# Research Papers — 2026-06 · bundle page 179 of 260 > Full-text markdown of papers #8901–8950 of 12993 published in 2026-06, newest first. AI-readable mirrors of the full 12993-paper 2026-06 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-06/page/179 [← Previous bundle](https://aipod.dev/papers/archive/2026-06/page/178.md) [Next bundle →](https://aipod.dev/papers/archive/2026-06/page/180.md) ### A Unified Adaptive Feature Composition Framework for Multi-Task Generalization in Wireless Foundation Models Authors: Yuxuan Shi, Tingting Yang, Kangning Ma, Liwen Jing, Yuwei Wang, Mengfan Zheng, Li Sun Published: 2026-06-09 Categories: cs.LG arXiv: https://arxiv.org/abs/2606.10277v1 Though wireless foundation models (WFMs) have shown strong potential in learning universal channel representations, their adaptation to various downstream tasks remains constrained by existing paradigms. Fine-tuning strategies introduces substantial computational and storage overhead, while frozen feature extraction leads to sub-optimal performance across diverse downstream tasks. To address this issue, we propose a unified adaptive feature composition framework for multitask generalization in WFMs, where the key component is the Routing Adapter for Feature Composition (RAFC). Instead of extracting only the final-layer output, this router treats the hidden states from different Transformer depths as a reusable pool of multi-level hidden features, and employs a lightweight task-driven feature composition network to generate layer-wise aggregation weights, then adaptively combine hierarchical representations through weighted summation. This design enables each downstream task to access suitable mixture of low-, mid-, and high-level wireless features without modifying the pretrained backbone. Extensive experiments on four representative wireless tasks demonstrate that RAFC consistently outperforms conventional adaptation baselines while introducing fewer than 50K additional parameters. Moreover, the learned routing weights provide interpretable evidence of task-specific layer preferences, making the proposed framework a low-complexity, scalable, and explainable interface for adapting WFMs to diverse downstream scenarios. --- ### Hierarchical Policies from Verbal and Egocentric Human Signals for Natural Human-Robot Interaction Authors: Dongjun Lee, Juheon Choi, Dong Kyu Shin, Sinjae Kang, Kimin Lee Published: 2026-06-09 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2606.10276v1 For natural human-robot interaction, a robot must understand human intent expressed not only through language but also through nonverbal signals such as gestures and gaze. However, current robot policies rely on language instructions as the sole interface for conveying intent, leaving nonverbal signals unused and placing the full burden of communication. In this work, we present EDITH, a robot framework that captures the human's nonverbal signals through continuous streams of first-person view and gaze from smart glasses, and uses them alongside language instructions as inputs to the robot policy. Our hardware system streams the human's first-person view, gaze, and speech to the robot in real time, transcribing the speech into language instructions. To handle these rich but noisy signals, we design a hierarchical policy in which a high-level policy infers the human's intent and produces a sequence of subtasks, where each subtask is represented as a fine-grained instruction paired with a keyframe that grounds the intent in the scene (e.g., the frame where the human points at the target object). A low-level policy then executes these subtasks. In our experiments on human-robot interactive tasks, EDITH enables the robot to act on the human's nonverbal signals even when intent is expressed only briefly, and significantly reduces user effort to convey intent compared to using language instructions alone. Visit our project page for source code and real-robot demo videos. --- ### FoA-SR: Faithful or Aesthetic? Profile-Aware Preference Optimization for Real-World Image Super-Resolution Authors: Amjad Mahdi Alqarni, Peizhong Ju Published: 2026-06-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.10275v1 Real-world image super-resolution (SR) is often designed with a single restoration objective, despite the current capacity of generative models to produce multiple high-quality reconstructions for the same input. In this paper, we argue that the best restoration strategy is subject to the specific restoration profile: a Faithful restoration prioritizes reference consistency, structure preservation, and hallucination suppression, whereas an Aesthetic restoration prioritizes visually pleasing and natural-looking details. We propose FoA-SR, a novel preference optimization approach to real-world SR based on profiles. To achieve this goal, FoA-SR starts with our supervised FLUX.2-based SR adapter (Flux2SR) trained with LR latent conditioning, flow matching, and image-space reconstruction losses for paired LR-to-HR image super-resolution. Following the development of the shared supervised super-resolution adapter, FoA-SR generates a shared stochastic candidate pool for each input image and ranks the same candidates using profile-specific Faithful and Aesthetic rewards to mine winner-loser pairs. These pairs are used to fine-tune separate LoRA adapters while keeping the base model frozen. Experiments on RealSR and DIV2K show that FoA-SR can steer the same SR adapter towards distinct restoration objectives: a Faithful adapter improves reference-consistent metrics while an Aesthetic adapter boosts metrics that measure perceptual quality without reference. Our candidate-pool analysis shows that Faithful and Aesthetic rewards frequently select different winners, and a Hybrid-LoRA ablation shows that collapsing both profiles into one reward yields an implicit compromise rather than explicit profile control. --- ### What Matters in Orchestrating Robot Policies: A Systematic Study of Hierarchical VLA Agents Authors: Jiaheng Hu, Mohit Shridhar, Caden Lu, Dhruv Shah, Hao-Tien Lewis Chiang, Jie Tan, Annie Xie Published: 2026-06-09 Categories: cs.RO, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2606.10267v2 Hierarchical vision-language-action (Hi-VLA) systems have emerged as a promising paradigm for complex robot manipulation, by using high-level VLM planners to decompose tasks into language subgoals executed by low-level VLA controllers. Despite recent empirical progress, there is a lack of unified design principles for these systems: existing Hi-VLA systems differ in how they choose and connect planners, controllers, mechanisms to switch between the two, and how observations and memory are represented in the planner. In this paper, we present a systematic study of Hi-VLA design for robot manipulation. We unify representative Hi-VLA agents under an options-style control framework and benchmark core design choices across short-horizon, long-horizon, and reasoning-intensive tasks. Our analysis distills practical principles for building Hi-VLA systems, showing how model choices and interface mechanisms jointly shape performance. Applying these principles yields a substantially stronger system than either flat VLA control or a naively designed hierarchy, across experiments both in simulation and on a real ALOHA robot. Overall, our results provide a foundation for building more capable, robust, and principled hierarchical VLA agents. More information and video at jiahenghu.github.io/hi-vla. --- ### What Matters in Orchestrating Robot Policies: A Systematic Study of Hierarchical VLA Agents Authors: Jiaheng Hu, Mohit Shridhar, Caden Lu, Dhruv Shah, Hao-Tien Lewis Chiang, Jie Tan, Annie Xie Published: 2026-06-09 Categories: cs.RO, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2606.10267v1 Hierarchical vision-language-action (Hi-VLA) systems have emerged as a promising paradigm for complex robot manipulation, by using high-level VLM planners to decompose tasks into language subgoals executed by low-level VLA controllers. Despite recent empirical progress, there is a lack of unified design principles for these systems: existing Hi-VLA systems differ in how they choose and connect planners, controllers, mechanisms to switch between the two, and how observations and memory are represented in the planner. In this paper, we present a systematic study of Hi-VLA design for robot manipulation. We unify representative Hi-VLA agents under an options-style control framework and benchmark core design choices across short-horizon, long-horizon, and reasoning-intensive tasks. Our analysis distills practical principles for building Hi-VLA systems, showing how model choices and interface mechanisms jointly shape performance. Applying these principles yields a substantially stronger system than either flat VLA control or a naively designed hierarchy, across experiments both in simulation and on a real ALOHA robot. Overall, our results provide a foundation for building more capable, robust, and principled hierarchical VLA agents. More information and video at jiahenghu.github.io/hi-vla. --- ### EvalDetectBench: A Benchmark for Measuring Evaluation Awareness in Frontier Language Models Authors: Xinning Li, Kemunto Ochwang'i, Aryasomayajula Ram Bharadwaj, Alexandra Souly, Robert Kirk Published: 2026-06-08 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2609.01611v1 Frontier large language models can often recognize when they are being evaluated, a capability known as evaluation awareness. If models behave differently in evaluations than in deployment, this undermines the validity of evaluation results, which are a crucial component of current AI safety frameworks. We introduce EvalDetectBench, an open pipeline and benchmark for measuring evaluation awareness that works with any Inspect-compatible evaluation, allowing practitioners to test against current and future benchmarks. EvalDetectBench ships with a newly curated transcript suite covering current frontier system-card evaluations and diverse deployment sources. The benchmark serves two purposes: measuring how reliably frontier LLMs recognize that they are being evaluated, and assessing how detectable individual benchmarks are as evaluations. We identify two methodological choices in the existing literature that introduce systematic bias: the identity of the model that generated the deployment transcripts accounts for 11.25% of measurement variance and can reorder model rankings; and elicitation