# Research Papers — 2026-04 · bundle page 130 of 233 > Full-text markdown of papers #6451–6500 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/130 [← Previous bundle](https://aipod.dev/papers/archive/2026-04/page/129.md) [Next bundle →](https://aipod.dev/papers/archive/2026-04/page/131.md) ### PipeLive: Efficient Live In-place Pipeline Parallelism Reconfiguration for Dynamic LLM Serving Authors: Xu Bai, Muhammed Tawfiqul Islam, Chen Wang, Adel N. Toosi Published: 2026-04-14 Categories: cs.DC, cs.LG arXiv: https://arxiv.org/abs/2604.12171v2 Pipeline parallelism (PP) is widely used to partition layers of large language models (LLMs) across GPUs, enabling scalable inference for large models. However, existing systems rely on static PP configurations that fail to adapt to dynamic settings, such as serverless platforms and heterogeneous GPU environments. Reconfiguring PP by stopping and redeploying service incurs prohibitive downtime, so reconfiguration must instead proceed live and in place, without interrupting inference. However, live in-place PP reconfiguration is fundamentally challenging. GPUs are already saturated with model weights and KV cache, leaving little room for new layer placements and necessitating KV cache resizing, at odds with systems like vLLM that preallocate for throughput. Moreover, maintaining KV consistency during execution is difficult: stop-and-copy introduces large pauses, while background synchronization risks inconsistency as states evolve. We present PipeLive, which enables live in-place PP reconfiguration with minimal disruption. PipeLive introduces a redesigned KV cache layout together with a co-designed extension to PageAttention, forming a unified mechanism for live KV resizing. It further adopts an incremental KV patching mechanism, inspired by live virtual machine migration, to synchronize KV states between source and target configurations and identify a safe switch point. PipeLive achieves a 2.5X reduction in time-to-first-token (TTFT) without KV cache overflow compared to disabling KV resizing. Furthermore, compared to a variant without KV patching, it reduces reconfiguration overhead from seconds to under 10ms, and improves TTFT and time-per-output-token (TPOT) by up to 54.7% and 14.7%, respectively. --- ### PipeLive: Efficient Live In-place Pipeline Parallelism Reconfiguration for Dynamic LLM Serving Authors: Xu Bai, Muhammed Tawfiqul Islam, Chen Wang, Adel N. Toosi Published: 2026-04-14 Categories: cs.DC, cs.LG arXiv: https://arxiv.org/abs/2604.12171v1 Pipeline parallelism (PP) is widely used to partition layers of large language models (LLMs) across GPUs, enabling scalable inference for large models. However, existing systems rely on static PP configurations that fail to adapt to dynamic settings, such as serverless platforms and heterogeneous GPU environments. Reconfiguring PP by stopping and redeploying service incurs prohibitive downtime, so reconfiguration must instead proceed live and in place, without interrupting inference. However, live in-place PP reconfiguration is fundamentally challenging. GPUs are already saturated with model weights and KV cache, leaving little room for new layer placements and necessitating KV cache resizing, at odds with systems like vLLM that preallocate for throughput. Moreover, maintaining KV consistency during execution is difficult: stop-and-copy introduces large pauses, while background synchronization risks inconsistency as states evolve. We present PipeLive, which enables live in-place PP reconfiguration with minimal disruption. PipeLive introduces a redesigned KV cache layout together with a co-designed extension to PageAttention, forming a unified mechanism for live KV resizing. It further adopts an incremental KV patching mechanism, inspired by live virtual machine migration, to synchronize KV states between source and target configurations and identify a safe switch point. PipeLive achieves a 2.5X reduction in time-to-first-token (TTFT) without KV cache overflow compared to disabling KV resizing. Furthermore, compared to a variant without KV patching, it reduces reconfiguration overhead from seconds to under 10ms, and improves TTFT and time-per-output-token (TPOT) by up to 54.7% and 14.7%, respectively. --- ### Fully Homomorphic Encryption on Llama 3 model for privacy preserving LLM inference Authors: Anes Abdennebi, Nadjia Kara, Laaziz Lahlou Published: 2026-04-14 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2604.12168v1 The applications of Generative Artificial Intelligence (GenAI) and their intersections with data-driven fields, such as healthcare, finance, transportation, and information security, have led to significant improvements in service efficiency and low latency. However, this synergy raises serious concerns regarding the security of large language models (LLMs) and their potential impact on the privacy of companies and users' data. Many technology companies that incorporate LLMs in their services with a certain level of command and control bear a risk of data exposure and secret divulgence caused by insecure LLM pipelines, making them vulnerable to multiple attacks such as data poisoning, prompt injection, and model theft. Although several security techniques (input/output sanitization, decentralized learning, access control management, and encryption) were implemented to reduce this risk, there is still an imminent risk of quantum computing attacks, which are expected to break existing encryption algorithms, hence, retrieving secret keys, encrypted sensitive data, and decrypting encrypted models. In this extensive work, we integrate the Post-Quantum Cryptography (PQC) based Lattice-based Homomorphic Encryption (HE) main functions in the LLM's inference pipeline to secure some of its layers against data privacy attacks. We modify the inference pipeline of the transformer architecture for the LLAMA-3 model while injecting the main homomorphic encryption operations provided by the concrete-ml library. We demonstrate high text generation accuracies (up to 98%) with reasonable latencies (237 ms) on an i9 CPU, reaching up to 80 tokens per second, which proves the feasibility and validity of our work while running a FHE-secured LLAMA-3 inference model. Further experiments and analysis are discussed to justify models' text generation latencies and behaviours. --- ### EMBER: Autonomous Cognitive Behaviour from Learned Spiking Neural Network Dynamics in a Hybrid LLM Architecture Authors: William Savage Published: 2026-04-14 Categories: cs.AI, cs.NE arXiv: https://arxiv.org/abs/2604.12167v1 We present (Experience-Modulated Biologically-inspired Emergent Reasoning), a hybrid cognitive architecture that reorganises the relationship between large language models (LLMs) and memory: rather than augmenting an LLM with retrieval tools, we place the LLM as a replaceable reasoning engine within a persistent, biologically-grounded associative substrate. The architecture centres on a 220,000-neuron spiking neural network (SNN) with spike-timing-dependent plasticity (STDP), four-layer hierarchical organisation (sensory/concept/category/meta-pattern), inhibitory E/I balance, and reward-modulated learning. Text embeddings are encoded into the SNN via a novel z-score standardised top-k population code that is dimension-independent by construction, achieving 82.2\% discrimination retention across embedding dimensionalities. We show that STDP lateral propagation during idle operation can trigger and shape LLM actions without external prompting or scripted triggers: the SNN determines when to act and what associations to surface, while the LLM selects the action type and generates content. In one instance, the system autonomously initiated contact with a user after learned person-topic associations fired laterally during an 8-hour idle period. From a clean start with zero learned weights, the first SNN-triggered action occurred after only 7 conversational exchanges (14 messages). --- ### Nucleus-Image: Sparse MoE for Image Generation Authors: Chandan Akiti, Ajay Modukuri, Murali Nandan Nagarapu, Gunavardhan Akiti, Haozhe Liu Published: 2026-04-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.12163v1 We present Nucleus-Image, a text-to-image generation model that establishes a new Pareto frontier in quality-versus-efficiency by matching or exceeding leading models on GenEval, DPG-Bench, and OneIG-Bench while activating only approximately 2B parameters per forward pass. Nucleus-Image employs a sparse mixture-of-experts (MoE) diffusion transformer architecture with Expert-Choice Routing that scales total model capacity to 17B parameters across 64 routed experts per layer. We adopt a streamlined architecture optimized for inference efficiency by excluding text tokens from the transformer backbone entirely and using joint attention that enables text KV sharing across timesteps. To improve routing stability when using timestep modulation, we introduce a decoupled routing design that separates timestep-aware expert assignment from timestep-conditioned expert computation. We construct a large-scale training corpus of 1.5B high-quality training pairs spanning 700M unique images through multi-stage filtering, deduplication, aesthetic tiering, and caption curation. Training follows a progressive resolution curriculum (256 to 512 to 1024) with multi-aspect-ratio bucketing at every stage, coupled with progressive sparsification of the expert capacity factor. We adopt the Muon optimizer and share our parameter grouping recipe tailored for diffusion models with timestep modulation. Nucleus-Image demonstrates that sparse MoE scaling is a highly effective path to high-quality image generation, reaching the performance of models with significantly larger active parameter budgets at a fraction of the inference cost. These results are achieved without post-training optimization of any kind: no reinforcement learning, no direct preference optimization, and no human preference tuning. We release the training recipe, making Nucleus-Image the first fully open-source MoE diffusion model at this quality. --- ### AlphaEval: Evaluating Agents in Production Authors: Pengrui Lu, Bingyu Xu, Wenjun Zhang, Shengjia Hua, Xuanjian Gao, Ranxiang Ge, Lyumanshan Ye, Linxuan Wu, Yiran Li, Junfei Fish Yu, Yibo Zhang, Ruixin Li et al. Published: 2026-04-14 