we hypothesize that these weights serve as the pivotal drivers for effective model optimization. Based on this insight, we propose LongAct, a strategy that shifts from uniform to saliency-guided sparse updates. By selectively updating only the weights associated with these significant activations, LongAct achieves an approximate 8% improvement on LongBench v2 and enhances generalization on the RULER benchmark. Furthermore, our method exhibits remarkable universality, consistently boosting performance across diverse RL algorithms such as GRPO and DAPO. Extensive ablation studies suggest that focusing on these salient features is key to unlocking long-context potential. --- ### Dual-Axis Generative Reward Model Toward Semantic and Turn-taking Robustness in Interactive Spoken Dialogue Models Authors: Yifu Chen, Shengpeng Ji, Zhengqing Liu, Qian Chen, Wen Wang, Ziqing Wang, Yangzhuo Li, Tianle Liang, Zhou Zhao Published: 2026-04-16 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.14920v1 Achieving seamless, human-like interaction remains a key challenge for full-duplex spoken dialogue models (SDMs). Reinforcement learning (RL) has substantially enhanced text- and vision-language models, while well-designed reward signals are crucial for the performance of RL. We consider RL a promising strategy to address the key challenge for SDMs. However, a fundamental barrier persists: prevailing automated metrics for assessing interaction quality rely on superficial proxies, such as behavioral statistics or timing-prediction accuracy, failing to provide reliable reward signals for RL. On the other hand, human evaluations, despite their richness, remain costly, inconsistent, and difficult to scale. We tackle this critical barrier by proposing a Dual-Axis Generative Reward Model, which is trained to understand complex interaction dynamics using a detailed taxonomy and an annotated dataset, produces a single score and, crucially, provides separate evaluations for semantic quality and interaction timing. Such dual outputs furnish precise diagnostic feedback for SDMs and deliver a dependable, instructive reward signal suitable for online reinforcement learning. Our model achieves state-of-the-art performance on interaction-quality assessment across a wide spectrum of datasets, spanning synthetic dialogues and complex real-world interactions. --- ### Beyond Prompts: Unconditional 3D Inversion for Out-of-Distribution Shapes Authors: Victoria Yue Chen, Emery Pierson, Léopold Maillard, Maks Ovsjanikov Published: 2026-04-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.14914v2 Text-driven inversion of generative models is a core paradigm for manipulating 2D or 3D content, unlocking numerous applications such as text-based editing, style transfer, or inverse problems. However, it relies on the assumption that generative models remain sensitive to natural language prompts. We demonstrate that for state-of-the-art native text-to-3D generative models, this assumption often collapses. We identify a critical failure mode where generation trajectories are drawn into latent "sink traps": regions where the model becomes insensitive to prompt modifications. In these regimes, changes to the input text fail to alter internal representations in a way that alters the output geometry. Crucially, we observe that this is not a limitation of the model's \textit{geometric} expressivity; the same generative models possess the ability to produce a vast diversity of shapes but, as we demonstrate, become insensitive to out-of-distribution \textit{text} guidance. We investigate this behavior by analyzing the sampling trajectories of the generative model, and find that complex geometries can still be represented and produced by leveraging the model's unconditional generative prior. This leads to a more robust framework for text-based 3D shape editing that bypasses latent sinks by decoupling a model's geometric representation power from its linguistic sensitivity. Our approach addresses the limitations of current 3D pipelines and enables high-fidelity semantic manipulation of out-of-distribution 3D shapes. Project webpage: https://daidedou.sorpi.fr/publication/beyondprompts --- ### Reward-Aware Trajectory Shaping for Few-step Visual Generation Authors: Rui Li, Bingyu Li, Yuanzhi Liang, Haibin Huang, Chi Zhang, XueLong Li Published: 2026-04-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.14910v4 Achieving high-fidelity generation in extremely few sampling