prompts selected for high performance on one model can perform near chance on others. EvalDetectBench corrects for both via per-model probe calibration and a stratified generator-harmonisation procedure. --- ### A collective capability boundary in frontier large language models on guideline-conformant and case-specific oncology decision-making Authors: Zhang Sheng, Jinming Li, Wangyang Chen, Zhiwei Bao, Yu YoSean Wang Published: 2026-06-08 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.28592v1 Large language models (LLMs) achieve high scores on medical knowledge examinations, yet real-world oncology is not a knowledge test--it is a sequence of guideline-pathway choices, escalation judgments, and commitments under uncertainty. Existing benchmarks largely measure factual recall, leaving open whether frontier LLMs share decision-path blind spots that combining models cannot fix. We built the Oncology Decision Boundary Benchmark (ODBB)--2,005 oncology decision points across NCCN guidelines and colorectal cancer cases--and evaluated nine frontier LLMs (four closed-source, five open-weight families) released between June 2025 and April 2026. A fully deterministic scorer (zero LLM inference) classified outputs into 14 failure types, independently validated by two oncologists (Cohen's weighted $κ$ = 0.939 and 0.790) on a 225-item stratified sample. Treating the nine as a pooled super-model, 42.1% (Wilson 95% CI 40.0--44.3%) of all items--35.7% of the 1,586 NCCN items and 66.4% of the 419 colorectal-cancer cases--were answered correctly by none, with failures concentrated in choosing between guideline pathways before reasoning within any: a consistent blind spot in clinical meta-judgment that likely requires architectural intervention rather than more training data. Two models tuned for decisiveness (GPT-5.5, Gemini 3.1 Pro Preview) made unsafe commitments three to five times more often than the seven cautious models without scoring higher. In 3--9% of items, models stated the correct next clinical step yet did not commit to it--failures of decision, not knowledge. Model quality is no longer the primary bottleneck for clinical LLM deployment; the binding constraint is the assumption that any single model can be the sole basis for a clinical decision. Progress requires architectures that detect when a model reaches its competence boundary and route the decision to a clinician. --- ### Active Inference as Context Acquisition for AI Agents Authors: Sanchayan Dutta, Sai Niranjan Ramachandran, Suvrit Sra Published: 2026-06-08 Categories: cs.AI, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2608.19202v1 Interactive AI agents must acquire the right context as efficiently as possible. When a user omits a constraint, preference, file, or task variable, an agent can proceed with a default assumption or spend tokens on a clarifying question, retrieval call, tool call, or prompt trial. We formulate this tradeoff as active inference for context acquisition. An inner inference step updates beliefs over a latent task state, and an outer decision selects the next context action, task action, or stop action to minimize expected free energy under cost. In deterministic settings, the epistemic term reduces to expected information gain, optionally normalized by token cost. We instantiate the framework in Optimal Question Asking (OQA), with exact posteriors and a dynamic programming oracle, and benchmark frontier language models on binary and multiway categorical tasks from 25 to 300 candidates. We also study clarification before generation and automated prompt optimization under token budgets. The formulation is model-agnostic and views active inference as a design principle for the context-acquisition layer of AI agents. --- ### FrenchNews-7: Benchmarking Cross-Publisher French News Editorial Desk Classification Authors: Amr Sobhy Published: 2026-06-08 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.18097v1 We present FrenchNews-7, a cross-publisher France-based French-language news editorial desk classification benchmark combining a large multi-outlet corpus, a URL-derived seven-class taxonomy, and a fine-tuned CamemBERT classifier. Labels are assigned via a hybrid pipeline combining publisher URL slugs with LLM annotation for structurally ambiguous cases, audited through an inter-rater study (2 humans + 2 LLMs; pairwise $κ\geq 0.766$, human--human $κ= 0.806$). We evaluate lexical, multilingual, and French-specific trained classifiers under both in-distribution and held-out-publisher settings, with additional comparison against zero-shot LLM baselines (GPT-OSS-120B, Mistral Small 3.2, Llama-3.3-70B) on the held-out pool. The strongest model, CamemBERT-base on full article text, outperforms headline-only input, generalizes to unseen outlets, and exceeds all three zero-shot LLM baselines on overall recall (0.799), with the gap concentrated in the ambiguous editorial-boundary categories Economie and Societe. Cross-publisher evaluation reveals uneven boundary stability: Sport, Culture & Loisirs, and International transfer cleanly, while Economie (recall = 0.517) is close to blinded human agreement (0.55), and Societe (precision = 0.577) absorbs boundary ambiguity, both suggesting editorial conventions rather than recoverable classifier headroom. The fine-tuned CamemBERT-base model, labeled manifest, reference collection scripts, and a reliability-tier guidance table are available at https://huggingface.co/LeFrenchNewsLab/camembert-base-frenchnews7 (model) and https://huggingface.co/datasets/LeFrenchNewsLab/frenchnews-7 (dataset). --- ### MAVEN: A Macro-Societal Value Evaluation Framework of Multimodal Content with Compact Aligned Evaluators Authors: Zijuan Zhao, Zheren Fu, Hou Xia, Licheng Zhang, Yi Liu, Zhendong Mao Published: 2026-06-08 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2608.18096v1 Assessing whether multimodal content aligns with macro-societal values, such as peace, justice, and freedom, has become an increasingly urgent challenge. Existing frameworks are largely confined to safety-oriented taxonomies, text-only psychometric probes, or single-label classification. Therefore, we propose MAVEN, a hierarchical framework for macro-societal value evaluation of multimodal content, grounded in international human-rights instruments and cultural value theory. MAVEN organizes values into 6 primary dimensions and 72 secondary indicators, supporting multi-level quantitative scoring. Building on MAVEN, we construct a human-verified multimodal benchmark and a soft-match metric to evaluate VLMs' assessments across value dimensions. For evaluator optimization, we propose a span-adaptive variant of multi-level preference optimization for evaluator distillation, together with a training-free multi-role consensus strategy at inference time. We evaluate existing open- and closed-source VLMs on our benchmark, revealing shared tendencies and clear differences in macro-societal value judgments. Experiments show that our compact 2B evaluator matches its 8B counterpart in the same family and approaches frontier closed-source VLMs, offering a practical path toward scalable macro-societal value evaluation. Our SA-MDPO implementation and MacroValue-Bench are available at https://github.com/zzzzzzzzjj/MAVEN. --- ### Backdoor Learning in Language Models and Vision-Language Models Authors: Weimin Lyu Published: 2026-06-08 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2608.18095v1 Recent advances in deep learning have significantly enhanced the capabilities of Natural Language Processing (NLP) and Vision-Language Models (VLMs). However, these advancements come with increased vulnerabilities, notably through backdoor attacks that pose severe security threats. This thesis addresses two critical dimensions of Trustworthy AI and Efficient Multimodal Representation Learning: (1) security through analyzing, detecting, and designing backdoor attacks in NLP and VLMs, and (2) efficiency through advanced multimodal representation methods tailored for clinical and medical imaging applications. --- ### How to Dogfood Your AI Chat Agent: A Three-Layer Evaluation Framework with Goal-Directed NPC Simulation Authors: Alexandre Cristovão Maiorano Published: 2026-06-08 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2608.09939v1 Production teams deploying LLM chat agents face a specific quality assurance gap: existing evaluation tools test individual responses or simulate social interactions, but none systematically verify whether real users can achieve their goals through multi-turn conversation. We introduce a three-layer dogfooding framework that bridges this gap by combining canonical question-bank testing (Layer 1), random-walk multi-turn evaluation (Layer 2), and a goal-directed NPC (Non-Player Character) simulator with five structured goal types and a ten-category failure taxonomy (Layer 3). In a longitudinal case study on a production multi-agent system over roughly three months (257 evaluation runs; a 108-scenario NPC suite), we find that the three layers produce complementary regression signals: cross-layer correlation for response quality is weak within a synchronized run (Spearman rho between -0.15 and 0.14) and negative across the longitudinal series (rho down to -0.46), confirming that canonical correctness does not predict goal-directed conversation success. The NPC simulator achieves 77 percent goal achievement at 0.17 dollars per run (6,272x cheaper than human evaluation), enabling daily CI/CD integration with automated PROMOTE/HOLD/ROLLBACK release decisions. We release full prompt templates, the failure taxonomy, and a Python-first replicability guide so that other teams can adopt the framework for their own LLM chat agents. --- ### Enhancing LLMs with Context-Specific Knowledge for Mitigating Misinformation in SMEs: A RAG-based Modeling and Analysis Authors: Md. Samiul Islam, Iqbal H. Sarker, Chadni Islam, Ahmad Mohsin, Ahmed Ibrahim, Helge Janicke Published: 2026-06-08 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.00006v1 Large Language Models (LLMs), a part of artificial intelligence (AI), are increasingly being adopted by Small and Medium Enterprises (SMEs) to enhance question-answering capabilities and support business decision-making processes. However, hallucinations in LLM-generated outputs can serve as a source of misinformation, reducing user confidence in their reliability and trustworthiness within SMEs. Retrieval-Augmented Generation (RAG) has emerged as a