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.12162v1 The rapid deployment of AI agents in commercial settings has outpaced the development of evaluation methodologies that reflect production realities. Existing benchmarks measure agent capabilities through retrospectively curated tasks with well-specified requirements and deterministic metrics -- conditions that diverge fundamentally from production environments where requirements contain implicit constraints, inputs are heterogeneous multi-modal documents with information fragmented across sources, tasks demand undeclared domain expertise, outputs are long-horizon professional deliverables, and success is judged by domain experts whose standards evolve over time. We present AlphaEval, a production-grounded benchmark of 94 tasks sourced from seven companies deploying AI agents in their core business, spanning six O*NET (Occupational Information Network) domains. Unlike model-centric benchmarks, AlphaEval evaluates complete agent products -- Claude Code, Codex, etc. -- as commercial systems, capturing performance variations invisible to model-level evaluation. Our evaluation framework covers multiple paradigms (LLM-as-a-Judge, reference-driven metrics, formal verification, rubric-based assessment, automated UI testing, etc.), with individual domains composing multiple paradigms. Beyond the benchmark itself, we contribute a requirement-to-benchmark construction framework -- a systematic methodology that transforms authentic production requirements into executable evaluation tasks in minimal time. This framework standardizes the entire pipeline from requirement to evaluation, providing a reproducible, modular process that any organization can adopt to construct production-grounded benchmarks for their own domains. --- ### Development, Evaluation, and Deployment of a Multi-Agent System for Thoracic Tumor Board Authors: Tim Ellis-Caleo, Timothy Keyes, Nerissa Ambers, Faraah Bekheet, Wen-wai Yim, Nikesh Kotecha, Nigam H. Shah, Joel Neal Published: 2026-04-14 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.12161v1 Tumor boards are multidisciplinary conferences dedicated to producing actionable patient care recommendations with live review of primary radiology and pathology data. Succinct patient case summaries are needed to drive efficient and accurate case discussions. We developed a manual AI-based workflow to generate patient summaries to display live at the Stanford Thoracic Tumor board. To improve on this manually intensive process, we developed several automated AI chart summarization methods and evaluated them against physician gold standard summaries and fact-based scoring rubrics. We report these comparative evaluations as well as our deployment of the final state automated AI chart summarization tool along with post-deployment monitoring. We also validate the use of an LLM as a judge evaluation strategy for fact-based scoring. This work is an example of integrating AI-based workflows into routine clinical practice. --- ### PubSwap: Public-Data Off-Policy Coordination for Federated RLVR Authors: Anupam Nayak, Baris Askin, Muhammed Ustaomeroglu, Carlee Joe-Wong, Gauri Joshi Published: 2026-04-14 Categories: cs.LG arXiv: https://arxiv.org/abs/2604.12160v1 Reasoning post-training with reinforcement learning from verifiable rewards (RLVR) is typically studied in centralized settings, yet many realistic applications involve decentralized private data distributed across organizations. Federated training is a natural solution, but scaling RLVR in this regime is challenging: full-model synchronization is expensive, and performing many local steps can cause severe client drift under heterogeneous data. We propose a federated RLVR framework that combines LoRA-based local adaptation with public-data-based off-policy steps to improve both communication efficiency and cross-client coordination. In particular, a small shared public dataset is used to periodically exchange and reuse response-level training signals across organizations, providing a lightweight anchor toward a more globally aligned objective without exposing private data. Our method selectively replaces locally incorrect responses with globally correct ones during public-data steps, thereby keeping training closer to the local policy while still benefiting from cross-client coordination. Across mathematical and medical reasoning benchmarks and models, our method consistently improves over standard baselines. Our results highlight a simple and effective recipe for federated reasoning post-training: combining low-rank communication with limited public-data coordination. --- ### VidTAG: Temporally Aligned Video to GPS Geolocalization with Denoising Sequence Prediction at a Global Scale Authors: Parth Parag Kulkarni, Rohit Gupta, Prakash Chandra Chhipa, Mubarak Shah Published: 2026-04-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.12159v1 The task of video geolocalization aims to determine the precise GPS coordinates of a video's origin and map its trajectory; with applications in forensics, social media, and exploration. Existing classification-based approaches operate at a coarse city-level granularity and fail to capture fine-grained details, while image retrieval methods are impractical on a global scale due to the need for extensive image galleries which are infeasible to compile. Comparatively, constructing a gallery of GPS coordinates is straightforward and inexpensive. We propose VidTAG, a dual-encoder framework that performs frame-to-GPS retrieval using both self-supervised and language-aligned features. To address temporal inconsistencies in video predictions, we introduce the TempGeo module, which aligns frame embeddings, and the GeoRefiner module, an encoder-decoder architecture that refines GPS features using the aligned frame embeddings. Evaluations on Mapillary (MSLS) and GAMa datasets demonstrate our model's ability to generate temporally consistent trajectories and outperform baselines, achieving a 20% improvement at the 1 km threshold over GeoCLIP. We also beat current State-of-the-Art by 25% on global coarse grained video geolocalization (CityGuessr68k). Our approach enables fine-grained video geolocalization and lays a strong foundation for future research. More details on the project webpage: https://parthpk.github.io/vidtag_webpage/ --- ### Domain-Specific Latent Representations Improve the Fidelity of Diffusion-Based Medical Image Super-Resolution Authors: Sebastian Cajas, Ashaba Judith, Rahul Gorijavolu, Sahil Kapadia, Hillary Clinton Kasimbazi, Leo Kinyera, Emmanuel Paul Kwesiga, Sri Sri Jaithra Varma Manthena, Luis Filipe Nakayama, Ninsiima Doreen, Leo Anthony Celi Published: 2026-04-14 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2604.12152v1 Latent diffusion models for medical image super-resolution universally inherit variational autoencoders designed for natural photographs. We show that this default choice, not the diffusion architecture, is the dominant constraint on reconstruction quality. In a controlled experiment holding all other pipeline components fixed, replacing the generic Stable Diffusion VAE with MedVAE, a domain-specific autoencoder pretrained on more than 1.6 million medical images, yields +2.91 to +3.29 dB PSNR improvement across knee MRI, brain MRI, and chest X-ray (n = 1,820; Cohen's d = 1.37 to 1.86, all p < 10^{-20}, Wilcoxon signed-rank). Wavelet decomposition localises the advantage to the finest spatial frequency bands encoding anatomically relevant fine structure. Ablations across inference schedules, prediction targets, and generative architectures confirm the gap is stable within plus or minus 0.15 dB, while hallucination rates remain comparable between methods (Cohen's h < 0.02 across all datasets), establishing that reconstruction fidelity and generative hallucination are governed by independent pipeline components. These results provide a practical screening criterion: autoencoder reconstruction quality, measurable without diffusion training, predicts downstream SR performance (R^2 = 0.67), suggesting that domain-specific VAE selection should precede diffusion architecture search. Code and trained model weights are publicly available at https://github.com/sebasmos/latent-sr. --- ### Distinct mechanisms underlying in-context learning in transformers Authors: Cole Gibson, Wenping Cui, Gautam Reddy Published: 2026-04-14 Categories: cs.LG, cond-mat.dis-nn, cond-mat.stat-mech arXiv: https://arxiv.org/abs/2604.12151v1 Modern distributed networks, notably transformers, acquire a remarkable ability (termed `in-context learning') to adapt their computation to input statistics, such that a fixed network can be applied to data from a broad range of systems. Here, we provide a complete mechanistic characterization of this behavior in transformers trained on a finite set $S$ of discrete Markov chains. The transformer displays four algorithmic phases, characterized by whether the network memorizes and generalizes, and whether it uses 1-point or 2-point statistics. We show that the four phases are implemented by multi-layer subcircuits that exemplify two qualitatively distinct mechanisms for implementing context-adaptive computations. Minimal models isolate the key features of both motifs. Memorization and generalization phases are delineated by two boundaries that depend on data diversity, $K = |S|$. The first ($K_1^\ast$) is set by a kinetic competition between subcircuits and the second ($K_2^\ast$) is set by a representational bottleneck. A symmetry-constrained theory of a transformer's training dynamics explains the sharp transition from 1-point to 2-point generalization and identifies key features of the loss landscape that allow the network to generalize. Put together, we show that transformers develop distinct subcircuits to implement in-context learning and identify conditions that favor certain mechanisms over others. --- ### MindGames Arena Generalization Track: In2AI Solution with Delayed Per-Step Reward Attribution Authors: Aliaksei Korshuk, Alexander Buyantuev, Ilya Makarov Published: 2026-04-13 Categories: cs.AI, cs.CL, cs.MA arXiv: https://arxiv.org/abs/2606.00017v1 Training language model agents for multi-agent strategic interaction presents a core difficulty: the quality of any action may depend on future events that never materialize, on moves that violate