steps has long been a central goal of generative modeling. Existing approaches largely rely on distillation-based frameworks to compress the original multi-step denoising process into a few-step generator. However, such methods inherently constrain the student to imitate a stronger multi-step teacher, imposing the teacher as an upper bound on student performance. We argue that introducing \textbf{preference alignment awareness} enables the student to optimize toward reward-preferred generation quality, potentially surpassing the teacher instead of being restricted to rigid teacher imitation. To this end, we propose \textbf{Reward-Aware Trajectory Shaping (RATS)}, a lightweight framework for preference-aligned few-step generation. Specifically, teacher and student latent trajectories are aligned at key denoising stages through horizon matching, while a \textbf{reward-aware gate} is introduced to adaptively regulate teacher guidance based on their relative reward performance. Trajectory shaping is strengthened when the teacher achieves higher rewards, and relaxed when the student matches or surpasses the teacher, thereby enabling continued reward-driven improvement. By seamlessly integrating trajectory distillation, reward-aware gating, and preference alignment, RATS effectively transfers preference-relevant knowledge from high-step generators without incurring additional test-time computational overhead. Experimental results demonstrate that RATS substantially improves the efficiency--quality trade-off in few-step visual generation, significantly narrowing the gap between few-step students and stronger multi-step generators. --- ### Reward-Aware Trajectory Shaping for Few-step Visual Generation Authors: Rui Li, Bingyu Li, Yuanzhi Liang, Haibin Huang, Chi Zhang, XueLong Li Published: 2026-04-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.14910v3 Achieving high-fidelity generation in extremely few sampling steps has long been a central goal of generative modeling. Existing approaches largely rely on distillation-based frameworks to compress the original multi-step denoising process into a few-step generator. However, such methods inherently constrain the student to imitate a stronger multi-step teacher, imposing the teacher as an upper bound on student performance. We argue that introducing \textbf{preference alignment awareness} enables the student to optimize toward reward-preferred generation quality, potentially surpassing the teacher instead of being restricted to rigid teacher imitation. To this end, we propose \textbf{Reward-Aware Trajectory Shaping (RATS)}, a lightweight framework for preference-aligned few-step generation. Specifically, teacher and student latent trajectories are aligned at key denoising stages through horizon matching, while a \textbf{reward-aware gate} is introduced to adaptively regulate teacher guidance based on their relative reward performance. Trajectory shaping is strengthened when the teacher achieves higher rewards, and relaxed when the student matches or surpasses the teacher, thereby enabling continued reward-driven improvement. By seamlessly integrating trajectory distillation, reward-aware gating, and preference alignment, RATS effectively transfers preference-relevant knowledge from high-step generators without incurring additional test-time computational overhead. Experimental results demonstrate that RATS substantially improves the efficiency--quality trade-off in few-step visual generation, significantly narrowing the gap between few-step students and stronger multi-step generators. --- ### Multi-User mmWave Beam and Rate Adaptation via Combinatorial Satisficing Bandits Authors: Emre Özyıldırım, Barış Yaycı, Umut Eren Akturk, Cem Tekin Published: 2026-04-16 Categories: cs.LG, eess.SY, stat.ML arXiv: https://arxiv.org/abs/2604.14908v1 We study downlink beam and rate adaptation in a multi-user mmWave MISO system where multiple base stations (BSs), each using analog beamforming from finite codebooks, serve multiple single-antenna user equipments (UEs) with a unique beam per UE and discrete data transmission rates. BSs learn about transmission success based on ACK/NACK feedback. To encode service goals, we introduce a satisficing throughput threshold $τ_r$ and cast joint beam and rate adaptation as a combinatorial semi-bandit over beam-rate tuples. Within this framework, we propose SAT-CTS, a lightweight, threshold-aware policy that blends conservative confidence