promising approach to address this challenge by incorporating external knowledge sources into the modeling process. In this paper, we present VectorRAG and GraphRAG modeling approaches to mitigate hallucinations and misinformation risks and evaluate their effectiveness in SME environments. Our experimental evaluation is conducted on multiple state-of-the-art LLMs, including LLaMA, Mistral, and Qwen, to assess performance in terms of useful response generation, risk of hallucination, contextual relevance, as well as human-interpretation. The results demonstrate that RAG-enhanced LLMs can significantly improve response quality by reducing hallucinations and misinformation, thereby supporting more reliable, trustworthy, and context-aware decision-making in SME environments. --- ### The Effect of Text Chunk Size on Retrieval-Augmented Generation Performance Authors: German Garrido-Lestache Belinchon, Hugo Garrido-Lestache Belinchon Published: 2026-06-08 Categories: cs.IR, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2607.24767v1 Retrieval-Augmented Generation (RAG) systems have emerged as a powerful process for allowing large language models (LLMs) to retrieve relevant information to use as source material during text generation. A critical yet under-explored component of these systems is the granularity at which source documents are segmented into retrievable chunks. The size of these chunks has the potential to significantly influence generation quality, contextual correctness, retrieval precision, and computational efficiency. Despite its importance, chunk size is often selected without proper evaluation of its impact on generation quality. Smaller chunks, such as individual sentences, may allow for precise retrieval by narrowing the focus of each chunk. However, they contain less information, which may limit the model's ability to generate coherent responses. Larger chunks, such as entire chapters, contain lots of broad information that may improve correctness, but also introduce additional noise and increase computational cost. Because larger chunks contain more information, the number of chunks returned to the model must also be considered. This paper evaluates how chunk size, along with the number of retrieved segments, influences generation quality and retrieval effectiveness. By comparing these configurations, this study seeks to better understand how document segmentation affects the performance and efficiency of Retrieval-Augmented Generation systems. segmentation affects the performance and efficiency of Retrieval-Augmented Generation systems. --- ### The Scaffold Effect in Coding Agents: Harness Choice as a Hidden Variable in Coding-Agent Evaluation Authors: Naman Vats, Oleg Golev Published: 2026-06-08 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.22585v1 Public leaderboards for coding agents typically rank systems by model name and pass rate, while the surrounding harness (the scaffold that issues tools, manages context, and decides when to stop) is often under-specified. Model-to-model comparison is valid when the harness is fixed; when it varies, performance and efficiency conflate model and scaffold effects. We evaluate Qwen 3.6 Plus and MiniMax M2.5 across three open-source harnesses (Goose, OpenCode, OpenHands-SDK) on a stratified 50-task subset of Terminal-Bench Pro. Harness choice induces up to a 40x difference in tokens per solved task, while paired within-model pass-rate differences remain 0-8 percentage points (95% paired-task bootstrap CIs include zero except for the largest gap). Failure fingerprints replicate across models (REASON for Goose, VERIFY/MAX_TURNS for OpenHands-SDK, idle-loop/TIME for OpenCode), indicating harness-level biases that are largely model-independent. For human-centered coding-agent evaluation, model name alone is an incomplete comparison unit: harness-model pairs determine real-world cost, latency, and oversight burden; no-action turns are a per-task wait tax, not just a token tax. We therefore recommend selecting harness-model pairs by pass rate under token/latency budgets, and reporting token usage, latency, and full harness specifications alongside any model comparison. We release anonymized configs, raw trial logs, aggregated snapshots, and analysis scripts. --- ### Source-Aware Reranking for Retrieval-Augmented Generation: A Reliability Prior Approach Authors: Yuktha Tata Koganti, Hugo Garrido-Lestache Belinchon Published: 2026-06-08 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2607.22584v1 Standard Retrieval-Augmented Generation pipelines rank retrieved documents by semantic similarity alone, without accounting for source provenance or credibility. This work evaluates a simple and interpretable modification to RAG retrieval ranking that incorporates domain-informed source reliability priors. Each document is assigned a prior lambda(s) based on its source type, and retrieval scores are reweighted using score(q, d) = sim(q, d) * lambda(s). The framework is evaluated against a similarity-only baseline on a 120-document health-domain corpus. In this controlled setting, source-aware reranking improves Precision@5 from 0.48 to 0.72 and reduces average adversarial document retrieval under the evaluated threat model, where low-credibility sources are identifiable via metadata. All experiments were executed on Rosie, the high-performance computing cluster at the Milwaukee School of Engineering, which provided the GPU-accelerated infrastructure necessary to run the full experimental pipeline reliably and reproducibly. These results suggest a potential mitigation strategy for source quality degradation in RAG pipelines, within the limits of the experimental setup described. --- ### Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization Authors: Muhammad Junaid Ali, Smail Niar, El-Ghazali Talbi Published: 2026-06-08 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2607.22583v2 Large Language Models (LLMs) have achieved widespread adoption because of their strong reasoning and query-response capabilities. However, deploying them in embedded and edge computing environments remains challenging because of strict latency, memory, and energy constraints. Their large parameter counts and computational demands hinder efficient execution on resource-constrained platforms. Although model pruning has emerged as a viable solution for reducing scale while preserving performance, jointly optimizing layers, attention heads, and Multi-Layer Perceptron (MLP) dimensions remains highly complex. Exhaustively exploring this combined design space is computationally expensive and often leads to local optima or unstable configurations. To address these limitations, we propose a hardware-aware, multi-objective structured pruning framework. The proposed two-stage method explicitly targets latency and model size for efficient deployment on edge devices. In the coarse-grained stage, multi-objective depth pruning removes entire attention and MLP blocks to reduce computational load and memory usage. In the subsequent fine-grained stage, Parallel Bayesian Optimization (PBO) searches for the optimal layer-wise pruning ratios for pruning under latency constraints, while importance-based strategies rank the specific components to be pruned within each layer's allocated budget. Experimental results show that our approach reduces model complexity with minimal impact on commonsense reasoning tasks and zero-shot performance. Our method achieves a favorable trade-off among accuracy, latency, and model size, making it suitable for edge deployment. Across multiple LLMs at 37.5% and 50% pruning ratios, the proposed approach achieves better performance on commonsense reasoning tasks than existing methods while significantly reducing inference cost. --- ### CRAWO: Custom Resources for Adaptive Workload Orchestration Authors: Eugênio Santos, Daniel Maia, Stefano Loss, José Manoel Silva, Aluizio Rocha Neto, Thais Batista, Everton Cavalcante, Nélio Cacho, Eduardo Nogueira, Daniel Araújo, Frederico Lopes Published: 2026-06-08 Categories: cs.AI, cs.DC, cs.ET arXiv: https://arxiv.org/abs/2607.20490v1 Edge Intelligence has emerged as a key paradigm for enabling real-time applications in smart cities by shifting computation from centralized cloud data centers to the network edge, thereby reducing latency and bandwidth consumption. However, deploying Artificial Intelligence (AI) pipelines across heterogeneous edge infrastructures remains challenging due to the wide range of device capabilities, from low-power microcontrollers to accelerator-equipped systems. Existing edge orchestration platforms primarily focus on deployment automation and infrastructure management, but these approaches are often inefficient and limit the ability to adaptively allocate resources under dynamic conditions. To tackle these issues, this paper introduces CRAWO (Custom Resources for Adaptive Workload Orchestration), an architectural framework for coordinating AI pipelines across distributed edge environments. CRAWO follows a control-loop-based model that separates allocation intelligence from execution by managing placement decisions, state management, and inter-stage data flows while instantiating services on edge nodes. The framework incorporates a hardware-aware allocator with a pluggable multi-criteria decision layer that leverages real-time infrastructure metrics to enable adaptive workload placement. The reference implementation adopts a microservices architecture deployed on a lightweight Kubernetes distribution (K3s), using Custom Resource Definitions (CRDs) for domain modeling and a dedicated operator for state reconciliation. Evaluation in a vehicle surveillance scenario using license plate recognition demonstrates improved workload distribution and reduced reliance on centralized cloud processing in latency-sensitive environments. --- ### Logic-Guided Data Extraction with Answer Set Programming and Large Language Models Authors: Mario Alviano, Lorenzo Grillo, Nicola Leone, Fabrizio Lo Scudo Published: 2026-06-08 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.19365v1 When Large Language Models (LLMs) are used for semantic data extraction from unstructured text, producing candidate relational facts from natural language, they may remain unreliable for tasks requiring complex combinatorial reasoning and global consistency. This paper proposes a logic-guided data extraction framework combining LLM-based extraction with Answer Set Programming (ASP). The LLM produces