game rules, or on decisions made by other players. Standard reinforcement learning assumes that rewards can be assigned at each step, but this assumption fails in settings where outcomes are entangled across time and agents. We introduce delayed per-step reward attribution with eligibility gating, an episode lifecycle and postprocessing pipeline that computes rewards only at episode end, propagates them back to originating steps according to task-specific semantics, and excludes steps that lack valid dependent information from training. Together with asynchronous rollout generation via vLLM's continuous batching, curriculum-based opponent sampling, and multi-level stratified batch construction, this approach enables stable, sample-efficient RL training in multi-agent environments. We evaluate on the MindGames Arena benchmark at NeurIPS 2025, where a single 8-billion-parameter open-source model trained with our method matched or surpassed substantially larger proprietary systems, including GPT-5, in head-to-head play and took first place in both the Open (unrestricted) and Efficient (<=8B parameters) tracks. --- ### AEyeDE: An Attention-Based Attribution Framework for AI-Generated Text Detection Authors: Aria Nourbakhsh, Adelaide Danilov, Christoph Schommer, Salima Lamsiyah Published: 2026-04-13 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2606.00016v1 Detecting AI-generated text is becoming increasingly challenging as modern language models approach human-level fluency and can evade detectors that rely on surface statistics or likelihood-based signals. We propose \textsc{AEyeDE}, an attribution-driven approach to human-AI authorship detection that leverages model attention as a discriminative signal. Specifically, we extract attention-based attribution matrices for both human- and AI-generated text using a \emph{proxy} Transformer model with white-box access and train a lightweight Convolutional Neural Network to learn representations from these attribution maps. Across encoder-decoder translation settings, our method consistently outperforms a text-only baseline. In decoder-only settings, it performs strongly in generator-specific detection, remains competitive on standard benchmarks, and shows robustness under cross-dataset transfer and alternative-spelling perturbations. We further show that attention maps exhibit recurring local structures whose relative frequencies differ consistently between human- and AI-generated text across datasets and proxy models. These findings suggest that attention-based attribution maps provide a complementary and interpretable signal for AI-generated text detection. We will make the code publicly available to support future research. --- ### SortingHat: Redefining Operating Systems Education with a Tailored Digital Teaching Assistant Authors: Yifan Zhang, Xinkui Zhao, Zuxin Wang, Zhengyi Zhou, Guanjie Chen, Shuiguang Deng, Jianwei Yin Published: 2026-04-13 Categories: cs.HC, cs.AI, cs.CY, cs.ET arXiv: https://arxiv.org/abs/2606.00015v1 Operating Systems (OS) courses are among the most challenging in computer science education due to the complexity of internal structures and the diversity of running environments. Traditional teaching methods often fail to address the diverse backgrounds, learning speeds, and practical needs of students. To tackle these challenges, we present SortingHat, a personalized digital teaching assistant tailored specifically for OS education. SortingHat integrates advanced AI technologies, including a retrieval augmented generation (RAG) framework and multi agent reinforcement learning (MARL), to deliver adaptive, scalable, and effective educational support. SortingHat features a 3D digital human interface powered by large language models (LLMs) to provide personalized, empathetic, and context aware guidance. It generates tailored exercises based on each student's learning history and academic performance, reinforcing weak areas and challenging advanced concepts. Additionally, the system incorporates a robust evaluation pipeline that ensures fair, consistent, and unbiased grading of student submissions while delivering personalized, actionable feedback for improvement. By combining personalized guidance, adaptive content creation, and automated assessment, SortingHat transforms OS education into an engaging, immersive, and scalable experience. --- ### Toward Robust In-Context Learning: Leveraging Out-of-distribution Proxies for Target Inaccessible Demonstration Retrieval Authors: Hao Xu, Rite Bo, Fausto Giunchiglia, Yingji Li, Rui Song Published: 2026-04-13 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2606.00014v1 Although studies have demonstrated that Large Language Models (LLMs) can perform well on Out-of-Distribution (OOD) tasks, their advantage tends to diminish as the distribution shift becomes more severe. Consequently, researchers aim to retrieve distributionally similar and informative demonstrations from the available source domain to boost the inference capabilities of LLMs. However, in practical scenarios where the target domain is inaccessible, evaluating the unknown distribution is challenging, which indirectly impacts the quality of the selected demonstrations. To address this problem, we propose \textbf{DOPA}, a demonstration search framework that incorporates an OOD proxy to approximate the inaccessible target domain and guide the retrieval process. Building on proxy-based evaluation, DOPA further introduces a Mahalanobis distance-based global diversity constraint to ensure sufficient diversity among the retrieved demonstrations. Experimental results on multiple LLMs and tasks demonstrate that DOPA effectively enhances robustness in OOD settings\footnote{https://github.com/bort64/ood\_code}. --- ### A phenomenon of AI-conformity: how algorithms change human moral decision-making Authors: Yana Venerina, Dmitry Koch, Nare Meloyan, Gerda Prutko, Valeriia Lelik, Victoria Taova, Andrey Kurpatov Published: 2026-04-13 Categories: cs.CY, cs.AI, cs.HC arXiv: https://arxiv.org/abs/2606.00013v1 Social conformity is a well-documented phenomenon in which individuals shift their opinions towards those of a social majority. As artificial intelligence (AI) becomes increasingly integrated into everyday life it may also create a novel source of influence giving rise to algorithmic conformity, mechanisms of which are poorly understood. The present study examined whether AI judgements affect moral decision-making in humans (n=165) adapting the classical Asch paradigm. Participants completed a series of moral dilemmas under three different conditions: in presence of social majority, with an AI model providing brief answers and with an AI model providing both answers and explanations of its choices. In all conditions the presented responses contradicted generally accepted moral norms. The results indicated that an AI model with a reasoning component affected the opinion of participants to a degree comparable to that of a human majority. These findings suggest that even moral judgements, despite their sensitivity and personal significance, may be susceptible to algorithmic conformity. However, the mechanism underlying algorithmic conformity appears to differ from the social one. Overall, the study challenges the assumption that moral decision-making lies in "AI inadmissibility zone" - a sphere that is considered as an area in which only human-made decisions are acceptable and highlights the need for a further investigation of this phenomenon as AI-based recommendations become increasingly embedded into human decision-making. --- ### DraDDP: A Multimodal Multi-Party Dialogue Discourse Parsing Dataset Authors: Shannan Liu, Peifeng Li, Yaxin Fan, Qiaoming Zhu Published: 2026-04-13 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2606.00012v1 Multi-party dialogue discourse parsing aims to identify dependency structures and relation types between utterances in conversations. Previous studies are mostly limited to textual modality or two-party dialogue, failing to meet the multimodal and multi-party settings. In this paper, we construct the first publicly available English multimodal dataset DraDDP for multi-party dialogue discourse parsing, based on American TV dramas. DraDDP contains 495 dialogue segments with 6,374 utterances and 9.1 hours of parallel video content, covering rich multi-party interaction scenarios. Moreover, we establish comprehensive benchmarks by evaluating this task on DraDDP and conducting in-depth analysis on the impact of different modalities. Experimental results demonstrate the value of multimodal information in capturing dialogue structures and relation types. We will publicly release the dataset, annotation guidelines, and code to promote future research in multimodal dialogue understanding. --- ### A Survey of Text and Speech Resources for Hausa and Fongbe: Availability, Quality, and Gaps for NLP Development Authors: Mahounan Pericles Adjovi, Victor Olufemi, Roald Eiselen, Prasenjit Mitra Published: 2026-04-13 Categories: cs.CL arXiv: https://arxiv.org/abs/2605.22828v1 This survey provides a comprehensive catalog of publicly available text and speech resources for two West African languages: Hausa, an Afroasiatic language with approximately 80-100 million speakers, and Fongbe, a Niger-Congo language spoken by approximately 2 million people in Benin. These languages represent contrasting cases on the resource availability spectrum. We address the question: \textit{What is the current state of publicly available NLP resources for Hausa and Fongbe, and what gaps remain?