estimates with posterior sampling, steering learning toward meeting $τ_r$ rather than merely maximizing. Our main theoretical contribution provides the first finite-time regret bounds for combinatorial semi-bandits with satisficing objective: when $τ_r$ is realizable, we upper bound the cumulative satisficing regret to the target with a time-independent constant, and when $τ_r$ is non-realizable, we show that SAT-CTS incurs only a finite expected transient outside committed CTS rounds, after which its regret is governed by the sum of the regret contributions of restarted CTS rounds, yielding an $O((\log T)^2)$ standard regret bound. On the practical side, we evaluate the performance via cumulative satisficing regret to $τ_r$ alongside standard regret and fairness. Experiments with time-varying sparse multipath channels show that SAT-CTS consistently reduces satisficing regret and maintains competitive standard regret, while achieving favorable average throughput and fairness across users, indicating that feedback-efficient learning can equitably allocate beams and rates to meet QoS targets without channel state knowledge. --- ### Comparison of Modern Multilingual Text Embedding Techniques for Hate Speech Detection Task Authors: Evaldas Vaiciukynas, Paulius Danenas, Linas Ablonskis, Algirdas Sukys, Edgaras Dambrauskas, Voldemaras Zitkus, Rita Butkiene, Rimantas Butleris Published: 2026-04-16 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2604.14907v1 Online hate speech and abusive language pose a growing challenge for content moderation, especially in multilingual settings and for low-resource languages such as Lithuanian. This paper investigates to what extent modern multilingual sentence embedding models can support accurate hate speech detection in Lithuanian, Russian, and English, and how their performance depends on downstream modeling choices and feature dimensionality. We introduce LtHate, a new Lithuanian hate speech corpus derived from news portals and social networks, and benchmark six modern multilingual encoders (potion, gemma, bge, snow, jina, e5) on LtHate, RuToxic, and EnSuperset using a unified Python pipeline. For each embedding, we train both a one class HBOS anomaly detector and a two class CatBoost classifier, with and without principal component analysis (PCA) compression to 64-dimensional feature vectors. Across all datasets, two class supervised models consistently and substantially outperform one class anomaly detection, with the best configurations achieving up to 80.96% accuracy and AUC ROC of 0.887 in Lithuanian (jina), 92.19% accuracy and AUC ROC of 0.978 in Russian (e5), and 77.21% accuracy and AUC ROC of 0.859 in English (e5 with PCA). PCA compression preserves almost all discriminative power in the supervised setting, while showing some negative impact for the unsupervised anomaly detection case. These results demonstrate how modern multilingual sentence embeddings combined with gradient boosted decision trees provide robust soft-computing solutions for multilingual hate speech detection applications. --- ### Unraveling the Mechanism of Drug Binding to SARS-CoV-2 RNA Pseudoknot with Thermodynamics-Driven Machine Learning Authors: Mariia Ivonina, Jakub Rydzewski Published: 2026-04-16 Categories: physics.bio-ph, cs.LG arXiv: https://arxiv.org/abs/2604.14906v4 The pseudoknot secondary structure in SARS-CoV-2 RNA is essential for regulating protein synthesis through $-$1 programmed ribosomal frameshifting ($-1$ PRF), a mechanism that allows the virus to generate both structural and non-structural proteins from overlapping reading frames. This pseudoknot exhibits both threaded and unthreaded long-lived topologies. The influence of ligand binding on its folding is a process critical for the development of $-$1 PRF small-molecule inhibitors. Understanding this process through unbiased molecular dynamics (MD) simulations can be facilitated by introducing collective variables (CVs) that capture the corresponding slowest dynamical modes. Here, we use spectral map (SM), a thermodynamics-driven machine learning technique, to learn such CVs directly from all-atom MD trajectories of the SARS-CoV-2 RNA pseudoknot in complex with the $-$1 PRF inhibitor merafloxacin and its two structural analogs in neutral and ionized forms. Free-energy landscapes (FELs) derived from the learned CVs indicate that ligand-induced destabilization is topology-selective. In the threaded pseudoknot, the inhibitors destabilize