candidate facts, whereas ASP performs validation, inference, consistency checking, and control. Unlike existing pipelines that query the LLM independently for all target predicates, the proposed approach uses ASP reasoning to identify which predicates are logically admissible at each stage and to guide extraction queries. By interleaving LLM calls with ASP derivation, the framework infers logically implied facts without further extraction and detects inconsistencies early. We formalize the pipeline and prove that, under mild assumptions, it is equivalent to the baseline approach with respect to the final extracted facts, while requiring fewer LLM calls. We also introduce a caching mechanism for logic-based control queries, exploiting monotonicity of conjunctive queries over incrementally constructed fact sets to reduce solver invocations. Experiments on ASP-derived benchmarks show that the framework reduces LLM calls and improves extraction quality by mitigating spurious outputs, demonstrating the value of non-monotonic logic programming for controlled semantic extraction. --- ### CCBENCH: Assessing LLM Cultural Competence via Implicitly Signaled Norms using Health Queries Authors: Vasudha Varadarajan, Akhila Yerukola, Mona T. Diab, Maarten Sap Published: 2026-06-08 Categories: cs.CY, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2607.05405v1 To interact with users fairly and without stereotyping, AI models must display cultural competency, i.e., the ability to infer and adapt to a user's implicitly signaled cultural values, rather than relying on static demographic traits. We introduce CCBENCH, a framework for evaluating cultural competency in large language models (LLMs), treating culture as a continuum of norm adherence states rather than as a binary state of cultural belongingness. As a case study on health, we create CCBENCH-Health, which includes 60 theoretically grounded personas exhibiting varied norm-adherence states across six cultures, each engaging in 18 realistic dialogues. Each persona is evaluated on 52 authentic healthcare questions drawn from real user forums, yielding 3,120 unique interactions. Benchmarking five leading models reveals that even the best achieve culturally appropriate responses only 20-30% of the time. When explicitly prompted to focus on culturally relevant cues from the conversational history (CoT), performance improves modestly by 3-5% on average. We find that models perform best when personas avoid cultural norms rather than follow them, revealing a persistent asymmetry, suggesting a preference in the models to align with built-in biases than adapt to cultural cues. This is especially observed in the Afghan context (Avg: 8.8%), where cultural cues rarely yield appropriate health advice. Finally, we find that models sometimes adapt more readily to implicit, cultural conversational styles than to explicitly stated cultural practices, though this varies across cultures. --- ### The Jagged Global Economy: Frontier AI Unevenly Exposes National Economies Authors: Arul Murugan, Tomás Aguirre, Abhishek Nagaraj, Rishi Bommasani Published: 2026-06-08 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2607.05404v1 Frontier AI's labor-market effects matter to workers, firms, and policymakers, but current evidence generally comes from a handful of high-income economies. The capabilities of frontier AI are jagged across work tasks and national economies diverge in how they allocate human labor. We introduce a national AI exposure metric that combines occupation-level exposure scores and international employment data for 141 countries. We find that high income countries are substantially more exposed than low income countries and that Europe and Central Asia are 50 percent more exposed than Sub-Saharan Africa. We also find a gender gap: women are more exposed than men in 91 percent of countries, driven by their concentration in white-collar and sales occupations. The exceptions are countries where women's employment remains concentrated in agriculture and household enterprises. We validate our national AI exposure estimates by showing they predict national AI adoption statistics published by Anthropic, Microsoft, and OpenAI. Beyond direct exposure, we identify a new mechanism for indirect exposure due to cross-country income dependencies. Some nations such as Tajikistan depend heavily on foreign workers remitting money back to their home countries: Tajikistan's direct exposure to frontier AI is below-average but because 37 percent of Tajikistan GDP is Russian remittance and Russia is very exposed, Tajikistan's remittance-accounted exposure becomes above-average. Our research shows that national variation in exposure is large enough that policy responses calibrated to U.S. or European labor markets will not generalize. --- ### AI tools in Arab University English classrooms: Looking back and forward Authors: Mohammed Q. Shormani, Muneef Yehia Alshawsh Published: 2026-06-08 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2607.05403v1 This paper aims to synthesize empirical research on AI tools used to support English as a second/foreign language (EL2) learners in Arab University classrooms (AUCs) between Jan 1st 2023 and Aug 31st 2025. We utilized 3 large datasets, namely Google Scholar, Web of Science, and Scopus as the data sources. Using PRISMA-guided searches across these well-known databases, we included only published articles. The search process results in 184 studies, but only 11 studies met the inclusion criteria. Findings unveil that EL2 learners have positive attitudes towards AI for drafting, revision, and practice. Empirical gains were most consistent for surface-level outcomes improvements in higher-order writing quality and speaking proficiency was mixed and often contingent on teacher mediation. The paper concludes by proposing a research agenda and practical guidelines for Arab universities seeking evidence-based AI integration in EL2 instruction. It also recommends scaffolded integration, teacher training, reflective tasks to reduce over-reliance on AI tools. --- ### ReasonRec: A Reasoning-Augmented Multimodal Agent for Unified Recommendation Authors: Yihua Zhang, Mingfu Liang, Jiyan Yang, Rong Jin, Wen-Yen Chen, Yiping Han, Huayu Li, Buyun Zhang, Liang Luo, Frank Shyu, Luke Simon, Sijia Liu et al. Published: 2026-06-08 Categories: cs.IR, cs.AI arXiv: https://arxiv.org/abs/2606.28357v1 Recent advances in multimodal recommenders excel at feature fusion but remain opaque and inefficient decision-makers, lacking explicit reasoning and self-awareness of uncertainty. We introduce ReasonRec, a reasoning-augmented multimodal agent structured around a three-stage explicit reasoning pipeline. Specifically, we propose a reasoning-aware visual instruction tuning strategy that systematically transforms diverse recommendation tasks into unified CoT prompts, enabling the VLM to explicitly articulate intermediate decision steps. Additionally, our evidence-horizon curriculum progressively enhances the reasoning complexity to better handle cold-start and long-tail user scenarios, significantly boosting model generalization. Furthermore, the uncertainty-guided delegation mechanism empowers the agent to assess its own confidence, strategically allocating computational resources to optimize both recommendation accuracy and inference efficiency. Comprehensive experiments on four standard recommendation tasks across five real-world datasets demonstrate that ReasonRec achieves over 30% relative improvement in key ranking metrics compared to state-of-the-art multimodal recommenders. Crucially, ReasonRec substantially reduces inference latency by dynamically delegating up to 35% of queries to efficient sub-models without compromising accuracy. Extensive ablation studies further confirm that each proposed reasoning and planning mechanism individually contributes substantially to ReasonRec's overall effectiveness. Collectively, our results illustrate a clear pathway towards interpretable, adaptive, and efficient multimodal recommendation through explicit reasoning and agentic design. --- ### SafeGEO: Understanding Generative Engine Optimization Risks in Recommendation Agents Authors: Qianfeng Wen, Yifan Simon Liu, Xin Liu, Difan Jiao, Blair Yang, Junda Wu, Zhenwei Tang Published: 2026-06-08 Categories: cs.IR, cs.AI arXiv: https://arxiv.org/abs/2606.28356v2 Generative Engine Optimization (GEO) lets content owners rewrite web content to increase their visibility in generative systems. In recommendation agents, this creates a risk that sources controlled by sellers make flawed products appear better supported than they are. We study this risk at the generation stage by asking whether recommendation agents continue to make decisions that align with user utility when these sources are rewritten for GEO. To make this question measurable, we construct SafeGEO, an evaluation suite with 22 GEO attack variants across 600 recommendation cases. We empirically show that GEO attacks can promote flawed target products: they increase the rate at which such flawed products enter the recommendation set by up to 83.2 percentage points (pp). We further study whether agent-side design choices can mitigate this risk and show that simple defenses reduce harmful target promotion by up to 39.2 pp. These gains are substantial but do not restore the no-GEO performance, showing that GEO remains a serious risk despite mitigation. --- ### SafeGEO: Understanding Generative Engine Optimization Risks in Recommendation Agents Authors: Qianfeng Wen, Yifan Simon Liu, Xin Liu, Difan Jiao, Blair Yang, Junda Wu, Zhenwei Tang Published: 2026-06-08 Categories: cs.IR, cs.AI arXiv: https://arxiv.org/abs/2606.28356v1 Generative Engine Optimization (GEO) lets content owners rewrite web content to increase their visibility in generative systems. In recommendation agents, this creates a risk that seller-controlled sources make flawed products appear better supported than they are. We study this risk by asking whether recommendation agents preserve utility-aligned decisions when seller-controlled sources are rewritten for GEO. To make this question measurable, we construct SafeGEO, an evaluation suite with 22 GEO attack variants across 600 recommendation cases. We empirically show that GEO attacks can promote flawed target products. On average, they increase the rate at which such flawed products enter the recommendation set by up to 83.2%. We further study whether agent-side design choices can