} Through systematic search of academic repositories, data platforms, and web sources, we catalog parallel corpora, monolingual text collections, speech datasets, pre-trained models, and evaluation benchmarks. For each resource, we document size, domain coverage, format, licensing, and accessibility. Our findings reveal that Hausa benefits from broader text resource diversity across news, encyclopedic, and educational domains. Fongbe, while having more limited text resources, has been the focus of recent academic speech data collection initiatives. Both languages are represented in Masakhane benchmarks for NER and POS tagging. We provide task-specific recommendations and identify priority gaps including domain-diverse Fongbe text and dedicated Hausa speech corpora. --- ### DualView: Adaptive Local-Global Fusion for Multi-Hop Document Reranking Authors: Litong Zhang, Jiaxin Li, Kuo Zhao Published: 2026-04-13 Categories: cs.IR, cs.AI arXiv: https://arxiv.org/abs/2605.18767v1 Multi-hop question answering requires aggregating information from multiple documents, a critical capability for knowledge-intensive applications. A fundamental challenge lies in efficiently identifying the minimal relevant document set from retrieved candidates while maintaining high recall. We present an efficient dual-view cascaded reranking framework for multi-hop document reranking. Operating as a lightweight post-retrieval stage over E5-base-v2 candidates, our architecture comprises: (1) a Local Scorer employing stacked cross-attention for fine-grained query-document relevance; and (2) a Global Scorer modeling inter-document dependencies via Transformer-based context aggregation. These views are dynamically fused through an Adaptive Gate conditioned on query semantics. Under the fixed candidate set reranking setting with offline cached embeddings, our model achieves competitive results, particularly outstanding on MuSiQue with 99.4% Top-4 Recall and 97.8% Full Hit accuracy at 4.0 ms latency (249 QPS). It substantially outperforms 600M-parameter cross-encoders (BGE-Large: 92.0% Recall, Jina-v3: 90.1% Recall) while maintaining 5 to 6 times lower latency. Ablation studies validate that both Local and Global views contribute substantially to multi-hop performance. --- ### MCQ Difficulty Prediction via Modeling Learner Heterogeneity Using Data-Driven Cognitive Profiling Authors: Dhriti Krishnan, Jaromir Savelka Published: 2026-04-13 Categories: cs.CY, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2605.16290v1 Predicting the difficulty of multiple-choice questions (MCQs) is important for effective assessment, yet current methods typically assume a unimodal student ability distribution, overlooking the heterogeneous nature of student misconceptions. We propose a persona-driven framework that replaces theoretical ability sampling with data-driven cognitive profiling. Using student interactions from the EEDI dataset, we identify behavioral personas via latent class analysis (LCA), then condition a large language model (LLM) to simulate response distributions for each persona. These signals are aggregated with topic context and fed into a Ridge Regression model to predict the item response theory (IRT) difficulty parameter. With five-fold cross-validation, our method improves over a recent baseline (MSE: 0.367 to 0.274; R2: 0.525 to 0.686). The discovered personas are interpretable and offer insights into why items are difficult, with potential applications to diagnostic assessment design. --- ### Linguistic Uncertainty and Reply Engagement on X: A Cross-Domain Replication of the Uncertainty-Reply Asymmetry Authors: Mohamed Soufan Published: 2026-04-13 Categories: cs.CY, cs.CL arXiv: https://arxiv.org/abs/2605.16289v1 Linguistic uncertainty is common in social media, but its relationship with engagement remains unclear across languages and topics. Using 2,258 English-language posts on Federal Reserve policy, inflation, and electoral politics collected over three days in April 2026, we test whether the Uncertainty-Reply Asymmetry observed in prior Arabic-language research replicates in a broader context. Posts are classified using a lexicon-based uncertainty framework, with approximately one-third identified as uncertain. Uncertain posts receive 82% more replies on average than certain posts, with smaller increases in reposts and likes, replicating the asymmetric engagement pattern observed in prior work. Regression results confirm a positive and statistically significant association between uncertainty and replies (\b{eta} = 0.126, p = 0.011), equivalent to ~13% higher expected reply engagement, while total engagement shows a positive but weaker association. These findings suggest that linguistic uncertainty systematically increases conversational engagement and may reflect a general interactional mechanism across languages and domains. --- ### When AI Tells You What You Want to Hear: Sycophantic Behavior of Large Language Models in Dementia Care Settings Authors: Christian Kolb Published: 2026-04-13 Categories: cs.CY, cs.CL arXiv: https://arxiv.org/abs/2605.16288v1 Large language models (LLMs) are increasingly used in clinical and care settings. This exploratory study investigates whether LLMs exhibit sycophantic behavior - adapting their responses to social expectation signals rather than maintaining professional quality - in the context of dementia care. Five prompts with systematically increasing confirmatory and authority-related framing (P1 neutral to P5 authority-signaled implementation support) were submitted to four LLMs (GPT-5, Claude Sonnet 4.6, Gemini 3.1 Pro, Mistral Large), each repeated five times (N = 100 responses). Responses were evaluated using an LLM-as-a-Judge methodology against seven nursing-ethical quality criteria (K1-K7) and a tone scale (0-3). All models showed significant negative Spearman correlations between prompt level and response quality (rho ranging from -0.543 to -0.734, all p < 0.01). Mistral Large exhibited the most pronounced effect (rho = -0.734), with mean scores dropping from 6.0/7 at P1 to 0.2/7 at P5. The findings suggest that LLMs pose context-sensitive risks in high-stakes care environments and that prompt framing significantly shapes response quality - a dimension that has received insufficient attention in healthcare AI deployment. --- ### Homoglyph-based Adversarial Perturbation of Introductory Computer Science Theory Problems Authors: Aidan Alexander, Chitrangada Juneja, Napaluck Tontrasathien, Miro Vanek, Reyan Ahmed, Saumya Debray, Sazzadur Rahaman Published: 2026-04-13 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2605.16286v1 Different AI tools such as ChatGPT, Gemini, and Claude are becoming very popular. Although they are helpful for many day-to-day tasks, they can be used in unexpected ways. For example, the learning objectives of a course may not be achieved if students use these tools to solve their homework problems. This paper proposes a simple method to address this issue in the lazy student model. The method uses homoglyph-based adversarial perturbation to first modify the question without changing the semantic meaning of the question. Then a few characters are perturbed by their homoglyphs. Our experimental result shows the theoretical problems of introductory computer science courses can be effectively perturbed. We also propose an interactive tool to conveniently use our method. --- ### A Hormone-inspired Emotion Layer for Transformer language models (HELT) Authors: Eslam Reda, Sara El-Metwally Published: 2026-04-13 Categories: cs.NE, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2605.13858v1 Large Language Models have demonstrated remarkable capabilities in generating contextually relevant and grammatically correct text. However, they fundamentally lack the ability to process and respond to emotional context in a manner analogous to human emotional cognition. Current approaches to emotion modeling in NLP systems rely primarily on discrete emotion classification or simplistic sentiment analysis, which fail to capture the continuous, multi-dimensional nature of human emotional states. In this paper, we introduce HormoneT5, a novel architecture that augments transformer language models with a biologically-inspired Hormone Emotion Block that simulates the human endocrine system's role in emotional processing. Our approach computes six continuous hormone-like values through specialized per-hormone attention heads, each with orthogonally initialized learnable queries, temperature-scaled attention mechanisms, and deep output projections. These hormone values are then transformed into an emotional embedding that modulates the encoder hidden states, enabling emotionally-appropriate response generation. We propose a multi-objective training framework combining sequence-to-sequence loss, hormone prediction loss with margin penalties, and diversity regularization to prevent attention collapse. Experimental results on our curated emotion-labeled dataset demonstrate that HormoneT5 achieves 85%+ per-hormone accuracy within a 0.15 tolerance threshold, with hormone differentiation ranges exceeding 0.85 across all six hormones between contrasting emotional tones. Human evaluation studies show significant preference (p < 0.01) for HormoneT5-generated responses in terms of emotional appropriateness and empathetic quality compared to baseline T5 outputs. Our work opens new directions for biologically-grounded affective computing and emotionally intelligent conversational agents. --- ### MorphOPC: Advancing Mask Optimization with Multi-scale Hierarchical Morphological Learning Authors: Yuting Hu, Lei Zhuang, Chen Wang, Ruiyang Qin, Hua Xiang, Gi-joon Nam, Jinjun Xiong Published: 2026-04-13 Categories: cs.CV, cs.AI, cs.AR arXiv: https://arxiv.org/abs/2605.12528v1 As feature sizes shrink to the nanometer scale, accurately transferring circuit patterns from photomasks to silicon wafers becomes increasingly challenging. Optical proximity correction (OPC) is widely used to ensure pattern fidelity and manufacturability. Recent generative mask optimization models based on encoder-decoder architecture can synthesize near-optimal masks, serving as fast machine learning (ML) surrogates for traditional OPC. However, these models often fail to capture the geometric transformations from target layouts to mask patterns, leading to suboptimal quality. In this work, we formulate mask generation as a sequence of morphological operations on local layout features and propose \textit{MorphOPC}, a multi-scale hierarchical model with neural morphological modules to learn these transformations. Experiments on edge-based OPC and ILT benchmarks across metal and via layers show that \textit{MorphOPC} consistently outperforms state-of-the-art methods, achieving higher printing fidelity and lower manufacturing cost, demonstrating strong potential for scalable mask optimization. --- ### Confronting Label Indeterminacy in Automated Bail Decisions Authors: Cor Steging, Tadeusz Zbiegień Published: 2026-04-13 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.04073v1 Bail decisions present a