the S2 stem, while in the unthreaded pseudoknot, destabilization occurs in the S1 and S3 stems. Furthermore, the extent to which each ligand reshapes the FEL matches experimentally reported antiviral potency, whereas the protonation state qualitatively alters dynamics within the same RNA topology. Overall, our results show how pseudoknot topology, ligand type, and protonation state collectively influence the slow conformational dynamics of viral RNA and establish physiological protonation as a critical factor for modeling RNA-targeted drug action. --- ### ADAPT: Benchmarking Commonsense Planning under Unspecified Affordance Constraints Authors: Pei-An Chen, Yong-Ching Liang, Jia-Fong Yeh, Hung-Ting Su, Yi-Ting Chen, Min Sun, Winston Hsu Published: 2026-04-16 Categories: cs.AI, cs.CL, cs.CV, cs.RO arXiv: https://arxiv.org/abs/2604.14902v2 Intelligent embodied agents should not simply follow instructions, as real-world environments often involve unexpected conditions and exceptions. However, existing methods usually focus on directly executing instructions, without considering whether the target objects can actually be manipulated, meaning they fail to assess available affordances. To address this limitation, we introduce DynAfford, a benchmark that evaluates embodied agents in dynamic environments where object affordances may change over time and are not specified in the instruction. DynAfford requires agents to perceive object states, infer implicit preconditions, and adapt their actions accordingly. To enable this capability, we introduce ADAPT, a plug-and-play module that augments existing planners with explicit affordance reasoning. Experiments demonstrate that incorporating ADAPT significantly improves robustness and task success across both seen and unseen environments. We also show that a domain-adapted, LoRA-finetuned vision-language model used as the affordance inference backend outperforms a commercial LLM (GPT-4o), highlighting the importance of task-aligned affordance grounding. --- ### Governing Reflective Human-AI Collaboration: A Framework for Epistemic Scaffolding and Traceable Reasoning Authors: Rikard Rosenbacke, Carl Rosenbacke, Victor Rosenbacke, Martin McKee Published: 2026-04-16 Categories: cs.AI, cs.CY, cs.HC arXiv: https://arxiv.org/abs/2604.14898v1 Large language models have advanced rapidly, from pattern recognition to emerging forms of reasoning, yet they remain confined to linguistic simulation rather than grounded understanding. They can produce fluent outputs that resemble reflection, but lack temporal continuity, causal feedback, and anchoring in real-world interaction. This paper proposes a complementary approach in which reasoning is treated as a relational process distributed between human and model rather than an internal capability of either. Building on recent work on "System-2" learning, we relocate reflective reasoning to the interaction layer. Instead of engineering reasoning solely within models, we frame it as a cognitive protocol that can be structured, measured, and governed using existing systems. This perspective emphasizes collaborative intelligence, combining human judgment and contextual understanding with machine speed, memory, and associative capacity. We introduce "The Architect's Pen" as a practical method. Like an architect who thinks through drawing, the human uses the model as an external medium for structured reflection. By embedding phases of articulation, critique, and revision into human-AI interaction, the dialogue itself becomes a reasoning loop: human abstraction -> model articulation -> human reflection. This reframes the question from whether the model can think to whether the human-AI system can reason. The framework enables auditable reasoning traces and supports alignment with emerging governance standards, including the EU AI Act and ISO/IEC 42001. It provides a practical path toward more transparent, controllable, and accountable AI use without requiring new model architectures. --- ### Toward Agentic RAG for Ukrainian Authors: Marta Sumyk, Oleksandr Kosovan Published: 2026-04-16 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.14896v1 We present an initial investigation into Agentic Retrieval-Augmented Generation (RAG) for Ukrainian, conducted within the UNLP 2026 Shared Task on Multi-Domain Document Understanding. Our system combines two-stage retrieval (BGE-M3 with BGE reranking) with a lightweight agentic layer performing query rephrasing