mitigate this risk and show that simple defenses, including defensive prompting and structured evidence checks, reduce harmful target promotion by up to 39.2%. These gains are substantial but do not restore the no-GEO performance, showing that GEO remains a serious risk despite developer-side mitigation. --- ### DBpedia-Enriched Company Representation for B2B Lead Recommendation Authors: Yuyan Qian, Claude Montacie, Milan Stankovic, Victoria Eyharabide Published: 2026-06-08 Categories: cs.IR, cs.LG arXiv: https://arxiv.org/abs/2606.28355v1 Selecting which companies to approach is a central challenge in business-to-business (B2B) sales, where decisions are often based on manual research and fragmented information sources. Modern B2B sales platforms centralize company records and use learned company embeddings to support tasks such as recommending and prioritizing potential clients. In this study, we investigate whether enriching these company embeddings with Semantic knowledge from DBpedia improves downstream interaction-prediction performance, within a pipeline that integrates structured company attributes and text embeddings deployed on a real B2B platform. We evaluate the learned embeddings on a downstream interaction prediction task using real user feedback data from the platform. Results show that DBpedia enrichment improves downstream performance, with gains observed on ranking and discrimination metrics. --- ### Generating in the Limit with Infinitely Many Hallucinations Authors: Irene Strauss, Alexandra Butoi, Ryan Cotterell Published: 2026-06-08 Categories: cs.CL, cs.FL, cs.LG arXiv: https://arxiv.org/abs/2606.28354v1 The classic paradigm of language identification in the limit models learning as a game between an adversary, who reveals strings from an unknown target language, and a learner tasked with identifying that language. The recently introduced framework of language generation in the limit shifted the objective to better reflect modern language modeling, requiring the learner to produce valid, unseen strings from the target language. Related work highlighted a fundamental tension: a broad coverage of the target often comes at the cost of validity. We introduce a new notion of precision and recast this problem as the classic recall-precision trade-off. We analyze generation in the limit under varying constraints on enumeration, novelty, and validity, aimed at reflecting settings closer to those encountered by large language models. A key contribution is our analysis of learners that are not eventually valid: we allow infinitely many mistakes, provided their frequency tends to zero so that precision remains one. We show that this relaxation can strictly increase recall when the adversary permanently withholds a large portion of the target language. We also study a continuous relaxation of the novelty constraint that requires only a fixed fraction of outputs to be novel. Taken together, our results move toward a more realistic model of language generation where occasional errors and repetitions are unavoidable, but their rates are controlled. --- ### Invisible to humans, visible to machines: a preregistered audit of Unicode fidelity across four biomedical bibliographic APIs Authors: Przemysław Czuma Published: 2026-06-08 Categories: cs.DL, cs.CL, cs.IR arXiv: https://arxiv.org/abs/2606.24897v1 Biomedical text mining, scientometrics, and the construction of training corpora for biomedical large language models (LLMs) all assume that the abstract text returned by a bibliographic API faithfully reproduces the published abstract. This pre-registered audit (OSF osf.io/269b5) tests that assumption for four widely used public APIs (PubMed E-utilities, Crossref, OpenAlex, Semantic Scholar) against PubMed Central (PMC) JATS XML as a common ground truth. From a complete enumeration of the PMC Open Access subset for 2024 (about 700,000 records), a simple random sample of 4,000 English-language research articles was drawn; for each, we recorded whether Unicode characters from four pre-specified classes present in the JATS abstract (typographic punctuation, mathematical/scientific symbols, Greek letters, special whitespace) were preserved by each API. Two systematic, deterministic losses met the pre-registered criterion (upper 95% CI bound below 5%): the PubMed AbstractText field preserved typographic punctuation in only 0.6% of eligible abstracts (95% CI 0.3-1.0%), and OpenAlex preserved special whitespace in 0% (0.0-0.4%). A blinded mechanism audit attributed the first loss to character substitution and the second to inverted-index serialization. Mathematical symbols and Greek letters were preserved faithfully (over 95%) by all four APIs. Separately, Crossref returned no abstract for 24.6% of papers (coverage 75.4%, 95% CI 74.1-76.7%), concentrated in specific publishers (Elsevier and ACS: 0%). Character-level fidelity is therefore API-dependent and undocumented: the same publisher-deposited JATS text carries different surface signatures depending on the serving API, with direct consequences for tokenization-sensitive bibliometrics, corpus construction, and character-level indicators of LLM-assisted writing. --- ### Heterogeneous 2D/1D Signal Representation Fusion for Underwater Acoustic Modulation Recognition Under Distribution Shift Authors: Ronglai Qian, Liang An, Xiaoyan Wang, Qing Fan, Ziwei Huang, Yang Ye Published: 2026-06-08 Categories: eess.AS, cs.AI, cs.SD arXiv: https://arxiv.org/abs/2606.23702v1 Modulation recognition systems rely on heterogeneous signal representations. 2D signal-image modalities such as time-frequency and cyclostationary maps capture structural patterns, while 1D statistical descriptors such as higher-order power spectra encode complementary cues. Under distribution shift, these modalities degrade unevenly, making robust fusion a central challenge for practical deployment. Progress is further limited by the lack of a unified evaluation protocol that systematically separates different shift types. This paper addresses both challenges through a joint benchmark-and-model study in underwater acoustic modulation recognition. UAMR-ShiftBench is the first benchmark to jointly cover in-distribution, low-SNR, unseen-environment, unseen-communication-parameter, and measured sea-trial evaluation under a single matched protocol, with two independent real-world subsets collected during two sea-trial campaigns conducted in March and November in the South China Sea. SCP-TriCA fuses STFT, cyclostationary, and P2/P4 (second- and fourth-order power spectra) modalities hierarchically: the two 2D modalities are first aligned through bidirectional cross-attention, and the 1D statistical modality is then incorporated through a sample-adaptive selective gate. On UAMR-ShiftBench, SCP-TriCA achieves 95.33% in-distribution accuracy and 74.59% simulated OOD average, outperforming the strongest baseline by 5.12 percentage points, and reaches 91.14% and 94.86% on the two sea-trial subsets, exceeding the best baseline by 15.71 and 23.00 percentage points respectively. Ablation results confirm that the gains stem from modality complementarity and the hierarchical fusion design. Code and models are available at https://github.com/ronglaiqian/UAMR-ShiftBench. --- ### Input-schema identifiability limits in physics-informed surrogates for mechanics-governed flow Authors: Daniel Cieslak, Andrzej Czyzewski Published: 2026-06-08 Categories: physics.comp-ph, cs.LG, physics.flu-dyn arXiv: https://arxiv.org/abs/2606.20655v1 Physics-informed and data-driven surrogates are increasingly used to approximate mechanics-governed flow fields, but the target quantities assigned to such models are not always identifiable from the input variables available at prediction time. We introduce an input-schema identifiability certificate for computational surrogates. Starting from a reduced physical model, the certificate decomposes a target field into components that are measurable from geometry, components that require boundary-condition information, and components identifiable only up to a symmetry quotient. This yields a pre-training audit: it predicts which oracle-channel interventions should reduce error, which should fail, and which ambiguity cannot be removed by changing the architecture, loss, optimizer, or sample size. We instantiate the framework for incompressible tubular flow using a Cosserat-rod reduction, where lumen velocity separates into a mesh-measurable tangent direction, a boundary-condition-dependent magnitude, and a signed-orientation ambiguity. Controlled experiments on patient-specific aortic CFD geometries, analytic Womersley flows, and an advection-diffusion transfer problem confirm the predicted pattern: supplying signed direction collapses angular error to the oracle regime, whereas supplying magnitude without orientation leaves the predicted sign ambiguity and yields 16-33 percent per-node sign flips. The results provide a mechanics-based diagnostic for deciding whether a surrogate modelling task is physically identifiable before training, and expose failure modes that aggregate error metrics can hide. --- ### Distributed Model Predictive Control with Adaptive Safety Zones for Multi-Fleet Drone Operations Authors: Linda Mümken, Diyar Altinses, Michael Schwung, Stefan Lier, Andreas Schwung Published: 2026-06-08 Categories: eess.SY, cs.AI, cs.RO arXiv: https://arxiv.org/abs/2606.20651v1 Autonomous drone swarms in space-constrained environments such as warehouses, inspection corridors, and urban delivery routes must share limited airspace safely at high vehicle density. Existing approaches rely on fixed safety zones sized for worst-case velocity, which wastes airspace in congested scenarios. We replace the fixed radius with an adaptive, speed-dependent safety sphere whose size scales with braking distance: tight at low speeds, expanded at high speeds. We develop both a centralized model predictive control (MPC) formulation and a distributed MPC (DMPC) in which each drone optimizes locally from detected neighbors, accommodating mixed fleets with non-cooperative agents. We prove feasibility up to the geometric packing limit evaluated at the minimum radius, establish Lyapunov stability under sufficient conditions on the adaptation parameter, drone density, and prediction horizon, and extend these guarantees to the distributed setting via a contraction condition that preserves the centralized stability margins. We further derive modified sphere-packing capacity bounds and a