fundamental challenge for data-driven decision support systems. When bail is denied, the counterfactual outcome of whether the defendant would have appeared in court remains unobserved. As a result, historical bail data embed structural label indeterminacy: future decisions are influenced by past decisions whose outcomes are only partially knowable. Building automated systems on such data risks introducing bias and reinforcing feedback loops. This raises a core question for machine-learning systems intended to assist judicial actors: how should cases in which bail was denied be treated during model development? In a case study of bail decisions from the Unified Judicial System of Pennsylvania, we evaluate five contemporary approaches to handling label indeterminacy across three machine learning models, including a novel label imputation method motivated by the dynamics of bail decisions. Each method relies on unverifiable assumptions, yet all influence the models' predictive behaviour, sometimes even more so than the choice of model itself. Explainable AI analysis further reveals that these effects extend to the models' internal decision-making processes as well. Finally, we consider the notion of label indeterminacy from a legal perspective and assess the legitimacy of these approaches in the context of bail decision-making. --- ### Sparse Autoencoder Decomposition of Clinical Sequence Model Representations: Feature Complexity, Task Specialisation, and Mortality Prediction Authors: Chris Sainsbury, Feng Dong, Andreas Karwath Published: 2026-04-13 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2605.04072v1 Sparse autoencoders (SAEs) have been applied to large language models and protein language models, but not systematically to electronic health record (EHR) foundation models. We train TopK SAEs on FlatASCEND, a 14.5-million-parameter autoregressive clinical sequence model, at all 10 residual stream extraction points on INSPECT (outpatient) and MIMIC-IV (ICU). SAE decomposition reveals progressive abstraction across transformer depth: layer-0 features are near-perfect token detectors (45.7% singleton), while layer-6 features span approximately 30 token types across multiple clinical categories (0.5% singleton). Under full-sequence simple linear probes, SAE features outperform dense representations for discrete event prediction (mortality) while dense representations outperform for continuous magnitude prediction (length of stay) - a probe-level representational phenomenon that does not extend to clinically relevant leakage-safe windows, where dense representations match or exceed SAE features across all tested settings (eICU-CRD 48-hour AUC: SAE 0.871 versus dense 0.880; base model zero-shot, SAE dictionaries trained on eICU activations; MIMIC-IV: 0.836 versus 0.914; INSPECT 1-year/3-year: 0.697 versus 0.800). A delta-mode intervention method reduces SAE perturbation noise by 86x, enabling cleaner feature-level experiments, though the resulting perturbation effects are larger than random controls in 3 of 4 conditions but not formally significant. Feature reproducibility across random seeds is 21%, and individual features should be interpreted as illustrative rather than stable. --- ### FlatASCEND: Autoregressive Clinical Sequence Generation with Continuous Time Prediction and Association-Based Pharmacological Testing Authors: Chris Sainsbury, Feng Dong, Andreas Karwath Published: 2026-04-13 Categories: cs.LG, cs.AI, q-bio.QM arXiv: https://arxiv.org/abs/2605.04071v1 Autoregressive models can predict clinical events, but generating patient-conditioned multi-step trajectories that respond to intervention tokens and testing whether those responses preserve known pharmacological associations has received limited attention. We present FlatASCEND, a 14.5M-parameter autoregressive clinical sequence model using flat composite tokens and a zero-inflated log-normal time head. Standard distributional metrics (Jaccard 0.889-0.954) do not distinguish FlatASCEND from trivial baselines; the model's value lies in conditional generation from patient-specific prefixes. A prompt-shuffle ablation shows patient-specific conditioning amplifies mechanistic pharmacological effects (2.0-2.2x for steroid to glucose, diuretic to potassium) while leaving confounding-driven associations unchanged (0.9x for insulin to glucose). An incident-user framework assesses directional consistency against prior pharmacological knowledge on MIMIC-IV (N=500 per comparison): 4/10 recover correct mechanistic directions, 2 reproduce treatment-context associations, 4 are incorrect (9/10 significant, Wilcoxon p<0.05). This pattern - partial recovery under residual confounding - is consistent with learned observational associations without causal distinction. Direct preference optimisation with surrogate reward destroys all correct associations (3/3 to 0/3), illustrating reward exploitation when reward and evaluation share an outcome domain. Generative evidence is strongest for short-horizon ICU data; outpatient temporal fidelity is weaker (median 10 vs 154 days on INSPECT), and zero-shot cross-site transfer degrades without adaptation. --- ### Toward Human-AI Complementarity Across Diverse Tasks Authors: Yuzheng Xu, Annya Dahmani, Matthew D. Blanchard, Niclas Dern, Edy Nastase, Francesca Bianco, Maja Pavlovic, Sukanya Krishna, Eric Modesitt, Miranda Anna Christ, Arth Singh, Gaia Molinaro et al. Published: 2026-04-13 Categories: cs.HC, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2605.04070v1 Human-AI complementarity, the idea that combining human and AI judgments can outperform either alone, offers a promising pathway toward robust oversight of advanced AI systems. However, whether human-AI complementarity can be achieved on realistic tasks remains an open question. We investigate this through two approaches: hybridization and two AI assistance methods (top-2 assistance and subtask delegation), evaluated on a multi-domain dataset of 1,886 samples spanning knowledge, factuality, long-context reasoning, and deception detection. We find only modest complementarity gains. Baseline hybridization yields just +0.4 percentage points (pp) over AI alone (69.3\% vs 68.9\%), limited both by a small complementarity region (only 8.9\% of items where AI errs but humans do not) and the inability of confidence-based routing to identify it, since the model's confidence is similarly distributed across correct and incorrect predictions. Applied when AI has low confidence, top-2 assistance increases human accuracy from 28.4\% to 38.3\%, surpassing AI alone (37.7\%) -- but primarily because humans adopt correct AI suggestions, not because they successfully override AI errors. These findings suggest that the primary bottleneck is not human task accuracy per se, but the ability to route decisions to humans when it matters and to design assistance methods that enable humans to catch AI mistakes. Our quantitative and qualitative analyses pinpoint where and why each method succeeds or fails, offering concrete targets for future work. We will release our dataset and code upon request to support progress toward more effective human-AI collaboration for AI oversight. --- ### Beyond Sequential Prediction: Learning Financial Market Dynamics in Volatile and Non-Stationary Environments through Sentiment-Conditioned Generative Modelling Authors: Alexis Lazanas, Spyridon Karpouzis Published: 2026-04-13 Categories: q-fin.ST, cs.LG arXiv: https://arxiv.org/abs/2604.22801v2 The problem of time-series forecasting in non-stationary and complex environments is a challenging task in machine learning, especially with heterogeneous numerical and textual data present. Traditional statistical models like AutoRegressive Integrated Moving Average (ARIMA) are based on the assumptions of linearity and stationarity, whereas recurrent neural networks like Long Short-Term Memory (LSTM) models do not necessarily represent distributional properties in highly volatile settings. This paper proposes a hybrid model that combines Generative Adversarial Networks (GANs) with Natural Language Processing (NLP)-based sentiment analysis to enable sentiment-conditioned time-series prediction. The model integrates adversarial learning on numerical sequences with contextual sentiment representations derived from unstructured text, enabling them to be jointly modelled to capture temporal dynamics and exogenous information. These results demonstrate the promise of hybrid generative and language-aware methods to enhance prediction robustness in non-stationary environments. --- ### RCSB PDB AI Help Desk: retrieval-augmented generation for protein structure deposition support Authors: Vivek Reddy Chithari, Jasmine Y. Young, Irina Persikova, Yuhe Liang, Gregg V. Crichlow, Justin W. Flatt, Sutapa Ghosh, Brian P. Hudson, Ezra Peisach, Monica Sekharan, Chenghua Shao, Stephen K. Burley Published: 2026-04-13 Categories: cs.IR, cs.AI, cs.CL, q-bio.QM arXiv: https://arxiv.org/abs/2604.22800v1 Motivation: Structural Biologists have contributed more than 245,000 experimentally determined three-dimensional structures of biological macromolecules to the Protein Data Bank (PDB). Incoming data are validated and biocurated by ~20 expert biocurators across the wwPDB. RCSB PDB biocurators who process more than 40% of global depositions face increasing challenges in maintaining efficient Help Desk operations, with approximately 19,000 messages in approximately 8,000 entries received from depositors in 2025. Results: We developed an AI-powered Help Desk using Retrieval-Augmented Generation (RAG) built on LangChain with a pgvector store (PostgreSQL) and GPT-4.1-mini. The system employs pymupdf4llm for Markdown-preserving PDF extraction, two-stage document chunking, Maximal Marginal Relevance retrieval, a topical guardrail that filters off-topic queries, and a specialized system prompt that prevents exposure of internal terminology. A dual-LLM architecture uses separate model configurations for question condensing and response generation. Deployed in production on Kubernetes with PostgreSQL (pgvector), it provides around-the-clock depositor assistance with citation-backed, streaming responses. Availability and implementation: Freely available at https://rcsb-deposit-help.rcsb.org. --- ### Hierarchical RL-MPC Control for Dynamic Wake Steering in Wind Farms