and answer-retry loops on top of Qwen2.5-3B-Instruct. Our analysis reveals that retrieval quality is the primary bottleneck: agentic retry mechanisms improve answer accuracy but the overall score remains constrained by document and page identification. We discuss practical limitations of offline agentic pipelines and outline directions for combining stronger retrieval with more advanced agentic reasoning for Ukrainian. --- ### Beyond Importance Sampling: Rejection-Gated Policy Optimization Authors: Ziwu Sun, Zhen Gao, Jiyong Zhang, Jiaheng Li Published: 2026-04-16 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2604.14895v1 We propose a new perspective on policy optimization: rather than reweighting all samples by their importance ratios, an optimizer should select which samples are trustworthy enough to drive a policy update. Building on this view, we introduce Rejection-Gated Policy Optimization (RGPO), which replaces the importance sampling ratio r_theta = pi_theta / pi_old with a smooth, differentiable acceptance gate alpha_theta(s, a) = g(r_theta(s, a)) in the range (0, 1). Unlike prior work that applies rejection sampling as a data-level heuristic before training, RGPO elevates rejection to an optimization principle: the gate participates directly in gradient computation and is implicitly updated alongside the policy. RGPO provides a unified framework: the policy gradients of TRPO, PPO, and REINFORCE all correspond to specific choices of the effective gradient weight w(r) = g'(r) * r. We prove that RGPO guarantees finite, bounded gradient variance even when importance sampling ratios are heavy-tailed (where IS variance diverges). We further show that RGPO incurs only a bounded, controllable bias and provides an approximate monotonic policy improvement guarantee analogous to TRPO. RGPO matches PPO in computational cost, requires no second-order optimization, and extends naturally to RLHF-style preference alignment. In online preference fine-tuning of Qwen2.5-1.5B-Instruct on Anthropic HH-RLHF (n = 3 seeds), RGPO uses a dual-ratio gate that anchors learning to both the previous policy and the reference model, achieving a Pareto-dominant outcome: the highest reward among online RL methods (+14.8% vs. PPO-RLHF) and the lowest KL divergence to the reference model (-16.0% vs. PPO-RLHF, -53.1% vs. GRPO). --- ### Can LLMs Accurately Score Medical Diagnoses and Clinical Reasoning? Authors: Amy Rouillard, Sitwala Mundia, Linda Camara, Ziyaad Dangor, Michael Cameron Gramanie, Ismail Kalla, Shabir A. Madhi, Kajal Morar, Marlvin T. Ncube, Haroon Saloojee, Bruce A. Bassett Published: 2026-04-16 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2604.14892v4 Evaluating medical AI systems using expert clinician panels is costly and slow, motivating the use of large language models (LLMs) as alternative adjudicators. Here, we evaluate an LLM Jury, composed of three frontier AI models, for scoring 3334 diagnoses on 300 real-world low- and middle-income country (LMIC) hospital cases. Both LLM- and clinician-generated diagnoses are scored against expert panel diagnoses across four dimensions: diagnosis, differential diagnosis, clinical reasoning, and negative treatment risk. The LLM Jury scores are compared with expert and independent re-scoring panel scores to assess error metrics, inter-rater agreement, severe-risk errors, and the effect of post hoc calibration using isotonic regression. In our data, we find that: (i) the uncalibrated LLM Jury scores preserve ordinal agreement with the expert clinician panel scores, but are systematically lower; (ii) the probability of severe-risk errors is lower for the LLM Jury than the human expert re-score panels; (iii) the LLM Jury combined with LLM diagnoses can be used to identify diagnoses at high risk of error, enabling targeted expert review and improved panel efficiency; (iv) the calibrated LLM Jury scores and rankings of diagnosing agents show excellent agreement with those of the primary expert panels; (v) LLM Jury models show no self-preference bias, they did not score diagnoses generated by their own underlying model or models from the same vendor more (or less) favourably than those generated by other models. Together, these results provide evidence that a calibrated LLM Jury is a trustworthy and reliable proxy for expert clinician evaluation in medical AI benchmarking. Confirming these findings in other clinical settings is an important direction for future work. ---