throughput-optimal crossing speed for narrow passages. Simulations confirm that the adaptive framework remains feasible where fixed-radius methods fail: it roughly doubles the admissible drone count, reduces traversal time through constrained passages by about 25 percent, and enables passage through openings impassable to static safety zones. The centralized variant realizes a larger fraction of the theoretical capacity, while the distributed variant offers a more realistic deployment model for mixed-fleet operations under the same safety guarantees. --- ### EmoInstruct-TTS: Dual-Path Instruction-Guided Emotional Speech Synthesis Authors: Minghui Wu, Ganjun Liu, Zikun Fang, Ting Meng, Hongchuan Wu, Bingao Xu, Yonglong Cai, Jiasheng Chen, Jun Du Published: 2026-06-08 Categories: cs.CL, cs.AI, cs.SD, eess.AS arXiv: https://arxiv.org/abs/2606.20650v1 Instruction-based controllable speech synthesis enables users to specify emotions through natural language. However, existing approaches often rely on coarse emotion labels and lack explicit modeling of fine-grained intensity. We propose EmoInstruct-TTS, a dual-path instruction-guided framework for emotional speech synthesis. We introduce Emotion2embed, a supervised semantic-acoustic emotion embedding covering 48 emotional states, including fine-grained categories and intensity levels. To infer embeddings from free-form instructions, we design an Instruction-Conditioned Emotion Flow Model (ICE-Flow) that generates acoustically grounded emotion representations. The inferred embeddings are integrated into an LLM-based synthesis pipeline to provide explicit emotional control while preserving semantic planning. Experiments show improved emotional controllability and speech naturalness over strong baselines. --- ### Computational Identifiability Authors: Lucius E. J. Bynum, Rajesh Ranganath, Kyunghyun Cho Published: 2026-06-08 Categories: cs.LG, cs.AI, math.NA, stat.CO, stat.ME, stat.ML arXiv: https://arxiv.org/abs/2606.19361v1 Identification conditions describe the computability of a target query or parameter of interest as a function of the type and amount of information available. In causal identification, this information is often expressed in the form of a causal graph, and data are observed or collected for some subset of variables in the graph. Target queries may be for a single effect alone or for a class of effects in a given model. The derivation of an identification algorithm then defines mathematically the process by which the desired causal effect(s) can be uniquely determined, theoretically, in expectation. Identifiability in expectation, or 'theoretical identifiability,' generally assumes asymptotic properties, infinite data, or other mathematically idealized conditions. In this paper, we explore a fundamental distinction between this theoretical, idealized notion of identifiability and a proposed alternative that is computation-bound. The framework we propose - 'computational identifiability' - is to instead define a finite computational search procedure for an empirical estimator. If this process finds an estimator empirically, within a desired error tolerance, then identifiability is satisfied, conditional on the specified assumptions of the search (i.e., a prior distribution over the parameters) and conditional on the search procedure itself. Through several experiments, we demonstrate how this framework allows us to answer fine-grained, practical identification questions, such as identification with small finite samples, with ambiguous graphical criteria, with mixed observational-interventional data, and across counterfactual data and estimands. Code is available at https://github.com/lbynum/metadentify. --- ### A Guide to Estimating Conditional Average Treatment Effects in Competing Risks Settings Authors: Daniel Klippert, Sarah Friedrich, Markus Pauly Published: 2026-06-08 Categories: stat.AP, cs.LG, stat.ML arXiv: https://arxiv.org/abs/2606.18281v1 Conditional average treatment effects (CATEs) are central to treatment decision-making in personalized medicine. In competing risks settings, estimating CATEs from survival data allows for patient-specific assessments of treatment effectiveness for a specific event of interest while properly accounting for alternative event types. This distinction is essential in the presence of comorbidities, where competing causes of death may otherwise confound the therapeutic benefit. Focusing on right-censored survival times with binary treatment, we examine CATEs defined as covariate-conditional differences in the absolute risk for the event of interest at a fixed time. To this end, we study meta-learners which adapt machine learning algorithms for CATE estimation in competing risks scenarios. We systematically compare six meta-learners, combining Cox regression or random survival forests for risk modeling with elastic net regression or random forests for direct CATE modeling. To provide practical guidance on model selection, we evaluate their performance in multiple simulation settings, that differ in hazard complexity, treatment heterogeneity, treatment assignment, event type distribution and censoring. To facilitate applied use, we provide the R package, crsurvlearners, which implements all considered approaches. --- ### XMedFusion: A Knowledge-Guided Multimodal Perception and Reasoning Framework for Autonomous Medical Systems Authors: Hamza Riaz, Arham Haroon, Maha Baig, Muhammad Dawood Rizwan, Muhammad Naseer Bajwa, Muhammad Moazam Fraz Published: 2026-06-08 Categories: cs.CV, cs.AI, cs.MA arXiv: https://arxiv.org/abs/2606.14766v1 Autonomous medical and robotic systems increasingly rely on intelligent perception and reasoning capabilities to interpret visual data and support clinical decision making. Radiology report generation represents a critical component of such automated diagnostic workflows, yet existing end-to-end multimodal models often suffer from weak visual grounding, resulting in unreliable interpretations and omission of subtle clinical findings. This paper presents XMedFusion, a modular AI framework designed as an intelligent perception and reasoning module for autonomous medical systems. The proposed framework decomposes visual information into coordinated functional components that emulate expert-driven analysis, including a visual perception agent that extracts image-grounded evidence, a knowledge graph construction agent that structures clinically relevant findings, and a retrieval-guided drafting process that ensures a consistent reporting structure. A synthesis agent iteratively integrates visual and structured evidence through reasoning-driven verification to produce reliable and interpretable diagnostic outputs. Experimental evaluation on a public chest radiograph dataset demonstrates significant improvements over baseline vision-language models, achieving gains from 0.0493 to 0.3359 in BLEU-1, 0.0863 to 0.2440 in ROUGE-L, and 0.0829 to 0.1708 in METEOR, along with substantial improvements in semantic evaluation metrics such as Consistency (2.38 to 7.80) and Accuracy (2.34 to 6.93). The results highlight the effectiveness of structured multi-agent perception and reasoning for enhancing robustness, transparency, and automation in intelligent medical imaging systems, enabling integration into autonomous healthcare and robotic diagnostic workflows. --- ### Momentum-Guided Semantic Forecasting (MoFore) for Self-Supervised Video Representation Learning Authors: Qinwu Xu Published: 2026-06-08 Categories: cs.CV, cs.AI, cs.LG, cs.MM arXiv: https://arxiv.org/abs/2606.14765v1 Self-supervised video representation learning has recently advanced through contrastive learning, masked reconstruction, and predictive representation learning. Reconstruction-based approaches such as MAE and VideoMAE learn representations by recovering masked visual content \cite{he2022mae,tong2022videomae}, while contrastive methods such as CLIP learn semantically meaningful embedding spaces through representation alignment \cite{radford2021clip}. In this work, we introduce a Momentum-Guided Semantic Forecasting framework (MoFore) for self-supervised video representation learning. Instead of optimizing for pixel-level reconstruction or task-specific semantic alignment, the proposed method learns temporally predictive video representations by forecasting future latent embeddings from temporally distant context clips. To improve robustness across temporal scales, we further introduce randomized temporal-gap forecasting during training. The framework combines predictive latent forecasting with contrastive regularization to encourage temporal consistency while preventing representation collapse. Experiments on the UCF101 dataset demonstrate that the proposed framework learns temporally consistent and semantically meaningful video representations without using action labels during training. Quantitative analysis shows strong temporal stability and emergent category-level structure in the learned embedding space, while qualitative retrieval experiments reveal motion-aware organization across related activities. Overall, the results suggest that long-range latent forecasting provides an effective and computationally efficient approach for self-supervised video representation learning without relying on reconstruction-based objectives. --- ### Avoiding Exponential Blow-Up in Distributive Lattice Submodular Minimization Authors: Ishant Shanu Published: 2026-06-08 Categories: cs.CV, cs.DM arXiv: https://arxiv.org/abs/2606.14764v1 Submodular function minimization has gained a lot of interest in recent years. They are highly applicable in the area of Computer Vision and Machine Learning. Often such applications require to work with submodular functions defined on distributive lattice. Current best way of dealing with it is using a transformation which extrapolates the submodular function for the respective boolean lattice. It makes optimization system too inefficient due to enlargement of the working space. Quantitatively, the expanded space has additional exponential (in set size) number of elements. We propose a generic framework for dealing with distributive lattice which only works within distributive lattice. Our framework allows one to use already established submodular function minimization algorithms for boolean lattice. In our experiment, we show the huge improvement in terms of running time over tranditional methods for handling distributive lattice. --- ### Bayesian Optimization for Learning