Authors: Marcus Binder Nilsen, Teodor Olof Benedict Åstrand, Tuhfe Göçmen, Pierre-Elouan Réthoré Published: 2026-04-13 Categories: eess.SY, cs.LG arXiv: https://arxiv.org/abs/2604.22797v1 Wind farm wake steering optimization is challenging due to complex flow physics and changing conditions. This paper presents a hierarchical framework that combines reinforcement learning with model predictive control, where an RL agent learns compensatory state estimates for an MPC controller, rather than directly controlling turbines. Evaluated on a three-turbine case, the approach achieves a 23\% power gain over the baseline control and surpasses the idealized MPC with perfect state knowledge. Compared to direct RL control, the hybrid architecture maintains superior safety characteristics during training while achieving comparable performance with more stable control actions. --- ### Load constrained wind farm flow control through multi-objective multi-agent reinforcement learning Authors: Teodor Åstrand, Marcus Binder Nilsen, Iasonas Tsaklis, Tuhfe Göçmen, Pierre-Elouan Réthoré, Nikolay Dimitrov Published: 2026-04-13 Categories: eess.SY, cs.LG arXiv: https://arxiv.org/abs/2604.22795v2 This study presents a multi-agent reinforcement learning (MARL) framework for load-constrained wind farm flow control (WFFC). While wake steering can enhance total wind farm power, it often introduces increased structural loads on downstream turbines. To address this, we integrate an Independent Soft Actor-Critic (I-SAC) architecture with a data-driven, local inflow sector-averaged surrogate model to provide real-time estimates of Damage Equivalent Loads (DELs). By incorporating these estimates into a shaped reward function, turbine-specific agents are trained to maximize power production while adhering to specific load-increase thresholds ($Δ_{max}$) of 10%, 20%, and 30% relative to a baseline controller. The framework is implemented within the WindGym environment using the DYNAMIKS flow solver with Dynamic Wake Meandering (DWM) model to capture non-stationary wake physics. Results indicate that the MARL agents successfully learn collaborative policies that prioritise power gain while actively retreating from high-DEL control strategies. --- ### Accelerating Reinforcement Learning for Wind Farm Control via Expert Demonstrations Authors: Marcus Binder Nilsen, Julian Quick, Tuhfe Göçmen, Nikolay Dimitrov, Pierre-Elouan Réthoré Published: 2026-04-13 Categories: eess.SY, cs.LG arXiv: https://arxiv.org/abs/2604.22794v1 Reinforcement learning (RL) offers a promising approach for adaptive wind farm flow control, yet its practical deployment is hindered by slow training convergence and poor initial performance, factors that could translate to years of reduced power output if an untrained agent were deployed directly. This work investigates whether domain knowledge from steady-state wake models can accelerate RL training and improve initial controller performance. We propose a pretraining methodology in which expert demonstrations are generated by deploying a PyWake-based steady-state optimizer within a dynamic wake simulation (WindGym), then used to initialize both the actor and critic networks of a Soft Actor-Critic agent via behavior cloning. Experiments on a 2x2 wind farm show that pretraining eliminates the costly initial learning phase: while an untrained agent underperforms the greedy zero-yaw baseline by approximately 12%, pretraining raises initial performance to near-baseline levels. During online fine-tuning, all configurations converge within 250,000 environment steps to achieve similar performance, ultimately exceeding that of a lookup-table controller, which reaches approximately 7% power gain after 500,000 steps. --- ### From Equations to Algorithms and Data: Transforming Microwave Engineering and Education with Machine Learning Authors: Mehmet Parlak, Islam Guven Published: 2026-04-13 Categories: eess.SP, cs.ET, cs.LG arXiv: https://arxiv.org/abs/2604.22792v1 Conventional microwave engineering education relies heavily on analytical methods, canonical circuit topologies, and intuition-driven design, which have proven effective at microwave frequencies. However, as systems increasingly operate in the millimeter-wave and terahertz regimes, parasitic effects, process-dependent electromagnetic interactions, and ultra-wideband performance requirements challenge both topology/layout-constrained traditional design methodologies and existing teaching paradigms. This paper proposes a pedagogical shift in microwave and RFIC (Radio Frequency Integrated Circuit) engineering and education by introducing machine-learning (ML) and data-driven electromagnetic synthesis as a complementary design framework for microwave circuits such as power dividers and combiners, couplers, and baluns. Rather than emphasizing predefined topologies, the proposed approach enables topology-agnostic, performance-oriented exploration of the design space, allowing students to directly engage with electromagnetic behavior through specification-driven synthesis. By integrating machine-learning-based inverse design and multi-objective optimization into the curriculum, the framework enhances physical intuition, encourages design creativity, and better aligns microwave education with emerging industrial practices in high-frequency and ultra-wideband system design. --- ### HHL with a Coherent Fourier Oracle: A Proof-of-Concept Quantum Architecture for Joint Melody-Harmony Generation Authors: Alexis Kirke Published: 2026-04-13 Categories: quant-ph, cs.AI, cs.SD arXiv: https://arxiv.org/abs/2604.20882v1 Quantum algorithms with a proven theoretical speedup over classical computation are rare. Among the most prominent is the Harrow-Hassidim-Lloyd (HHL) algorithm for solving sparse linear systems. Here, HHL is applied to encode melodic preference: the system matrix encodes Narmour implication-realisation and Krumhansl-Kessler tonal stability, so its solution vector is a music-cognition-weighted note-pair distribution. The key constraint of HHL is that reading its output classically cancels the quantum speedup; the solution must be consumed coherently. This motivates a coherent Fourier harmonic oracle: a unitary that applies chord-transition weights directly to the HHL amplitude vector, so that a single measurement jointly selects both melody notes and a two-chord progression. A two-note/two-chord (2/2) block is used to contain the exponential growth of the joint state space that would otherwise make classical simulation of larger blocks infeasible. For demonstrations of longer passages, blocks are chained classically - each block's collapsed output conditions the next -- as a temporary workaround until fault-tolerant hardware permits larger monolithic circuits. A four-block chain produces 8 notes over 8 chords with grammatically valid transitions at every block boundary. Independent rule-based harmony validation confirms that 97% of generated chord progressions are rated strong or acceptable. The primary motivation is that HHL carries a proven exponential speedup over classical linear solvers; this work demonstrates that a coherent HHL+oracle pipeline - the prerequisite for that speedup to be realised in a musical setting - is mechanically achievable. Audio realisations of representative outputs are made available for listening online. --- ### Neuromorphic Continual Learning for Sequential Deployment of Nuclear Plant Monitoring Systems Authors: Samrendra Roy, Sajedul Talukder, Syed Bahauddin Alam Published: 2026-04-13 Categories: cs.NE, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2604.18611v1 Anomaly detection in nuclear industrial control systems (ICS) requires continuous, energy-efficient monitoring across multiple subsystems that are often deployed at different stages of plant commissioning. When a conventional neural network is sequentially trained to monitor new subsystems, it catastrophically forgets previously learned anomaly patterns, a safety-critical failure mode. We present the first spiking neural network (SNN)-based anomaly detection system with continual learning for nuclear ICS, addressing both challenges simultaneously. Our approach introduces spike-encoded asynchronous sensor fusion, a delta-based encoding that converts heterogeneous sensor streams into sparse spike trains at rates dictated by each sensor's natural dynamics, achieving 92.7% input sparsity. We evaluate five continual learning strategies, including sequential fine-tuning, Elastic Weight Consolidation (EWC), Synaptic Intelligence (SI), experience replay, and a hybrid EWC+Replay approach, on the HAI 21.03 nuclear ICS security dataset across three sequentially deployed subsystems (boiler, turbine, water treatment). The hybrid EWC+Replay method achieves an average F1 score of 0.979 with near-zero average forgetting (AF = 0.000 single seed; 0.035 +/- 0.039 across three seeds), while requiring 12.6x fewer operations (an estimated 2.5x in energy based on published hardware specifications) than an equivalent artificial neural network. The system detects all tested attacks with a mean latency of 0.6 seconds. These results demonstrate that neuromorphic computing offers a viable path toward always-on, energy-efficient, and adaptable safety monitoring for next-generation nuclear facilities. --- ### SpikeMLLM: Spike-based Multimodal Large Language Models via Modality-Specific Temporal Scales and Temporal Compression Authors: Han Xu, Zhiyong Qin, Di Shang, Jiahong Zhang, Xuerui Qiu, Bo Lei, Tiejun Huang, Bo Xu, Guoqi Li Published: 2026-04-13 Categories: cs.NE, cs.AI arXiv: https://arxiv.org/abs/2604.18610v1 Multimodal Large Language Models (MLLMs) have achieved remarkable progress but incur substantial computational overhead and energy consumption during inference, limiting deployment in resource-constrained environments. Spiking Neural Networks (SNNs), with their sparse event-driven computation, offer inherent energy efficiency advantages on neuromorphic hardware, yet extending them to MLLMs faces two key challenges: heterogeneous modalities make uniform spike encoding insufficient, and high-resolution image inputs amplify timestep unfolding overhead. We propose SpikeMLLM, the first spike-based framework for MLLMs, which unifies existing ANN quantization methods in the spiking representation space and incorporates