Nonlinear MPC in Autonomous Agent Navigation Authors: Lorenzo Ortolani, Gabriel Voss, Gabriele Beltrami, Francesco Dorati, Tommaso Felice Banfi Published: 2026-06-08 Categories: cs.RO, cs.LG, math.OC arXiv: https://arxiv.org/abs/2606.14763v1 Real-time autonomous navigation in dynamic, unknown environments remains a fundamental challenge for mobile robotics. We propose a map-free framework that tightly integrates reactive rolling-horizon planning with nonlinear Model Predictive Control (MPC). At each control cycle, a LiDAR-based Gaussian occupancy representation is constructed and used to generate collision-free trajectories via A* search, which are then tracked by a CasADi/IPOPT MPC formulation incorporating a smooth sigmoid obstacle barrier. To improve robustness to parameter sensitivity, we adopt an offline Bayesian optimization scheme based on Tree-structured Parzen Estimators (TPE), which identifies near-optimal controller parameters with respect to a composite navigation objective. In addition, a Gaussian Process surrogate is used to analyze parameter sensitivity and provide insight into the optimization landscape. The proposed framework is robot-agnostic and is evaluated on the Unitree Go2 quadruped in simulation using Gazebo, followed by deployment on the physical robot. Experimental results show that parameters tuned in simulation transfer effectively to hardware, maintaining comparable performance without additional tuning. The full system achieves up to a 90.0\% navigation success rate when deployed, along with a 38.9\% average improvement in the evaluation metrics across simulated environments. --- ### Scribby: A Multi-Level LLM Framework for Semantic Video Analysis Authors: Julian Abelarde, Hugo Garrido-Lestache Belinchon Published: 2026-06-08 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2606.14762v1 As video content continues to expand across educational platforms, recorded lectures, and live-streamed entertainment, the need for efficient and structured analysis of long-form footage has increased \cite{1}. Although many existing AI programs provide high-level video summaries based on AI-generated transcripts \cite{2,3,4,5}, these approaches are often limited to coarse overviews and lack detailed analysis of a video's structure, thematic progression, and semantic relationships, all of which are required for comprehensive video analysis. This paper proposes an LLM-based video summarization framework that balances macro-level comprehension with micro-level semantic analysis \cite{6,12,13}. The first stage of the process indexes the video at a micro level by (1) analyzing the full transcript, (2) analyzing individual transcript sentences, and (3) grouping these sentences by semantic similarity using an LLM as a judge \cite{6,13}. Contextual continuity is retained during sentence-level processing by incorporating both the global transcript analysis and adjacent sentence information into each evaluation prompt. This framework establishes a foundation for video analysis tools that visualize semantic chunking and semantic matching through relevance-based heatmaps. Limitations and future expansions of the framework are also discussed. --- ### GeoRoPE: Ground-Aware Rotary Adaptation for Remote Sensing Foundation Models Authors: Yu Luo, Kun Hu, Mengwei He, Xiaogang Zhu, Shan Zeng, Allen Benter, Wei Xiang, Patrick Filippi, Thomas Francis Bishop, Zhiyong Wang Published: 2026-06-08 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2606.14760v1 Remote-sensing foundation models (RSFMs) benefit from pretraining on imagery from multiple sensors and ground sampling distances (GSDs), but such exposure alone does not resolve scale mismatch during downstream adaptation. A fixed token-grid offset can correspond to different ground distances across sensors, making grid-based positional priors physically inconsistent. Meanwhile, heterogeneous spatial granularity means that compact urban regions and homogeneous landscapes may require different positional sensitivities even under the same GSD. Therefore, we propose {GeoRoPE}, a ground-aware, RoPE-compatible, and parameter-efficient spatial adaptation method for RSFMs. GeoRoPE recalibrates token-level positional interactions from two complementary aspects. First, \textit{Geo-Coordinate Calibration (GCC)} rescales raw token-grid offsets according to the ground distance represented by one token-grid step, producing geo-calibrated relative coordinates across GSDs. Second, \textit{Geo-Frequency Calibration (GFC)} adjusts the native RoPE frequency with a relation-specific factor, enabling position sensitive adaptation to scene-dependent spatial granularity. GeoRoPE is injected into pretrained RSFMs through a lightweight adapter, preserving the frozen spatial prior while adding geo-aware positional corrections. Experiments across multiple RSFMs, sensors, resolutions, and downstream tasks demonstrate that GeoRoPE improves cross-resolution robustness and scale-sensitive representation learning. --- ### Temporally Consistent and Controllable Video Generation of 2D Cine CMR via Latent Space Motion Modeling Authors: Yiheng Cao, Gustavo Andrade-Miranda, Jiatian Zhang, Guillaume Sallé, Xin Gao Published: 2026-06-08 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2606.14759v1 Cine cardiac magnetic resonance is the gold standard for assessing cardiac function, but the scarcity of public datasets limits the development of advanced data-driven models. To address this limitation, we propose a generative method for synthesizing temporally coherent and anatomically consistent cardiac sequences. Our text-to-video framework decouples cardiac spatial structure from temporal motion. First, a fine-tuned diffusion model synthesizes an initial frame from a clinical text prompt, controlling anatomical features. Then, a latent flow model conditioned on a cardiac phase embedding generates the complete cardiac motion, ensuring spatial consistency and temporal control. Our model generates anatomically and pathologically diverse sequences with high temporal coherence and strong fidelity to input prompts, achieving a FID of 31.68 for image realism and a CLIP score of 31.04 for text-image alignment. These experimental results highlight its potential to produce high-fidelity, on-demand medical data, offering a scalable solution to data scarcity. --- ### Disentangling Hallucinations: Orthogonal Semantic Projection for Robust Interpretability Authors: Emirhan Bilgiç, Baptiste Caramiaux, Zhi Yan, Gianni Franchi Published: 2026-06-08 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2606.14758v1 As Vision-Language Models are increasingly deployed in safety-critical applications, the trustworthiness of their explanations becomes crucial. Explainable AI (XAI) methods for Vision-Language Models often suffer from semantic hallucination, where attribution maps highlight prominent image regions even when prompted with incorrect text descriptions (e.g., highlighting a dog when prompted ``cat''). Although this problem is widespread, a formal mathematical analysis of XAI methods and CLIP embeddings is largely missing in the literature. We demonstrate that this phenomenon is not specific to a single architecture but is a fundamental consequence of Linear Semantic Leakage in high-dimensional embedding spaces. We propose a unified theoretical framework, Linear Semantic Attribution (LSA), which generalizes across discriminative methods. We introduce OSP, a geometric intervention that utilizes the residual property of OMP to disentangle unique semantic signals from shared concepts. We prove theoretically and demonstrate empirically that OSP minimizes hallucination by orthogonalizing the query vector against distractor concepts, rendering the attribution model blind to shared features while preserving fidelity for correct prompts. Our code is available at: https://github.com/emirhanbilgic/Orthogonal-Semantic-Projection --- ### Spatial Priors via Space Filling Curves for Small and Limited Data Vision Transformers Authors: Leyla Naz Candogan, Arshia Afzal, Pol Puigdemont, Volkan Cevher Published: 2026-06-08 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2606.14757v1 Though Vision Transformers (ViTs) have become the dominant backbone in many computer vision tasks, due to permutation equivariance, their attention mechanism lacks explicit spatial inductive biases. This become particularly important in two settings: when model capacity is small or training data is limited. Inspired by the attention masking strategies in Linear Transformers and the scanning patterns of Vision SSMs, we introduce VIOLIN, a lightweight masked attention mechanism that encodes spatial structure within attention via Space Filling Curves (SFCs) with less than 0.0015% extra parameters and negligible computational overhead. VIOLIN scans the image using multiple SFCs to construct curve-specific decay masks, which are then combined and multiplied with the attention matrix. Across a wide range of evaluations, VIOLIN consistently improves performance. In limited data regimes such as fine-tuning on VTAB-1K, it boosts accuracy across all task groups and by up to 8.7% on the tasks where spatial information is essential. It can be combined with parameter-efficient fine-tuning methods such as LoRA to further increase the performance. Beyond fine-tuning, VIOLIN improves various small scale ViT architectures (e.g., DeiT, DINO) during pretraining on ImageNet-1K. Additionally, on pixel-level CIFAR-100 training, a task that is highly dependent on location information, VIOLIN increases accuracy by up to 7.2%. Overall, VIOLIN provides a computationally efficient yet effective way to inject spatial inductive bias into ViTs, especially benefiting small models and limited data settings. --- ### Divide-and-Denoise: A Game-Theoretic Method for Fairly Composing Diffusion Models Authors: Abhi Gupta, Polina Barabanshchikova, Vikas Garg, Samuel Kaski, Tommi Jaakkola Published: 2026-06-08 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2606.14756v1 The abundance of pre-trained diffusion models provides an opportunity for composition. Combining several models, however, runs the risk of one model dominating or models disagreeing with each other. Here, we propose Divide-and-Denoise, a method for coordinating multiple pre-trained diffusion models during sampling. Much like managing a specialized workforce, our method creates a fair but efficient division of labor across models. Central to our method is the notion of an allocation which defines the responsibility of each model to every region of the noisy sample. At every timestep, we then denoise by (i) updating the allocation by solving a fair division game, where we divide the sample into regions that maximize total utility under fairness constraints, and (ii) aligning the models with this allocation, where we guide each model to denoise within its assigned region. This leads to a new composite denoising process that evolves in tandem with a division process. We evaluate Divide-and-Denoise on conditional image generation. Across several quality metrics, including the GenEval benchmark, our method outperforms baselines and resolves common failures including missing objects and mismatched attributes. Experiments show that Divide-and-Denoise utilizes each model's expertise without neglecting any other model. --- ### History of the Muddy Children Puzzle Authors: Hans van Ditmarsch Published: 2026-06-08 Categories: cs.AI, cs.GL, cs.LO arXiv: https://arxiv.org/abs/2606.13703v1 The Muddy Children Puzzle is a puzzle about knowledge and ignorance that has been inspiring for the development of epistemic logic. Who came up with it first? This is unclear. We trace the origin of the Muddy Children Puzzle through logical and literary publications over the past two centuries. The puzzle inspired a numerous variations such as involving numbers or coloured hats. We also present a novel hats puzzle involving self-reference. --- ### My Chemical Harness: Evolutionary Molecular Design over Synthetic Pathways with Large Language Model Agents Authors: César Ojeda, Darius A. Faroughy, Maryam Karimi, Payam Zarrintaj, Mir Mehdi Seyedebrahimi, Martín Carballo-Pacheco Published: 2026-06-08 Categories: physics.chem-ph, cs.LG, cs.NE arXiv: https://arxiv.org/abs/2606.11256v1 Designing molecules with target properties is most useful when candidate structures are accompanied by feasible synthetic routes. We introduce My Chemical Harness, a route-native evolutionary framework for goal-directed molecular design in which the search population consists of executable synthetic pathways rather than isolated molecular graphs. Each route is built from purchasable building blocks and reaction templates, executed by deterministic chemistry tools, and scored through task-specific molecular oracles. Large language models (LLMs) are used only as strategy controllers that select high-level preferences over route length, move type, reaction families, motifs, and exploration pressure, while local code performs route construction, validation, deduplication, scoring, selection, and memory updates. This separation lets the LLM guide exploration without allowing it to introduce hallucinated products or unsupported reaction steps. On a soluble epoxide hydrolase proxy task, our LLM agent improves over single pass LLM and deterministic controllers, reaching state-of-the-art performance across the sEH score, synthetic accessibility score, and AiZynthFinder success rate metrics. These results suggest that constrained LLM agents can play a significant role in molecular discovery without requiring training, fine-tuning, or dedicated generative models. --- ### Bernstein-Schur Kernels: Random Features by Sketched Modulation and Radial Randomization Authors: Taha Bouhsine Published: 2026-06-08 Categories: cs.LG arXiv: https://arxiv.org/abs/2606.11255v2 Bernstein--Schur kernels are products of a finite-feature kernel and a completely monotone shift-invariant kernel: nonstationary kernels falling between the shift-invariant and dot-product templates random features exploit, so neither Bochner sampling nor polynomial sketching applies to the full kernel directly. We give one random-feature construction for the whole class that randomizes both factors: it sketches the finite modulation and samples the radial factor's one-dimensional Bernstein--Widder scale before applying Gaussian random Fourier features, giving feature dimension $Dm$, free of the $O(d^2)$ size of the exact modulation feature. With the modulation kept exact (the $m\to\infty$ limit), we prove unbiasedness, an exact variance, and a matrix-Bernstein operator-norm bound controlled by the top kernel and modulation eigenvalues and an intrinsic dimension rather than the crude $N\max_{ij}$ route. Whitening this argument at the ridge makes the effective dimension $d_{\mathrm{eff}}(λ)$ the \emph{exact} intrinsic dimension of the matrix variance, so $O((1+\|P\|_{\mathrm{op}}/λ)\log(d_{\mathrm{eff}}/δ))$ radial draws preserve the kernel-ridge solution; tilting the draw by a closed-form whitened leverage improves this to the effective-dimension count $O((1+d_{\mathrm{eff}})\log(d_{\mathrm{eff}}/δ))$. Conditioning on the sketch carries every guarantee to the deployed doubly-randomized estimator up to one additive sketch term, and all hold for the whole class with the modulation Gram in place of the polynomial one. The flagship instance is the biased $yat$-kernel $k_{yat,b}(w,x)=(w^\top x+b)^2/(\|w-x\|^2+\varepsilon)$, whose family span contains the inverse-multiquadric kernel by finite differences in $b$. --- ### AugRelNet: Relation-Augmented Dynamics for Structure Discovery and Forecasting from Limited Data Authors: Xingji Cui Published: 2026-06-08 Categories: cs.LG arXiv: https://arxiv.org/abs/2606.11251v2 Complex dynamics often arise from persistent interactions whose effects vary with the system state. We introduce AugRelNet for short- and medium-horizon trajectory forecasting from limited data. A shared learnable relation matrix explicitly routes source signals to targets, while evolving local features \(u\) and a persistent response state \(η\) transform them into nonlinear, history-dependent responses. Feeding these responses back into the dynamics separates shared relational organization from its changing realization. The learned relations reflect dense coupling in Lotka--Volterra systems and develop structured, neighbour-preferential organization in locally interacting systems. On 40-dimensional Lorenz--96, AugRelNet uses about 4,000 training states, roughly an order of magnitude fewer than representative prior Lorenz--96 forecasting studies. Across five seeds, every true interaction ranks above every nonedge, with a mean absolute-weight contrast of approximately \(146{:}1\). Under the same data budget, eight-step RMSE is about \(23\)--\(59\times\) lower than MNO, DySLIM, DeepSkip, and AL-RNN, \(14\)--\(55\times\) lower than NRI and dense GraphODE, and 37\% lower than PySINDy with a matched quadratic dictionary. The same relational representation extends to grids by treating sites as variables and sharing relations across spatial offsets: in discrete (Game of Life), continuous (FitzHugh--Nagumo), and stochastic (Ising) dynamics, learned weights rank physical neighbours above other candidate offsets while supporting multi-step prediction. AugRelNet learns these relations through prediction losses and regularization, without structural labels or system-specific physical losses. --- ### Mechanical Field Networks: Structured Neural Dynamics for Multivariate Systems Authors: Xingji Cui Published: 2026-06-08 Categories: cs.LG arXiv: https://arxiv.org/abs/2606.11251v1 Many multivariate dynamical systems are observed only through trajectories, leaving the mechanisms governing their joint dynamics hidden. Existing approaches can impose interpretable dynamics or learn flexible state transitions, yet the resulting interaction structure is typically either specified in advance or left implicit within the learned dynamics. We introduce MF-Net, a recurrent dynamical model that represents all variables in a shared field state and updates this state through a learned relation law. Each variable carries a field component, and these components evolve jointly through a learnable mechanical transition. Here, mechanical refers to the relation-to-motion organization of the transition, where learned relations shape state-dependent flows, field responses, and motion tendencies that move the field state forward. The resulting structure is part of the rollout itself: learned relations influence how the field moves, and the same internal quantities support both forecasting and structural readout. Across known-law interaction systems, chaotic benchmarks, real neural recordings, and ecological time series, MF-Net achieves competitive short- and medium-horizon forecasting while retaining inspectable structural readout. On the 40-dimensional Lorenz--96 testbed, MF-Net achieves an eight-step $R^2$ of $0.798\pm0.018$; across five seeds, its learned relation matrix recovers the local coupling support with a local/nonlocal strength ratio of $19.80\pm1.00$ and Precision@$K$ of $1.000\pm0.000$. MF-Net provides a structure-readable dynamical modeling framework in which learned relations are trained through forward evolution and, on real data, interpreted as functional predictive couplings under appropriate observational limits. --- ### MASK: Multi-Agent Semantic K-Scheduling for Risk-Sensitive 6G Robotics Authors: Ahmet Gunhan Aydin, Elif Tugce Ceran Published: 2026-06-08 Categories: cs.RO, cs.LG, cs.MA arXiv: https://arxiv.org/abs/2606.11249v1 Realizing the vision of 6G connected robotics requires reconciling high-performance collaborative control with the rigid spectral limitations of physical wireless channels. In realistic collaborative sensing scenarios, spectral resources are quantized into finite physical resource blocks or orthogonal subcarriers, rendering simultaneous transmission by all agents infeasible. To address this, we propose Multi-Agent Semantic K-Scheduling (MASK), a control architecture designed to sustain robust, risk-aware coordination under strict instantaneous bandwidth caps. We introduce Arbiter-Assisted Semantic Information Gating (A-SIG), a lightweight coordination mechanism that enforces hard access constraints by scheduling only the top-K agents based on locally computed semantic importance scores. By aggregating these prioritized observations into a compact latent state, a self-supervised global encoder enables a distributional policy to mitigate tail risks despite data sparsity. We evaluate MASK across diverse benchmarks, demonstrating that it matches the performance of communication-unconstrained baselines even when channel access is restricted to a small fraction of the swarm size. Furthermore, the framework exhibits inherent resilience to packet erasures, validating semantic scheduling as a critical enabler for resource-constrained 6G systems. ---