Modality-Specific Temporal Scales (MSTS) guided by Modality Evolution Discrepancy (MED) and Temporally Compressed LIF (TC-LIF) for timestep compression from T=L-1 to T=log2(L)-1. Experiments on four representative MLLMs across diverse multimodal benchmarks show that SpikeMLLM maintains near-lossless performance under aggressive timestep compression (Tv/Tt=3/4), with average gaps of only 0.72% and 1.19% relative to the FP16 baseline on InternVL2-8B and Qwen2VL-72B. We further develop a dedicated RTL accelerator tailored to the spike-driven datapath, observing 9.06x higher throughput and 25.8x better power efficiency relative to an FP16 GPU baseline under a deployment-oriented co-design setting, suggesting the promise of algorithm-hardware co-design for efficient multimodal intelligence. --- ### NL2SQLBench: A Modular Benchmarking Framework for LLM-Enabled NL2SQL Solutions Authors: Shizheng Hou, Wenqi Pei, Nuo Chen, Quang-Trung Ta, Peng Lu, Beng Chin Ooi Published: 2026-04-13 Categories: cs.DB, cs.AI, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2604.16493v1 Natural Language to SQL (NL2SQL) technology empowers non-expert users to query relational databases without requiring SQL expertise. While large language models (LLMs) have greatly improved NL2SQL algorithms, their rapid development outpaces systematic evaluation, leaving a critical gap in understanding their effectiveness, efficiency, and limitations. To this end, we present NL2SQLBench, the first modular evaluation and benchmarking framework for LLM-enabled NL2SQL approaches. Specifically, we dissect NL2SQL systems into three core modules: Schema Selection, Candidate Generation, and Query Revision. For each module, we comprehensively review existing strategies and propose novel fine-grained metrics that systematically quantify module-level effectiveness and efficiency. We further implement these metrics in a flexible multi-agent framework, allowing configurable benchmarking across diverse NL2SQL approaches. Leveraging NL2SQLBench, we rigorously evaluate ten representative open-source methods on two datasets, the BIRD development set and the ScienceBenchmark development set, using two LLMs, DeepSeek-V3 and GPT-4o mini. We systematically assess each approach across the three core modules and evaluate multiple critical performance dimensions. Our evaluation reveals significant gaps in existing NL2SQL methods, highlighting not only substantial room for accuracy improvements but also the significant computational inefficiency, which severely hampers real-world adoption. Furthermore, our analysis identifies critical shortcomings in current benchmark datasets and evaluation rules, emphasizing issues such as inaccurate gold SQL annotations and limitations in existing evaluation rules. By synthesizing these insights into a unified benchmarking, our study establishes a clear reference point for fair comparison and serves as essential guidance for future targeted innovation in NL2SQL technology. --- ### LayerCache: Exploiting Layer-wise Velocity Heterogeneity for Efficient Flow Matching Inference Authors: Guandong Li Published: 2026-04-13 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2604.16492v1 Flow Matching models achieve state-of-the-art image generation quality but incur substantial inference cost due to iterative denoising through large Transformer networks. We observe that different layer groups within a Transformer exhibit markedly heterogeneous velocity dynamics: shallow layers are highly stable and amenable to aggressive caching, while deep layers undergo large velocity changes that demand full computation. Existing caching methods, however, treat the entire Transformer as a monolithic unit, applying a single caching decision per timestep and thus failing to exploit this heterogeneity. Based on this finding, we propose LayerCache, a layer-aware caching framework that partitions the Transformer into layer groups and makes independent, per-group caching decisions at each denoising step. LayerCache introduces an adaptive JVP span K selection mechanism that leverages per-group stability measurements to balance estimation accuracy and computational savings. We formulate a three-dimensional scheduling problem over timesteps, layer groups, and JVP span, and solve it with a greedy budget allocation algorithm. On Qwen-Image (1024x1024, 50 steps), LayerCache achieves PSNR 37.46 dB (+5.38 dB over MeanCache), SSIM 0.9834, and LPIPS 0.0178 (a 70% reduction over MeanCache) at 1.37x speedup, dominating all prior caching methods on the quality-speed Pareto frontier. --- ### A Lightweight Transformer for Pain Recognition from Brain Activity Authors: Stefanos Gkikas, Christian Arzate Cruz, Yu Fang, Lu Cao, Muhammad Umar Khan, Thomas Kassiotis, Giorgos Giannakakis, Raul Fernandez Rojas, Randy Gomez Published: 2026-04-13 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2604.16491v5 Pain is a multifaceted and widespread phenomenon with substantial clinical and societal burden, making reliable automated assessment a critical objective. This paper presents a lightweight transformer architecture that fuses multiple fNIRS representations through a unified tokenization mechanism, enabling joint modeling of complementary signal views without requiring modality-specific adaptations or increasing architectural complexity. The proposed token-mixing strategy preserves spatial, temporal, and time-frequency characteristics by projecting heterogeneous inputs onto a shared latent representation, using a structured segmentation scheme to control the granularity of local aggregation and global interaction. The model is evaluated on the AI4Pain dataset using stacked raw waveform and power spectral density representations of fNIRS inputs. Experimental results demonstrate competitive pain recognition performance while remaining computationally compact, making the approach suitable for real-time inference on both GPU and CPU hardware. --- ### An Uncertainty-Aware Loss Function Incorporating Fuzzy Logic: Application to MRI Brain Image Segmentation Authors: Hanuman Verma, Akshansh Gupta, Pranabesh Maji, Saurav Mandal, Vijay Kumar Pandey Published: 2026-04-13 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2604.16490v1 Accurate brain image segmentation, particularly for distinguishing various tissues from magnetic resonance imaging (MRI) images, plays a pivotal role in finding the neurological dis ease and medical image computing. In deep learning approaches, loss functions are very crucial for optimizing the model. In this study, we introduce a novel loss function integrating fuzzy logic to deals uncertainty issues in brain image segmentation into various tissues. It integrates the well-known categorical cross-entropy (CCE) loss function and fuzzy entropy based on fuzzy logic. By employing fuzzy logic, this loss function accounts for the inherent uncertainties in pixel classifications. The proposed loss function has been evaluated on two publicly available benchmark datasets, IBSR and OASIS, using two widely recognised architectures, U-Net and U-Net++. Experimental results demonstrate that the trained model with proposed loss function provided better results in comparison to the CCE optimisation function in terms of various performance metrics. Additionally, it effectively enhances segmentation performance while handling meaningful uncer tainty during training. The findings suggest that this approach not only improves segmentation outcomes but also contributes to the reliability of model predictions. --- ### Geometry-Aware CLIP Retrieval via Local Cross-Modal Alignment and Steering Authors: Nirmalendu Prakash, Narmeen Fatimah Oozeer, Xin Su, Phillip Howard, Shaan Shah, Zoe Wanying He, Shuang Wu, Shivam Raval, Roy Ka-Wei Lee, Meenakshi Khosla, Amir Abdullah Published: 2026-04-13 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2604.16487v2 CLIP retrieval is typically framed as a pointwise similarity problem in a shared embedding space. While CLIP achieves strong global cross-modal alignment, many retrieval failures arise from local geometric inconsistencies: nearby items are incorrectly ordered, leading to systematic confusions (e.g., pentagon vs. hexagon) and produces diffuse, weakly controlled result sets. Prior work largely optimizes for point wise relevance or finetuning to mitigate these problems. We instead view retrieval as a problem of neighborhood alignment. Our work introduces (1) neighborhood-level re-ranking via Hungarian matching, which rewards structural consistency; (2) query-conditioned local steering, where directions derived from contrastive neighborhoods around the query reshape retrieval. We show that these techniques improve retrieval performance on attribute-binding and compositional retrieval tasks. Together, these methods operate on local neighborhoods but serve different roles: re-ranking rewards alignment whereas local steering controls neighborhood structure. This shows that retrieval quality and controllability depend critically on local structure, which can be exploited at inference time without retraining. --- ### Aletheia: Physics-Conditioned Localized Artifact Attention (PhyLAA-X) for End-to-End Generalizable and Robust Deepfake Video Detection Authors: Devendra Ghori Published: 2026-04-13 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2604.16486v1 State-of-the-art deepfake detectors achieve near-perfect in-domain accuracy yet degrade under cross-generator shifts, heavy compression, and adversarial perturbations. The core limitation remains the decoupling of semantic artifact learning from physical invariants: optical-flow discontinuities, specular-reflection inconsistencies, and cardiac-modulated reflectance (rPPG) are treated either as post-hoc features or ignored. We introduce PhyLAA-X, a novel physics-conditioned extension of Localized Artifact Attention (LAA-X). PhyLAA-X injects three end-to-end differentiable physics-derived feature volumes - optical-flow curl, specular-reflectance skewness, and spatially-upsampled rPPG power spectra - directly into the LAA-X attention computation via cross-attention gating and a resonance consistency loss. This forces the network to learn manipulation boundaries where semantic inconsistencies and physical violations co-occur - regions inherently harder for generative models to replicate consistently. PhyLAA-X is embedded across an efficient spatiotemporal ensemble (EfficientNet-B4+BiLSTM, ResNeXt-101+Transformer, Xception+causal Conv1D) with uncertainty-aware adaptive weighting. On FaceForensics++ (c23), Aletheia reaches 97.2% accuracy / 0.992 AUC-ROC; on Celeb-DF v2, 94.9% / 0.981; on DFDC, 90.8% / 0.966 - outperforming the strongest published baseline (LAA-Net (1)) by 4.1-7.3% in cross-generator settings and maintaining 79.4% accuracy under epsilon = 0.02 PGD-10 attacks. Single-backbone ablations confirm PhyLAA-X alone delivers a 4.2% cross-dataset AUC gain. The full production system is open-sourced at https://github.com/devghori1264/Aletheia (v1.2, April 2026) with pretrained weights, the adversarial corpus (referred to as ADC-2026 in this work), and complete reproducibility artifacts. --- ### Saccade Attention Networks: Using Transfer Learning of Attention to Reduce Network Sizes Authors: Marc Estafanous Published: 2026-04-13 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2604.16485v1 One of the limitations of transformer networks is the sequence length due to the quadratic nature of the attention matrix. Classical self attention uses the entire sequence length, however, the actual attention being used is sparse. Humans use a form of sparse attention when analyzing an image or scene called saccades. Focusing on key features greatly reduces computation time. By using a network (Saccade Attention Network) to learn where to attend from a large pre-trained model, we can use it to pre-process images and greatly reduce network size by reducing the input sequence length to just the key features being attended to. Our results indicate that you can reduce calculations by close to 80% and produce similar results. --- ### DexWorldModel: Causal Latent World Modeling towards Automated Learning of Embodied Tasks Authors: Yueci Deng, Guiliang Liu, Kui Jia Published: 2026-04-13 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2604.16484v1 Deploying generative World-Action Models for manipulation is severely bottlenecked by redundant pixel-level reconstruction, $\mathcal{O}(T)$ memory scaling, and sequential inference latency. We introduce the Causal Latent World Model (CLWM), which employs DINOv3 features as generative targets to disentangle interaction semantics from visual noise, yielding highly robust domain generalization. To overcome memory scaling, CLWM features a Dual-State Test-Time Training (TTT) Memory that guarantees a strict $\mathcal{O}(1)$ footprint for long-horizon tasks. To overcome deployment latency, we propose Speculative Asynchronous Inference (SAI) to mask partial diffusion denoising behind physical execution, cutting blocking latency by about $50\%$. To scale robust policies, we present EmbodiChain, an online framework that establishes the Efficiency Law by injecting an infinite flow of physics-grounded trajectories during training. Extensive experiments validate that CLWM achieves state-of-the-art performance in complex dual-arm simulation and unprecedented zero-shot sim-to-real transfer on physical robots, outperforming baselines explicitly finetuned on real-world data. --- ### DSS: Dynamic Semantic Steering for Robust Concept Erasure in Diffusion Models Authors: Qinghui Gong, Zhengchun Zhou, Hua Meng, Yihuai Liang, Yuxuan Zhang Published: 2026-04-13 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2604.16483v2 Text-to-image (T2I) diffusion models have introduced new security risks, as adversaries can exploit flexible text prompts to induce the generation of sensitive or policy-violating content (e.g., NSFW or copyrighted concepts). Concept erasure has emerged as a promising defense, aiming to suppress targeted semantics while preserving benign generation. However, existing approaches face a fundamental trade-off: training-based methods are costly and inflexible to emerging threats, while inference-time interventions often rely on unconstrained feature manipulation, leading to over-correction, semantic drift, and degraded utility. More critically, they lack an explicit understanding of local semantic structure, resulting in unstable behavior under adversarial or compositional prompts. In this paper, we propose Dynamic Semantic Steering (DSS), a training-free, inference-time defense framework for robust and controllable concept erasure under prompt-level adversarial settings. DSS introduces a geometry-aware formulation that explicitly models local semantic neighborhoods and constrains feature updates within this structure, which is key to achieving precise suppression without sacrificing benign semantics. Specifically, DSS (i) automatically identifies benign semantic anchors via density-based boundary modeling, and (ii) performs context-aware, constrained feature correction using cross-attention signals with a closed-form solution. Extensive experiments demonstrate that DSS achieves strong and consistent suppression across diverse concept categories and adversarial prompts, reaching an average erasure rate of 91.0\%, outperforming prior defenses (18.6\%--85.9\%). At the same time, DSS substantially reduces semantic drift and preserves generation fidelity. --- ### Dynamic Eraser for Guided Concept Erasure in Diffusion Models Authors: Qinghui Gong Published: 2026-04-13 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2604.16483v1 Concept erasure in Text-To-Image (T2I) diffusion models is vital for safe content generation, but existing inference-time methods face significant limitations. Feature-correction approaches often cause uncontrolled over-correction, while token-level interventions struggle with semantic granularity and context. Moreover, both types of methods are prone to severe semantic drift or even complete representation collapse. To address these challenges, we present Dynamic Semantic Steering (DSS), a lightweight, training-free framework for interpretable and controllable concept erasure. DSS introduces: 1) Sensitive Semantic Boundary Modeling (SSBM) to automate the discovery of safe semantic anchors, and 2) Sensitive Semantic Guidance (SSG), which leverages cross-attention features for precise detection and performs correction via a closed-form solution derived from a well-posed objective. This ensures optimal suppression of sensitive content while preserving benign semantics. DSS achieves an average erasure rate of 91.0\%, significantly outperforming SOTA methods (from 18.6\% to 85.9\%) with minimal impact on output fidelity. --- ### A Survey of Spatial Memory Representations for Efficient Robot Navigation Authors: Ma. Madecheen S. Pangaliman, Steven S. Sison, Erwin P. Quilloy, Rowel Atienza Published: 2026-04-13 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2604.16482v1 As vision-based robots navigate larger environments, their spatial memory grows without bound, eventually exhausting computational resources, particularly on embedded platforms (8-16GB shared memory, $<$30W) where adding hardware is not an option. This survey examines the spatial memory efficiency problem across 88 references spanning 52 systems (1989-2025), from occupancy grids to neural implicit representations. We introduce the $α= M_{\text{peak}} / M_{\text{map}}$, the ratio of peak runtime memory (the total RAM or GPU memory consumed during operation) to saved map size (the persistent checkpoint written to disk), exposing the gap between published map sizes and actual deployment cost. Independent profiling on an NVIDIA A100 GPU reveals that $α$ spans two orders of magnitude within neural methods alone, ranging from 2.3 (Point-SLAM) to 215 (NICE-SLAM, whose 47,MB map requires 10GB at runtime), showing that memory architecture, not paradigm label, determines deployment feasibility. We propose a standardized evaluation protocol comprising memory growth rate, query latency, memory-completeness curves, and throughput degradation, none of which current benchmarks capture. Through a Pareto frontier analysis with explicit benchmark separation, we show that no single paradigm dominates within its evaluation regime: 3DGS methods achieve the best absolute accuracy at 90-254,MB map size on Replica, while scene graphs provide semantic abstraction at predictable cost. We provide the first independently measured $α$ reference values and an $α$-aware budgeting algorithm enabling practitioners to assess deployment feasibility on target hardware prior to implementation. --- ### Machine learning approaches to uncover the neural mechanisms of motivated behaviour: from ADHD to individual differences in effort and reward sensitivity Authors: Nam Trinh Published: 2026-04-13 Categories: q-bio.NC, cs.LG arXiv: https://arxiv.org/abs/2604.15363v1 Motivated behaviour relies on the brain's capacity to evaluate effort and reward. Dysregulation within these processes contributes to a spectrum of conditions, from hyperactivity in attention-deficit/hyperactivity disorder (ADHD) to diminished goal-directed behaviour in apathy. This thesis investigates the neural mechanisms underlying ADHD using electroencephalography (EEG) and examines individual differences in effort and reward sensitivity using neuroimaging, applying machine learning approaches through three main studies. In Study 1, task-based and resting-state EEG were employed with machine learning models to classify adult individuals with ADHD and healthy controls. Machine learning classifiers trained on task-based EEG during a stop signal task outperformed those trained on resting-state EEG, with the strongest predictive features arising from gamma-band spectral power over fronto-central and parietal regions. In Study 2, diffusion MRI and whole-brain permutation-based analyses identified associations between white matter integrity and computationally modelled parameters reflecting effort and reward sensitivity, with SMA-connected tracts emerging as a central hub. In Study 3, grey matter volumes from structural T1-weighted MRI were used to examine correlates of effort sensitivity, reward sensitivity, and subclinical apathy, with machine learning confirming robust decoding of reward sensitivity and apathy levels. Across studies, fronto-parietal circuits emerged as central to effort valuation and reward processing. These findings may serve as neural biomarkers for improving diagnostic accuracy in ADHD and motivational impairments, and for guiding personalised neurotechnological interventions. ---